CN103207947A - Method for predicting activity of angiotensin converting enzyme inhibitor - Google Patents
Method for predicting activity of angiotensin converting enzyme inhibitor Download PDFInfo
- Publication number
- CN103207947A CN103207947A CN2013101095362A CN201310109536A CN103207947A CN 103207947 A CN103207947 A CN 103207947A CN 2013101095362 A CN2013101095362 A CN 2013101095362A CN 201310109536 A CN201310109536 A CN 201310109536A CN 103207947 A CN103207947 A CN 103207947A
- Authority
- CN
- China
- Prior art keywords
- amino acid
- converting enzyme
- chemical parameters
- quantum chemical
- angiotensin converting
- 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.)
- Pending
Links
Images
Abstract
A method for predicting activity of an angiotensin converting enzyme inhibitor comprises the steps of selecting quantum chemistry parameters of natural amino acids, obtaining 19 principal components by principal component analysis, enabling the principal components to serve as principal component amino acid quantization parameters for describing every amino acid, utilizing amino acid quantum chemistry parameter scores to perform representation on an amino acid sequence of the angiotensin converting enzyme inhibitor, enabling medicine activity of the angiotensin converting enzyme inhibitor to serve as to a dependent variable for establishing a model, utilizing a step-by-step linear regression method to perform variable selection, finding out amino acid quantum chemistry parameter components remarkably associated with the dependent variable, utilizing step-by-step linear regression to process all the quantum chemistry parameter components of the amino acids obtained in every step, sequentially utilizing a method of partial least squares to construct medicine activity models of the angiotensin converting enzyme inhibitor according to an importance sequence of all the quantum chemistry parameter components, and adopting a leave-one-out method to perform cross check and external validation on predicating capability of the evaluation models. The method for predicting the activity of the angiotensin converting enzyme inhibitor has the advantages of being simple to operate and uniform in form and enabling data to be obtained easily and the like.
Description
Technical field
The present invention relates to the D-M (Determiner-Measure) construction-character/active technical field of peptide, particularly a kind of method of predicting the angiotensin-converting enzyme inhibitor activity.
Background technology
(Angiotensin-converting enzyme, ACE) inhibitor is a kind of compound that suppresses hypertensin conversion enzyme activity to angiotensin converting enzyme.(rennin-angiotensin system RAS) plays key effect to the plain – hypertensin system of kidney in regulating human blood-pressure.The proangiotensin that is produced by liver is fractured into nonactive decapeptide angiotensin I through feritin catalysis, passing through angiotensin converting enzyme (ACE) catalytic pyrolysis again is the octapeptide Angiotensin II with extremely strong vessel retraction function, so ACE just becomes the action target spot of blood-pressure drug research.The ACE inhibitor suppresses the effective biologically active purpose of ACE (J.Chem.Soc.Perkin Trans.I.1984,23:155 – 162) by simulation ACE substrate angiotensin I activity part structure feature thereby reach competition.Therefore the ACE inhibitor also becomes disease medicament precursors such as treatment hypertension, heart disease, diabetes and ephrosis.The peptides that the ACE inhibitor generally is made up of amino acid residue, yet to the research and development of peptide medicament and the discovery of lead compound, so far be still costly but a job that efficient is very low, therefore, press for the new theoretical method of development and peptide quasi-molecule designing technique and instruct the peptide medicament exploitation.In recent years, be the design of based computer accessory molecule with various theoretical calculation methods and Molecular Simulation Technique, in the research and development of peptides, be used widely.Carry out conformational analysis with computing machine molecular modeling, molecular dynamics and quantum chemistry etc., seek the pharmacophore of polypeptide and analog, carry out QSAR research, the design that ins all sorts of ways has peptide class and the non-peptide mimics of greater activity, has become in the world very active research field.But, in the QSAR of peptide medicament research, on the one hand, because the relative complexity of peptide matters structure and high flexibility, make its parameter based on whole peptide molecule be difficult to determine that on the other hand, the functional characteristic of peptide relates to factors such as amino acid position in the sequence, formation and physicochemical property thereof, so cause the QSAR research of peptide also not have comparatively ripe methodology guidance at present, among the whole bag of tricks and technology all also are in and constantly attempt and develop.
Summary of the invention
In order to overcome the shortcoming of above-mentioned prior art, the purpose of this invention is to provide a kind of method of predicting the angiotensin-converting enzyme inhibitor activity, have simple to operate, unity of form, data and characteristics such as obtain easily.
In order to achieve the above object, the present invention solves by the following technical programs:
A kind of method of predicting the angiotensin-converting enzyme inhibitor activity may further comprise the steps:
1) choose 2236 Quantum chemical parameters of 20 kinds of natural amino acids, 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids specifically comprise: highest occupied molecular orbital energy, minimum track energy, energy gap, overall flex, the highest minimum orbital energy that occupies of occupying are than, the final frontier electron density of heat, gross energy, internuclear repulsion, ionization potential, electronic characteristic value (EEVA) descriptor, close electric atom, the frontier electron density of nucleophilic atom, total close electric superdelocalizability, average close electric superdelocalizability, total nucleophilic superdeloca lizability, the average nucleophilic superdeloca lizability of generating;
2) utilize SPSS13.0 software to do principal component analysis (PCA) to 2236 Quantum chemical parameters of 20 kinds of natural amino acids, obtain 19 major components, as shown in table 1,
Table 1 is 19 major components of 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids
a20 kinds of natural amino acids represent with conventional single English alphabet,
3) 19 major components are quantized parameter as describing each amino acid whose 19 major component amino acid, be called amino acid quantum chemical parameters score;
4) with 19 amino acid quantum chemical parameters scores angiotensin converting enzyme (ACE) inhibitor amino acid sequence is characterized, wherein each amino acid residue characterizes with 19 amino acid quantum chemical parameters scores, and with the independent variable of characterization result as active forecast model;
5) with the pharmaceutically active value of angiotensin converting enzyme (ACE) inhibitor as the dependent variable of setting up model, carry out the variable screening with progressively linear regression (SMR) method, find out the amino acid quantum chemical parameters score with the dependent variable significant correlation, be specially: the level of signifiance value P with inclined to one side F test value correspondence is foundation: when the maximum level of signifiance value P of F test value partially in candidate's variable≤0.99, then introduce this amino acid quantum chemical parameters score and carry out modeling; In the variable of introducing equation, if its minimum level of signifiance value P of F test value partially 〉=1.00 o'clock, then remove this amino acid quantum chemical parameters score and carry out modeling;
6) all the Quantum chemical parameters scores of amino acid that per step of progressively linear regression (SMR) obtained, according to its sequence of importance, use offset minimum binary (PLS) method to make up the pharmaceutically active model of angiotensin converting enzyme (ACE) inhibitor successively, and adopt the predictive ability of leaving-one method crosscheck and external inspection evaluation model.
The invention has the beneficial effects as follows:
A new amino acid descriptor of the present invention---amino acid quantum chemical parameters score can obtain parameter by the pharmaceutically active model of angiotensin converting enzyme (ACE) inhibitor activity that makes up, and is used for the activity of prediction angiotensin converting enzyme (ACE) inhibitor.Characteristics such as that this method has is simple to operate, unity of form, data are obtained easily are expected to become valuable structure characterization methods in the forecasting research of angiotensin converting enzyme (ACE) inhibitor activity.
Description of drawings
Fig. 1 is the predicted value of 58 ACE inhibitor dipeptides activity and the correlation scatter diagram of experiment value.
Fig. 2 is the predicted value of 55 ACE inhibitor tripeptide actives and the correlation scatter diagram of experiment value.
Embodiment
Below in conjunction with drawings and Examples the present invention is described in detail.
A kind of method of predicting the angiotensin-converting enzyme inhibitor activity may further comprise the steps:
1) choose 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids, 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids specifically comprise: highest occupied molecular orbital energy, minimum track energy, energy gap, overall flex, the highest minimum orbital energy that occupies of occupying are than, the final frontier electron density of heat, gross energy, internuclear repulsion, ionization potential, electronic characteristic value (EEVA) descriptor, close electric atom, the frontier electron density of nucleophilic atom, total close electric superdelocalizability, average close electric superdelocalizability, total nucleophilic superdeloca lizability, the average nucleophilic superdeloca lizability of generating;
2) utilize SPSS13.0 software to do principal component analysis (PCA) to 2236 Quantum chemical parameters of 20 kinds of natural amino acids, obtain 19 major components, as shown in table 1,
Table 1 is 19 major components of 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids
a20 kinds of natural amino acids represent with conventional single English alphabet,
3) 19 major components are quantized parameter as describing each amino acid whose 19 major component amino acid, be called amino acid quantum chemical parameters score, these 19 scores combine the full detail of 2236 kinds of quantization parameters substantially, therefore, can use it for the structural characterization of peptide;
4) with 19 amino acid quantum chemical parameters scores angiotensin converting enzyme (ACE) inhibitor amino acid sequence is characterized, wherein each amino acid residue characterizes with 19 amino acid quantum chemical parameters scores, and with the independent variable of characterization result as active forecast model;
5) with the pharmaceutically active value of angiotensin converting enzyme (ACE) inhibitor as the dependent variable of setting up model, with the screening of progressively linear regression (SMR) method and the closely-related parameter of angiotensin converting enzyme (ACE) inhibitor structure, find out the Quantum chemical parameters score with the dependent variable significant correlation;
Carry out the variable screening with regression technique (SMR) progressively, introduce variable successively by Fischer significance test, level of signifiance value P with inclined to one side F test value correspondence is foundation: when the maximum level of signifiance value P of F test value partially in candidate's variable≤0.99, then introduce this variable; In the variable of introducing equation, if its minimum level of signifiance value P of F test value partially 〉=1.00 o'clock, then reject this variable;
6) all the Quantum chemical parameters scores of amino acid that per step of progressively linear regression (SMR) obtained, according to its sequence of importance, use offset minimum binary (PLS) method to make up the pharmaceutically active model of angiotensin converting enzyme (ACE) inhibitor successively, and adopt the predictive ability of leaving-one method crosscheck and external inspection evaluation model.
Biologically active value pIC with angiotensin converting enzyme (ACE) inhibitor
50(log(1/IC
50)) for the dependent variable of prediction angiotensin converting enzyme (ACE) inhibitor activity model, in conjunction with progressively linear regression (SMR) modeling, come the predictive ability of evaluation model with offset minimum binary (PLS) with the accumulation multiple correlation coefficient of leaving-one method crosscheck; Then, further come the predictive ability of verification model by the method for external certificate, sample is divided into training set and external certificate test set, wherein the ratio of training set sample and test set sample is 4:1, training set is used for modeling, then with the activity of the model prediction test set sample of building up.
Be that amino acid quantum chemical parameters score is for the application example of ACE inhibitor activity prediction below
Below the Quantum chemical parameters score is characterized 58 angiotensin converting enzyme (ACE) inhibitor dipeptides and two kinds of peptide class formations of 55 angiotensin converting enzyme (ACE) inhibitor tripeptides respectively, adopt progressively linear regression in conjunction with the offset minimum binary modeling, thereby checking Quantum chemical parameters score is in the validity of angiotensin converting enzyme (ACE) inhibitor activity forecasting research.
1) prediction of angiotensin converting enzyme (ACE) inhibitor dipeptides activity
Selected 58 angiotensin converting enzyme (ACE) inhibitor dipeptides derives from (Angiotensin converting enzyme inhibitors such as Cushman, 1981, pp.3 – 25), each angiotensin converting enzyme (ACE) inhibitor dipeptides can characterize with 19 * 2 amino acid quantum chemical parameters scores, adopt SMR-PLS to select variable, with model crosscheck multiple correlation coefficient (Q
LOO 2) the descriptor number is set up final PLS model when reaching maximum.When introducing 12 amino acid quantum chemical parameters score (v
20, v
2, v
27, v
3, v
28, v
22, v
24, v
4, v
12, v
19, v
25, v
26) time, gained PLS model is explained Y variable 93.8% variance with 1 remarkable major component, and crosscheck (CV) the Y variable variance of explaining is 91.0%, and root-mean-square error (RMSE) is 0.352.Fig. 1 provides 58 angiotensin converting enzyme (ACE) inhibitor, two peptide biological activity calculated values and experimental observation value correlation circumstance, and all samples all were dispersed near 45 ° of straight lines of initial point as can be seen from Figure 1, the Non Apparent Abnormality point.In order further to check the predictive ability of amino acid quantum chemical parameters score modeling, 58 angiotensin converting enzyme (ACE) inhibitor dipeptides is divided into training set and test set two parts at random, wherein 43 samples are as training set, remaining 15 as test set.The choosing method of test set is chosen one then at first 58 angiotensin converting enzyme (ACE) inhibitor dipeptides being sorted from small to large by its activity from per four samples.Multiple correlation coefficient (the R of training set institute established model
Cum 2) and crosscheck multiple correlation coefficient (Q
LOO 2) be respectively 0.915,0.831, external samples verification multiple correlation coefficient (Q
Ext 2) be 0.767.
2) prediction of angiotensin converting enzyme (ACE) inhibitor tripeptide active
Selected 55 angiotensin converting enzyme (ACE) inhibitor tripeptides from Wu etc. (J Agric Food Chem.2006,54:732-738).At first use amino acid quantum chemical parameters score that 55 angiotensin converting enzyme (ACE) inhibitor tripeptides structure is characterized, common property is given birth to 19 * 3 descriptor variablees, and modeling method is the same.At first progressively screen modeling behind the variable with 55 sample sets, in the variable screening process, when introducing 13 amino acid quantum chemical parameters score (v
55, v
52, v
19, v
43, v
3, v
20, v
5, v
24, v
44, v
7, v
22, v
42, v
16) time, gained offset minimum binary (PLS) model is explained Y variable 99.4% variance with 2 remarkable major components, and crosscheck (CV) the Y variable variance of explaining is 97.9%, and RMSE is 0.074.Fig. 2 provides 55 angiotensin converting enzyme (ACE) inhibitor, three peptide biological activities and calculates and the observed reading correlation circumstance, can find out that most of sample all was dispersed near 45 ° of straight lines of initial point the Non Apparent Abnormality point.In order further to verify the predictive ability of amino acid quantum chemical parameters score modeling, we adopt identical method that 55 angiotensin converting enzyme (ACE) inhibitor tripeptides is divided into 41 training set samples and 14 test set samples at random.Multiple correlation coefficient (the R of training set institute established model
Cum 2) and crosscheck multiple correlation coefficient (Q
LOO 2) be respectively 0.984,0.944, external samples verification multiple correlation coefficient (Q
Ext 2)
Be 0.846.The result shows that the predictive ability of amino acid quantum chemical parameters score modeling is stronger.
The above, it only is preferred embodiment of the present invention, be not that the present invention is done any pro forma restriction, every foundation technical spirit of the present invention all still belongs in the scope of technical solution of the present invention any simple modification, equivalent variations and modification that above embodiment does.
Claims (1)
1. a method of predicting the angiotensin-converting enzyme inhibitor activity is characterized in that, may further comprise the steps:
1) choose 2236 Quantum chemical parameters of 20 kinds of natural amino acids, 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids specifically comprise: highest occupied molecular orbital energy, minimum track energy, energy gap, overall flex, the highest minimum orbital energy that occupies of occupying are than, the final frontier electron density of heat, gross energy, internuclear repulsion, ionization potential, electronic characteristic value (EEVA) descriptor, close electric atom, the frontier electron density of nucleophilic atom, total close electric superdelocalizability, average close electric superdelocalizability, total nucleophilic superdeloca lizability, the average nucleophilic superdeloca lizability of generating;
2) utilize SPSS13.0 software to do principal component analysis (PCA) to 2236 Quantum chemical parameters of 20 kinds of natural amino acids, obtain 19 major components, as shown in table 1,
Table 1 is 19 major components of 2236 kinds of Quantum chemical parameters of 20 kinds of natural amino acids
a20 kinds of natural amino acids represent with conventional single English alphabet,
3) 19 major components are quantized parameter as describing each amino acid whose 19 major component amino acid, be called amino acid quantum chemical parameters score;
4) with 19 amino acid quantum chemical parameters scores angiotensin converting enzyme (ACE) inhibitor amino acid sequence is characterized, wherein each amino acid residue characterizes with 19 amino acid quantum chemical parameters scores, and with the independent variable of characterization result as active forecast model;
5) with the pharmaceutically active value of angiotensin converting enzyme (ACE) inhibitor as the dependent variable of setting up model, carry out the variable screening with progressively linear regression (SMR) method, find out the amino acid quantum chemical parameters score with the dependent variable significant correlation, be specially: the level of signifiance value P with inclined to one side F test value correspondence is foundation: when the maximum level of signifiance value P of F test value partially in candidate's variable≤0.99, then introduce this amino acid quantum chemical parameters score and carry out modeling; In the variable of introducing equation, if its minimum level of signifiance value P of F test value partially 〉=1.00 o'clock, then remove this amino acid quantum chemical parameters score and carry out modeling;
6) all the Quantum chemical parameters scores of amino acid that per step of progressively linear regression (SMR) obtained, according to its sequence of importance, use offset minimum binary (PLS) method to make up the pharmaceutically active model of angiotensin converting enzyme (ACE) inhibitor successively, and adopt the predictive ability of leaving-one method crosscheck and external inspection evaluation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101095362A CN103207947A (en) | 2013-03-29 | 2013-03-29 | Method for predicting activity of angiotensin converting enzyme inhibitor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101095362A CN103207947A (en) | 2013-03-29 | 2013-03-29 | Method for predicting activity of angiotensin converting enzyme inhibitor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103207947A true CN103207947A (en) | 2013-07-17 |
Family
ID=48755166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101095362A Pending CN103207947A (en) | 2013-03-29 | 2013-03-29 | Method for predicting activity of angiotensin converting enzyme inhibitor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103207947A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678951A (en) * | 2013-12-11 | 2014-03-26 | 陕西科技大学 | Prediction for activity of medicine against Aids through molecule surface random sampling analytical method |
| CN106124659A (en) * | 2016-06-23 | 2016-11-16 | 井冈山大学 | The method of prediction sulfa antibiotics rate of photocatalytic oxidation |
| CN108763863A (en) * | 2018-05-30 | 2018-11-06 | 西北民族大学 | The quantitative structure activity relationship model of ace inhibitory peptide and its application |
| CN114496112A (en) * | 2022-01-21 | 2022-05-13 | 内蒙古工业大学 | Multi-objective optimization-based breast cancer resistant drug component intelligent quantification method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2486431A1 (en) * | 2002-05-20 | 2003-12-04 | Rosetta Inpharmatics Llc | Computer systems and methods for subdividing a complex disease into component diseases |
| CN102323973A (en) * | 2011-05-31 | 2012-01-18 | 陕西科技大学 | Method for predicting common environment poison property/activity on the basis of intelligent correlation index |
| CN102663271A (en) * | 2012-05-08 | 2012-09-12 | 重庆理工大学 | Method for representing activity relationships of antibacterial proteins or polypeptides |
-
2013
- 2013-03-29 CN CN2013101095362A patent/CN103207947A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2486431A1 (en) * | 2002-05-20 | 2003-12-04 | Rosetta Inpharmatics Llc | Computer systems and methods for subdividing a complex disease into component diseases |
| CN102323973A (en) * | 2011-05-31 | 2012-01-18 | 陕西科技大学 | Method for predicting common environment poison property/activity on the basis of intelligent correlation index |
| CN102663271A (en) * | 2012-05-08 | 2012-09-12 | 重庆理工大学 | Method for representing activity relationships of antibacterial proteins or polypeptides |
Non-Patent Citations (7)
| Title |
|---|
| AKINORI KIDERA,ET AL.,: "Statistical analysis of the physical properties of the 20 naturally occurring amino acids", 《JOURNAL OF PROTEIN CHEMISTRY 》, vol. 4, no. 1, 31 December 1985 (1985-12-31), pages 23 - 55 * |
| TONG J,ET AL.,: "A novel descriptor of amino acids and its application in peptide QSAR", 《JOURNAL OF THEORETICAL BIOLOGY》, vol. 253, no. 1, 31 December 2008 (2008-12-31), pages 90 - 97, XP022717478, DOI: doi:10.1016/j.jtbi.2008.02.030 * |
| 仝建波等: "一种新三维氨基酸描述子SVTD及在肽QSAR的应用", 《分析科学学报》, vol. 24, no. 5, 20 October 2008 (2008-10-20), pages 522 - 526 * |
| 仝建波等: "一种新的三维氨基酸描述子及其在肽类药物QSAR中的应用", 《物理化学学报》, vol. 23, no. 1, 15 January 2007 (2007-01-15), pages 37 - 43 * |
| 仝建波等: "三维氨基酸结构描述子矢量SVRDF及其在肽QSAR中的应用", 《药学学报》, vol. 42, no. 1, 12 January 2007 (2007-01-12), pages 40 - 46 * |
| 仝建波等: "氨基酸描述子SVG及其在肽序列QSAR中的应用", 《精细化工》, vol. 25, no. 7, 31 July 2008 (2008-07-31), pages 654 - 659 * |
| 车挺: "新型氨基酸描述子及其在肽QSAR中的应用", 《中国优秀硕士学位论文全文数据库基础科学辑（月刊 ）》, no. 9, 15 September 2012 (2012-09-15), pages 006 - 22 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678951A (en) * | 2013-12-11 | 2014-03-26 | 陕西科技大学 | Prediction for activity of medicine against Aids through molecule surface random sampling analytical method |
| CN106124659A (en) * | 2016-06-23 | 2016-11-16 | 井冈山大学 | The method of prediction sulfa antibiotics rate of photocatalytic oxidation |
| CN108763863A (en) * | 2018-05-30 | 2018-11-06 | 西北民族大学 | The quantitative structure activity relationship model of ace inhibitory peptide and its application |
| CN114496112A (en) * | 2022-01-21 | 2022-05-13 | 内蒙古工业大学 | Multi-objective optimization-based breast cancer resistant drug component intelligent quantification method |
| CN114496112B (en) * | 2022-01-21 | 2023-10-31 | 内蒙古工业大学 | Intelligent quantification method for anti-breast cancer drug ingredients based on multi-objective optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Barash et al. | Modeling dependencies in protein-DNA binding sites | |
| Xu et al. | PDC-SGB: Prediction of effective drug combinations using a stochastic gradient boosting algorithm | |
| CN103093108B (en) | A kind of Chinese medicine system Pharmacological Analysis platform and the method for analysis | |
| Frimurer et al. | A physicogenetic method to assign ligand-binding relationships between 7TM receptors | |
| CN103207947A (en) | Method for predicting activity of angiotensin converting enzyme inhibitor | |
| Moretti et al. | The class of microarray games and the relevance index for genes | |
| Yang et al. | Knowledge-based analysis for detecting key signaling events from time-series phosphoproteomics data | |
| Vert et al. | Extracting active pathways from gene expression data | |
| Matter et al. | Development of in silico filters to predict activation of the pregnane X receptor (PXR) by structurally diverse drug-like molecules | |
| US20230402130A1 (en) | Method, device, and computer program for predicting interaction between compound and protein | |
| CN104978474B (en) | A kind of method of evaluating drug effect and system based on molecular network | |
| Hopfinger et al. | Extraction of pharmacophore information from high-throughput screens | |
| Sheehy et al. | Time-warped comparison of gene expression in adaptive and maladaptive cardiac hypertrophy | |
| CN102509029A (en) | Affinity prediction and analysis method for human amphiphysin-1 Src homology-3 domain binding peptide | |
| Pappalardo et al. | Sequential application of ligand and structure based modeling approaches to index chemicals for their hH4R antagonism | |
| Stork et al. | Computational prediction of frequent hitters in target-based and cell-based assays | |
| Netzer et al. | A network-based feature selection approach to identify metabolic signatures in disease | |
| Kumar | PLHINT: A knowledge-driven computational approach based on the intermolecular H bond interactions at the protein-ligand interface from docking solutions | |
| Yu et al. | Machine learning approaches to investigate the structure–activity relationship of angiotensin-converting enzyme inhibitors | |
| JP6884389B2 (en) | Analytical equipment, analysis methods and programs | |
| Gennebäck et al. | Using OPLS-DA to find new hypotheses in vast amounts of gene expression data—Studying the progression of cardiac hypertrophy in the heart of aorta ligated rat | |
| Katebi et al. | Random parametric perturbations of gene regulatory circuit uncover state transitions in cell cycle | |
| Zhang et al. | Network motif-based identification of breast cancer susceptibility genes | |
| Gu et al. | Artificial intelligence methods in kinase target profiling: Advances and challenges | |
| Krotzky et al. | Extraction of protein binding pockets in close neighborhood of bound ligands makes comparisons simple due to inherent shape similarity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130717 |