CN114464269A - Virtual medicine generation method and device and computer equipment - Google Patents
Virtual medicine generation method and device and computer equipment Download PDFInfo
- Publication number
- CN114464269A CN114464269A CN202210359239.2A CN202210359239A CN114464269A CN 114464269 A CN114464269 A CN 114464269A CN 202210359239 A CN202210359239 A CN 202210359239A CN 114464269 A CN114464269 A CN 114464269A
- Authority
- CN
- China
- Prior art keywords
- processing
- link
- computing resources
- processing tool
- processing link
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/50—Molecular design, e.g. of drugs
Landscapes
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- Crystallography & Structural Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a virtual medicine generation method, a virtual medicine generation device and computer equipment, wherein the virtual medicine generation method comprises the following steps: acquiring a workflow file corresponding to a virtual medicine to be generated; determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file; determining at least one processing tool corresponding to each processing link from the software pool; performing componentization on the processing tool corresponding to each processing link to obtain a processing tool component corresponding to each processing link; determining computing resources corresponding to each processing link, wherein the computing resources comprise cloud computing resources and super computing resources; and controlling the processing tool component to call corresponding computing resources to process the corresponding processing links. The method and the device can process the whole flow of the virtual medicine to be generated according to actual requirements, the processing mode of each processing link is more flexible, and the applicability and operability for virtual medicine generation are stronger.
Description
Technical Field
The invention relates to the technical field of medicine generation, in particular to a virtual medicine generation method and device and computer equipment.
Background
With the rapid development of computer technology, in the process of modern medicine research and development, computer aided design is used to reduce the cost and cycle of new medicine research and development. At present, the related technology for computer-aided drug design usually carries out deep research on a virtual drug screening link, and is mostly realized based on a cloud computing technology. However, the processes involved in the drug generation process are very many, and also include processes such as protein structure prediction, precursor chemical and physical optimization, patent drug analysis and the like, some processes can be completed by computing with cloud computing resources, and some processes can be completed by utilizing the powerful computing power of super computing. Therefore, it is very necessary to integrate cloud computing and super computing and study the full-flow computing of virtual drug generation on the basis of the cloud computing and super computing.
Disclosure of Invention
In view of this, the present invention provides a virtual drug generation method, an apparatus and a computer device, which utilize a computing resource integrated by cloud computing and super computing to compute a full process of virtual drug generation, so as to at least partially solve the problems in the prior art.
The specific invention content is as follows:
a virtual medication generation method, comprising:
acquiring a workflow file corresponding to a virtual medicine to be generated;
determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file;
determining at least one processing tool corresponding to each processing link from the software pool;
performing componentization on the processing tool corresponding to each processing link to obtain a processing tool component corresponding to each processing link;
determining computing resources corresponding to each processing link, wherein the computing resources comprise cloud computing resources and super computing resources;
and controlling the processing tool component to call corresponding computing resources to process the corresponding processing links.
Further, the method further comprises:
and respectively packaging each processing tool in the software pool according to the preset input and output standard of each processing tool to obtain a primary assembly corresponding to each processing tool.
Further, the componentizing the processing tool corresponding to each processing link to obtain the processing tool component corresponding to each processing link includes:
determining the number of processing tools corresponding to each processing link, and if the number of the processing tools is 1, acquiring a primary assembly of the processing tool corresponding to the processing link as a processing tool assembly of the processing link;
if the number of the processing tools is larger than 1, packaging the primary assemblies of the processing tools corresponding to the processing link according to the input and output standards of the processing links specified in advance to obtain the processing tool assemblies corresponding to the processing link.
Further, the controlling the processing tool component to call the corresponding computing resource to process the corresponding processing link includes:
determining the processing sequence of each processing link corresponding to the virtual medicine to be generated according to the workflow file;
according to the processing sequence, controlling the corresponding processing tool components in sequence to call the corresponding computing resources through the computing resource calling interface module to process the corresponding processing links;
the computing resource calling interface module is respectively connected with a cloud computing server service interface and a super computing server service interface so as to call the cloud computing resources and the super computing resources.
Further, while the control module calls the corresponding computing resource to process the corresponding processing link, the method further includes:
and monitoring the load condition of the cloud computing server, controlling the processing tool assembly in current operation to call the super computing resource through the computing resource calling interface module to process the current processing link when the load is higher than a preset value, wherein the cloud computing server is used for providing cloud computing resources.
Further, the controlling the currently running processing tool component calls the super computing resource through the computing resource calling interface module to process the current processing link, including:
and acquiring the load condition of each computing operation occupying the cloud computing server in the current processing link, and controlling the processing tool assembly in current operation to sequentially call super computing resources for the corresponding computing operation through the computing resource calling interface module for computing according to the sequence from high to low of the load occupying the cloud computing server until the load of the cloud computing server is not higher than the preset value.
Further, the method further comprises:
determining processing links for virtual drug generation, and generating at least one visual component for each processing link; the visualization component is used for generating a workflow file corresponding to the virtual medicine to be generated according to the operation instruction.
Further, while controlling the processing tool component to call the corresponding computing resource to process the corresponding processing link, the method further includes:
after the processing of each processing link is finished, the processing conditions of the processing link are subjected to statistical analysis;
and acquiring an operation instruction input by a user according to the statistical analysis condition, and executing the operation instruction.
A virtual medication generation apparatus, comprising:
the workflow acquisition module is used for acquiring a workflow file corresponding to the virtual medicine to be generated;
the processing link determining module is used for determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file;
the processing tool determining module is used for determining at least one processing tool corresponding to each processing link from the software pool;
the processing tool componentization module is used for respectively componentizing the processing tools corresponding to each processing link to obtain processing tool components corresponding to each processing link;
the computing resource determining module is used for determining computing resources corresponding to each processing link, and the computing resources comprise cloud computing resources and super computing resources;
and the processing module is used for controlling the processing tool component to call the corresponding computing resources to process the corresponding processing links.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the virtual medication generation method when executing the computer program.
The invention has the following beneficial effects:
the method and the device can process the whole flow of the virtual medicine to be generated according to actual requirements, the processing mode of each processing link is more flexible, and the applicability and operability for virtual medicine generation are stronger. The invention utilizes the modularized software tool to process each processing link, can effectively reduce the time for software deployment and debugging of users, and improves the working efficiency. According to the invention, cloud computing resources and super computing resources are fused, and full computation can be performed on each processing link, so that the processing efficiency is improved, the processing period is shortened, and the time cost for generating virtual medicines is further reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flowchart of a method for generating a virtual drug according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a flow architecture for invoking computing resources through an API micro-service interface according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a virtual drug generation method according to an embodiment of the present invention;
FIG. 4 is a flow chart of another method for generating a virtual medication according to an embodiment of the present invention;
fig. 5 is a block diagram of a virtual medication device according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be noted that, in the case of no conflict, the features in the following embodiments and examples may be combined with each other; moreover, all other embodiments that can be derived by one of ordinary skill in the art from the embodiments disclosed herein without making any creative effort fall within the scope of the present disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the disclosure, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to or other than one or more of the aspects set forth herein.
The invention provides an embodiment of a virtual drug generation method, as shown in fig. 1, comprising:
s11: acquiring a workflow file corresponding to a virtual medicine to be generated; sources of the workflow file include: the method comprises the steps of inputting by a user, automatically generating according to the requirement of a virtual medicine to be generated, and obtaining by a network;
s12: determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file;
s13: determining at least one processing tool corresponding to each processing link from the software pool;
the software pool comprises software and a framework for virtual drug generation, such as alphafold, virtualflow, autodock, Gromacs and amber; according to the processing content of each processing link, some processing links only need one processing tool, and some processing links need a plurality of processing tools; when at least one processing tool corresponding to each processing link is determined from the software pool, the processing tool can be determined from the software pool by a user, and can also be determined from the software pool automatically according to the processing requirements; in the software pool, labels can be added to the processing tools according to the processing links which can be processed by the processing tools and are used for virtual drug generation, when a user determines the software tools from the software pool, the processing tools which can be selected in each processing link can be recommended to the user according to the labels, the user is prevented from not selecting, and the working efficiency is improved;
s14: performing componentization on the processing tool corresponding to each processing link to obtain a processing tool component corresponding to each processing link;
s15: determining computing resources corresponding to each processing link, wherein the computing resources comprise cloud computing resources and super computing resources;
the determining method of the computing resource corresponding to each processing link comprises the following steps: automatically determining according to the comparison table, and automatically determining by a user according to the calculated amount of each processing link; the comparison table comprises a comparison relation between each processing link for virtual drug generation and the corresponding computing resource; in the virtual drug generation process, some processing links can be completed by utilizing cloud computing resource processing, and some processing links can be completed by utilizing the powerful processing capacity of super computing, so that the computing resources corresponding to each processing link can be evaluated according to the calculated amount of each processing link, and a comparison table is generated so as to realize the automatic determination of the computing resources corresponding to each processing link;
s16: and controlling the processing tool component to call corresponding computing resources to process the corresponding processing links.
The embodiment shown in fig. 1 can process workflow files of various forms and various requirements, so as to meet the requirements of full-flow customized generation of virtual drugs, and meanwhile, the processing modes of the processing links corresponding to the virtual drugs to be generated are more flexible, and the applicability and operability are stronger. The cloud computing resources and the super computing resources are fused to process each processing link of virtual drug generation, each processing link can be fully calculated, the processing efficiency is improved, the processing period is shortened, and the time cost of virtual drug generation is further reduced.
Preferably, the method of this embodiment further includes:
and respectively packaging each processing tool in the software pool according to the preset input and output standard of each processing tool to obtain a primary assembly corresponding to each processing tool. The input/output standard of each processing tool is defined in a manner including: according to the execution sequence of each processing tool when used for virtual drug generation, the input standard of the corresponding processing tool is defined according to the output of the immediately preceding processing tool, and the output standard of the corresponding processing tool is defined according to the input request of the immediately following processing tool. After the processing tools are respectively packaged through the input and output standards of the processing tools specified in advance to obtain the corresponding primary assemblies, the connection of the processing links when the processing links corresponding to the virtual medicine to be generated are processed is facilitated, the miscalculation rate is effectively reduced, and the accuracy of the processing result is improved. The process of the preferred embodiment may be completed before the process starts, i.e., before the step S11, or before the step S14 after the process starts, and if the process is completed before the step S14 after the process starts, it is not necessary to package each processing tool in the software pool, and only the processing tools corresponding to each processing link corresponding to the virtual drug to be generated are respectively packaged to obtain the primary component of each processing tool to be used in the process.
Preferably, in this embodiment, the componentizing the processing tool corresponding to each processing link to obtain the processing tool component corresponding to each processing link includes:
determining the number of processing tools corresponding to each processing link, and if the number of the processing tools is 1, acquiring a primary assembly of the processing tool corresponding to the processing link as a processing tool assembly of the processing link; if the number of the processing tools is larger than 1, packaging the primary assemblies of the processing tools corresponding to the processing link according to the input and output standards of the processing links specified in advance to obtain the processing tool assemblies corresponding to the processing link. According to the processing content of each processing link, only one processing tool is needed in some processing links, multiple processing tools are needed in some processing links, and when a certain processing link needs multiple processing tools for processing, in order to further ensure the connectivity of each processing link corresponding to the virtual medicine to be generated, the accuracy of the processing result is further improved, and secondary packaging needs to be carried out on the primary component of each processing tool corresponding to the processing link. The input and output standard regulation mode of each processing link comprises the following steps: according to the processing sequence of each processing link in the virtual drug generation process, the input standard of the corresponding processing link is specified according to the output of the processing link before tightening, and the output standard of the corresponding processing link is specified according to the input requirement of the processing link after tightening.
The virtual drug generation involves many links and complex flow, wherein the involved processing tools are very many, each processing link corresponding to the virtual drug to be generated needs different processing tool supports, and a plurality of processing tool chains are involved according to different processing requirements. According to the preferred scheme, the processing tool is modularized through the preset input and output standard, so that the time for a user to deploy and debug software can be effectively shortened, and the working efficiency is improved.
Preferably, the controlling the processing tool component to call the corresponding computing resource to process the corresponding processing link includes:
determining the processing sequence of each processing link corresponding to the virtual medicine to be generated according to the workflow file;
according to the processing sequence, controlling the corresponding processing tool components in sequence to call the corresponding computing resources through the computing resource calling interface module to process the corresponding processing links;
the computing resource calling interface module is respectively connected with a cloud computing server service interface and a super computing server service interface so as to call the cloud computing resources and the super computing resources; the service interface includes: storage interface, calculation interface.
The computing resource calling interface module in the preferred scheme can be realized through an API micro-service interface. In a hardware environment, cloud computing resources and super computing resources are physically isolated, a computing resource calling interface module is respectively connected with a cloud computing server service interface and a super computing server service interface, and the cloud computing resources and the super computing resources are dynamically called according to the processing requirements of each processing link corresponding to the virtual medicine to be generated, so that the cloud computing resources and the super computing resources are fused, the computing resources are not wasted, and the resource utilization rate is improved. At the front end of a user, the computing resources can be abstracted into micro-services loaded by containers by using an API micro-service interface, so that the security and the robustness of the computing resource calling are improved, and no perception is generated at the user side. Accordingly, the present embodiment provides a flow architecture for invoking computing resources through an API microservice interface, as shown in fig. 2.
Preferably, the embodiment, while controlling the processing tool component to call the corresponding computing resource to process the corresponding processing link, further includes:
and monitoring the load condition of the cloud computing server, controlling the currently running processing tool assembly to call the super computing resources through the computing resource calling interface module to process the current processing link when the load is higher than a preset value, wherein the cloud computing server is used for providing cloud computing resources. The preset value can be set according to an actual operating environment, such as 80% of the utilization rate of a CPU of the cloud computing server.
Preferably, the controlling the currently running processing tool component to call the super computing resource through the computing resource call interface module to process the current processing link includes:
and acquiring the load condition of each computing operation occupying the cloud computing server in the current processing link, and controlling the processing tool assembly in current operation to sequentially call super computing resources for the corresponding computing operation through the computing resource calling interface module for computing according to the sequence from high to low of the load occupying the cloud computing server until the load of the cloud computing server is not higher than the preset value. For example, after the super computing resources are called to calculate the computing job a and the computing job B, the CPU utilization rate of the cloud computing server is recovered to be less than 80%, and at this time, the calling of the super computing resources is suspended, and other computing jobs such as the computing job C and the computing job D are still handled by the cloud computing resources. The optimal scheme can dynamically adjust and allocate cloud computing resources and super computing resources in real time, effectively improves computing performance, and is beneficial to shortening the computing period of virtual drug generation.
Preferably, the method of this embodiment further includes:
determining processing links for virtual drug generation, and generating at least one visual component for each processing link; the visualization component is used for generating a workflow file corresponding to the virtual medicine to be generated according to the operation instruction. The processing link for virtual drug generation comprises: protein structure prediction, virtual drug screening, lead compound optimization and pharmacodynamic analysis; the visualization component comprises the following forms: a chart, an icon with a processing link identifier; the operation instruction comprises the following steps: clicking, dragging and sequencing.
Taking virtual drug generation starting with target protein design as an example, a complete virtual drug generation process can be 'protein structure prediction- > virtual drug screening- > lead compound optimization- > pharmacodynamic analysis'. Through the preferred scheme, four links in the process are displayed in a visual component mode, the display mode can be charts, animations, labels and the like, and each link is a square with the link identification. A user can edit a workflow file corresponding to a virtual medicine to be generated by clicking and dragging a corresponding square block, arranging the sequence relation of each square block and the like in an interactive mode. The user can design a workflow file from the beginning of the first link of 'protein structure prediction' to the end of the last link of 'pharmacodynamic analysis', and can also edit the workflow file of a certain process independently, for example, the workflow file is edited to be circulated for a specified number of times according to 'virtual drug screening- > lead compound optimization- > pharmacodynamic analysis' so as to obtain an optimal result. The optimal scheme can further meet the full-process customization requirement of the user on the virtual medicine to be generated.
Preferably, the embodiment, while controlling the processing tool component to call the corresponding computing resource to process the corresponding processing link, further includes:
after the processing of each processing link is finished, the processing conditions of the processing link are subjected to statistical analysis; and acquiring an operation instruction input by a user according to the statistical analysis condition, and executing the operation instruction. The statistical analysis condition comprises: molecular structure, binding free energy ordering; the operation instruction comprises the following steps: continuing the calculation of the workflow, returning to the previous link, adjusting the workflow, reselecting a processing tool and finishing the calculation. For example, the virtual drug workflow file to be generated is cycled for a specified number of times according to "virtual drug screening- > lead compound optimization- > pharmacodynamic analysis", after the processing of the first "virtual drug screening" link is finished, the user considers that the workflow can be continuously executed through statistical analysis, the processing of the "lead compound optimization" link is performed, and so on. After the treatment is carried out according to the rule for a certain number of times in a circulating way, if the user finds that the treatment result of the latest step of 'pharmacodynamic analysis' is not good, the user needs to carry out 'lead compound optimization' again, and then the user selects to return to the previous step for retreatment. The optimal scheme can effectively improve the accuracy of generating the virtual medicine.
In practical application, in order to further improve user experience, the embodiment can further integrate management processes, including file management, task management, and the like, and is used for providing functions of a user for uploading and downloading, starting, pausing, ending, monitoring, and the like of workflow files and tasks corresponding to virtual drugs to be generated.
The method embodiment illustrated in fig. 1 can be divided into four parts from the aspect of architecture implementation, and comprises a user front end, a database, a software pool and an underlying computing resource. The bottom layer computing resources comprise cloud computing resources and super computing resources and are used for completing the full-process processing task of the virtual medicine to be generated; the software pool comprises software and a framework for generating virtual drugs, such as alphafold, virtualflow, autodock, gromas, amber; the database is integrated with a small molecule database required for generating virtual medicines, and the small molecule database can be an open source small molecule database and can also be added into a user private database to provide data storage in the virtual medicine generation process; the user front end serves as the top layer and is used for providing visual interactive services including workflow design, statistical analysis and the like. In order to connect the four parts of the user front end, the database, the software pool and the bottom layer computing resource in series, a uniform resource scheduling API can be set, and the computing resource, the storage resource, the software resource, the visual resource and other resources are scheduled uniformly and are used by each part. Accordingly, a schematic diagram of a virtual drug generation method is provided, as shown in fig. 3.
To further explain the present invention, in combination with the foregoing preferred embodiments, another embodiment of a virtual drug generation method is provided, as shown in fig. 4, including:
s41: acquiring an operation instruction of a user for triggering a visual component; the visual components correspond to processing links for virtual drug generation, and each processing link at least corresponds to one visual component, so that a user can multiplex a certain processing link according to processing requirements; the operation instruction comprises the following steps: clicking, dragging and sequencing;
s42: generating a workflow file corresponding to the virtual medicine to be generated according to the operation instruction;
s43: determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file;
s44: determining at least one processing tool corresponding to each processing link from the software pool;
s45: according to the preset input and output standard of each processing tool, packaging each processing tool determined from the software pool respectively to obtain a primary assembly of each processing tool; the input/output standard of each processing tool is defined in a manner including: according to the execution sequence of each processing tool when the processing tools are used for generating the virtual medicine, the input standard of the corresponding processing tool is regulated according to the output of the processing tool before the processing tool is processed, and the output standard of the corresponding processing tool is regulated according to the input requirement of the processing tool after the processing tool is processed;
s46: determining the number of processing tools corresponding to each processing link, and judging whether the number of the processing tools is greater than 1; if the number of processing tools is greater than 1, the process proceeds to S47, and if the number of processing tools is 1, the process proceeds to S48;
s47: according to the input and output standards of each processing link specified in advance, packaging the primary components of each processing tool corresponding to the processing link to obtain the processing tool components corresponding to the processing link, and entering S49; the input and output standard regulation mode of each processing link comprises the following steps: according to the processing sequence of each processing link in the virtual medicine generation process, the input standard of the corresponding processing link is specified according to the output of the processing link before tightening, and the output standard of the corresponding processing link is specified according to the input requirement of the processing link after tightening;
s48: acquiring a primary component of a processing tool corresponding to the processing link as a processing tool component of the processing link, and entering S49;
s49: determining the computing resources corresponding to each processing link according to the computing resource comparison table; the computing resources comprise cloud computing resources and super computing resources;
s410: determining the processing sequence of each processing link corresponding to the virtual medicine to be generated according to the workflow file;
s411: according to the processing sequence, controlling the corresponding processing tool components in sequence to call the corresponding computing resources through the computing resource calling interface module to process the corresponding processing links; the computing resource calling interface module is respectively connected with a cloud computing server service interface and a super computing server service interface so as to call the cloud computing resources and the super computing resources;
s412: monitoring the load condition of the cloud computing server, and acquiring the load condition of the cloud computing server occupied by each computing operation in the current processing link when the load is higher than a preset value; the cloud computing server is used for providing the cloud computing resources;
s413: controlling the currently running processing tool assembly to sequentially call super computing resources for corresponding computing operation through the computing resource calling interface for computing according to the sequence of the load occupying the cloud computing server from high to low until the load of the cloud computing server is not higher than the preset value;
s414: after the processing of each processing link is finished, the processing conditions of the processing link are subjected to statistical analysis;
s415: acquiring an operation instruction input by a user according to the statistical analysis condition, and executing the operation instruction; the operation instruction comprises the following steps: continuing the workflow calculation, returning to the previous link, adjusting the workflow, reselecting a processing tool and finishing the calculation;
s416: and finishing the generation of the virtual medicine when the workflow file is processed or the operation instruction for finishing the calculation is obtained, and outputting a corresponding result. According to the difference of the workflow files determined by the user, the content of the final output result is also different, and the content of the output result mainly depends on the last processing link contained in the workflow files, for example, if the last processing link contained in the workflow files is optimized for a lead compound, the final output result is a group of candidate lead compounds, and if the last processing link contained in the workflow files is pharmacodynamic analysis, the final output result is the pharmacodynamic analysis result of the generated group of virtual drugs.
The embodiment shown in fig. 3 can meet the requirement of a user for visually customizing the workflow file corresponding to the virtual medicine to be generated according to actual needs, and realizes the full-flow customized processing of virtual medicine generation. In each processing link, a user determines a processing tool in the software pool according to the processing requirement, so that the processing mode of each processing link corresponding to the virtual medicine to be generated is more flexible, and the applicability and the operability are stronger. The processing tool is modularized through the preset input and output standard, so that the time for a user to carry out software deployment and debugging can be effectively shortened, and the working efficiency is improved. And after each processing link is finished, returning the statistical analysis condition to the user, and determining the next execution strategy by the user according to the statistical analysis condition, so that the flexibility of user operation is improved, and the accuracy of generating the virtual medicine is further improved. Meanwhile, the cloud computing resources and the super computing resources are fused to process each processing link generated by the virtual medicine, and the cloud computing resources and the super computing resources can be dynamically called in real time according to the processing requirements of each processing link corresponding to the virtual medicine to be generated, so that the computing performance is effectively improved, the computing resources are not wasted, the resource utilization rate is improved, the processing period is further shortened, and the time cost for generating the virtual medicine is reduced.
The present invention also provides an embodiment of a virtual drug generation apparatus, as shown in fig. 5, including:
the workflow obtaining module 51 is configured to obtain a workflow file corresponding to a virtual medicine to be generated;
a processing link determining module 52, configured to determine, according to the workflow file, at least one processing link corresponding to the virtual drug to be generated;
a processing tool determining module 53, configured to determine at least one processing tool corresponding to each processing link from the software pool;
a processing tool componentization module 54, configured to componentize the processing tool corresponding to each processing link to obtain a processing tool component corresponding to each processing link;
a computing resource determining module 55, configured to determine a computing resource corresponding to each processing link, where the computing resource includes a cloud computing resource and a super computing resource;
and the processing module 56 is configured to control the processing tool component to call the corresponding computing resource to process the corresponding processing link.
Preferably, the apparatus of this embodiment further includes an initial componentization module, configured to respectively package each processing tool in the software pool according to a predefined input/output standard of each processing tool, so as to obtain a primary component corresponding to each processing tool.
Preferably, the componentizing the processing tool corresponding to each processing link to obtain the processing tool component corresponding to each processing link includes:
determining the number of processing tools corresponding to each processing link, and if the number of the processing tools is 1, acquiring a primary assembly of the processing tool corresponding to the processing link as a processing tool assembly of the processing link;
if the number of the processing tools is larger than 1, packaging the primary assemblies of the processing tools corresponding to the processing link according to the input and output standards of the processing links specified in advance to obtain the processing tool assemblies corresponding to the processing link.
Preferably, the controlling the processing tool component to call the corresponding computing resource to process the corresponding processing link thereof includes:
determining the processing sequence of each processing link corresponding to the virtual medicine to be generated according to the workflow file;
according to the processing sequence, controlling the corresponding processing tool components in sequence to call the corresponding computing resources through the computing resource calling interface module to process the corresponding processing links;
the computing resource calling interface module is respectively connected with a cloud computing server service interface and a super computing server service interface so as to call the cloud computing resources and the super computing resources.
Preferably, the apparatus of this embodiment further includes a computing resource calling module, configured to monitor a load condition of the cloud computing server when the processing module 56 is executed, and when the load is higher than a preset value, control a currently running processing tool component to call the super computing resource through the computing resource calling interface module to process a current processing link, where the cloud computing server is configured to provide cloud computing resources.
Preferably, the controlling the currently running processing tool component calls the super computing resource through the computing resource call interface module to process the current processing link, including:
and acquiring the load condition of each computing operation occupying the cloud computing server in the current processing link, and controlling the processing tool assembly in current operation to sequentially call super computing resources for the corresponding computing operation through the computing resource calling interface module for computing according to the sequence from high to low of the load occupying the cloud computing server until the load of the cloud computing server is not higher than the preset value.
Preferably, the apparatus of this embodiment further includes a visualization component generation module, configured to determine processing links for virtual drug generation, and generate at least one visualization component for each processing link; the visualization component is used for generating a workflow file corresponding to the virtual medicine to be generated according to the operation instruction.
Preferably, the apparatus of this embodiment further includes a statistical analysis module, configured to perform statistical analysis on the processing condition of each processing link after the processing of each processing link is finished when the processing module 56 executes; and acquiring an operation instruction input by a user according to the statistical analysis condition, and executing the operation instruction.
The apparatus of fig. 5 of the present invention is similar to the method of fig. 1 and 4 in part, and therefore the apparatus of fig. 5 is described in a simpler manner, and reference is made to the method of fig. 1 and 4 in corresponding parts.
The present invention further provides an embodiment of a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method described in the foregoing embodiment when executing the computer program, and the method may refer to the description of the embodiment described in fig. 1 and 4, and is not described herein again.
The method and the device can process the whole flow of the virtual medicine to be generated according to actual requirements, the processing mode of each processing link is more flexible, and the applicability and operability for virtual medicine generation are stronger. The invention utilizes the modularized software tool to process each processing link, can effectively reduce the time for software deployment and debugging of users, and improves the working efficiency. According to the invention, cloud computing resources and super computing resources are fused, and full computation can be performed on each processing link, so that the processing efficiency is improved, the processing period is shortened, and the time cost for generating virtual medicines is further reduced.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A virtual medication generation method, comprising:
acquiring a workflow file corresponding to a virtual medicine to be generated;
determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file;
determining at least one processing tool corresponding to each processing link from the software pool;
performing componentization on the processing tool corresponding to each processing link to obtain a processing tool component corresponding to each processing link;
determining computing resources corresponding to each processing link, wherein the computing resources comprise cloud computing resources and super computing resources;
and controlling the processing tool component to call corresponding computing resources to process the corresponding processing links.
2. The method of claim 1, further comprising:
and respectively packaging each processing tool in the software pool according to the preset input and output standard of each processing tool to obtain a primary assembly corresponding to each processing tool.
3. The method of claim 2, wherein the componentizing the processing tool corresponding to each processing link to obtain the processing tool component corresponding to each processing link comprises:
determining the number of processing tools corresponding to each processing link, and if the number of the processing tools is 1, acquiring a primary assembly of the processing tool corresponding to the processing link as a processing tool assembly of the processing link;
if the number of the processing tools is larger than 1, packaging the primary assemblies of the processing tools corresponding to the processing link according to the input and output standards of the processing links specified in advance to obtain the processing tool assemblies corresponding to the processing link.
4. The method of any of claims 1-3, wherein controlling the processing tool component to invoke the corresponding computing resource to process its corresponding processing link comprises:
determining the processing sequence of each processing link corresponding to the virtual medicine to be generated according to the workflow file;
according to the processing sequence, controlling the corresponding processing tool components in sequence to call the corresponding computing resources through the computing resource calling interface module to process the corresponding processing links;
the computing resource calling interface module is respectively connected with a cloud computing server service interface and a super computing server service interface so as to call the cloud computing resources and the super computing resources.
5. The method of claim 4, wherein while the controlling the processing tool component invokes the corresponding computing resource to process its corresponding processing link, the method further comprises:
and monitoring the load condition of the cloud computing server, controlling the currently running processing tool assembly to call the super computing resources through the computing resource calling interface module to process the current processing link when the load is higher than a preset value, wherein the cloud computing server is used for providing cloud computing resources.
6. The method of claim 5, wherein controlling the currently running processing tool component to call the super computing resource through the computing resource call interface module to process the current processing link comprises:
and acquiring the load condition of each computing operation occupying the cloud computing server in the current processing link, and controlling the processing tool assembly in current operation to sequentially call super computing resources for the corresponding computing operation through the computing resource calling interface module for computing according to the sequence from high to low of the load occupying the cloud computing server until the load of the cloud computing server is not higher than the preset value.
7. The method of claim 6, further comprising:
determining processing links for virtual drug generation, and generating at least one visual component for each processing link; the visualization component is used for generating a workflow file corresponding to the virtual medicine to be generated according to the operation instruction.
8. The method of claim 7, wherein while controlling the processing tool component to invoke the corresponding computing resource to process its corresponding processing link, the method further comprises:
after the processing of each processing link is finished, the processing conditions of the processing link are subjected to statistical analysis;
and acquiring an operation instruction input by a user according to the statistical analysis condition, and executing the operation instruction.
9. A virtual medication generating device, comprising:
the workflow acquisition module is used for acquiring a workflow file corresponding to the virtual medicine to be generated;
the processing link determining module is used for determining at least one processing link corresponding to the virtual medicine to be generated according to the workflow file;
the processing tool determining module is used for determining at least one processing tool corresponding to each processing link from the software pool;
the processing tool componentization module is used for respectively componentizing the processing tools corresponding to each processing link to obtain processing tool components corresponding to each processing link;
the computing resource determining module is used for determining computing resources corresponding to each processing link, and the computing resources comprise cloud computing resources and super computing resources;
and the processing module is used for controlling the processing tool component to call the corresponding computing resources to process the corresponding processing links.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the virtual medication generation method of any of claims 1 to 8 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210359239.2A CN114464269B (en) | 2022-04-07 | 2022-04-07 | Virtual medicine generation method and device and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210359239.2A CN114464269B (en) | 2022-04-07 | 2022-04-07 | Virtual medicine generation method and device and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114464269A true CN114464269A (en) | 2022-05-10 |
CN114464269B CN114464269B (en) | 2022-07-08 |
Family
ID=81418220
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210359239.2A Active CN114464269B (en) | 2022-04-07 | 2022-04-07 | Virtual medicine generation method and device and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114464269B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024063585A1 (en) * | 2022-09-21 | 2024-03-28 | (주)신테카바이오 | Cloud platform system and service method capable of distributed and parallel processing for large-scale workflows |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102375731A (en) * | 2010-08-23 | 2012-03-14 | 融建信息技术(厦门)有限公司 | Coding-free integrated application platform system |
CN105183554A (en) * | 2015-07-31 | 2015-12-23 | 国家超级计算深圳中心(深圳云计算中心) | Hybrid computing system of high-performance computing and cloud computing, and resource management method therefor |
CN105404542A (en) * | 2015-08-14 | 2016-03-16 | 国家超级计算深圳中心(深圳云计算中心) | Cloud computing system and method for running high-performance computation in same |
CN106020969A (en) * | 2016-05-05 | 2016-10-12 | 云神科技投资股份有限公司 | High-performance cloud computing hybrid computing system and method |
CN111180020A (en) * | 2019-12-20 | 2020-05-19 | 深圳晶泰科技有限公司 | Data management system in drug research and development process and use method thereof |
CN112076391A (en) * | 2020-09-04 | 2020-12-15 | 深圳市威浩康医疗器械有限公司 | Operation method of traditional Chinese and western medicine anesthesia auxiliary control system, electronic device and storage medium |
CN112102904A (en) * | 2019-06-18 | 2020-12-18 | 杭州中软安人网络通信股份有限公司 | Traditional Chinese medicine big data cloud service system |
CN112116963A (en) * | 2020-09-24 | 2020-12-22 | 深圳智药信息科技有限公司 | Automated drug design method, system, computing device and computer-readable storage medium |
CN112201301A (en) * | 2020-10-23 | 2021-01-08 | 深圳晶泰科技有限公司 | Virtual reality-based drug design cloud computing flow control system and method thereof |
CN113096726A (en) * | 2016-02-03 | 2021-07-09 | 维里纳塔健康公司 | Use of cell-free DNA fragment size to determine copy number variation |
CN113254201A (en) * | 2021-05-17 | 2021-08-13 | 清华大学 | Supercomputing cloud computing platformization management method and management platform |
CN113254382A (en) * | 2021-07-09 | 2021-08-13 | 国家超级计算天津中心 | Data processing system for constructing digital numerical value fusion device based on supercomputer |
US20210265022A1 (en) * | 2018-05-09 | 2021-08-26 | Shenzhen Jingtai Technology Co., Ltd. | Drug crystal structure landscape analysis system and landscape analysis method thereof |
CN113741862A (en) * | 2020-08-31 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Communication system and method for mobile terminal expansion development |
CN113744867A (en) * | 2021-08-30 | 2021-12-03 | 平安科技(深圳)有限公司 | Drug recommendation evidence-based support method, device, equipment and storage medium |
CN114064923A (en) * | 2021-11-18 | 2022-02-18 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
CN114186266A (en) * | 2022-02-16 | 2022-03-15 | 国家超级计算天津中心 | Big data security and privacy computing control method in super computing and cloud computing environment |
-
2022
- 2022-04-07 CN CN202210359239.2A patent/CN114464269B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102375731A (en) * | 2010-08-23 | 2012-03-14 | 融建信息技术(厦门)有限公司 | Coding-free integrated application platform system |
CN105183554A (en) * | 2015-07-31 | 2015-12-23 | 国家超级计算深圳中心(深圳云计算中心) | Hybrid computing system of high-performance computing and cloud computing, and resource management method therefor |
CN105404542A (en) * | 2015-08-14 | 2016-03-16 | 国家超级计算深圳中心(深圳云计算中心) | Cloud computing system and method for running high-performance computation in same |
CN113096726A (en) * | 2016-02-03 | 2021-07-09 | 维里纳塔健康公司 | Use of cell-free DNA fragment size to determine copy number variation |
CN106020969A (en) * | 2016-05-05 | 2016-10-12 | 云神科技投资股份有限公司 | High-performance cloud computing hybrid computing system and method |
US20210265022A1 (en) * | 2018-05-09 | 2021-08-26 | Shenzhen Jingtai Technology Co., Ltd. | Drug crystal structure landscape analysis system and landscape analysis method thereof |
CN112102904A (en) * | 2019-06-18 | 2020-12-18 | 杭州中软安人网络通信股份有限公司 | Traditional Chinese medicine big data cloud service system |
CN111180020A (en) * | 2019-12-20 | 2020-05-19 | 深圳晶泰科技有限公司 | Data management system in drug research and development process and use method thereof |
CN113741862A (en) * | 2020-08-31 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Communication system and method for mobile terminal expansion development |
CN112076391A (en) * | 2020-09-04 | 2020-12-15 | 深圳市威浩康医疗器械有限公司 | Operation method of traditional Chinese and western medicine anesthesia auxiliary control system, electronic device and storage medium |
CN112116963A (en) * | 2020-09-24 | 2020-12-22 | 深圳智药信息科技有限公司 | Automated drug design method, system, computing device and computer-readable storage medium |
CN112201301A (en) * | 2020-10-23 | 2021-01-08 | 深圳晶泰科技有限公司 | Virtual reality-based drug design cloud computing flow control system and method thereof |
CN113254201A (en) * | 2021-05-17 | 2021-08-13 | 清华大学 | Supercomputing cloud computing platformization management method and management platform |
CN113254382A (en) * | 2021-07-09 | 2021-08-13 | 国家超级计算天津中心 | Data processing system for constructing digital numerical value fusion device based on supercomputer |
CN113744867A (en) * | 2021-08-30 | 2021-12-03 | 平安科技(深圳)有限公司 | Drug recommendation evidence-based support method, device, equipment and storage medium |
CN114064923A (en) * | 2021-11-18 | 2022-02-18 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
CN114186266A (en) * | 2022-02-16 | 2022-03-15 | 国家超级计算天津中心 | Big data security and privacy computing control method in super computing and cloud computing environment |
Non-Patent Citations (1)
Title |
---|
张宝花等: "超大规模药物虚拟筛选的实现与应用", 《计算机科学与探索》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024063585A1 (en) * | 2022-09-21 | 2024-03-28 | (주)신테카바이오 | Cloud platform system and service method capable of distributed and parallel processing for large-scale workflows |
Also Published As
Publication number | Publication date |
---|---|
CN114464269B (en) | 2022-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106775632B (en) | High-performance geographic information processing method and system with flexibly-expandable business process | |
Dastgeer et al. | Auto-tuning SkePU: a multi-backend skeleton programming framework for multi-GPU systems | |
US10007495B2 (en) | Code generation method for scheduling processors using hook function and exception handling function | |
CN108984171B (en) | Continuous scene construction method based on Unity3D and storage medium | |
CN102521024B (en) | Job scheduling method based on bioinformation cloud platform | |
CN110427258B (en) | Resource scheduling control method and device based on cloud platform | |
CN1744038A (en) | Member assembling method based on united member package structure | |
CN114464269B (en) | Virtual medicine generation method and device and computer equipment | |
CN110515620B (en) | Automatic resource processing method and system | |
CN108664314A (en) | Big data process flow module management method and device | |
CN111459621B (en) | Cloud simulation integration and scheduling method and device, computer equipment and storage medium | |
CN105094984A (en) | Resource scheduling method and system | |
CN112559156A (en) | Multi-dependency task grouping management method, device, equipment and storage medium | |
CN111475137A (en) | Method, system and equipment for predicting software development requirements | |
Wu et al. | A distributed workflow management system with case study of real-life scientific applications on grids | |
CN105933136A (en) | Resource scheduling method and system | |
Ernst et al. | A task framework for the web interface W2H | |
Thavappiragasam et al. | Performance portability of molecular docking miniapp on leadership computing platforms | |
US6934947B1 (en) | Visual tool for developing real time task management code | |
US20230214252A1 (en) | System and method of path execution optimization | |
CN110928672B (en) | Task arranging method, device and equipment and storage medium | |
CN103543986B (en) | The implementation method and device of the calculating task of CFX | |
CN114356550A (en) | Three-level parallel middleware-oriented automatic computing resource allocation method and system | |
Minotti et al. | Developing web client applications with JaCa-Web. | |
CN113992941B (en) | Cloud edge collaborative video analysis system and method based on server-free function computing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |