WO2020109900A1

WO2020109900A1 - Welfare system and method of operation thereof

Info

Publication number: WO2020109900A1
Application number: PCT/IB2019/059701
Authority: WO
Inventors: Stephen Philip Gardner; Gert Lykke Soerensen MØLLER; Claus Erik Jensen
Original assignee: Precisionlife Ltd
Priority date: 2018-11-30
Filing date: 2019-11-12
Publication date: 2020-06-04

Abstract

There is disclosed a welfare system that provides welfare support, when in operation, to a plurality of individuals in an assistive environment. The welfare system includes a data processing arrangement implementing a RACE engine that receives in operation a plurality of measurands of a given individual. Furthermore, the data processing arrangement includes a decision support knowledge model including a plurality of treatment strategies and genomic data. The data processing arrangement provides output signals for developing a personalized identification of one or more active drug combinations for the treatment or prevention of a given patient individual's specific disease. The data processing arrangement executes a software product that, when in execution, performs a high-order combinatorial search within the decision support knowledge model based upon the plurality of measurands and generates the output signals, to compute a welfare trajectory for an individualized welfare of each individual.

Description

WELFARE SYSTEM AND METHOD OF OPERATION THEREOF

TECHNICAL FIELD

The present disclosure relates generally to welfare systems, namely to welfare systems that provide, when in operation, customized welfare support to individuals in assistive environments to enhance their comfort and physical condition; the welfare systems provide, for example, improved nutritional, therapeutic and targeted treatments for the individuals, for example by developing medicines for the individuals, and by repurposing medicines for the individuals. Moreover, the welfare systems provide for selective breeding through DNA analysis of blastocysts and embryos, to select embryos with preferred predicted phenotype characteristics, wherein selected embryos are implanted via IVF to provide individuals with enhanced properties, for example for providing more efficient conversion of nutrition provided (for example, Bos Taurus is much more food efficient and produces more milk but is less resistant to heat or drought than Bos Indicus). Moreover, the present disclosure also relates to methods of (namely methods for) operating aforesaid welfare systems. The methods provide reduced stress and improved physical condition of the individuals, for example by providing customized nutritional, therapeutic and targeted treatments to the individuals in the assistive environments. Furthermore, the present disclosure also relates to computer program products comprising a non-transitory computer-readable storage medium having computer-readable instructions stored thereon, the computer- readable instructions being executable by a computerized device comprising processing hardware to execute aforementioned methods.

BACKGROUND

With increasing human population, there has been a corresponding increase in demand for animal products such as meat, milk, wool and leather. This increase in demand has led to an increase in selective breeding of animals such as cows, horses, sheep, and pigs as well as insects, plants, fungi, microbes and the like. Furthermore, the animals being bred for producing animal products are kept in specific environments (such as farming environments, marginal environments including pastures and so forth), where the animals are monitored and nurtured. Moreover, different animals potentially benefit from customized types and quantities of food, and potentially have different needs such as external grazing, heat, cold and the like for producing an optimal quality and quantity of animal products, with reduced stress and enhanced wellbeing for the animals.

Conventionally, farming environments, with animals hosted therein, are monitored by personnel responsible for managing the farming environments. The personnel take care of cleanliness, food, and health of the animals and other factors related to the farming environments. Moreover, welfare is closely associated with providing suitable combinations of nutrition, medication and care to animals to improve their comfort and wellbeing. Optimized animals with commercially desirable phenotype characteristics (such as, animals capable of exhibiting desirable phenotypes in specific environments in which the animals are raised) are extremely valuable assets, and hence their welfare during growth, and treatment in an event of illness, is very important to address. However, the personnel are potentially unable to respond in an optimal precision manner while monitoring the assistive environments and animals hosted therein. Furthermore, the personnel are potentially unable to identify adverse living conditions or suitable combinations of nutrition, medication (such as, in an event of illness) and living conditions for the animals in the assistive environments. This lack of identification is a technical problem that requires more efficient techniques for monitoring the assistive environments and caring for the individual animals hosted therein.

Presently, there exist several known techniques that are employed for monitoring assistive environments, to care for the animal's health and welfare. However, there exist certain limitations associated with these known techniques. Firstly, animals within a particular breed may appear to be substantially similar but may be different genetically and microbiomically, having different nutritional (food) requirements, environment and husbandry requirements that personnel may get confused; for example, a given livestock farmer becomes overwhelmed by the mutually different individual needs of the farmer's animals. As a result, there may arise situations in which inaccurate data is recorded for a given animal, or that improper treatment and medication may be provided to the given animal . Secondly, data related to the monitored assistive environment, and the animals hosted therein, are often maintained manually. As a result, there may be inaccuracies and inconsistencies associated with the monitored data. Animals potentially become ill, even when they have highly desirable phenotype characteristics. Selecting customized therapeutic treatments for given individuals is often a complex task, especially when an animal's phenotypic characteristics are highly optimized in certain desirable ways. Conventionally, drug discovery or therapy selection typically focuses on a single mechanism, for example a single biological mechanism, a single biological pathway or similar, for example described by a single gene or SNP. An easiest way to identify a given candidate therapy against a specific given target is to design a high throughput screening (HTS) or microfluidic assay. More recent drug discovery and development has focused on disease targets for which a clear, testable genetic explanation of their mechanism and phenotypic association is forthcoming as a predictor of drug development tractability and efficacy. Most diseases are, however, complex phenotypes that embody contributions from multiple SNPs, genes and pathways, have dependencies on non-genomic features such as epigenetics, environment and epidemiological attributes and which exhibit different system-wide behaviours that cannot be accounted for in an isolated assay. Such multi-omic complexity is a challenge when undertaking drug discovery, for example for animal treatment as aforementioned, and hence also a challenge for prescription, as medicines are typically approved in isolation for use in one or more specific conditions where patients/animals share an endpoint phenotype that is recognisable for diagnostic purposes. This contemporary 'one-size-fits-all' approach is more recently giving way to personalized/precision medicine for animals (likewise humans), but approaches have not yet been properly developed regarding how to use knowledge of combinations of the underlying genomic and non-genomic variants in a given animal to design an optimal therapeutic intervention strategy for the given animal. Therefore, it becomes difficult for personnel looking after the assistive environment to monitor effectively the health and to design the optimum care of each of the animals hosted therein. Moreover, the existing techniques do not consider the interactions between the genome of an animal and the environmental conditions animal in which it is raised and other factors such as pathogens (for example, disease-causing bacteria), the local environmental microbiome, humidity, temperature and so forth that may considerably affect production of animal products, and the wellbeing and ability to thrive of the animals.

Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned drawbacks associated with existing techniques for improving selective breeding of animals for specific environments, the monitoring and refinement of welfare in assistive environments, as well as conventional techniques used to identify disease- or trait-associated variants and the drawbacks associated with the development of one or more active drug combinations for the treatment or prevention of a specific given disease, for example as a part of welfare.

Mutatis mutandis, there is also a need to improve welfare system effectiveness for human beings to improve their nutrition, their lifestyle factors and also improve customization of medical treatments when they become unwell . Technology described in this disclosure is both applicable to animals in farming environments, and also human beings in care facilities, in hospitals, in care homes, and in home (e.g. domestic) environments in which welfare care is provided.

SUMMARY

The present disclosure seeks to provide a welfare system that provides an improved welfare support in operation to one or more individuals in an assistive environment, for example to animals in a farming and veterinary environment or to people in a care homes, hospitals, domestic caring home environments or clinical facilities.

The present disclosure also seeks to provide an improved method of (namely method for) operating a welfare system that provides welfare support in operation to a plurality of individuals in a assistive environment, such as for developing a personalized customized identification of nutrition, as well as one or more active drug combinations for the treatment or prevention of a given individual's specific disease when encountered.

Moreover, the present disclosure also seeks to provide improved apparatus and methods for selection of embryos, by way of DNA analysis of embryotic DNA or blastocystic DNA, to select embryos for IVF having preferred phenotype characteristics.

It will be appreciated that while the various embodiments are explained with respect to treatment of animals, the same embodiments will be similarly applicable for treatment of humans, for example as aforementioned.

According to a first aspect, the present disclosure provides an welfare system that provides, when in operation, welfare support to one or more individuals hosted in a assistive environment, wherein the welfare system includes a data processing arrangement implementing a RACE engine that receives, when in operation, a plurality of measurands of a given individual that is hosted within the assistive environment, wherein the data processing arrangement includes a decision support knowledge model including a plurality of nutritional and treatment strategies and at least one of: drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each individual, individual genotype data, and SNP data, wherein the data processing arrangement provides output signals that provide a personalized identification of one or more nutrition types and active drug combinations for growth of the given individual and treatment or prevention of the given individual's specific disease, and wherein the data processing arrangement executes a software product that, when executed, performs a high-order combinatorial search within the decision support knowledge model based upon the plurality of measurands and generates the output signals, characterized in that the welfare system in operation :

(a) employs the given individual's SNP genotypes and/or one or more other features which synergistically affect a nutritional status and a disease status as a part of the measurands;

(b) the software product is configured to perform a multi-dimensional solution search in the decision support knowledge model to identify high-order combinations of the given individual's SN P genotypes, using a computational engine, implemented as the RACE engine, with combinatorial methodology for combinatorial feature analysis executed in the data processing arrangement, for the given individual hosted within the assistive environment; and

(c) the software product computes a welfare trajectory for the given individual, wherein the welfare trajectory comprises a course of nutrition and treatment to be prescribed to the given individual.

The invention is of advantage in that it provides, for example, an improved welfare system and an improved method of (namely method for) operation thereof; the system is capable of providing precision welfare for each of the individuals in the assistive environment; specifically, the system considers phenotypic characteristics as well as genotypic factors (and optionally, other factors including environmental factors, epigenetic factors, epidemiological factors and so forth) associated with the individuals in order to provide an efficient and comprehensive welfare trajectory for the individuals in the assistive environment, such that the welfare trajectory comprises a course of treatment to be prescribed to the individuals. Moreover, the present disclosure seeks to address, for example to overcome, various drawbacks associated with conventional techniques used to identify disease-associated variants and the drawbacks associated with the development of one or more active drug combinations for the treatment or prevention of a specific given disease. Correspondingly, the present disclosure also seeks to provide a solution to the existing problem of developing a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's (such as an animal's or human patient's) specific disease. Thus, the present disclosure seeks to provide a solution that overcomes, at least partially, the problems encountered in known assistive environments, and offers a reliable and dynamic system (using the aforesaid RACE engine) for providing personalized treatment to individuals with specific nutritional requirements or diseases.

From the famous EPO Vicom decision T0208/84, it will be appreciated that complex mathematical algorithms when applied to real-life situations and resulting in a technical effect are acceptable for patentability both in the EPO and the USPTO. Utilizing mathematical algorithms for practical purposes is not excluded from patentability pursuant to Art 52(2) EPC and the principles of the Strasbourg Convention 1963. Many subsequent EPO decisions after T0208/84 confirm this principle of technical effect. Moreover, just because a method of surgery on a human or individual body is excluded by Art 52(2) EPC and Art 53 EPC, apparatus for use in surgery are not excluded from patentability. Thus, in embodiments of the present disclosure, a RACE engine is applied in a practical manner to control an assistive environment and improve its manner of operation and welfare of individuals associated with the assistive environment (such as, animals hosted in the real-life individual husbandry system or human patients within care homes, hospitals and so forth).

Optionally, the system further comprises a sensor arrangement that is spatially distributed within the assistive environment, wherein the data processing arrangement receives sensor signals from the sensor arrangement that senses in operation environmental conditions for each individual hosted in the assistive environment, including monitoring a food intake for each individual, and wherein the data processing arrangement executes the software product that analyses the sensor signals in respect of the decision support knowledge model by performing a multi-dimensional solution search in the decision support knowledge model based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each patient individual hosted within the assistive environment. Optionally, the genomic data is associated with a given genetic makeup of the patient individual, wherein the data processing arrangement executes in operation the high- order combinatorial search in a range of 3 to 20 orders.

Optionally, the genomic data is associated with a given genetic makeup of the patient individual, wherein the data processing arrangement executes in operation the high- order combinatorial search in a range of 5 to 13 orders.

Optionally, the SNP data includes single nucleotide polymorphisms (SNPs) characterizing each individual, for example determined by using genotyping or diagnostic microarrays, DNA sequencing, CRISPR tests or Polymerase Chain Reaction (PCR) to read genetic tissue samples derived for each individual .

Optionally, the sensor arrangement includes a plurality of sensors that are spatially distributed within the assistive environment and are coupled in communication with the data processing arrangement by using a wireless dynamically reconfigurable communication network. Optionally, the wireless dynamically reconfigurable communication network is implemented as a peer-to-peer network.

Optionally, the system collects in operation one or more pathogens present in the assistive environment, genotype sequences the pathogen to characterize the pathogen, and employs the characterization of the pathogen as an input parameter to the software product when executed in the data processing arrangement to use in performing its search for computing the welfare trajectory for each individual and/or decision support.

Optionally, the system collects in operation one or more microbes present in the assistive environment or within the individual (for example, within rumen contents or skin microbiome associated with diseases such as mastitis), genotype sequences the one or more microbes (for example Borrelia, causing Lyme disease) to characterize the one or more microbes, and employs the characterization of the populations of the one or more microbes as an input parameter to the software product when executed in the data processing arrangement to use in performing its search and/or decision support. Optionally, the one or more microbes are characterized by employing a technique such as Hi-C sequencing, metabolite measurement and the like. Optionally, in the system, the output signals are used to control at least one of type and/or quantity of food provided to the individuals; a time when food is provided to the individuals; additional food supplements, probiotic regimen and/or one or more drugs to be administered to the individuals; selective heating or cooling to be supplied to the individuals; and pathogen reducing processes to be applied to the assistive environment.

Optionally, the system in operation computes the welfare trajectory comprising the course of treatment to be prescribed to the individual by engineering the patient individual's disease-associated SNPs into an animal avatar; and screening a plurality of approved drugs via use of the avatar. Alternatively, instead of using avatars, or in addition thereto, tissue cultures can be used that are derived from biological samples taken from a given individual to be treated, wherein at least one of the tissue cultures is designated to be a control culture, and other of the tissue cultures are used to test efficacies of various combinations of drugs. Such a sample approach is especially effective when treating tumours and similar oncological ailments.

Optionally, the system includes an avatar testing arrangement including the animal avatar into which the individual's disease-associated SNPs are imported, and combinations of approved drugs and/or food supplements are tested to determine whether or not toxicological problems are likely to arise if the given combinations of approved drugs and/or food supplements are administered to the given individual .

Optionally, the avatar testing arrangement uses the animal avatar implemented as at least one of: an insect, Drosophila a fruit fly, a rat, a mouse, a rabbit, a dog, a cat, a pig, a monkey, an ape, a frog, a zebrafish.

Optionally, for example as an alternative to using avatars, the system in operation computes the welfare trajectory comprising the course of treatment to be prescribed to the individual by acquiring a biological sample from a given individual, culturing the biological sample to provide test tissue cultures, screening various drugs (for example, repurposed drugs) by applying the various drugs to the test tissue cultures and determining response from the test tissue cultures.

Optionally, the data processing arrangement, finds in operation high-order combinations of SNP genotypes which synergistically affect a disease status of the given individual represented in the input parameters.

Optionally, the welfare system operates to identify a treatment for a disease that is selected from a group including diabetes, cancer, cardiovascular, neurological disease and respiratory disease.

Optionally, the data processing arrangement, finds in operation single diseases or other phenotypic output case sub-populations that share high-order disease-associated combinatorial features.

Optionally, the data processing arrangement, for example using the aforesaid MARKERS engine, employs case sub-populations that share high-order disease- associated combinatorial features to provide personalized diagnosis and/or therapy selection.

Optionally, the data processing arrangement, for example using the aforesaid RACE engine, designs in operation a course of treatment for the given individual, wherein the treatment is based on at least one of: the given individual's SNP genotype, at least one non-genomic feature of the given individual . Optionally, the treatment is based upon the given individual's SNP genotype, and at least one non-genomic feature of the given individual .

Optionally, the data processing arrangement, for example using the aforesaid RACE engine, designs in operation the course of treatment for the given individual based only on phenotypic features of the individual .

Optionally, the data processing arrangement, for example using the aforesaid RACE engine, selects in operation at least one of the one or more features from veterinary observations, tests carried out on the given individual and information of medications and drugs.

Optionally, the data processing arrangement employs, when in operation, ongoing observations, as the medications are used for treating the given individual, that are added as features to the input parameters used by the data processing arrangement (for example, that uses the aforesaid RACE engine).

According to a second aspect, the present disclosure provides a welfare system that provides welfare support in operation to a one or more individuals in an assistive environment (for example, animals in a farming and veterinary environment, or humans within care homes, hospitals, domestic caring home environments or clinical facilities), wherein the welfare system includes a data processing arrangement that receives, when in operation, sensor signals from a sensor arrangement that is spatially distributed within the assistive environment, wherein the data processing arrangement includes a decision support knowledge model (implemented using a RACE engine) against which the sensor signals are compared, wherein the data processing arrangement provides output signals that control operation of the assistive environment, and wherein the data processing arrangement executes a software product that in execution analyses the sensor signals in respect of the decision support knowledge model and generates the output signals, characterized in that:

(a) the software product (implementing the RACE engine) is configured to perform a multi-dimensional solution search in the decision support knowledge model, the search being based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each individual within the assistive environment;

(b) the sensor arrangement senses, when in operation, environmental conditions for each individual, including monitoring food and water intake for each individual;

(c) the decision support knowledge model (for example, implementing the RACE engine or similar computing engine) is populated with at least one of drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each individual, the individual's genotype, SN P and microbiome data; and

(d) the software product (implementing the RACE engine) is arranged to compute a welfare trajectory for each individual.

According to a third aspect, an embodiment of the present disclosure provides an welfare system that, when in operation, develops a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's specific disease, wherein the medical development system includes a data processing arrangement (using the aforesaid RACE engine) that receives a plurality of measurands of the given individual and accesses a decision support knowledge model including a plurality of treatment strategies and genomic data, wherein the data processing system (using the aforesaid RACE engine) executes in operation a high-order combinatorial search within the decision support knowledge model based upon the plurality of measurands, characterized in that the welfare system, when in operation :

(a) employs the given individual's SNP genotypes and/or one or more other features which synergistically affect disease status as a part of the measurands, and

(b) the data processing arrangement (using the aforesaid RACE engine) identifies high-order combinations of the individual's SNP genotypes, using a computational engine with combinatorial methodology (using the aforesaid MARKERS engine) for combinatorial feature analysis executed in the data processing arrangement;

(c) identifies a course of treatment to be prescribed to the given individual.

The welfare system is of advantage in that it is capable of performing high-order combinatorial searches (using the aforesaid MARKERS engine) within a database (such as the decision support knowledge model) to identify all possible treatment modalities. By "high-order" is meant at least an order 3, more optionally at least an order 8, yet more optionally at least an order 20, and yet more optionally at least an order 50 (if input datasets allow for such a high-order as 50).

Known combinatorial search engines can reach combinations of 3 features in limited preselected circumstances; in contradistinction, embodiments of the present disclosure (using the aforesaid MARKERS engine) are able to perform searching at higher-orders than an order 3, as well as searching comprehensively for an order 3; at present, embodiments of the present disclosure have no pre-set limit to this, but are dependent on a size of an available dataset to be searched. For example, embodiments of the present disclosure are able to find significant clusters of up to an order 20 or so features in combination, but finding search results at an order 50 or even higher is possible in embodiments of the present disclosure, given suitable data to search.

The welfare system of the present disclosure provides a new approach to combinatorial and multi-modal biomarker discovery and to designing optimal therapeutic and targeted treatments (using the aforesaid MARKERS engine). Moreover, methods of the present disclosure include employing the medical development systems to use a corpus of knowledge of variants in a given individual to design an optimal therapeutic intervention specific to the given individual. The methods include performing a high- order combinatorial search (using the aforesaid RACE engine) within the database (such as the decision support knowledge model), wherein the search is based upon a plurality of measurands derived from the given individual's variants. By "high-order" is meant at least an order 3, more optionally at least an order 8, yet more optionally at least an order 20, and yet more optionally at least an order 50 (if input datasets allow for such a high-order as 50).

In a fourth aspect, the present disclosure provides a method of (namely a method for) operating an welfare system that provides welfare support in operation to one or more individuals in an assistive environment (for example, to animals in a farming and veterinary environment, or to people in a care homes, hospitals, domestic caring home environments or clinical facilities), wherein the welfare system includes a data processing arrangement implementing a RACE engine that receives in operation a plurality of measurands of a given individual within the assistive environment, wherein the data processing arrangement includes a decision support knowledge model including a plurality of treatment strategies and at least one of: drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each individual, individual genotype data, and SN P data, wherein the data processing arrangement provides output signals for developing a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's specific disease, and wherein the data processing arrangement executes a software product that in execution performs a high-order combinatorial search within the decision support knowledge model based upon the plurality of measurands and generates the output signals, characterized in that the method includes:

(a) employing the given individual's SNP genotypes and/or one or more other features which synergistically affect disease status as a part of the measurands;

(b) arranging for the software product to perform a multi-dimensional solution search in the decision support knowledge model to identify high-order combinations of the given individual's SN P genotypes, using a computational engine, implemented as the RACE engine, with combinatorial methodology for combinatorial feature analysis executed in the data processing arrangement, for each individual within the assistive environment; and

(c) using the software product to compute a welfare trajectory for each individual, wherein the welfare trajectory comprises a course of treatment to be prescribed to the patient individual.

Optionally, the method includes arranging for the SNP data to include single nucleotide polymorphisms characterizing each individual, determined by using microarrays, DNA sequencing, CRISPR or Polymerase Chain Reaction (PCR) to read genetic tissue samples derived for each individual.

In a fifth aspect, an embodiment of the present disclosure provides a method of (namely, a method for) operating an welfare system that provides welfare support in operation to a plurality of individuals in an assistive environment (for example, an assistive environment), wherein the welfare system includes a data processing arrangement (using the aforesaid RACE engine) that receives in operation sensor signals from a sensor arrangement that is spatially distributed within the assistive environment, wherein the data processing arrangement (using the aforesaid RACE engine) includes a decision support knowledge model against which the sensor signals are compared, wherein the data processing arrangement (using the aforesaid RACE engine) provides output signals that control operation of the assistive environment, and wherein the data processing arrangement (using the aforesaid RACE engine) executes a software product that in execution analyses the sensor signals in respect of the decision support knowledge model and generates the output signals, characterized in that the method includes:

(a) arranging for the software product (using the aforesaid RACE engine) to perform a multi-dimensional solution search in the decision support knowledge model, the search being based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each individual within the assistive environment;

(b) using the sensor arrangement to sense in operation environmental conditions for each individual, including monitoring a food intake for each individual;

(c) populating the decision support knowledge model (of the aforesaid RACE engine) with at least one of drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each breed of individual, individual genotype, SNP and microbiome data; and

(d) using the software product (using the aforesaid RACE engine) to compute a welfare trajectory for each individual. Optionally, the method includes arranging for the sensor arrangementto include a plurality of sensors that are spatially distributed within the assistive environment and are coupled in communication with the data processing arrangement by using a wireless dynamically reconfigurable communication network.

Optionally, the method includes arranging for the wireless dynamically reconfigurable communication network to be implemented as a peer-to-peer network.

Optionally, the method includes arranging for the system to collect in operation one or more pathogens and/or other microorganisms (for example, neutral, commensal and/or other beneficial microorganisms) present in the assistive environment, to perform genotype sequencing of the one or more pathogens to characterize the one or more pathogens and/or other microorganisms, and to employ the characterization of the one or more pathogens and/or other microorganisms as an input parameter to the software product (using the aforesaid RACE engine) when executed in the data processing arrangement to use in performing its search and/or decision support.

Optionally, the method includes using one or more microbes present in the assistive environment, with genotype sequence of the one or more microbes to characterize the one or more microbes, and employing the characterization of the populations of the one or more microbes as an input parameter to the software product when executed in the data processing arrangement (using the aforesaid RACE engine) to use in performing its decision support.

Optionally, the method includes using the output signals to control at least one of a type and/or a quantity of food provided to the individuals; a time when food is provided to the individuals; additional food supplements and/or one or more drugs to be administered to the individuals; selective heating or cooling to be supplied to the individuals; and pathogen reducing processes to be applied to the assistive environment.

Optionally, the method includes arranging for the data processing arrangement (using the aforesaid MARKERS engine) to find in operation high-order combinations of SNP genotypes which synergistically affect a disease status or optimal husbandry practice for an individual represented in the input parameters.

Optionally, the method includes arranging for the data processing arrangement (using the aforesaid MARKERS engine) to find in operation single disease or other phenotypic output case sub-populations that share high-order disease-associated combinatorial features. By "high-order" is meant at least an order 3, more optionally at least an order 8, yet more optionally at least an order 20, and yet more optionally at least an order 50 (if input datasets allow for such a high-order as 50).

Optionally, the method includes arranging for the data processing arrangement (for example, using the aforesaid RACE engine or similar computing engine) to design in operation a course of treatment that is customized for a given individual, wherein the treatment is based upon the individual's SNP genotype and at least one non-genomic feature of the given individual .

Optionally, the method includes arranging for the data processing arrangement (using the aforesaid RACE engine) to select in operation at least one of the one or more features from veterinary observations, tests carried out on the given individual and information of medications and drugs.

Optionally, the method includes arranging for the data processing arrangement (using the aforesaid RACE engine) to employ in operation ongoing observations, as the medications are used by the given individual, that are added as features to the input parameters used by the data processing arrangement.

Optionally, the method of (namely the method for) treating an individual in need thereof, comprises:

(a) identifying high-order combinations of SNP genotypes and/or one or more other features which synergistically affect disease status, using the aforesaid system (using the aforesaid MARKERS engine), and/or the aforesaid method;

(b) designing (using the aforesaid RACE engine) a course of treatment to be prescribed to the individual, the treatment based upon the individual's genotype (SNPs) and/or at least one or more non-genomic feature; and

(c) administering the prescribed treatment of the individual .

Optionally, the method of (namely the method for) treating an individual in need thereof includes: (a) identifying high-order combinations of the individual's SN P genotypes and/or one or more other features which synergistically affect disease status, using the aforesaid system (using the aforesaid RACE engine), and/or the aforesaid method;

(b) identifying a course of treatment to be prescribed to the individual ; and

(c) the prescribed treatment to the individual .

Optionally, the method of (treating an individual in need thereof includes implementing a treatment using a combination of drugs.

Optionally, method of designing a course of treatment to be prescribed to an individual comprises:

(a) identifying high-order combinations of SN P genotypes and/or one or more other features which synergistically affect disease status, using the aforesaid method which is implemented using a welfare system (using the aforesaid RACE engine); and

(b) designing (for example using the aforesaid RACE engine or similar computing engine) a course of treatment based upon the case's genotype (SN Ps) and/or at least one more non- genomic feature.

Optionally, the method of identifying a course of treatment to be prescribed to a case comprises:

(a) identifying high-order combinations of the individual's SNP genotypes and/or one or more other features which synergistically affect disease status, using the aforesaid method (using the aforesaid RACE engine) or the aforesaid system (using the aforesaid RACE engine);

(b) identifying a best course of treatment based on results from the screening, the individual's SN P genotypes and/or one or more other features.

In a sixth aspect, an embodiment of the present disclosure provides a method of (namely a method for) using an welfare system that, when in operation, develops a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's specific disease, wherein the medical development system includes a data processing arrangement (using the aforesaid RACE engine) that receives a plurality of measurands of the given individual and accesses a decision support knowledge model including a plurality of treatment strategies and genomic data, wherein the data processing system executes in operation a high-order combinatorial search (using the aforesaid RACE engine) within the decision support knowledge model based upon the plurality of measurands, characterized in that the method includes:

(a) employing the given individual's SNP genotypes and/or one or more other features which synergistically affect disease status as a part of the measurands, and the data processing arrangement identifies high-order combinations of the given individual's SN P genotypes (using the aforesaid RACE engine), using a computational engine with combinatorial methodology for combinatorial feature analysis executed in the data processing arrangement;

(b) identifying (using the aforesaid RACE engine) a course of treatment to be prescribed to the given individual.

In a seventh aspect, the present disclosure provides a control apparatus (using the aforesaid RACE engine) for processing one or more data inputs in a computing arrangement to provide one or more control outputs and/or one or more analysis output and/or one or more recommendation outputs, characterized in that the control apparatus includes a user interface for interacting with a user of the control apparatus for controlling operation of the control apparatus, a data processing arrangement that is operable to receive the one or more data inputs and to output the one or more control outputs and/or one or more analysis output and/or one or more recommendation outputs, wherein the computing arrangement is operable to execute a software product for implementing the method.

In an eighth aspect, the present disclosure provides a software product recorded on machine-readable non-transitory (non- transient) data storage media, wherein the software product is executable upon computing hardware for implementing the aforementioned method (using the aforesaid RACE engine); in other words, the present disclosure provides a computer program product comprising a non-transitory computer-readable storage medium having computer-readable instructions stored thereon, the computer-readable instructions being executable by a computerized device comprising processing hardware to execute the aforesaid method (using the aforesaid RACE engine). In a further aspect, there is provided a drug or combination of drugs for use in individual therapy, characterized in that the drug or combination of drugs to be administered to the individual are identified using the aforesaid method (using the aforesaid RACE engine).

Additional aspects, advantages, features and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative embodiments construed in conjunction with the appended claims that follow.

It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.

DESCRIPTION OF THE DRAWINGS

The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein. Moreover, those in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.

Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams wherein :

FIG. 1 is a schematic illustration of a welfare system that provides welfare support in operation to a plurality of individuals in a assistive environment (for example, an assistive environment), in accordance with an embodiment of the present disclosure;

FIG. 2 is a process diagram illustrating steps that are implemented by the welfare system for enabling a software product toperform a multi-dimensional solution search in a decision support knowledge model, in accordance with an embodiment of the present disclosure, wherein the software product is supplied with sensor data captured by a sensor arrangement disposed in the assistive environment, for example using Internet-of-Things 'loT") coupled sensors; FIG. 3 is a process diagram illustrating steps that are implemented by an avatar testing arrangement, in accordance with an embodiment of the present disclosure;

FIG. 4 illustrates steps of a method of (namely, a method for) operating an welfare system that provides welfare support in operation to a plurality of individuals in a assistive environment (for example, a assistive environment), in accordance with an embodiment of the presentdisclosure;

FIG. 5 illustrates steps of a method of (namely, a method for) treating an individual in need thereof, in accordance with an embodiment of the present disclosure;

FIG. 6 is an illustration of steps of a method of identifying a course of treatment to be prescribed to a given individual, in accordance with an embodiment of the present disclosure;

FIG. 7 is an illustration of a cycle of continuous welfare to be provided to animals, in accordance with an embodiment of the present disclosure;

FIG. 8 is an illustration depicting selection of routes that do not impinge on other selected phenotypes, in accordance with an embodiment of the present disclosure; and

FIG. 9 is a schematic illustration of a Precisionlife Data Annotation Platform that is employed in the welfare system of FIG. 1, wherein the Annotation Platform, includes multiple source objects from MARKERS (namely, networks, SN Ps and genes), multiple annotation sources, storage and integration of semantic knowledge, heuristics and human knowledge.

In the accompanying drawings, an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent. A non-underlined number relates to an item identified by a line linking the non-underlined number to the item . When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.

DESCRIPTION OF EMBODIMENTS In overview, the present disclosure is concerned with welfare systems that provide welfare support, when in operation, to a plurality of individuals in assistive environments (for example, farming and veterinary environments for animals, care homes, hospitals, and the like for people (i .e. human beings), and with methods of operating the aforesaid welfare systems. Furthermore, the present disclosure is concerned with welfare systems that, when in operation, develop personalized identifications of one or more active drug combinations for the treatment or prevention of a given patient individual's specific disease, and with a method of (namely, a method for) using such welfare systems.

Referring to FIG. 1, there is shown a schematic diagram of a welfare system 100 that is usable to provide welfare support, when in operation, to the plurality of individuals in an assistive environment; for example, the assistive environment pertain to animals in a farming and veterinary environment, alternatively people within care homes, hospitals and the like, in accordance with an embodiment of the present disclosure. The welfare system 100 comprises a data processing arrangement 102, a sensor arrangement 104 and a decision support knowledge model 106; the data processing arrangement 102, the sensor arrangement 104 and the decision support knowledge model 106 operate synergistically together to provide an enhanced quality of life for the individuals. As will be described in more detail later, the welfare system 100 employs a RACE engine to receive sensor and measurement signals (for example gene variant information, environmental sensor data, individual food data, individual measurement data) and to provide outputs for controlling the welfare system 100 to deliver enhanced welfare support. The welfare system 100 also utilizes a MARKERS model and ANNOTATION model that will be described in greater detail later. Such a RACE engine (used interchangeably as " RACE model"), MARKERS model (used interchangeably as "MARKERS engine") and ANNOTATION model (used interchangeably as "ANNOTAΉON engine") can form a part of, and operate collaboratively with each other, under a "Predsionlife pbtfomf. Consequently, when the ANNOTATION model forms a part of the Precisionlife platform, for example, the ANNOTATION model has been referred to as" Predsionlife Data Annotation Platform” (such as, with reference to FIG. 9).

The welfare system 100 refers to a system that, when is operation, performs a targeted and contextualized decision support (using the aforesaid RACE engine) for a plurality of individuals under consideration. The welfare system 100 prepares the targeted decision support based on one or more genotypes of the plurality of individuals under consideration, and any relevant polymorphism determined via Single Nucleotide Polymorphism (SNP) thereof. The welfare system 100 monitors the growth process of the plurality of individuals under consideration in order to provide the plurality of individuals with improved welfare, for example optimal welfare (for example, adapting support to the plurality of individuals i n a cu stom i zed m a n ne r that addresses special needs of each individual within the plurality of individuals under consideration, that may vary from one individual to another (for example, certain individuals may have disease susceptibilities or anatomical features such as weak feet or legs that requires special attention, other conditions causing the certain individuals discomfort and pain, requiring administration of food supplements such as glucosamine)). Furthermore, the welfare system 100 utilizes methods of (namely methods for) using a knowledge of variants in a given individual to design an optimal therapeutic intervention specifically customized to the given patient individual. The welfare system includes a high-order combinatorial search (using the aforesaid RACE engine) within the decision support knowledge model 106 is based upon the plurality of measurands derived from a given individual's variants, for example, using the sensor arrangement 104. By " high-order " is meant at least an order 3, more optionally at least an order 8, yet more optionally at least an order 20, and yet more optionally at least an order 50 (if input datasets allow for such a high-order as 50). For example, the combinatorial search is performed to find all significantly associated combinations in a hypothesis- free manner. Such a finding of all associated combinations does not relate to pre selection of specific pathways/genes. A detailed explanation for what is meant by "high-order" is provided herein later. The welfare system 100 is further operable to evaluate an optimal support regime for each individual in the plurality of individuals under consideration and to plan a support trajectory for each of the individuals in the plurality of individuals under consideration. Furthermore, the plurality of individuals under consideration belong to the assistive environment, namely are hosted in the assistive environment. The assistive environment may be, in a case of animals, a farm with farmhouse and outbuildings, a cattle breeding farm or any area used for keeping and breeding of the plurality of individuals under consideration. In a case of humans, the assistive environment may be a care home, a hospital, a domestic caring home environment, a clinical facility and the like. Optionally, the combinatorial analysis is performed to identify combinations of features that are predictive of specific phenotypes and a combination of features associated with a variety of responses to particular diets and/or environment. Thereafter, the combinations of features are employed to derive combinatorial risk scores and the features as well as the risk scores will form one of the inputs to the RACE engine, alternatively to the aforesaid MARKERS engine and ANNOTATION engine. Optionally, other constraints and data can be incorporated into the RACE engine as well, such as, IoT and environmental data, in order to further optimize and personalize the predictions and decision support recommendations.

Furthermore, the welfare system 100 includes the data processing arrangement 102 (using the aforesaid RACE engine) that receives in operation sensor signals from the sensor arrangement 104 that is spatially distributed within the assistive environment. Furthermore, the data processing arrangement 102, when in operation, processes (using the aforesaid RACE engine) the received sensor signals. Additionally, optionally, the data processing arrangement 102 is an arrangement of Internet-compatible devices having data processing capabilities, that are mutually coupled together via a data communication network. Notably, the data processing arrangement 102 constitutes a powerful computing engine arrangement (forexample using the aforesaid RACE engine) that facilitates performing data processing for provision of individualized support (namely, customized support) to individuals in the assistive environment. The data processing arrangement 102 may be a software, hardware, firmware or a combination thereof, for example custom-designed digital hardware. The data processing arrangement 102 may include one or more processors connected to each other in any architecture such as parallel orpipelined. In an example, the data processing arrangement 102 may include a communication module for receiving sensor signals from the plurality of sensors. Furthermore, the sensor arrangement 104 senses in operation environmental conditions for each individual, including monitoring a food intake for each individual. Additionally, sensor arrangement 104 is an arrangement of Internet-compatible devices having sensing capabilities. The sensor arrangement 104 senses, when in operation, environmental conditions experienced by each individual, including monitoring a food intake for each individual, spatial movement of each individual, a temperature of each individual, a water intake of each individual. Examples of the environmental conditions include, but are not limited to, temperature within the assistive environment, humidity within the assistive environment, sunlight exposure within the assistive environment, air quality within the assistive environment, and chemical exposure within the assistive environment. In an example, the plurality of sensors include cameras to view the plurality of individuals under consideration (skin, face, manner of movement, sleeping pattern and posture, temperature sensors, humidity sensor, sunlight exposure sensors in individual housings, such as, via wireless tags attached to animals or humans, food intake monitoring sensors (e.g. from mechanized feeding trays), gas sensors (such as Carbon Dioxide CO₂, methane CH₄, Hydrogen Sulphide HS, and the like) and light exposure monitoring sensors (e.g. individual tags worn on animals or humans). Specifically, humidity sensors are implemented as thin-film polyamide sensors, temperature sensors are implemented as thermistor or integrated-circuit solid-state temperature sensors (for example as temperature sensors housed in injection-moulded plastic tags (namely, animal tags or human tags) that can be attached to each of the plurality of individuals, to food troughs, to water troughs, to barriers between animal pens, to doors and gates of individual pens, suspended from a roof/ ceiling). The animal tags, likewise the human tags, have network connectivity with a peer-to-peer network communication around the assistive environment, wherein, due to movement of any of the plurality of animals or humans, the peer-to-peer network is dynamically reconfigurable (for example, by using a calibration routine periodically around the peer-to-peer network based on signal strength to find principal Eigenvector routes of communication). Air-flow sensors in the animal environment are beneficially implemented as heated wire pair transducers or thermistor pair transducers. Optionally, there is employed Internet of Things (IoT) technology, for implementing a data communication network using standard proprietary commercially-available communication devices. Moreover, the plurality of sensors in the sensor arrangement 104 are positioned deterministically or randomly within the assistive environment. Additionally, the plurality of sensors is positioned in a way to achieve maximum coverage of the assistive environment. Moreover, the positioning of the plurality of sensors in the sensor arrangement 104 is implemented in a way to achieve a maximum connectivity therebetween. At an example, the plurality of sensors may communicate with each other to communicate the sensor signals to the data processing arrangement 102. In another example embodiment, the plurality of sensors may communicate the sensor signals to a base station that may further aggregate the sensor signals received form the plurality of sensors to the data processing arrangement 102.

Optionally, the sensor arrangement 104 includes the plurality of sensors that are spatially distributed within the assistive environment and are coupled in communication with the data processing arrangement 102 by using a wireless dynamically-reconfigurable communication network. The plurality of sensors may communicate with each other via a wireless sensor network. Furthermore, channels for wireless communication may not be dedicated and may be reconfigured as and when required. In an example embodiment, the wireless communication network may be non-reconfigurable. More optionally, the data processing arrangement receives satellite signals, other imagery, digital biomarkers and/or employs non-local monitoring methods. More optionally, the wireless dynamically-reconfigurable communication network is implemented as the peer-to-peer (P2P) network. Beneficially, use of spatially distributed sensors of the sensor arrangement 104 in the assistive environment with reconfigurable wireless peer-to-peer network allows the plurality of sensors to be deployed easily with very modest infrastructure cost. Moreover, hardware used in the communication network may be designed to be recycled from one generation of the plurality of individuals to next generation thereof (e.g. reusing electronic sensor- equipped individual tags).

Furthermore, the data processing arrangement 102 includes the decision support knowledge model 106 (for example using the aforesaid RACE engine, MARKERS engine or ANNOTATION engine) against which the sensor signals are compared. The decision support knowledge model 106 is populated with at least one of drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each individual, individual genotype data, and SNP data. Moreover, the decision support knowledge model 106 includes genotype information, potential diets, potential medications, medication list, food supplement list and the like to be followed for each of the plurality of individuals under consideration. The sensor signals compared with the decision support knowledge model 106 provide details for targeted precision support for each of the individuals in the plurality of individuals under consideration. Additionally, data gathered for each of the individuals in the plurality of individuals by the sensor arrangement 104 allows for the decision support knowledge model 106 to be iteratively updated. Beneficially, the welfare system is capable of learning from past experiences derived from gathered and archived data related to phenotypic data, genotypic data like single nucleotide polymorphism associated with the plurality of individuals under consideration, environmental data, food intake data, drug interventions and so forth. Optionally, the decision support knowledge model 106 employs artificial intelligence (AI) algorithms for monitoring individual behaviour of each individual and its habits, developing a corresponding model characterizing each individual, and then identifying deviations from the corresponding model characterizing each individual that are potential indicative when each individual is any manner uncomfortable (for example, stressed or unable to achieve expected outcome metrics), distressed or ill. In an event that a given individual has deteriorating wellbeing, the welfare system 100 initiates care measures to assist the given individual achieve an improved state of wellbeing.

Optionally, the SNP data includes single nucleotide polymorphism characterizing each individual, determined by using microarrays, DNA sequencing, CRISPR tests or Polymerase Chain Reaction (PCR) to read genetic tissue samples derived for each individual . The term "single nucleotide polymorphisms" (SN Ps) relates to genetic variations among a given species of the individuals. Notably, such single nucleotide polymorphisms are identified upon analysis of DNA sequences of the given individuals, wherein each single nucleotide polymorphism represents a variation in a single nucleotide within DNA sequences of different members of the given individuals. It will be appreciated that the genetic tissue samples derived for each of the individuals allow for obtaining DNA sequences for each of the individuals, wherefrom, the single nucleotide polymorphisms characterizing each individual (namely, phenotypes of the individuals) are determined by using microarrays, DNA sequencing, CRISPR tests or Polymerase Chain Reaction (PCR) . Furthermore, Polymerase Chain Reaction (PCR) is a molecular biology technique that allows for amplification of a segment of a given DNA sequence across several orders of magnitude whilst making multiple copies of the segment of the given DNA sequence. Optionally, such SNP data is obtained in respect of embryos (for example from corresponding blastocysts) for selecting embryos that will give rise to desired phenotype characteristics, wherein selected embryos are subsequently implanted using IVF to generate individuals with preferred phenotype characteristics; such an approach avoids a need to generate individuals with undesirable phenotype characteristics and thus enables the welfare system 100 to operate more efficiently by needing to support only desired individuals. Alternatively, the SN P data is obtained for identification of elite parents for selective breeding of offspring. For example, the SNP data is obtained for optimized selective breeding, such as, for reducing a generational interval and optimizing for multiple traits simultaneously. Furthermore, the selection criteria can include non-genomic criteria such as epigenetic factors, expression levels, and so forth, as well as diversity in part, as indicated by pedigree of animals.

The welfare system 100, when in operation, develops a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's specific disease, in accordance with an embodiment of the present disclosure. The welfare system 100 includes the data processing arrangement 102 (that employs the aforesaid RACE engine) that receives a plurality of measurands of the given individual from the sensor arrangement 104 and accesses the decision support model 106 including a plurality of treatment strategies and genomic data.

The welfare system 100, when in operation, employs the patient individual's SN P genotypes and/or one or more other features which synergistically affect traits (such as, disease status associated with humans and animals; yield, food conversion, fertility, milk quality and so forth associated with animals) as a part of the measurands obtained using the sensor arrangement 104. It will be appreciated that a same disease can be caused due to presence of a plurality of different SNPs. Furthermore, individuals having the disease may share a number of SNPs therebetween. Moreover, such individuals can correspond to one or more common features, such as one or more phenotypic features, clinical features, lifestyle features and so forth. In such an example, the welfare system 100, when in operation, employs the patient individual's SN P genotypes and/or one or more other features (such as, epigenetic factors, epidemiologic factors, environmental factors or a combination thereof) which synergistically affect the disease status as part of the measurands. Optionally, the welfare system 100 comprises a single-nucleotide polymorphism (referred to as "SNP" hereinafter) genotyping device (such as, implemented as part of the sensor arrangement 104) that is capable of determining SNP genotypes within a population. Such a SNP genotyping device can employ one or more SNP genotyping techniques for the determination of the SNP genotypes, including but not limited to, hybridization- based techniques such as SNP microarrays, enzyme-based techniques such as PCR- based techniques, or next generation sequencing (NGS) techniques such as temperature gradient gel electrophoresis (TGGE), which are performed over a wide and non-biased selection of SNP samples. Optionally, the SNP genotyping device is also capable of determining one or more additional features associated with the SNPs within the population. The features associated with the SNPs are obtained from performing DNA base readout from biological samples. In an example, the DNA base readout from the biological samples is performed as part of a Genome-Wide Association Study (referred to as "GWAS" hereinafter).

In another example, SNP-genotyping arrays are employed to identify the features associated with a given population of individuals. Such an SNP-genotyping array can perform SNP genotyping for tens of thousands of individuals (patient individuals and healthy individuals). The SNP-genotyping array is employed as part of a canine genomic study, to identify novel clusters of disease causing mutations (in developmental as well as adult stages) corresponding to chondrodysplasia within a population of 1,600 canines (120 breeds). The SNP-genotyping array employed is CanineHD array by Illumina® (alternatively, very highly enriched signals can be used for accurate risk scoring and/or diagnosis for individuals, to determine a best intervention strategy), the array corresponding to anonymised 150,000 SNPs. Correspondingly, it was identified that 90% of cases contained a top 30 signature (985 SN Ps) while a 98% of cases contained a top 100 signature (1,500 SNPs). Furthermore, the SNP-genotyping arrays are available in multiplex formats for huge throughput. Moreover, the features of the one or more SNPs are stored in the decision support knowledge model 106. Furthermore, the biological samples are collected from a plurality of patient individuals suffering from a specific disease or disorder and a plurality of as healthy individuals not suffering from the specific disease or disorder. The measurands obtained from performing the DNA base readout of the biological samples comprise information about SNP genotypes and features associated with the SN Ps for the plurality of patient individuals and the plurality of healthy individuals. In one embodiment, the features associated with a given population of individuals are identified using quantitative trait association, outlier comparison, non-diploid genotypes, and so forth.

Furthermore, the data processing arrangement 102, when in operation, generates data (using a MARKERS engine, see ANNEX II that provides a detailed disclosure of implementation of the MARKERS engine) by using the measurands obtained via the sensor arrangement 104. Such data generated from the measurands is stored in the decision support knowledge model 106 as data files. In an example, the data files comprise the measurands in a structured format (such as a table), wherein the measurands comprise an individual identifier, a CC vector, SNP genotypes and SNP identifiers (referred to as "SNPid" hereinafter). In one example, the CC vector can have a value of O' when the individual is the patient individual suffering from the specific disease or disorder, or a value of Ί' when the individual is the healthy individual not suffering from the specific disease or disorder. In an example, the SNP genotype can take a value of 'O' when the SNP genotype is a homozygous major (or normal) allele, a value of Ί' when the SNP genotype is a heterozygous allele, a value of '2' when the SNP genotype is a homozygous minor (or variant) allele, or a value of '3' when the SNP genotype is unknown. In one example, the SNPid can comprise information about the SNP, such as an index or an "rs number" of the SNP. In an example, the SNP genotype and the SNPid can be stored together in a form of tuples comprising the index of the SNP and the genotype of the SNP. In such an example, when the index of the SNP is 247 and the SNP is associated with a homozygous major allele genotype, the SNP genotype and the SNPid can be stored together as 247^, wherein the index 247 of the SNP can be associated with an rs number such as rsl2345678. Thus, the data for each of the plurality of patient individuals and/or healthy individuals can be stored in a structured format as CC vector of the individual, followed by the tuples comprising the index of the SNP and the genotype of the SNP. In one example, when a patient individual corresponds to an individual identifier of number 27, the data can be expressed as:

Case #27 1 1° 2° 3¹ 4° 5² 6¹... n^k

The data processing arrangement 102 executes (using the aforesaid RACE engine), when in operation, a high-order combinatorial search within the decision support knowledge model 106 based upon the plurality of measurands obtained using the sensor arrangement 104. The data processing arrangement 102 is operable to receive the plurality of measurands of the given patient individual and the plurality of treatment strategies and genomic data from the decision support knowledge model 106 and perform processing thereon (as described in detail hereinafter).

Optionally, the data processing arrangement 102, when in operation, uses a computational engine ( na me ly, the aforesa i d " RAC E e ng i n e") with combinatorial methodology that is used for combinatorial feature analysis (see ANNEX I that provides a detailed disclosure of implementation of the RACE engine). The combinatorial feature analysis may take into account epistatic interactions between various genetic and non-genetic factors. The term "epistatic interaction" as used herein, refers to combinations of multiple features in a gene, such as SNP genotypes, affecting phenotypes in another allele in a reproducible manner. The term "phenotype" used herein, relates to physical traits, diseases, disease-associated factors, disease risk, therapy response and so forth. In an example, the patient individuals are associated with cancer or mutation. In such an example, a number of patient individuals corresponding to specific phenotypes are selected and high-order combinations of the patient individuals' SNP genotypes are identified. It will be appreciated that such SNP genotypes will be present in a plurality of patient individuals but absent in a plurality of healthy individuals (It will be appreciated that in late-onset diseases, there may be many young controls who share the genotypic features that will increase their eventual disease risk, but who have not encountered sufficient sporadic mutations or environmental factors to cause them to develop the disease). Furthermore, such SN P genotypes are determined to be disease-associated SNP genotypes and thus, such SNP genotypes are considered for further testing and validation by the welfare system 100

Optionally, the welfare system 100 operates to analyse the patient individual's entire exome from a patient individual's tumour biopsy provided as measurands to the data processing arrangement 102. The term "exome" as used herein, refers to a portion of genome that encodes for functional proteins. The patient individual's entire exome is analysed using standard techniques comprising at least one of: Sanger sequencing (followed by linkage analysis and autogygosity mapping), DNA microarrays, next generation sequencing (NGS) techniques, genome-wide association study (GWAS), whole exome sequencing (WES) and analysis and the like. The analysis of the patient individual's entire exome enables to identify measurands within a population, such as SN Ps, SNP genotypes, features associated with a phenotype and so forth, for conducting association studies or testing for future disease risk, prevention and treatment. It will be appreciated that exome data may only have a small subset (such as, less than 2%) of features that are disease-associated. Consequently, gene expression control features are more heavily involved than coding region mutations in most complex traits.

The patient individual's disease-associated SNPs can be obtained by performing a tumour biopsy for the patient individual. Alternatively, the patient individual's disease- associated SNPs can be obtained from a DNA-containing sample, such as blood, skin tissue, amniotic fluid, buccal swab, hair, saliva, faeces and so forth. The term "biopsy" as used herein, refers to a technique of removing a small tissue sample (such as a tumour) using a needle, or by surgical removal of a suspicious lump or nodule from a site of biopsy. Optionally, imagingguidance by employing X-ray, ultrasound, magnetic resonance imaging (MRI), computed tomography (CT or CAT) and so forth, allows for accurate placement of the needle (or other surgical equipment) to locate the site of biopsy. Subsequently, upon location of the site of biopsy, a small incision is made at the skin around the site and the needle is inserted into a lesion caused by the incision, to remove the tissue sample therefrom. Optionally, the tumour biopsy can be performed by employing a technique such as, fine-needle biopsy, core-needle biopsy, vacuum-assisted biopsy and the like. More optionally, the tumour biopsy is performed automatically the sensor arrangement 104. Thereafter, at an end of the biopsy, the site of biopsy is covered with a dressing or bandage. The welfare system 100 provides the patient individual's tumour biopsy as measurands to the data processing arrangement 102. Subsequently, the data processing arrangement 102 determines an outcome by executing computations on the measurands. For example, the data processing arrangement 102 is given the measurands comprising two or more SN P genotypes and the outcome from computations executed by the data processing arrangement 102 includes at least one specific phenotype. In such an example, the phenotype can be a disease caused by at least one of the two or more SNP genotypes. Optionally, the data processing arrangement 102 finds from the specific phenotype, one or more causal SNP genotypes associated with various other genes that may cause the disease.

Optionally, the data processing arrangement 102, when in operation, (using the aforementioned RACE engine) finds high-order combinations of SNP genotypes which synergistically affect a disease status of an individual. Furthermore, such SNP genotypes can be stored by the data processing arrangement 102 within a database (not shown) communicatively coupled with the data processing arrangement 102, to be employed as input measurands at a later time.

The welfare system 100 further operates to capture a tumour network pertaining to the patient individual's entire exome. It will be appreciated that a large number of genes are associated with disease risk, and identification of the genes along with their association to other related pathways is essential for analysing the patient individual's entire exome. For example, when one or more SNPs result in formation of malignant tumours, the welfare system 100 identifies the SNPs responsible for the formation of the tumours.

Furthermore, apart from the genetic factors (such as SNPs), non-genetic factors influence the formation of the tumours. Such non-genetic factors comprise one or more of: non-coding variants, biological insights, metabolic pathways, lifestyle (such as diet, sleep, physical activity and the like), clinical information (such as existing diseases, diagnostic results like imaging, assays and the like), phenotypic information (such as age, sex, race, weight, comorbidities) and so forth. In such an example, the welfare system 100 captures the tumour network comprising a network of causal genetic factors (such as SNPs) and non-genetic factors (such as lifestyle).

Optionally, SNPs obtained from a dataset are engineered into a Drosophila fruit fly by DNA transfection techniques. The DNA transfection technique uses standard cloning techniques for introduction of foreign DNA (patient individual's disease-associated SN Ps) into a host cell (such as cells of the Drosophila fruit fly), without adversely affecting the host cell or the foreign DNA during the transfection. The recombinant Drosophila fruit fly produces large amounts of the patient individual's disease- associated SNPs. Optionally, an activity of orthologs (genes in different species that have retained same function in course of evolution) of the patient individual's disease- associated genes is up-regulated or down-regulated based on their activities.

Optionally, a small piece of cancer tumour biopsy sample is implanted into a mouse, for example a BALB/c nude mouse. Optionally, the abdominal wall of the mouse is opened, under strict aseptic conditions, to access a desired organ for implanting the tumour. Subsequently, the tumour sample is anchored to the organ through surgical stitches, and the abdominal cavity is hydrated and sutured. The tumour implantation is monitored for its growth. It will be appreciated that the tumour growth depends on tumour type, tumour aggressiveness and the site of implant.

Optionally, a successful treatment model for treating a disease comprises a single drug or a combination of drugs (cancer- related and non-cancerdrugs), operable to target multiple nodes in the tumour-growth network.

Optionally, the welfare system 100 operates to identify a treatment for a disease that is selected from a group including : diabetes, cancer, back pain, irritable bowel syndrome, allergy, depression, autoimmune disease, respiratory disease, insomnia, UTI, migraine. In an example, the disease is type-1 diabetes.

The welfare system 100 (using the aforesaid RACE engine) in operation identifies a course of treatment to be prescribed to the patient individual. Optionally, the treatment is based upon the patient individual's SNP genotype and at least one non- genomic feature of the patient individual . It will be appreciated that conventional treatments for treating complex diseases such as, diabetes, cancer, back pain, irritable bowel syndrome, allergy, autoimmune disease, res p i ra to ry d i se a se , UTI and so forth, include prescribing drugs for the specific disease, without taking into account the combination of the genetic and non-genetic (such as phenotypic) factors that may vary for each patient individual. The welfare system 100 identifies the course of treatment for such complex diseases by considering the combination of the genetic (SNPs) and non-genetic (such as phenotypic) factors for a given patient individual. It will be appreciated that such a consideration of the combination of the genetic (SNPs) and non-genetic (such as phenotypic) factors enables development of personalized treatment regimens that are specific to individual patient individuals. Such personalized treatment regimens enable improved treatment of diseases, such as, by targeting multiple diseases affecting the patient individuals, by reducing undesired effects (such as side-effects, allergies and so forth) experienced by the patient individuals, by improving an efficacy of a medication for the patient individuals, by prescribing improved treatment schedules for the patient individuals, by prescribing alternative treatments or therapies for the patient individuals and so forth. Furthermore, genes whose expressions are associated with specific SNPs may be good drug targets for treating a disease. Specifically, one or more proteins associated with expression from the gene can be the drug target for treating the disease.

In such an example, the data processing arrangement 102, when in operation, determines a homology of the protein to one or more known drug targets, such as kinases, receptors, proteases, and so forth, or already established experimentally with various level of confidence in vitro, or for existing drugs, through their mechanism of action. Furthermore, the drug targets determined to have homology to the protein can be used for treatment of the disease of the patient individual.

Optionally, the treatment is a combination of active drugs. For example, the treatment of cancer comprises a combination of cancer-related and non-related drugs that target multiple nodes in the tumour-growth network.

Furthermore, the data processing arrangement 102 (using the aforesaid RACE engine) provides output signals that control operation of the assistive environment. The output signals determine action to be taken in order to provide customized welfaretoeach of the individuals in the plurality of individuals under consideration. In an example, for an input sensor signal indicating digestion problems of a specific individual, an output signal may be generated by the data processing arrangement 102 directing a required medication and diet as the prescribed treatment for the individual with digestion problems.

The prescribed treatment is administered to the patient individual by the welfare system 100. The prescribed treatment comprises one or more active drugs, a dosage level of active drugs, a frequency of doses, a mode of delivery (such as injection into muscles, intravenous, intra-arterial, intraperitoneal, topically, orally and so forth) and time period of treatment, and so forth. Furthermore, the prescribed treatment is specific to an individual and is designed based on the genetic factors and/or non-genetic factors associated with the specific disease. For example, the welfare system 100 determines an ideal frequency of doses, such that, the doses are administered to achieve the desired patient individual care but an interval between successive doses is long enough to reduce a toxicity associated with the doses. In an embodiment, the treatment prescribed to the individual is optimized in an on going, such as in an iterative manner, by the welfare system 100. For example, an optimal treatment for a 2-day old chick will be very different than an optimal treatment for a 30-day old broiler going into final finishing. Furthermore, optimization within an assistive environment involves providing each individual with optimum conditions for healthy growth within constraints of underlying genomic factors, epigenetic factors, microbiomic makeup, environmental factors, diet and husbandry protocol in which the assistive environment is managed. Such conditions will depend on changing combinations of a wide variety of factors at various points during the individual's (such as, an animal's) regular growth cycle and in response to unexpected events such as disease or a failure to thrive. Furthermore, a modern assistive environment (such as, an animal production environment) will include molecular characterization of livestock animals either by direct testing, or pedigree information from elite seedstock parents. Furthermore, additional data is collected from sensor-based equipment that measures a type and amount of food and water consumed by the animals identified using RFID tags on a real-time continuous basis. Such animals are further automatically monitored for weight, activity, gait and other diagnostic behaviors.

It will be appreciated that an optimum strategy for production of animals is to achieve a target weight, composition and conformation consistent with their genetics, with a minimum number of inputs. Such a strategy typically has multiple benefits, including minimization of costs and environmental impact of raising animals (as food efficient individual produce less methane), and improving welfare (as healthier animals are less stressed). Moreover, it is not possible for a human operator (personnel) to monitor and control the amount of food, water and the incorporation of supplements, medicines and other inputs for each individual in real-time. This results in inefficiencies that manifest as sub-optimal economic performance of the animal production environment and reduced welfare of the animals hosted therein.

The data processing arrangement 102 is capable of using data gathered from equipment in the animal production environment (such as stalls, milking machines, food/drink weigh stations and the like) with pre-existing knowledge of molecular makeup of each animal and behavioral monitoring sensors (including sensors for measuring gait, activity, location and so forth). Consequently, when an animal interacts with a sensor (for example, on a milking machine), data are collected, for example on milk yield and milk quality. These real-time individual specific data are provided with historical baselines as input to the data processing arrangement 102. The data processing arrangement 102 identifies the performance of the animal and compares against its personal target and if adjustment in diet is required, sends a signal to the food bins to adjust the volume and ratio of high-low protein/calcium foodstuff to be fed to the animal.

Specifically, the data processing arrangement 102 executes the software product (using the aforesaid RACE engine) that, when executed on data processing hardware, analyses the sensor signals obtained using the sensor arrangement 104 in respect of the decision support knowledge model 106 and generates the output signals. The software product is operable to take the sensor signals as an input and analyse the sensor signals against the decision support knowledge model 106. Moreover, the software product (using the aforesaid RACE engine) is operable to consider various phenotypic factors affecting the plurality of individuals for providing output signals that control welfare of each of the plurality of individuals and conditions in the assistive environment. In an example, as an input to the software product, microbial pathogens found in a farming and veterinary environment are DNA sequenced and an analysis of pathogen type is determined by comparing the DNA sequence of the pathogens with data stored on the decision support knowledge model 106, including any single nucleotide polymorphism; a suitable approach is employed to change environmental conditions for the plurality animals to reduce or eradicate the pathogens. For example, in an event of fungal or mould growth, the animals that are most susceptible to fungal infections may be temporarily moved to an open field environment whilst animals stalls thereof and indoor accommodation may be fumigated with ozone gas that is effective at killing microbes without leaving any environmentally damaging residues.

As mentioned previously, the welfare system 100 comprises a software product (using the aforesaid RACE engine) configured to perform a multi-dimensional solution search in the decision support knowledge model 106, the search being based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each individual within the assistive environment. Notably, information stored in the decision support knowledge model 106 acts as an addressable solution space that substantially represents all valid solutions that satisfy all constraints of the welfare system 100. In other words, the decision support knowledge model 106 includes valid Cartesian sub-spaces of states or combinations that satisfy a conjunction of all the welfare system 100 constraints for all interconnected variables such as the subset of the sensor signals and the genotype determination by DNA sequencing of each individual within the assistive environment. Invalid Cartesian sub-spaces are excluded from computations performed in respect of the decision support knowledge model 106 provide for a high degree of computational efficiency.

Optionally, the system 100 collects in operation one or more pathogens and/or other microorganisms (for example, neutral, commensal and/or other beneficial microorganisms) present in the assistive environment, genotype sequences the pathogens and/or other microorganisms to characterize the pathogen and/or microorganisms, and employs the characterization thereof as an input parameter to the software product when executed in the data processing arrangement 102 to use in performing its search.

Referring next to FIG. 2, there is shown a process diagram illustrating steps that are implemented by the welfare system 100 for enabling the software product (using the aforesaid RACE engine) to perform the multi-dimensional solution search in the decision support knowledge model 106, in accordance with an embodiment of the present disclosure. At a step 202, the welfare system 100 (as shown in FIG. 1) collects in operation one or more pathogens and/or other microorganisms (for example, neutral, commensal and/or other beneficial microorganisms) present in the assistive environment. Additionally, the welfare system 100 uses one or more mediums for collecting the one or more pathogens and/or other microorganisms from the assistive environment. Specifically, the welfare system 100 automatically collects the one or more pathogens and/or other microorganisms present in the assistive environment without any human intervention. In an example, the medium for collecting the one or more pathogens are a combination of hardware and software, for example a robotic probe that routinely moves in an autonomous manner around the assistive environment to collect samples. In another example, the medium for collecting the one or more pathogens from the assistive environment may require human intervention. At a step 204, the welfare system 100 genotype sequences the one or more pathogens to characterize the pathogen. The genotypes are DNA sequenced and analysis of pathogen type is determined by comparing the DNA sequence of the one or more pathogens, with information stored in the decision support knowledge model 106. Subsequently, at a step 206, the welfare system 100 employs the characterization of the pathogen as an input parameter to the software product when executed in the data processing arrangement 102 to use in performing its search. The input parameters include features of one or more SNPs obtained from performing DNA base readout from biological samples. In an example, the DNA base readout from biological samples is performed as part of a GWAS (Genome-Wide Association Study). Furthermore, large SNP-genotyping arrays for tens of thousands of individuals (cases and controls) and tens of thousands of SNPs, such as 100,000 individuals and 50,000 SN Ps, are available in multiplex formats for huge throughput. In such an example, the features of the one or more SN Ps obtained as part of the GWAS are stored in the decision support knowledge model 106. Furthermore, the biological samples are collected from a plurality of cases, such as the plurality of individuals suffering from a specific disease or disorder and a plurality of controls (such as healthy individuals not suffering from the specific disease or disorder). It will be appreciated that the GWAS datasets can be generated using well-known techniques, including but not limited to, SN P genotyping using SNP microarrays, exome sequencing, genome sequencing and so forth. Furthermore, input parameters obtained from performing the DNA base readout of the biological samples comprise information about SNP genotypes associated with the plurality of cases and the plurality of controls. Alternatively, the data processing arrangement 102 performs a trait phenotype investigation study. Consequently, individuals are segregated based on high trait performance and low trait performance respectively, to generate the trait phenotype investigation study. Subsequently, individuals with ±2 standard deviations are selected for a specific trait (for example, in case of animals, yield) and compared either directly or as separate sets against a common control. This enables identification of pathways involved in the trait and correspondingly, derivation of predictive markers. For example, in a potato study, top 21 markers were determined to be more predictive of yield than 10,000+ markers that are conventionally used by existing predictive scoring tools (such as, GBLUP).

The data is generated from the input parameters. Such data generated from the plurality of input parameters is stored in the decision support knowledge model 106 (using the aforesaid RACE engine) as data files. In an example, the data files comprise the input parameter in the structured format (as explained in detail hereinabove).

The data processing arrangement 102 (using the aforesaid RACE engine) processes the genotype sequences and data from the decision support knowledge model 106 to generate input parameter to the software product for performing the solution search thereof.

Moreover, the software product (using the aforesaid RACE engine) is used to compute a welfare trajectory for each individual. Specifically, the software product executed by the data processing arrangement 102 computes (using the aforesaid RACE engine) the welfare trajectory after performing the multi-dimensional solution search in the decision support knowledge model 106, as will be described herein later.

Notably, a welfare trajectory of a given individual includes at least one constraint and/or at least one environmental condition pertaining to the assistive environment, wherein the at least one constraint and/or the at least one environmental condition is favourable for the given individual . The welfare trajectory is created based upon the information stored in the decision support knowledge model 106 and results of the multi-dimensional solution search in the decision support knowledge model 106. Optionally, the welfare trajectory is also based upon the input parameter (namely, the characterization of the one or more pathogens and/or microorganisms collected from the assistive environment 200). Optionally, the welfare trajectory is based upon a course of treatment identified to be prescribed to a patient individual and administering of the prescribed treatment to the patient individual .

It will be appreciated that the information stored in the decision support knowledge model 106, the results of the multi-dimensional solution search in the decision support knowledge model 106, and optionally, the input parameter, constitute a "dataset" (namely, "a corpus of data") on which the software product implements processing operations, to compute the welfare trajectory to be used in providing welfare support for each individual .

Optionally, to compute welfare trajectories for the livestock animals, the software product is operated to:

(a) perform pre-filtering of the dataset, to reduce a number of inputs that are considered for computing the welfare trajectories;

(b) perform mining (using the aforesaid MARKERS engine) within the pre-filtered dataset to find distinct n-combinations of SNP genotypes and/or other types of features found in the livestock animals;

(c) perform (b) repeatedly (using the aforesaid MARKERS engine) for mining a plurality of random permutations of properties using a same set of mining parameters;

(d) find networks (using the aforesaid MARKERS engine) of distinct n-combinations sharing one or more properties;

(e) find networks (using the aforesaid MARKERS engine) using the same set of parameters from among the distinct n-combinations and from among the plurality of random permutations, compare null hypothesis and determine one or more p-values with FDR correction to eliminate random observations;

(f) perform annotation (using the aforesaid ANNOTATION engine) of the networks with a semantically normalised knowledge graph containing information about the shared one or more properties; and

(g) perform re-clustering of the networks (using the aforesaid ANNOTATION engine), after correlating the networks found at (e) with the semantically normalized knowledge graph of (f) containing information about the shared one or more properties.

The data processing arrangement 102, when in operation, performs the pre-filtering from the datasets, comprising tens of thousands of individuals and/or pathogens (and/or microorganisms) and tens of thousands of SNPs or even more (~2.5 million), to reduce a number of the SNPs that are considered for generating the outputs. According to one example implementation, the pre-filtering of the specific datasets includes at least one of removing SNPs where a minor allele frequency associated therewith is below a threshold at which it can satisfy a >MinCases criterion for a population; optionally removing SN Ps which are approximately co-located and within linkage disequilibrium regions using linkage disequilibrium based clumping; removing SN Ps where a majon minor allele distribution is close to 50 : 50; and including or selecting SNPs that are relevant to a hypothesis or other analytical strategy. In one example embodiment, the pre-filtering of the specific datasets includes removing SNPs where a minor allele frequency associated therewith is below a threshold at which it can satisfy a >MinCases criterion for a population. The MinCases criterion for the population is a numerical value that denotes a minimum number of cases within the population that satisfy a requirement, such as, a minimum number of individuals that have a specific SNP. Such a MinCases criterion can be automatically specified, such as, by the data processing arrangement 102. Alternatively, the MinCases criterion can be manually specified by a user of the welfare system 100. In one example embodiment, the pre-filtering of the specific datasets includes removing SN Ps which are approximately co-located and within linkage disequilibrium regions, using linkage disequilibrium-based clumping.

In another example implementation, the pre-filtering of the specific datasets includes removing SNPs where a majon minor allele distribution is close to 50: 50, such as, where the majon minor allele distribution is 52 :48. The data processing arrangement 102 is further operable (using the aforesaid MARKERS engine) to perform mining to find all, or a substantial majority of, distinct n- combinations of SNP genotypes and/or other types of features found in the input parameter of the plurality of individuals provided in the decision support knowledge model 106. In an example implementation, the mining includes finding combinations of SNP genotypes which occur in a plurality of cases (> MinCases) or in zero or just a few controls (<MaxControls), analysing in ascending levels of order, in an n number of layers, one layer at a time and storing the n-combinations as N-states in an output data structure. Optionally, the mining includes evaluating a highest skew of trait- associated features using Odds Ratio-based (or OR-based) ranking. The MaxControls criterion for the population is a numerical value that denotes a maximum number of controls within the population that satisfy a requirement, such as, a maximum number of individuals that have a specific SNP. Such a MaxControls criterion can be either specified automatically, such as by the data processing arrangement 102, or manually by a user of the welfare system 100. The data processing arrangement 102, when in operation, performs (namely, "performs in operation ") mining to determine all such SN Ps that are associated with the >MinCases and the <MaxControls criterions respectively, such as SNPs that occur with a maximum number of cases and a minimum number of controls. Optionally, during mining of the input parameter (for example, input parameters) and data by the data processing arrangement 102, a new data-type such as epigenetics data (a series of new elements) can be incorporated as features into the input parameter in addition to the SNP genotypes.

Optionally, the data processing arrangement 102 (using the aforesaid RACE engine) finds, when in operation, high-order combinations of SNP genotypes which synergistically affect a disease status of an individual represented in the input parameters. More optionally, the data processing arrangement 102 (using the aforesaid RACE engine) identifies, when in operation, a course of treatment to be prescribed to the patient individual, and recommends the administration of the prescribed treatment to the patient individual.

Furthermore, the data processing arrangement 102, when in operation (using the aforesaid RACE engine), performs the mining in ascending levels of order, in an n number of layers, one layer at a time and storing the n-combinations in an output data structure. For example, the data processing arrangement 102 analyses SNPs at a layer 1, wherein SNPs associated with all cases and controls within the population are analysed. At an instance, the data processing arrangement 102 terminates the determination of combinations (namely, "order") of n-SNPs (or n-combinations) in successive layers. In one embodiment, the data processing arrangement 102 is operable to determine n-combinations in 20 or more layers.

Optionally, upon successful determination of n-combinations of SN Ps in one layer that satisfy the > MinCases and the <MaxControls criterions, the MinCases is incremented by the data processing arrangement 102 to analysis a successive layer. Such incrementing of the MinCases criterion upon successful determination of n- combinations of SN Ps in previous layers, enables the data processing arrangement 102 to determine largest possible subgroups of cases that are associated with the n- combination of SNPs within the population. In an example, the data processing arrangement 102 comprises at least one multicore GPU. The data processing arrangement 102 is operable to employ the GPU and/or the FPGA for the determination of the n-combination of SNPs in the n number of layers. More optionally, the Graphics Processing Unit (GPU) and/or the Field Programmable Gate Array (FPGA) comprise a memory associated therewith. In one example, the memory is implemented as a random access memory (RAM).

Furthermore, as mentioned hereinbefore, the data processing arrangement 102, when in operation, stores the n-combinations of SNPs determined in each layer, as well as individual identifiers for the cases. For example, the data processing arrangement 102, when in operation, assigns a binary vector (indicated by BV hereinafter) to each case, subsequent to determining the n-combinations of SNPs within a layer. The binary vector can take a value of O' that indicates a specific case not being associated with the n-combination of SNPs for the layer, and a value of Ί' that indicates the specific case being associated with the n-combination of SN Ps for the layer. The BV is updated by the data processing arrangement 102 for each layer and is employed for determining n-combinations of SNPs for subsequent layers (whereas the individual identifiers for each of the plurality of individuals in the assistive environment are input to the GPU of the data processing arrangement 102 prior to initiation of operation thereof). Moreover, the data processing arrangement 102, when in operation, stores the n-combinations of SNPs determined in each layer and the BV values associated with the cases, such as, within the memory (such as a random access memory or RAM) associated with the GPU. For example, the data processing arrangement 102, when in operation, stores the n-combinations of SNPs and the BV values associated with the cases in the output, such as an output represented by N-states. Furthermore, the data processing arrangement 102, when in operation, performs execution of permutations or repeating when mining a plurality of random permutations of the genotype sequences and pathogens (and/or microorganisms) using a same set of mining parameters. The data processing arrangement 102, when in operation, repeats the mining (as explained in detail hereinabove) a predefined number of times of the plurality of individuals in the assistive environment, with the plurality of random permutations thereof. It will be appreciated that the execution of the permutations by the data processing arrangement 102 provides statistical significance to the n-states determined by the data processing arrangement 102 and enables to increase a confidence associated therewith.

The data processing arrangement 102, when in operation (using the aforesaid MARKERS engine), performs execution of a network analysis or finding networks of distinct n- combinations sharing one or more properties. For example, the networks of distinct n- combinations can be different N-states that have at least one common SNP. In a first example, N-states determined by the data processing arrangement 102 in a third layer comprise 6-states A to F, such as,

A [3¹ 5² 247°], B [3¹ 218¹ 775¹], C [3¹ 5² 842¹], D [3¹ 247° 264¹],

E [218¹ 264¹ 511²] and F [511² 775¹ 842¹] .

In such an example, the data processing arrangement 102, when in operation, finds networks from the N-states corresponding to each SN P common to one or more N- states, such as,

3¹ [A, B, C, D], 5² [A, C], 2470

264¹ [D, E], 218¹ [B, E],

842¹ [C, F], 775¹ [B, F] and 511² [E, F]

Optionally, the data processing arrangement 102, whe n i n operation (using the aforesaid MARKERS engine), merges identical networks, such as, networks having all identical properties. Optionally, the data processing arrangement 102, when in operation, determines a p-value for each network, against a network having higher NC and density than the network. The "p-value" indicates a probability that a SNP is associated with a particular phenotype, wherein the phenotype is any one of: a physical trait, a disease and so forth. Furthermore, p-value represents the significance of a genetic difference between two populations (case and control) at a particular locus on a gene. Furthermore, the data processing arrangement 102, when in operation, performs execution of network validation or finding networks from the n-combinations and from all random permutations using the same set of parameters, comparing null hypothesis and determining one or more p-values with false discovery rate (FDR) correction to eliminate random observations. In one example, the data processing arrangement 102, when in operation, compares a number of pseudo-cases within the network associated with permutations, against a number of cases within the network before performing the permutations. In such an example, if the number of pseudo cases within the network is more than the number of cases within the network before performing the permutations for more than 50 networks out of 1,000 networks (or the p-value is more than 0.05), the null hypothesis is validated.

Optionally, the data processing arrangement 102, when in operation (using the aforesaid MARKERS engine), performs false discovery rate (FDR) correction during multiple testing of the networks to compare the null hypothesis. In one example, the data processing arrangement 102, when in operation, employs a technique such as a Benjamini- Hochberg procedure or a Benjamini-Hochberg-Yekutieli procedure to correct for the multiple testing on the networks. For example, the data processing arrangement 102, when in operation, employs a FDR of 1% for comparing a null hypothesis. It will be appreciated that comparing the null hypothesis for the networks enables the data processing arrangement 102 substantially to eliminate random n-combinations that may have been determined by the data processing arrangement 102

Optionally, the data processing arrangement 102, when in operation (using the aforesaid MARKERS engine), determines a penetrance of the networks, such that the penetrance is associated with an amount of population that corresponds to the network. In an example, the penetrance is expressed as a percentage value.

Furthermore, the data processing arrangement 102, when in operation (using the aforesaid ANNOTATION engine), performs execution of network annotation or annotating networks with a semantically normalized knowledge graph containing information about the shared one or more properties. The ANNOTATION engine enables use of biological knowledge and understanding of mechanisms and functions (the one or more properties) into an analysis. The ANNOTATION engine also enables interpretation of results, such as, by allowing generation of the semantically normalized knowledge graph. The semantically normalized knowledge graph is used, for example, for identification of genes and potential drug discovery and/or repurposing opportunities. The semantically normalized knowledge graph contains information about the shared one or more properties including but not limited to, SNPs, genes, pathways, targets, drugs, diseases, pharmacogenetics, drug interaction and so forth. In one embodiment, the data processing arrangement 102, when in operation, selects one or more properties from the SNPs, genes, pathways, targets, drugs, diseases, pharmacogenetics and drug interaction in the semantically normalized knowledge graph. Subsequently, the one or more properties selected by the data processing arrangement 102 are correlated with the network of SNPs determined by the data processing arrangement 102, to determine information about the SNPs, such as, if the SN Ps are in a coding, non-coding or eQTL (expression quantitative trait loci) region; the genes or pathways that are affected by the SNPs; diseases or phenotypes associated with the SNPs; a location within the genome where the SNPs are occurring; known phenotypic associations of the SNPs within the networks; if the diseases or phenotypes associated with the SNPs are druggable, and so forth.

Furthermore, the data processing arrangement 102 (using the aforesaid ANNOTATION engine), when in operation, performs re-clustering of the networks, after correlating the validated networks with the semantically normalized knowledge graph containing information about the shared one or more properties. The data processing arrangement 102, when in operation, (using the aforesaid ANNOTATION engine) perform the re-clustering of the networks by merging networks comprising at least one common SN P therein. In the first example, the networks comprising the SNPs 3¹' 5^ and 2470 share the N-states A, C, D therebetween. Thus, the networks corresponding to the 3¹' 5^ and 2470 _{ca n} b_e merged into a cluster, such that the merged network has a connection between the N-states. In such an example, the data processing arrangement 102, when in operation, merges the cases corresponding to the N-states into the cluster. Furthermore, hypothesis driven criteria based on biological insights, role of specific metabolic pathways, phenotypic factors, veterinary factors, and the like, may be applied and tested in the re-clustering stage by re-segmenting the case and control populations based on specific conditions.

According to an embodiment, the re-clustering is used to correlate validated networks with extended phenotypic and veterinary data to find biological explanations for observed associations. The data processing arrangement 102, when in operation, correlates phenotypic and veterinary data (such as, in case of animals hosted within the farming and veterinary environment) to find the biological explanations for the observed associations of the SNPs within the cluster. In one example, the phenotypic and veterinary data is stored in the decision support knowledge model 106, for example, as semantically normalized knowledge graphs. In another example, the phenotypic and veterinary data can be associated with merged networks corresponding to various other populations. In yet another example, the data processing arrangement 102, when in operation, correlates hypothesis-driven criteria comprising biological insights, role of metabolic pathways, lifestyle data and so forth, find the biological explanations for the observed associations of the SNPs within the cluster.

In one embodiment, the data retrieved from the decision support knowledge model 106 by the data processing arrangement 102 comprises epigenetic data. However, the epigenetic data may correspond to continuous variables. In such an example, the data processing arrangement 102 converts the epigenetic data from the continuous variables into finite domains.

According to an embodiment, the data processing arrangement 102, when in operation, finds at least one other feature that is selected from omics,or non-genetic factors. As mentioned hereinabove, the data processing arrangement 102 correlates phenotypic and veterinary data to find the biological explanations for the observed associations of the SN Ps within the cluster. Furthermore, such phenotypic and veterinary data associated with the cases can be used to determine the at least one other feature from omics, or non-genetic factors. In one example, the data processing arrangement 102, when in operation, finds cases and controls that share at least one non-genetic factor, such as a phenotypic, veterinary, environmental and/or husbandry factor.

Furthermore, the data processing arrangement 102 (using the aforesaid MARKERS engine) performs high-order (for example, of an order 3 or higher, more optionally of an order 8 or higher, yet more optionally of a 20 or higher, and yet more optionally of an order 50 or higher) combinatorial association of the non-genetic factors and genetic factors, such as, presence and absence of SNPs in the cases and controls respectively, to identify disease protective effects associated with the controls. Moreover, in order to produce the output signals the software considers not only genotype of each of the plurality of individuals, observations and tests carried out on each of the plurality of individuals, detailed information of various medication and drugs that are given to each of the plurality of individuals, on-going observations as the medications are applied to each of the plurality of individuals as well as various data obtained by the plurality of sensors in the sensor arrangement 104 (such as, food intake, sun time, and so forth).

Optionally, the output signals are used to control at least one of: type and/or quantity of food provided to the individuals; a time when food is provided to the individuals; additional food supplements, probiotics and/or one or more drugs to be administered to the individuals; selective heating or cooling to be supplied to the individuals; pathogen reducing processes to be applied to the assistive environment. The output signals indicate actions required to be taken in order provide the plurality of individuals with optimal welfare. The required actions may relate to different constraints related to feeding provided to the individuals. In an example, the output signals may indicate that a specific individual is deficient in a specific nutrient. Consequently, the output signal may indicate to introduce ingredients/supplements rich in the specific nutrient in food provided to the individuals. In another example, the output signals may indicate a frequent and increased quantity of food to be provided to the individuals. Furthermore, the output signals may be generated based on analysing an increase in number of pathogens associated with a specific disease in the assistive environment. Consequently, effective measures may be taken to eradicate the pathogens from the assistive environment. Furthermore, the sensor signals may indicate abnormal health conditions of a specific individual in the assistive environment. Consequently, the output signals generated by the software product may direct additional food supplements and/or one or more drugs to be administered to the individuals.

Additionally, the output signals may indicate need of providing selective heating or cooling to the individuals. Beneficially, this may provide the individuals a more personalized and dedicated welfare. Optionally, the data processing arrangement 102 finds, when in operation, single disease case sub-populations that share high-order disease-associated combinatorial features. Notably, many diseases are caused by a combination of genetic as well as non-genetic (such as phenotypic and environmental) factors. Furthermore, a same disease can be caused due to presence of a plurality of different genetic factors, such as SNPs, in different cases within a population. Moreover, the plurality of different case sub-populations may not share any common SN Ps or may share a minimal number of SNPs therebetween. In such an example, identification of disease risk-factors, determination of treatment for each individual within the population and so forth, requires identification of the case sub-populations that share SNPs therebetween. The data processing arrangement 102 finds such single disease case sub-populations that share high-order disease-associated combinatorial features (such as SNPs). Optionally, the data processing arrangement 102 (using the aforesaid RACE engine) designs, when in operation, a course of treatment that is customized for the given individual, wherein the treatment is based upon the individual's SNP genotype and at least one non-genomic feature of the individual. As mentioned hereinabove, complex diseases are caused by a combination of genetic (such as SNPs) as well as non-genetic (such as phenotypic) factors. Furthermore, conventional treatments for treating such complex diseases (such as, for drug discovery) include prescribing drugs for a specific disease, without taking into account the combination of the genetic and non-genetic (such as phenotypic) factors that may vary among the individuals. Therefore, there is a requirement to design treatments for such complex diseases by considering combinations of genetic (SNPs) and non-genetic (such as phenotypic) factors for specific individuals. The data processing arrangement 102, w h e n in operation designs a course of treatment that is customized for the given individual, wherein the treatment is based upon the individual's SNP genotype and at least one non-genomic feature (such as phenotypic) of the case. In one example, micro-biopsies of the given individual are conducted to obtain a cellular assay platform. Subsequently, organoids associated with one or more organs affected by disease are developed for the given individual. Thereafter, SNP genotypes associated with the organoids for the given individual is determined. Alternatively, SNP sequencing techniques are employed to determine SNPs genotypes associated with the disease for the given individual.

More optionally, the data processing arrangement 102 (using the aforesaid RACE engine) selects, when in operation, at least one of the one or more features from clinical observations, tests carried out on the given individual and information of medications and drugs. For example, the data processing arrangement 102 receives information associated with the disease of the given individual from clinical observations, tests carried out on the given individual and/or medications and drugs used by the given individual for treatment of the disease. In another embodiment, the data processing arrangement 102 employs in operation ongoing observations, as the medications that are used for treating the given individual, that are added as features (input drivers) to the input parameters used by the data processing arrangement 102. For example, the data processing arrangement 102 receives information of medications used for treating the given individual and determines an efficacy associated therewith. In such an example, the data processing arrangement 102 can perform the drug discovery iteratively, to suggest improved drugs for treating the given individual with each iteration. Referring next to FIG. 4, there is shown an illustration of steps of a method 400 of operating a welfare system (such as the system 1 0 0 of FIG. 1) that provides welfare support, when in operation, to a plurality of individuals in an assistive environment, in accordance with an embodiment of the present disclosure. The method 400 makes use of a system that includes a data processing arrangement that receives, when in operation, sensor signals from a plurality of sensors that are spatially distributed within the assistive environment, wherein the data processing arrangement includes a decision support knowledge model against which the sensor signals are compared, wherein the data processing arrangement provides output signals that control operation of the assistive environment, and wherein the data processing arrangement executes a software product that in execution analyses the sensor signals in respect of the decision support knowledge model and generates the output signals. At a step 402, the software product is arranged to perform a multi dimensional solution search in the decision support knowledge model, the search being based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each individual within the assistive environment. At a step 404, the sensor arrangement is used to sense in operation environmental conditions for each individual, including monitoring a food intake for each individual. At a step 406, the decision support knowledge model is populated with at least one of drug characteristics, food supplement characteristics, husbandry strategies (such as, when the individual is an animal hosted within a farming and veterinary environment) depending on individual health complications, disease characteristics of each individual, individual genotype data, and SNP polymorphism data. At a step 408, the software product is used to compute a welfare trajectory for an individualized customized husbandry of each individual .

Optionally, the method includes arranging for the SNP data to include single nucleotide polymorphisms characterizing each individual, determined by using microarrays, DNA sequencing, CRISPR or Polymerase Chain Reaction (PCR) to read genetic tissue samples derived for each individual. Beneficially, the method is used to select preferred embryos having desired phenotype characteristics, wherein selected embryos are implemented using IVF techniques to enable individuals to be realised having the desired phenotype characteristics.

Optionally, the method includes arranging for the sensor arrangementto include a plurality of sensors that are spatially distributed within the assistive environment and are coupled in communication with the data processing arrangement by using a wireless dynamically reconfigurable communication network.

Optionally, the method includes arranging for the wireless dynamically reconfigurable communication network to be implemented as a peer-to-peer (P2P) network.

Optionally, the method includes arranging for the system to collect in operation one or more pathogens and/or microorganisms (for example, neutral, commensal and/or other beneficial microorganisms) present in the assistive environment or within the individual, perform genotype sequencing of the one or more pathogens and/or microorganisms to characterise the one or more pathogens and/or microorganisms, and employ the characterisation of the one or more pathogens and/or microorganisms as an input parameter to the software product when executed in the data processing arrangement to use in performing its search.

Optionally, the method includes employing the output signals to control at least one of:

(i) a type and/or a quantity of food provided to the individuals;

(ii) a time when food is provided to the individuals;

(iii) additional food supplements, probiotics and/or one or more drugs to be administered to the individuals;

(iv) changes to husbandry practices (such as, when the individual is an animal hosted within a farming and veterinary environment) including selective heating or cooling to be supplied to the individuals;

(v) pathogen reducing processes to be applied to the assistive environment.

Optionally, the method includes arranging for the data processing arrangement to find in operation high-order combinations of SNP genotypes which synergistically affect a disease status of an individual represented in the input parameters.

Optionally, the method includes arranging for the data processing arrangement to find in operation single disease case sub-populations that share high-order disease- associated combinatorial features.

Optionally, the method includes arranging for the data processing arrangement to design in operation a course of treatment that is customized for a given individual, wherein the treatment is based upon the individual's SNP genotype and at least one non-genomic feature of the individual.

Optionally, the method includes arranging for the data processing arrangement to select in operation at least one of the one or more features from clinical observations, tests carried out on the given individual and information of medications and drugs.

Optionally, the method includes arranging for the data processing arrangement to employ in operation ongoing observations, as the medications are used for treating the individual, that are added as features to the input parameters used by the data processing arrangement.

Referring next to FIG. 5, there are illustrated therein steps of a method 500 of operating the system 100, for example when treating an individual in need thereof, in accordance with an embodiment of the present disclosure. At a step 502, high-order combinations ofSNP genotypes and/or one or more other features which synergistically affect disease status are identified, using the welfare system and/or the method of (namely, the method for) operating a welfare system; "high-order" is as defined in the foregoing. At a step 504, a course of treatment to be prescribed to the individual is designed, the treatment being based upon the individual's genotype (SNPs) and/or at least one or more non-genomic feature. At a step 506, the prescribed treatment of the individual is administered.

Optionally, the method includes:

(a) identifying (using the aforesaid RACE engine) high-order combinations of the individual's SNP genotypes and/or one or more other features which synergistically affect disease status;

(b) administering the prescribed treatment to the individual.

Optionally, the method includes implementing a treatment using a combination of drugs, for example using repurposed drugs.

Optionally, the method includes designing a course of treatment to be prescribed to an individual, characterized in that the method comprises:

(a) identifying (using the aforesaid RACE engine) high-order combinations of SN P genotypes and/or one or more other features which synergistically affect disease status, using the method or the welfare system; and

(b) designing (using the aforesaid RACE engine) a course of treatment based upon the case's genotype (SNPs) and/or at least one more non-genomic feature.

Referring next to FIG. 6, there are illustrated therein steps of a method 600 of identifying a course of treatment to be prescribed to a given individual, in accordance with an embodiment of the present disclosure. The method 600 relates to using the welfare system 100 of FIG. 1 that, wh e n in operation, develops a personalized identification of one or more active drug combinations for the treatment or prevention of a given patient individual's specific disease The welfare system 100 includes the data processing arrangement 102 of FIG. 1 that receives a plurality of measurands of the given patient individual and accesses the decision support knowledge model 106 of FIG. 1 including a plurality of treatment strategies and genomic data. At a step 602, the data processing arrangement 102 (using the aforesaid RACE engine) identifies, when in operation, high-order combinations of the individual's SNP genotypes and/or one or more other features which synergistically affect disease status, using a computational engine (namely the RACE engine) with combinatorial methodology for combinatorial feature analysis executed in the data processing arrangement 102; "high-order" is to be construed as, for example more than a two-element combinatorial search, for example a three element combinatorial search. Typically, the high-order combinatorial searches are performed for higher orders. For example, in case of a given gene, the high-order combinatorial search ranges from about 5 to about 20, more preferably circa 6 to circa 17 orders. In another example, in case of a given gene, the high-order combinatorial search ranges from about 3 to about 15 and more preferably circa 5 to circa 13 orders.

The steps 602 to 608 are only illustrative and other alternatives can also be provided where one or more steps are added, one or more steps are removed, or one or more steps are provided in a different sequence without departing from the scope of the claims herein. In an example, there is a control apparatus (using the aforementioned RACE engine) for processing one or more data inputs in a computing arrangement to provide one or more control outputs (such as, for controlling the aforesaid assistive environment) and/or one or more analysis output and/or one or more recommendation outputs (such as, for prescribing a course of treatment for a given individual within the assistive environment), characterized in that the control apparatus includes a user interface for interacting with a user of control apparatus for controlling operation of the control apparatus, a data processing arrangement that is operable to receive the one or more data inputs and to output the one or more control outputs and/or one or more analysis output and/or one or more recommendation outputs, wherein the computing arrangement is operable to execute a software product for implementing the method. In an example, the SNPs are selected from SNPs found present in non-coding regions of genes, in the intergenic regions or in coding regions of genes. In another example, the drug or combination of drugs for use in therapy comprises the drug or combination of drugs to be administered to the patient individual identified using the method of the invention.

Referring to FIG. 7, there is shown an illustration of a cycle of continuous welfare to be provided to animals, in accordance with an embodiment of the present disclosure. The welfare to be provided to the animals is guided by multiple dimensions and combinations of data predictive of one or more outcome phenotypes, such as, the data comprising genomic data, veterinary records, microbiomic data, epigenetic data, data acquired from real-time monitoring of the animals, data related to pathogens and/or other microorganisms collected from a farming and veterinary environment that the animals are hosted therein, data related to dietary and water intake of the animals, and data acquired by performing veterinary analysis of the animals. Such combinations of data are analyzed to determine a best course of treatment to be prescribed to the animals for improving welfare of the animals and a performance of the animals is evaluated on an on-going basis (and in an iterative manner). Subsequently, the course of treatment to be prescribed to the animals is optimized, based on the performance of the animals.

Referring next to FIG. 8, there is shown an illustration depicting selection of routes that do not impinge on other selected phenotypes, in accordance with an embodiment of the present disclosure. As shown, an aim is to use insights about which genes and pathways are involved in development towards a specific phenotype, to evaluate interdependencies and independence of different phenotypes. Furthermore, selective breeding of animals can be performed by impacting independent pathways, enabling a better chance of being able to simultaneously improve multiple phenotypes and thus, enable selective breeding of animals to fit multiple environments.

Referring to FIG. 9, there is shown a schematic illustration of a PrecisionHfe Data Annotation Platform that is employed in the welfare system of FIG. 1, wherein the

Annotation Platform, includes multiple source objects from MARKERS (namely, networks, SNPs and genes), multiple annotation sources, storage and integration of semantic knowledge, heuristics and human knowledge. Primary steps concern analysis and risk factor (RF) scoring, whereas secondary steps concern performing automated annotated, and whereas tertiary steps concern integrating semantic knowledge to compute a most optimal welfare trajectory for a given individual. Reference is made here to ANNEX 2 below.

Furthermore, there is disclosed a control apparatus (using the aforesaid RACE engine) that processes one or more data inputs in a computing arrangement to provide one or more control outputs (such as, for controlling the aforesaid assistive environment) and/or one or more analysis output and/or one or more recommendation outputs (such as, for prescribing a course of treatment for a given individual within the assistive environment), characterized in that the control apparatus includes a user interface that interacts with a user of the control apparatus to control operation of the control apparatus, a data processing arrangement that, when in operation, receives the one or more data inputs and to output the one or more control outputs and/or one or more analysis output and/or one or more recommendation outputs, wherein the computing arrangement, when in operation, execute a a software product for implementing the method.

Furthermore, there is disclosed a software product recorded on machine-readable non- transitory (non-transient) data storage media, wherein the software product is executable upon computing hardware for implementing the aforementioned method; in other words, the present disclosure provides a computer program product comprising a non-transitory computer-readable storage medium having computer- readable instructions stored thereon, the computer-readable instructions being executable by a computerized device comprising processing hardware to execute the method.

The welfare system and the method of using the welfare system as described in the present disclosure enables precision monitoring and design of optimal customized welfare strategies for individuals in an assistive environment. Furthermore, the present disclosure provides for identifying and analysing pathogens present in the assistive environment and generating output signals to control actions required to eradicate the pathogens that might harm the individuals inthe assistive environment. Moreover, the welfare system, and the method of (namely, the method for) employing the welfare system, as described in the present disclosure, provides personalized customized treatment strategies for treating a specific disease of an individual. Such personalized treatment strategies enable improved treatment of patient individuals by reducing undesired effects (such as side-effects, allergies and so forth) experienced by the patient individuals, by improving an efficacy of a medication used for treating the patient individuals, by prescribing improved treatment schedules for the patient individuals, by prescribing alternative treatments or therapies for the patient individuals and so forth.

It will be appreciated that the welfare system 100, and its component parts are susceptible to being used individually or in combination; for example, using the system 100, concurrently enables optimal control of individualized husbandry of animals, selection of animals with preferred phenotype characteristics and also optimal treatment of animals when their health is affected by illness or pathogens.

It will be appreciated from the above disclosure that the welfare system 100 is susceptible to being employed for improved selective breeding of animals, such as, for optimization of complex traits such as yield, food conversion, fertility, fit to environment and so forth. Moreover, the welfare system 100 can be employed for improved selection of therapy for individuals (for animals as well as human patients) based on genomic, phenotypic, clinical and/or veterinary data. The welfare system 100 can be employed for providing improved welfare to individuals, such as, better fit of individuals to diet, environment and the like. The welfare system 100 also enables better risk scoring using combinations of features and integration of such data into decision support models (for example, for prediction of range of phenotypes including disease risk, rate of disease progression, therapy response, opportunities for repurposing drugs). Moreover, the welfare system 100 can be employed for development of decision support tools including precision medicine, precision agriculture and the like, to make real-time fully contextualized responses and recommendations for optimizing food, management, husbandry and so forth of animals, based on combinations of data associated with genomics, epigenetics, environmental, acquired using sensors, acquired from IoT apparatuses, acquired using satellites, and the like.

Modifications to embodiments of the invention described in the foregoing are possible without departing from the scope of the invention as defined by the accompanying claims. Expressions such as "including", "comprising", "incorporating", "consisting of", "have", "is" used to describe and claim the present invention are intended to be construed in a non-exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural. Numerals included within parentheses in the accompanying claims are intended to assist understanding of the claims and should not be construed in any way to limit subject matter claimed by these claims.

GLOSSARY

"Constraint resolution" means establishing substantially all valid combinations of variables satisfying substantially all constraints of a given system . Optionally, all valid combinations of the variables satisfying all the constraints of the given system are established, namely computed, wherein, in an optional case, valid Cartesian sub spaces of states or combinations satisfy a conjunction of all system constraints for all interconnected variables. The valid Cartesian sub-spaces may comprise Cartesian planes. A point in such Cartesian planes can be represented as tuples (or a list) of 'h' real numbers, wherein 'h' can be dimensions associated with the Cartesian plane. It will be appreciated that when the Cartesian sub-spaces are associated with Cartesian planes, the variables and the constraints corresponding to the variables can comprise more than 3 values associated with abscissa (x-axis), ordinate (y-axis) and applicate (z-axis) of the Cartesian co-ordinate system .

The term " optimizing " means applying a heuristic selection of combinations within a set of valid combinations.

The term " a system spanned by variables on finite domains and/or intervals” indicates that each variable of a given system consists of a finite set of elements or state values (for example, logical truth values) or a finite set of intervals.

The term "an addressable solution space" indicates that substantially all valid combinations are explicitly represented.

The term "a Cartesian sub-space " is a compact representation of one or more valid combinations, wherein all combinations are derivable/calculable as a Cartesian product of elements or state values for each variable. It will be appreciated that when the Cartesian sub-space comprises Cartesian planes, the Cartesian product of elements or state values of each variable may be associated with products of more than the 3 values corresponding to the Cartesian coordinates x, y and z.

The term "system constraints” refers to relations (namely propositional functions) for variables defined for a given system .

The term " interconnecting variables" indicates variables present in at least two relations. The term "link variable" means a variable generated by a method according to the present disclosure and added to a given relationship with a unique index, wherein the unique index identifies one corresponding Cartesian sub-space.

The term "interconnected valid Cartesian sub-spaces " means valid Cartesian sub spaces with at least one common variable associated therewith.

The term "external variables" means variables that are to be used by or being accessible from an environment during a runtime simulation. The term external variable is used herein interchangeably as external state variable.

The term "internal variables " or "interim variables" means variables that are not to be used by, or are not to be accessible from an outer environment during a runtime simulation.

The term "cluster" means an accumulation of states, or a list of state vectors associated with known attributes. The state variables are subsets of domain of static array system model and/or external variables.

AN NEX I : RACE ENGINE

The RACE engine is susceptible to being used in the aforementioned welfare system 100 for executing complex mathematical computations relating to sensed signals and genetic analysis data relating to individuals serviced by the system 100 and providing corresponding control output signals for controlling a assistive environment, nutrition or treatment, or both, relating to the individuals. The RACE engine operates on a knowledge model incorporating many dimensions of data including combinations of features associated with a specific phenotype (or an optimal set of such features that best achieve a simultaneous multi-trait optimization) that have been discovered using the MARKERS platform (described in AN NEX II).

This connection of MARKERS output to the rest of the RACE engine is critical to this application.

Moreover, embodiments o f t h e RA C E e n g i n e d e s c r i b e d b e l o w are capable of performing real-time processing. Furthermore, "real-time" means in practice while a user of the system waits for results of computations that are delivered in a time scale of tens of seconds, or within several minutes, even when large-scale constraint problems are being computed and resolved by the system. It will be appreciated that, in practice, personalized (context-sensitive) recommendations from hyper-dimensional data foods may be provided in real time on a wearable, mobile or IoT (" Internet of Things ") device. The aforementioned hyper-dimensional data foods provide hyper-dimensional data that are stored in an array system model, wherein the array system model may represent constraints as well as other types of knowledge associated with each valid combination of the array system model, namely one or more object functions, all of which must interface with an environment provided to a given system in a simple interactive way, via a user interface. The term "tractable-time" means in practice a time, of the polynomial order (i.e. n², n³, n⁴ and so on), required by a computing arrangement for computation of a large-scale constraint problem .

In overview, embodiments of the present disclosure employ in operation a multi dimensional system model (namely, an array system model), for performing data processing using a computing arrangement of a control apparatus. The terms "multi dimensional system model" and "array system model" are hereinafter used interchangeably in the description. Moreover, the computing arrangement is capable of performing real-time processing.

Furthermore, the control apparatus includes a user interface for interacting with a user of control apparatus for controlling operation of the control apparatus, a data processing arrangement that is operable to receive the one or more data inputs and to output the one or more control outputs and/or one or more analysis output and/or one or more recommendation outputs, and the computing arrangement thatsupports automatic modelling, analysis and real-time inference processing on multi dimensional system models, can be implemented by way of a wide range of computational hardware. Such computational hardware includes, signal processing and embedded controllers to mobile devices (for example, smart watches, smartphones and tablets), standard computers (for example, personal computers or laptop computers), graphics processing units (GPUs), distributed computers with parallel processing capabilities, and so forth. The data processing using such computing hardware of the control apparatus, is capable of enabling a wide range of innovative decision support tools, such as veterinary decision support systems, to be realized in practice. Optionally, the multi-dimensional system models are constraint problems expressed in terms of truth tables with M raised to the power of N combinations, wherein each combination assumes either a truth-value true (valid) or a truth-value false (invalid). In such a case, the multi-dimensional system models assume that N variables are involved, wherein each variable has M elements. In general, each valid combination in a solution space computed in embodiments of the present disclosure may have one or more associated attributes or object functions, for example a price. In a special case of an embodiment of the present disclosure, all combinations may be valid, namely without any constraints on the system model being employed when computing results.

It will be appreciated that computing M raised to the power of N combinations using contemporary known computation methods will result in a " combinatorial explosion" in a contemporary computing device, that would result in an unacceptably long computation time for providing results to users via a user interface. Therefore, it is not currently a trivial task to solve large constraint problems with a multitude of variables. Nevertheless, embodiments of the present disclosure make it possible to unify seemingly contradictory requirements for completeness (all combinations must be accessible to ensure logical consistency) with compactness of representation and real- time inference processing even with complex combinatorial applications on relatively low power computational devices (for example, as aforementioned).

Furthermore, it will be appreciated that the control apparatus ispractical and useful, and optionally, compact and portable. As mentioned previously, the control apparatus includes data processing arrangements that are operable to execute software products that are able to provide solutions to veterinary problems and other types of technical control problems, without resulting in a "combinatorial explosion " that results when multi-dimensional tasks are being addressed. As it will be understood from the following description, embodiments of the present disclosure employ an advantageous form of data representation, referred to as the "array system mode G or the "multi dimensional system model". While the array system model is an optimal tool for complex constraint problems described in the foregoing, it will be appreciated that embodiments of the present disclosure are not limited to addressing veterinary related problems; for example, embodiments of the present disclosure can be used in safety critical power stations (for example, nuclear power plant, arrays of wind turbines, arrays of ocean wave energy converters and so forth), for supervising oil well equipment, for chemical plant, for airborne radar systems, for railway network management, for automatic driverless vehicle systems, and similar. Thus, embodiments of the present disclosure concern a method of generating the array system model useful for interrogating and/or configuring and/or optimizing and/or verifying a logical system spanned by variables on finite domains and/or intervals, wherein the method comprises:

(a) generating and storing, in a memory or a storage medium of the computing arrangement, an addressable solution space for a set of external variables, wherein the addressable solution space is expressed in terms of all valid Cartesian sub-spaces of states or combinations for the set of external variables with interconnected valid Cartesian sub-spaces being addressable as valid combinations of indices of link variables and/or core link variables; and

(b) arranging for the solution space to satisfy a conjunction of all, or substantially all, relations of the set of external variables, in order to establish a system model in which all, or substantially all, valid solutions are stored as nested relations, and all invalid solutions are excluded.

In embodiments of the present disclosure, there are encountered raw data foods (one or more inputs provided to the system) that are complex and multi-dimensional; such raw data foods are, for example, derived, at least in part, from sensor arrangements. However, there arises a need to transform such complex and multi-dimensional raw data foods into useful actionable insight, wherein real-time inferencing is required to be performed and personalized, and wherein there is generated context-specific recommendations or advice. In practice, for embodiments of the present disclosure, there are distinct advantages to being able to compute across such raw data on data collection hardware itself that generates the raw data in operation (for example, a smartwatch, a mobile phone or a remote sensing platform), as such a manner of operation negates requirements for large data transfers that are a potential target of data interception; moreover, such large data transfers potentially consume expensive resources in terms of both network bandwidth and power on small, battery powered mobile devices.

Embodiments of the present disclosure are operable to employ, for their variables and constraints, a semantically normalized knowledge graph (namely, "knowledge graph"). Moreover, such knowledge graphs are beneficially used in the embodiments to represent all available information from a variety of public and other data sources containing information associated with variables, relationships and constraints operating on a given complex system .

Such knowledge graphs are optionally based on a master multi-relational ontology, which includes a plurality of individual assertions, wherein an individual assertion comprises a first concept, a second concept, and a relationship between the first concept and the second concept, wherein at least one concept in a first assertion of the plurality of individual assertions is a concept in at least a second assertion of the plurality of assertions.

For each pair of related concepts, there is beneficially a broad set of descriptive relationships connecting the related concepts, for example expressed in a logical and/or probabilistic as well as linguistic manner. As each concept within each pair is potentially paired (and thus related by multiple descriptive relationships) with other concepts within a given ontology, a complex set of logical connections is formed. A corresponding superset of these connections provides a comprehensive "knowledge graph” describing what is known directly and indirectly about an entirety of concepts within a single domain. The knowledge graph is also optionally used to represent knowledge and relationships between and among multiple domains and derived from multiple original sources.

In another beneficial embodiment of the present disclosure, a semantic distance or relatedness of concepts in a specific context is calculated. Such probabilistic semantic distance metrics are susceptible to being represented as relationships between two concepts in the semantically normalized knowledge graph and used to determine a degree of connectedness of concepts above, below or between selected thresholds in a context of a specific domain or corpus.

In these aforementioned embodiments of the present disclosure, the specification of a given subset of the knowledge graph to be derived for the array system model optionally includes a selection of two or more concepts or types of concepts from a plurality of assertions of a master multi-relational ontology, applying one or more queries to two or more concepts or concept types to yield a subset of individual assertions from the plurality of assertions, wherein the queries identify one or more individual assertions from the plurality of individual assertions of the master multi-relational ontology. Specifically, the master multi-relational ontology connects the two or more concepts directly or indirectly. In a context of complex domains such as healthcare (for example, healthcare of individuals for providing welfare) examples described in the foregoing, such derived knowledge graphs potentially contain millions of concepts, each of which has multiple properties (namely, variables) with multiple potential values, and each of which may have up to tens of thousands of direct or derived logical constraints.

In describing embodiments of the present disclosure, a term "logical system" is used to mean a complete system, alternatively a sub-system that is a part of a larger system . When used to refer to a sub-system, variables associated with other sub systems are treated as being "external variables”.

In embodiments of the present disclosure, for example implemented as a control apparatus employing data processing hardware, all invalid states or combinations violating constraints of a given system are excluded from relations that are employed in operation of the multi-dimensional system model. Such exclusion of invalid states or combinations is beneficially performed when the system model is generated by a method pursuant to the present disclosure; in other words, in embodiments of the present disclosure, the invalid states or combinations are excluded from computations whenever identified to enable more rapid computation of useful results to be achieved. In practice, a state of contradiction or inconsistency is present in a system if just one relation of the system has no valid combination or state. Conversely, the system is regarded as being consistent if at least one state or combination of states is valid; namely, one state or a combination of states satisfies all system constraints. At an instance, when generating a given system model, just one relation of a system is found to have no valid combination or state, then that whole system is in a state of contradiction or inconsistency and is excluded for achieving enhanced computational efficiency.

Optionally, the method includes operating the multi-dimensional system model to have a plurality of system model states, and to change state from a given preceding system model state in among the system model states to a subsequent system model state among the system model states, depending upon a computed solution to the given preceding system model state and operative input data applied to the multi dimensional system model. Furthermore, a process of colligating relations (that is, combining relations to arrive at a more complex sub-system or system) is elucidated in detail. It will be appreciated that on each level of a process of colligation, inconsistencies or contradictions are identified in embodiments of the present disclosure, and will, thus, result in exclusion of the colligated sub-system or system. Thus, when a generating process has been completed in embodiments of the present disclosure, the system will be consistent, as manifested by all relations having at least one valid Cartesian sub-space.

In the present disclosure, the term " system " is used to refer to an entire system of variables or, alternatively, to a part of the entire system of variables, for example as aforementioned. With reference to a specific application (for example healthcare), the system provides a representation of a complete set of available domain knowledge upon which real-time reasoning or inferencing can be performed using embodiments of the present disclosure to provide useful, actionable controls, insights and recommendations using decision support tools incorporating an array system model (for example, for selecting a best available therapy for a specific patient individual within an assistive environment; for example, for selecting a best available selection of replacement component parts to be used when repairing an item of machinery). There is thereby provided an interaction between the array system model and an environmentthat is carried out by a state vector representing states of all variables involved, including physical measurements as well as decision parameters. Thus, in example embodiments of the present disclosure, variables involved can include sensor signals acquired using physical sensors, and decision parameters can be outputs that are used to control operating states of various apparatus, for example in a hospital, in an industrial plant, in a vehicle, in an energy power plant, and so forth.

In embodiments of the present disclosure, the given system is completely defined in that every combination under the system is either valid or invalid with respect to each of the system constraints relevant to use of the multi-dimensional system model and preferably with respect to absolutely each of the system constraints. Thus, the term "system" used to refer to the entire system of variables, indicates that the entire system is completely defined with respect to all system constraints relevant to the use of the system model, and optionally with respect to absolutely all system constraints. When the system of variables is not completely defined in above sense of this term, then only that part of the system which is in fact completely defined is covered by the term "system" pursuant to the present disclosure. The term " substantially " indicates a system in which process of colligation has not been completed, and where a runtime environment must be adapted to perform certain tests for consistency; for example, "substantially all" refers to at least 90%, more optionally at least 95%, and most optionally at least 99%. As aforementioned, the system constraints are optionally determined by conjugating one or more relations, wherein each relation represents valid Cartesian sub-spaces of states or combinations on a given subset of variables. The conjugation of the one or more relations comprises calculating Cartesian sub-spaces satisfying the combined constraints of the one or more relations. If no relations have common variables, no further action is required to conjugate the relations in embodiments of the present disclosure.

According to an important optional feature of the invention, all relations with at least one common variable are colligated. The colligation comprises conjugating the constraints of two or more relations that are connected by having common variables therebetween to establish one or more Cartesian sub-spaces satisfying combined constraints of the two or more relations. Furthermore, the colligation of two or more relations will normally be performed by joining the two or more relations up to a predetermined limit. Such joining comprises an operation of replacing a set of relations with a single relation satisfying combined constraints of the set of relations.

The set of relations is not limited to two relations, but can in general be any finite number of relations. In an example embodiment of the present disclosure, a case where three or more relations are joined is typically decomposed into a number of pairwise joins; this pairwise joining optionally comprises a predetermined strategy or this pairwise joining is optionally in a random order. Moreover, joining of relations will typically reduce the number of relations, and the result will be one or more relations with common link variables. Moreover, the linking of the relations consists of adding link variables and adding one or more calculated relations representing constraints on the link variables.

In an embodiment of the present disclosure, any relation with non-connecting variables as well as connecting variables is extended by adding a unique link variable with a unique index identifying each valid Cartesian sub-space on either the non-connecting variable or the connecting variables. In such situations, it is often advantageous to split a given relation into two relations, wherein one relation pertains to the non-connecting variables and the link variable, and the other relation pertains to the connecting variables and the link variable.

In relation to embodiments of the present disclosure, a term "completeness of deduction " indicates that all logical consequences are required to be deduced for one or more variables. Moreover, in embodiments of the present disclosure, the completeness of deduction relates to all logical consequences on all variables, but as indicated above, the embodiments of the present disclosure are not limited to computing all logical consequences.

When the colligation process is completed, relations for isolated variables are optionally split into a plurality of smaller interconnected relations with the isolated variables expanded to form (namely tuples). It is to be understood that such a representation is potentially more compact than compressed Cartesian arguments, and will make it possible to associate object functions to each single combination of the defining variables.

When the array system model is to be used for optimization or learning, one or more object functions, for example pricing functions, are optionally incorporated into the array system model. An object function of a given subset of variables, wherein the object function derives characteristics of a given subset of variables, is linked to a complete solution space by deducing constraints imposed by the object function on each link variable connected to the given subset of variables. After the array system model has been generated by the method pursuant to the present disclosure, object functions can provide information between a set of variables and a set of object function values, for example cost, price, risk or weight.

As an example in healthcare of individuals, given a patient individual's set of co morbidities and co-prescriptions, it is potentially contemporarily not possible to select a drug for a particular disease from any of available options that does not present some significant risk of interactions or side-effects arising. In such a case, it is necessary to choose a best available drug, which reduces, for example minimizes, a likelihood and/or severity of any of these potential interactions or side-effects. Such a reduction, for example minimization, can be achieved by accepting a partially incomplete deduction (with, for example, a single invalid variable), and then using object functions as described below to evaluate and optimize the likely outcomes, such as potential patient individual benefit, treatment cost and side-effect risk.

If a set of object function values does not have a "natural" order, in contrast, for example with numbers, an arbitrary order can be assigned to the set of object function values. Characteristics of the object function are susceptible to being determined; moreover, constraints on the link variables deduced on each combination of the given variables can be determined, wherein the result is represented as a relation on the object function, the given variables, and the link variables. These characteristics are optionally values of the object function given by functional mapping of a set of independent variables or a set of constrained variables. The mapping can also be a general relation yielding one or more object function values for each combination of the variables.

Embodiments of the present disclosure provide a method of interrogating and/or configuring and/or optimizing and/or verifying and/or controlling a system spanned by variables on finite domains, wherein the method comprises:

(a) providing an array system model in which substantially all valid solutions in the system are stored as nested arrays representing valid Cartesian subspaces on all external variables, with all interconnected valid Cartesian subspaces being addressable as valid combinations of indices of link variables; and

(b) deducing any sub-space, corresponding to an input statement and/or query, of states or combinations spanned by one or more variables of the system represented by the nested arrays by deriving the consequences of a statement and/or a query by applying the constraints defined by the statement and/or query to the system model.

In respect of embodiments of the present disclosure, "deducing" refers to deriving or determining logical inferences or conclusions, for example all inferences or conclusions, from a given set of premises, namely all the system constraints.

In respect of embodiments of the disclosure, the term "query" refers to a question for which the array system model is operable to provide answers, for example, a question regarding a particular combination of sensor signal values, but not limited thereto, subject to defined conditions. An exemplary question concerns one or more valid combinations of a given set of variables satisfying the system constraints and, optionally, also satisfying an external statement. An external statement may be a number of asserted and/or measured states and/or constraints from the environment. Moreover, a deduction of any subspace of states or combinations is performed on a given subset of one or more variables either without or colligated with asserted and/or measured states and/or constraints from the environment. An interaction between the system represented by the array system model and the environment is suitably performed by means of a state vector (SV) representing all valid states or values of each variable.

Thus, an input state vector (SV1) is employed to represent the asserted and/or measured states from the environment, whereas an output state vector (SV2) is used to represent one or more deduced consequences on each variable of the entire system when the constraints of SV1 are colligated with all system constraints in the array system model .

Optionally, the multidimensional system model includes static constraints, clusters of accumulated states, and dynamic rules which represents valid transitions between valid states.

In a preferred embodiment of the present disclosure, each invalid variable may be either discarded from the environment (SV1) or may bededuced as a consequence (SV2). Furthermore, optionally, variables defined as output variables are allowed to change a state without causing a contradiction. Moreover, deduction may be optionally performed by consulting one or more relations and/or one or more object functions at a time by colligating a given subset of variables in a relation with given subsets of states in a state vector and then there is deduced therefrom possible states of each variable.

In embodiments of the present disclosure, the method comprises (using the aforesaid RACE engine) computing one of three different types inferences, namely: deduction, abduction or induction, as described in the following examples:

Deduction :

General method:

Rule : If A, then B.

Observation : A is true.

Conclusion : B is true.

The method (using the aforesaid RACE engine) :

SV1 (input state vector) : A is true, B is unknown.

SV2 (output state vector) : A is true, B is true. Abduction :

General method:

Rule : If A, then B.

Observation : B.

Conclusion : Possibly A.

The method (using the aforesaid RACE engine) :

Find all input state vectors (SV1) implying output state vector (SV2) B is true. For example, find SVl(a), SVl(b), SVl(c)...SVl(n) implying SV2(B).

Induction :

General method:

Observed : A.

Observed : B.

The method (using the aforesaid RACE engine) :

All asserted and/or measured states from an environment are captured, counted and represented in a table. For example, where four different asserted and/or measured states are counted :

A B Count

0 0 300

0 1 50

1 0 3

1 1 600

The above table is an array system model computed using the RACE engine, with all asserted and/or measured states from the environment. Furthermore, all four valid states may be represented with an object function (Count), or rare observations may be eliminated (to be considered invalid), in order to build compact and fast models. For example:

A B Count (truth table of implication : A implies B)

0 0 300 0 1 50

1 1 600

A B Count (truth table of implication : A implies B and B implies A)

0 0 300

1 1 600

Thus, the method allows deduction and abduction to be performed on an existing decision support knowledge model . Furthermore, the method allows induction to be performed to build a decision support knowledge model based on asserted and/or measured states (or state vectors) from the environment.

In embodiments of the present disclosure, clustering and dynamic properties are employed in operation of the array system model . Such clusters represent a list of state vectors associated with known attributes. States of the cluster are determined from external variables (EV) and/or internal state variables that span the array system model . Relationships between the states of the clusters and state variables are defined by a cluster relation . For example, a given cluster relation has three state variables: a state of the cluster, and variables VI and V2. In operation of embodiments of the present disclosure, there may be a logical OR between rows in a relation table (namely, as in a disjunctive form). Alternatively, the cluster relation is a relation between the states of the clusters and state variables, wherein states of clusters are input and state variables are output. For example, a cluster state variable may represent a set of n- states with combinations of genomic features (using the aforesaid MARKERS engine), while a cluster relation is the relation between such a cluster state variable and assodated one or more phenotypic or clinical variables. The cluster relations reduce a hyper-dimensional space, having millions of parameters, to a corresponding multi-dimensional array system model . When the states of the external variables are known, processing of the cluster relation in run-time may be described as including steps as follows :

(a) comparing external measurements with the states of cluster in the cluster relation and identifying corresponding matching rows;

(b) deducing values of the output state variables VI and V2; and

(c) deducing the constraints on all other state variables by a state propagation in the array system model . Completeness without colligation can be ensured as the given cluster may be only a part of one relation and therefore considered as an isolated variable in the multi dimensional and complete array system model. Exemplary applications of clustering include, precision medicine, d ru g d i scovery, state-event processing and many other exceptionally complex applications.

A consultation of a relation is beneficially performed by colligating, for example joining, the relation and states of variables present in the relation. The consultation provides a result that can be a projection (namely, a union of all elements) on each variable of the colligated relation, or the result can be the colligated relation. The colligation is optionally a joining, however, it will be appreciated that the consultation of each relation is not limited thereto. In an example embodiment of the present disclosure, two or more variables are colligated in parallel; projections on two or more variables are similarly performed in parallel.

However, it will be appreciated that embodiments of the present disclosure are not limited to such parallel implementation, and the embodiments are optionally susceptible to being implemented sequentially.

In an embodiment of the present disclosure, completeness of deduction is obtained by consulting connected relations, until no further consequences can be deduced on any link variable. Such an operation is termed "state propagation" . Moreover, such a state propagation comprises consulting two or more relations in parallel, namely concurrently.

The parallel execution of the state propagation may be implemented on one or more GPUs (Graphics Processing Units) or hardware designed for such parallel execution. The interaction between the array system model and the environment by the state vector may be carried out by simple operations that are suitable for a hardware implementation on devices such as embedded control systems, Internet of Things (IoT) sensors or Field Programmable Gate Arrays (FPGAs).

An important feature of configurations and/or optimizations employed in embodiments of the present disclosure is that states of contradiction can be identified, namely when no valid states or values are deduced when consulting, namely investigating or checking, at least one relation. Such identification of contradictions and an elimination of a need to perform computations in connection with the contradictions, enable methods of the present disclosure to reduce computational resources required for performing complex hyper-dimensional computations.

The array system model (referred to as ASM in the following) is a compact and complete representation of all valid combinations and associated object functions of constraint problems on finite domains or intervals. The ASM is used to represent a person, an individual, an apparatus, a facility, a factory or similar system . A solution space of valid states or combinations is beneficially represented geometrically in terms of nested data arrays, and the ASM is simulated very efficiently in operation by simple operations on these arrays using CPUs (Central Processing Units), GPUs (Graphics Processing Units) or hardware devices designed for this specific use.

Major data flows required for performing ASM modelling include input data, for example a user-defined specification of system constraints in terms of a set of rules or relations pertaining to a given set of variables. Thus, the ASM modelling is implemented in a six-step procedure, wherein the six-step procedure includes STEP 1 to STEP 6 as follows:

STEP 1 : Compile variables and relations

Each user-defined variable and each relation is compiled into the internal array representation. At this stage STEP 1, the relations are considered as independent items.

STEP 2: Colligate relations, verification of system

The solution space of the entire system is determined by colligating interconnected relations (constraint elimination). The system is simultaneously tested for logical consistency and redundancy. Embodiments of the present disclosure relate inter alia to a more efficient colligation strategy.

STEP 3: Minimize and link complete solution space

The complete solution space can be, for example, minimized and restructured in order to meet requirements in a runtime environment. Examples include: minimizing memory footprint to enable operation on a wearable device; splitting the array system model into multiple instances for parallel processing hardware; adding object functions on combinations of selected variables; and adding dynamic constraints in terms of relations as well as states to enable real-time response to signals from IoT or wearable sensors.

Step 4: Link object functions

Optionally, the relations may be extended with further attributes, when the valid combinations satisfying the system constraints are associated with values or object functions to be optimized or used for specific applications, such as, for example, a price or "soft constraints" such as side-effect risk and severity with further values than just true or false.

Step 5: Cluster states and cluster relations

Optionally, clustering is performed to reduce the hyper-dimensional space, potentially with millions of parameters, to the multi-dimensional ASM for performing decision support. Examples include: millions of genomic phenotypic and veterinary variables that are condensed/reduced to a few hundred variables, which is utilized by decision support system (such as, the welfare system). Clustering is based on cluster states (i.e. "states of clusters ") and cluster relations, for example clusters of biomarkers discovered by the MARKERS platform .

Step 6: State-event relations

Optionally, state-event relations utilize external events to describe the change from one state to another. Clustering is based upon internal state variables representing the conditions for change of state.

At this stage, the process of ASM modelling is finished. The entire solution space is now susceptible to being addressed by coordinate indexing and other simple operations on the nested arrays.

Each item of the state vector SV represents the state (namely the valid values) of an associated variable. For example, in respect of the input state vector SV1, one or more variables are bounded due to external measurements or assertions. Moreover, the input state vector SV2 represents the resulting constraints on all variables. The properties of the ASM are summarized as follows:

(a) a run-time execution on the ASM is performed with completeness of deduction in real-time, namely with predictable use of processing time and memory. The ASM technology is therefore suitable for use in embedded decision support or for use in control systems on small computer devices: and

(b) the ASM representation is compact and complete. Embedded applications of embodiments of the present disclosure are required to fulfil all requirements for compactness, completeness and real-time capability with limited computing resources, even on large system models.

SIMPLE COLLIGATION STRATEGY (ADB)

Optionally, a generation of the ASM technology (to be abbreviated to "ADB" in the following) is based on a simple colligation strategy by pairwise joins of relations and then linking isolated variables whenever possible the relations are operable to share variables. Moreover, the colligation graph is an illustration of a structure of interconnected relations, wherein nodes represent relations and arcs represent common variables of two of the relations.

A first colligation step is to compile each relation, namely to determine valid combinations of each relation. It will be appreciated that all invalid combinations are eliminated from each of the relations. Moreover, the valid combinations are expressed in terms of Cartesian sub-spaces; however, it will be appreciated that other coordinate spatial reference frames may be optionally employed for implementing embodiments of the present disclosure.

A second colligation step is to colligate the relations to determine the solution space of the conjunction of all relations. It is now possible to perform inference processing by performing simple array operations. The state vector is the important link between the compiled (colligated) array system model and the environment. The output state vector is deduced by consulting the complete solution space. The state of each variable is deduced by computing the union of elements from the two valid Cartesian sub-spaces. In general, the colligation process is carried out by pairwise joins of the relations, and after each join isolated variables are separated (assuming at least two isolated variables) into new relations connected by common link variables representing the valid Cartesian sub-spaces. The state vector is deduced by consulting one relation at a time, until no further constraints are added to each variable (state propagation).

Thus, the state propagation on a tree structure of interconnected relations (by the valid states of the common link variables) ensures completeness of a given deduction; in other words, all constraints on all variables are deduced in embodiments of the present disclosure. It will be appreciated that completeness of deduction is not possible by state propagation on the array representation of user-defined relations. Thus, there arises a need to colligate all interconnected relations in advance, even on such a very simple cyclic structure with only a single variable connecting each relation pair.

The simple colligation strategy (namely ADB technology) described in the following is susceptible to being summarized as follows:

A given process of joining relations with common variables and linking isolated relations on isolated variables is potentially impossible to implement in practice on large sets of relations due to a possible blow-up in size of a corresponding joined result (namely, is computationally impossible to achieve in practice using contemporary computing hardware). Such requirement for huge computational resources is an insurmountable and constant issue arising on account of a complexity of constraints in a range of practical technical fields of use of intelligent data processing systems in fields such as healthcare and life sciences.

If the process of joining relations can be completed, a binary output that is thereby achieved does satisfy requirement for completeness, but does not satisfy other requirements for embedded solutions, namely:

(a) A representation thereby derived will not be as compact as possible, and potentially must be reduced in size, for example minimized in size, to meet specific hardware requirements for achieving size and real-time capability.

(b) A complete solution space will not necessarily be accessible by parallel processing hardware using simple instructions, for example using GPUs.

(c) The complete solution space must be addressable in order to include object functions. A compressed data format (namely, nested Cartesian arguments) may not be a suitable representation for variables defining an object function; relations for these variables are beneficially in an expanded form representing all valid tuples rather than Cartesian arguments.

(d) Relations without any constraints (tautologies) are potentially also a part of static constraints of a system model interacting with dynamic constraints from an environment.

PARALLEL COLLIGATION

Initially, relations are joined pairwise using an approach as described in published patent documents WO 1999048031A1 and WO 2001022278A2. Moreover, isolated variables (namely, variables only present in their corresponding single relations) are separated and linked into new relations. A trivial case of parallel colligation is to join all relations into a single relation (wherein such an approach is suitable for smaller problems) or into a tree structure of interconnected relations with isolated variables (wherein such an approach is suitable for larger problems), and the colligation is thus thereby completed. In respect of aforementioned larger problems, it is not potentially feasible to use known joining methods due to a size of the joined result arising from such joining methods. It is thereby beneficial to introduce a parallel colligation of smaller parts of the system, wherein :

a parallel join of a relation pair is performed or a parallel colligation of variable groups is performed.

PARALLEL JOIN OF RELATION PAIRS

In an internal array representation in compressed form, relations are represented by 5 and 3 Cartesian arguments. Such small relations are susceptible to being joined in different ways. However, in respect of large relations, such an approach would cause a combinatorial explosion of possible argument intersections, which would be very expensive in terms of central processing unit (CPU) resources and data memory to compute in a practical example. Thus, pursuant to embodiments of the present disclosure, it is therefore beneficial to use a much more efficient methodology for colligating a smallest possible subsystem spanned by just a single variable step of a join algorithm as a result of expanding the local intersections of each variable to the matching indices of arguments in the joined relation. This indexing procedure is highly efficient and does not benefit from being implemented by employing parallel data processing. Thus, it will be appreciated from the foregoing that the number of arguments in the joined result, and data memory requirements, for computing and storing results, can be predicted from said indexing procedure. The local results of each colligated variable are now expanded to the attributes of the joined relation using the associated indices.

COLLIGATION STRATEGY FOR VARIABLE GROUPS

Initially, relations are joined and compressed pairwise using an approach as described in published patent documents WO 1999048031A1 and WO 2001022278A2 (namely, as per Step 1 in the foregoing). Isolated variables (only present in a single relation) are separated and linked into new relations. A trivial case is to join all relations into a single relation (suitable for small problems) or the tree structure of connected relations with isolated variables (suitable for larger problems), and the colligation is thus thereby completed. On large problems, it is not potentially feasible to join all relations due to the size of the joined result. It is thereby beneficial to introduce the colligation of relations on selected variable groups.

In an embodiment, the number of Cartesian arguments in the relations is very large, and it is not possible to join the relations. A corresponding workflow for colligation in respect of groups of variables shared by same given relations is:

Step 1 : Determine distinct variable groups shared by two or more relations: all variables shared by same relations are grouped. An aim in the Step 1 is to find distinct groups (namely, with no overlap), and therefore there is performed a merging of the small group into the larger one.

Step 2: Split relations on each variable group: all relations share the variable group. A copy of the relations on these variables and the associated link variables is made.

Steps 3 and 4: Join and link relations on each variable group: joining the relations on the variable group yields a relation with the following variables. Next, the variable group is isolated and a new link variable indexing each Cartesian argument is thereafter added. There is thereby generated a result that is a relation.

Step 5: Substitute variable groups in original relations with the associated link variables. The relation defines the relationship between variables. Step 6: Colligate relations on link variables. The original relations are now defined on the link variables of isolated relations. These results are also colligated by join and, if possible, to isolate variables. Assuming that it is required to join to provide a single relation, there is thereby provided a relation.

MINIMIZE AND LINK COMPLETE SOLUTION SPACE

Furthermore, there is thereby now completed the colligation process yielding the addressable complete solution space. All invalid combinations are eliminated (with a state of contradiction as a special case). A final task is to prepare the model for embedded applications, namely to seek to minimize a size of the binary file (to achieve compactness) and to optimize a run-time performance in respect of specific hardware, whether with or without parallel processing capabilities, for example multi-core GPUs are susceptible of providing parallel processing functionality. Each individual relation is potentially split into more relations in two different ways, depending upon a size of an output to be generated and upon whether or not there is use made of parallel processing hardware.

Option 1 :

Split core relation into pairs and split model for parallel processing. A given relation is extended with a link variable (LINK) indexing the Cartesian arguments (in a compressed form) or tuples (in an expanded form) of the given relation with variables VAR1, VAR2, ... VARn. The given relation is then split into n derived relations on (VARl, LINK), (VAR2, LIN K), (VARn, LINK), respectively; n is an integer of value 2 or greater (namely, a plurality). Such a method will always be used on a core relation of a complete array system model, whenever the model is to be split and distributed for parallel processing. In a runtime environment, it is thereby feasible to ensure completeness of deduction by a simple state propagation of a state vector.

Option 2 :

Split relation into tree structure of interconnected relations: the original relation is split into a tree structure of relations. There is employed a method as follows:

Step 1 : Find smallest derived relation on N variables in the Step 1, the smallest number of Cartesian arguments (or, alternatively, tuples in expanded form) is on the variables. Step 2, 3: Add new link variable and isolate relation in the Steps 2 and 3 and the relation on variables is extended with a link variable and then isolated (namely stored) for the binary output file.

Step 4: Update relation R: remove VAR1, VAR2 and substitute with link variable in the method.

The aforementioned Steps 1 to 4 of the method are executed recursively to yield a list of relations and finally a relation which is not split (namely, representing a root of the aforementioned tree).

BUILDING DECISION SUPPORT SYSTEMS

The construction of the Array System Model and Decision Support Application is a multi-stage process involving the following steps:

Step 1 - Mining of Source Data and Semantic Normalization (using the aforesaid

MARKERS engine);

Step 2 - Compilation and Validation of Array System Model; and

Step 3 - Accessing Array System Model on mobile/wearable device via Runtime

API using the User's Input State Vector.

The array system model is converted by the Array System Model compiler into a verified and normalized structure, that can be represented in a 428 KB file, which is an amount of memory the model consumes when loaded into an Array Runtime API on a given user's mobile device, for example a smart phone or a smart watch. A significant proportion of this memory (namely, over 60% thereof) is simply used for storing names of drugs being considered in the computation, as well as diseases and foods; such data is potentially further optimized, if necessary, so that the Array System Model requires even less computing resources in operation. The Array System Model provides an analytical and predictive substrate to power a personalized decision support app (namely, application software) on the given user's mobile device. This substrate enables the Runtime API running directly on the user's mobile device (smart watch, phone, or tablet) to use the Array System Model to perform logical inferences on the data and deduce all the consequences of a given parameter for a selected data set. Embodiments of the present disclosure are operable to provide a decision support system for performing aforementioned analyses within a predictable and very short time; for example, a proprietary Google Nexus Apple® or Microsoft® tablet computer running an Android software platform is capable of implementing analyses within five to ten milliseconds. Such computational performance is provided with a constant and low memory footprint (namely, around 430 KB in practice), and is guaranteed to find all the potential adverse consequences given by constraints imposed by a given user's inputstate vector.

Optionally, the computing arrangement includes at least one of: a computing device and a distributed arrangement including a plurality of computing devices.

Optionally, the sub-models are distributed over a plurality of computing devices that are mutually coupled together in operation via a data communication network.

Optionally, the method includes generating and storing, in a data memory or data storage medium of the computing arrangement, an addressable solution space defining all valid transitions between all valid states.

Optionally, the method includes computing the state of the entire system model in real time by consulting one or more sub-systems and/or relations at a time by deducing possible states of each variable and propagating one or more bound link variables to connected one or more relations until no further constraints can be added to the state vectors.

Optionally, the control apparatus is configured to be employable for controlling one or more of:

(i) industrial production facilities;

(ii) agricultural production facilities;

(iii) healthcare providing facilities;

(iv) drug discovery systems;

(v) smart metering arrangements;

(vi) autonomous and self-drive vehicle driving arrangements;

(vii) in intelligent drones for surveillance use;

(viii) in airborne radar systems; and

(ix) in intelligent apparatus for assisting veterinary surgery and/or treatment. AN NEX II : MARKERS ENGINE

The MARKERS engine employs combinatorial methodology to perform combinatorial feature analysis, wherein the computational engine works on GWAS datasets. The combinatorial feature analysis takes into account epistatic and pleiotropic interactions between various genetic and non-genetic factors. The epistatic interaction refers to combinations of multiple features, such as single-nucleotide polymorphisms (SNPs) genotypes and other features associated with a phenotype, that in a specific combination are found in individuals associated with a disease (namely, cases) but not in healthy population (namely, controls). The pleiotropic interaction refers to the same combination of features associated with different diseases or phenotypes. The computational engine employs GWAS datasets that may be stored in a database arrangement. Furthermore, the GWAS datasets can be generated using well-known techniques, including but not limited to, SNP genotyping using SN P microarrays, exome sequencing, genome sequencing, and so forth. Furthermore, a pre-filtering of specific datasets to be analyzed is employed. The pre-filtering step is performed to reduce the number of SNPs to be considered, wherein the pre-filtering includes at least one of removing SNPs that are in linkage disequilibrium; removing SNPs and/or other features that are irrelevant to or not likely to be of sufficient statistical significance for the analysis; and selecting specific SNPs and features. It will be appreciated that the SN Ps that are within linkage disequilibrium have non-random associations with each other and thus, a likelihood of determining a random association therebetween that may lead to generation of outputs of medical products or methods is low. The pre filtering includes removing SNPs and/or other features that are irrelevant to or not likely to be of sufficient statistical significance for the analysis. Such pre-filtering of the irrelevant SN Ps or SNPs having a less likelihood of having sufficient statistical significance, enables removal of SN Ps that will have a negligible effect on the generated output. In yet another example, the pre-filtering is performed, such that the pre-filtering includes selecting specific SN Ps and features, such as, SNPs or features corresponding to one or more hypotheses. In such an example, the hypothesis can correspond to variations (or polymorphisms) due to non-coding variants, biological insights, metabolic pathways, lifestyle (such as diet, smoking, drinking, sleep, exercise, and the like), clinical information (such as existing prescriptions, diagnostic results like imaging, assays, and the like), phenotypic information (such as age, sex, race, weight, comorbidities), and so forth.

The MARKERS engine performs mining to find all or a substantial majority of distinct n-combinations of SNP genotypes and/or other types of features found in the input measurands of cases and not controls provided in the database arrangement. Such mining is performed in ascending levels of order, in an n number of layers, one layer at a time and the n-combinations are stored in an output data structure. For example, 20 SNPs are analyzed at a layer 1, wherein SN Ps associated with all cases and controls within the population are analyzed. Alternatively, a specific set of cases and controls are analyzed at the layer 1, wherein such a specific set can be predefined by a user (for example, based on a hypothesis). Subsequently, combinations of 2 SNPs occurring in the cases and controls in a layer 2 are determined from the set of SNPs determined in the layer 1, wherein such combinations of 2 SNPs satisfy the >MinCases and the <MaxControls criterions. Thereafter, combinations of 3 SNPs occurring in the cases and controls in a layer 3 are determined from the set of SNPs determined in the layer 1. Similarly, incremental (n+1) combinations of SN Ps are determined in successive layers, until no valid combinations of SNPs are found at a particular layer. In such an instance, the determination of combinations of n-SNPs (or n-combinations) is terminated in successive layers. In one example, the n-combinations are determined in 20 or more layers.

Furthermore, a penetrance of the networks is determined, such that the penetrance is associated with an amount of population that corresponds to the network. In an example, the penetrance is expressed as a percentage value. Moreover, the MARKERS engine performs, in operation, execution of network annotation or annotating networks with a semantically normalized knowledge graph containing information about the shared one or more properties. The semantically normalized knowledge graph contains information about the shared one or more properties including but not limited to, SNPs, genes, pathways, targets, drugs, diseases, pharmacogenetics and drug interactions and so forth. In one embodiment, one or more properties from the SNPs, genes, pathways, targets, drugs, diseases, pharmacogenetics and drug interactions are selected in the semantically normalized knowledge graph. Subsequently, the one or more properties selected is correlated with the network of SNPs to determine information about the SNPs, such as, if the SNPs are in a coding, non-coding or eQTL (expression quantitative trait loci) region; the genes or pathways that are affected by the SNPs; diseases or phenotypes associated with the SNPs; a location within the genome where the SNPs are occurring; known phenotypic associations of the SNPs within the networks; if the diseases or phenotypes associated with the SNPs are druggable, and so forth. Moreover, the MARKERS engine, in operation, performs re-clustering of the networks, after correlating the validated networks with the semantically normalized knowledge graph containing information about the shared one or more properties. The re clustering of the networks is performed by merging networks comprising at least one common SNP therein. Furthermore, hypothesis driven criteria based on biological insights, role of specific metabolic pathways, lifestyle factors, clinical factors, and the like, may be applied and tested in the re-clustering stage by re-segmenting the case and control populations based on specific conditions.

The re-clustering is used to correlate validated networks with extended phenotypic and clinical data to find biological explanations for observed associations. The correlation of phenotypic and clinical data is performed to find the biological explanations for observed associations of the SNPs within the cluster. In an example, the phenotypic and clinical data can be associated with merged networks corresponding to various other populations. In another example, hypothesis-driven criteria comprising biological insights, role of metabolic pathways, lifestyle data and so forth, are correlated to find the biological explanations for the observed associations of the SNPs within the cluster.

In exemplary operation, a data processing arrangement implementing the MARKERS engine finds at least one other feature that is selected from omics, or non-genetic factors. As mentioned hereinabove, the data processing arrangement correlates phenotypic and clinical data to find the biological explanations for observed associations of the SNPs within a cluster. Furthermore, such phenotypic and clinical data associated with the cases can be used to determine the at least one other feature from omics, or non-genetic factors. In one example, the data processing arrangement in operation finds cases and controls that share at least one non-genetic factor, such as a phenotypic, clinical and/or lifestyle factor. Furthermore, the data processing arrangement performs high-order combinatorial association of the non-genetic factors and genetic factors, such as, presence and absence of SNPs in the cases and controls respectively, to identify disease protective effects associated with the controls. In an example, the controls comprise individuals of a population that had not developed breast cancer by an age of 55 years (1,458) and the cases comprise individuals of the population that had developed breast cancer before an age of 40 years (1,576). In such an example, the data processing arrangement identifies high-order non-disease- associated combinatorial features in 451 individuals of 1,458 controls, using a false discovery rate (FDR) of 5%, within the population used that can be used to identify disease protective effects within the population. These are also prime candidate for novel drug discovery or repurposing, because they offer an opportunity to increase functioning of those pathways.

Claims

1. A welfare system that provides welfare support, when in operation, to a plurality of individuals in an assistive environment, wherein the welfare system includes a data processing arrangement implementing a RACE engine that receives in operation a plurality of measurands of a given individual within the assistive environment, wherein the data processing arrangement includes a decision support knowledge model including a plurality of treatment strategies and at least one of: drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each individual, individual genotype data, and SNP data, wherein the data processing arrangement provides output signals for developing a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's specific disease, and wherein the data processing arrangement executes a software product that in execution performs a high-order combinatorial search within the decision support knowledge model based upon the plurality of measurands and generates the output signals, characterized in that the welfare system, when in operation :

(a) employs the given individual's SNP genotypes and/or one or more other features which synergistically affect disease status as a part of the measurands;

(b) the software product is configured to perform a multi-dimensional solution search in the decision support knowledge model to identify high-order combinations of the given individual's SN P genotypes, using a computational engine, implemented as the RACE engine, with combinatorial methodology for combinatorial feature analysis executed in the data processing arrangement, for each individual within the assistive environment; and

(c) the software product is used to compute a welfare trajectory for an individualized welfare of each individual, wherein the welfare trajectory comprises a course of treatment to be prescribed to the given individual.

2. A welfare system of claim 1, characterized in that the system further comprises a sensor arrangement spatially distributed within the assistive environment, wherein the data processing arrangement receives sensor signals from the sensor arrangement that senses in operation environmental conditions for each individual, including monitoring a food intake for each individual, and wherein the data processing arrangement executes the software product that analyses the sensor signals in respect of the decision support knowledge model by performing a multi-dimensional solution search in the decision support knowledge model based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each individual within the assistive environment.

3. A welfare system of claim 1, characterized in that the genomic data is associated with a given gene of the given individual, wherein the data processing arrangement executes in operation the high-order combinatorial search in a range of 3 to 20 orders.

4. A welfare system of claim 1, characterized in that the genomic data is associated with a given gene of the given individual, wherein the data processing arrangement executes in operation the high-order combinatorial search in a range of 5 to 13 orders.

5. A welfare system of claim 1, characterized in that the SNP data includes single nucleotide polymorphisms characterizing each individual, determined by using microarrays, DNA sequencing, CRISPR or Polymerase Chain Reaction (PCR) to read genetic tissue samples derived for each individual.

6. A welfare system of any one of the preceding claims, characterized in that the welfare system collects in operation one or more pathogens present pathogens and/or other microorganisms in the assistive environment, genotype sequences the pathogens and/or other microorganisms to characterize the pathogens and/or other microorganisms, and employs the characterization of the pathogens and/or other microorganisms as an input parameter to the software product when executed in the data processing arrangement to use in performing its search for computing the welfare trajectory for the individualized welfare of each individual.

7. A welfare system of any one of the preceding claims, characterized in that the output signals are used to control at least one of:

(i) type and/or quantity of food provided to the individuals;

(ii) a time when food is provided to the individuals;

(iii) additional food supplements and/or one or more drugs to be administered to the individuals;

(iv) changes to husbandry practices including selective heating or cooling to be supplied to the individuals; and

(v) pathogen reducing processes to be applied to the assistive environment.

8. A welfare system of any one of the preceding claims, characterized in that the welfare system operates to analyse the given individual's entire exome from the given individual's tumour biopsy provided as measurands to the data processing arrangement, to capture a tumour network pertaining to the given individual's entire exome.

9. A welfare system of any one of the preceding claims, characterized in that the data processing arrangement finds in operation high-order combinations of SNP genotypes which synergistically affect a disease status of the given individual represented in the input parameters.

10. A welfare system of claim 9, characterized in that the welfare system operates to identify a treatment for the disease that is selected from a group including : diabetes, cancer, cardiovascular, neurological disease and respiratory disease.

11. A welfare system of claim 10, characterized in that the data processing arrangement designs in operation a course of treatment for the given individual, wherein the treatment is based upon the patient individual's SNP genotype and at least one non-genomic feature of the given individual.

12. A method of (A method for) operating an welfare system that provides welfare support, when in operation, to a plurality of individuals in an assistive environment, wherein the welfare system includes a data processing arrangement implementing a RACE engine that receives, when in operation, a plurality of measurands of a given individual within the assistive environment, wherein the data processing arrangement includes a decision support knowledge model including a plurality of treatment strategies and at least one of: drug characteristics, food supplement characteristics, husbandry strategies depending on individual health complications, disease characteristics of each individual, individual genotype data, and SNP data, wherein the data processing arrangement provides output signals for developing a personalized identification of one or more active drug combinations for the treatment or prevention of a given individual's specific disease, and wherein the data processing arrangement executes a software product that in execution performs a high-order combinatorial search within the decision support knowledge model based upon the plurality of measurands and generates the output signals, characterized in that the method includes:

(a) employing the given individual's SN P genotypes and/or one or more other features which synergistically affect disease status as a part of the measurands;

(b) arranging for the software product to perform a multi-dimensional solution search in the decision support knowledge model to identify high-order combinations of the given individual's SNP genotypes, using a computational engine, implemented as the RACE engine, with combinatorial methodology for combinatorial feature analysis executed in the data processing arrangement, for each individual within the assistive environment; and

(c) using the software product to compute a welfare trajectory for an individualized welfare of each individual, wherein the welfare trajectory comprises a course of treatment to be prescribed to the given individual.

13. A method of claim 12, characterized in that the welfare system further comprises a sensor arrangement spatially distributed within the assistive environment, wherein the method comprises arranging for the data processing arrangement to:

(a) receive sensor signals from the sensor arrangement that senses in operation environmental conditions for each individual, including monitoring a food intake for each individual, and

(b) execute the software product that analyses the sensor signals in respect of the decision support knowledge model by performing a multi-dimensional solution search in the decision support knowledge model based on at least a subset of the sensor signals and a genotype determination by DNA sequencing of each individual hosted within the assistive environment.

14. A method of any one of the claims 12 or 13, characterized in that the SN P genotypes are selected from SNP genotypes present in non-coding regions of genes, in the intergenic regions or in coding regions of genes.

15. A method of any one of the claims 12 to 14, characterized in that the method includes arranging for the SNP data to include single nucleotide polymorphisms characterizing each individual, determined by using microarrays, DNA sequencing, CRISPR or Polymerase Chain Reaction (PCR) to read genetic tissue samples derived for each individual .

16. A computer program product comprising a non-transitory computer readable storage medium having computer-readable instructions stored thereon, the computer- readable instructions being executable by a computerized device comprising processing hardware to execute the method of claim 12.