Back to Search
Start Over
Proteochemometric modeling in a Bayesian framework
- Source :
- Journal of Cheminformatics, Journal of Cheminformatics, 2014, 6, pp.35. ⟨10.1186/1758-2946-6-35⟩, Journal of Cheminformatics, Chemistry Central Ltd. and BioMed Central, 2014, 6, pp.35. ⟨10.1186/1758-2946-6-35⟩, Journal of Cheminformatics, 2014, 6 (1), pp.35, Journal of Cheminformatics, 6, 35
- Publication Year :
- 2014
- Publisher :
- HAL CCSD, 2014.
-
Abstract
- Proteochemometrics (PCM) is an approach for bioactivity predictive modeling which models the relationship between protein and chemical information. Gaussian Processes (GP), based on Bayesian inference, provide the most objective estimation of the uncertainty of the predictions, thus permitting the evaluation of the applicability domain (AD) of the model. Furthermore, the experimental error on bioactivity measurements can be used as input for this probabilistic model. In this study, we apply GP implemented with a panel of kernels on three various (and multispecies) PCM datasets. The first dataset consisted of information from 8 human and rat adenosine receptors with 10,999 small molecule ligands and their binding affinity. The second consisted of the catalytic activity of four dengue virus NS3 proteases on 56 small peptides. Finally, we have gathered bioactivity information of small molecule ligands on 91 aminergic GPCRs from 9 different species, leading to a dataset of 24,593 datapoints with a matrix completeness of only 2.43%. GP models trained on these datasets are statistically sound, at the same level of statistical significance as Support Vector Machines (SVM), with R 0 2 values on the external dataset ranging from 0.68 to 0.92, and RMSEP values close to the experimental error. Furthermore, the best GP models obtained with the normalized polynomial and radial kernels provide intervals of confidence for the predictions in agreement with the cumulative Gaussian distribution. GP models were also interpreted on the basis of individual targets and of ligand descriptors. In the dengue dataset, the model interpretation in terms of the amino-acid positions in the tetra-peptide ligands gave biologically meaningful results.
- Subjects :
- Computer science
Adenosine Receptors
Library and Information Sciences
computer.software_genre
Bayesian inference
01 natural sciences
GPCRs
03 medical and health sciences
chemistry.chemical_compound
symbols.namesake
Chemogenomics
Physical and Theoretical Chemistry
Gaussian process
030304 developmental biology
[INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM]
0303 health sciences
[SDV.BIBS] Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]
[SDV.BBM.BS]Life Sciences [q-bio]/Biochemistry, Molecular Biology/Structural Biology [q-bio.BM]
Statistical model
Applicability Domain
Computer Graphics and Computer-Aided Design
0104 chemical sciences
Computer Science Applications
[SDV.BBM.BP]Life Sciences [q-bio]/Biochemistry, Molecular Biology/Biophysics
010404 medicinal & biomolecular chemistry
chemistry
symbols
Bayesian Inference
Bayesian framework
Data mining
Gaussian Process
[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]
computer
Proteochemometrics
Research Article
Applicability domain
Subjects
Details
- Language :
- English
- ISSN :
- 17582946
- Database :
- OpenAIRE
- Journal :
- Journal of Cheminformatics, Journal of Cheminformatics, 2014, 6, pp.35. ⟨10.1186/1758-2946-6-35⟩, Journal of Cheminformatics, Chemistry Central Ltd. and BioMed Central, 2014, 6, pp.35. ⟨10.1186/1758-2946-6-35⟩, Journal of Cheminformatics, 2014, 6 (1), pp.35, Journal of Cheminformatics, 6, 35
- Accession number :
- edsair.doi.dedup.....0f846f36df4d44f8f56d9987c3f7c35f