An Analysis of Proteochemometric and Conformal Prediction Machine Learning Protein-Ligand Binding Affinity Models
| Autor: | Rommie E. Amaro, Conor Parks, Zied Gaieb |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
protein-ligand binding affinity
deep neural net (DNN) 0301 basic medicine Computer science proteochemometric Conformal map Machine learning computer.software_genre Biochemistry Genetics and Molecular Biology (miscellaneous) Biochemistry conformal prediction 03 medical and health sciences 0302 clinical medicine Molecular Biosciences bemis-murcko scaffolding lcsh:QH301-705.5 Molecular Biology Original Research Artificial neural network business.industry Prediction interval Random forest Data set 030104 developmental biology lcsh:Biology (General) 030220 oncology & carcinogenesis Test set Artificial intelligence business computer random forest Protein ligand |
| Zdroj: | Frontiers in Molecular Biosciences Frontiers in Molecular Biosciences, Vol 7 (2020) |
| ISSN: | 2296-889X |
| DOI: | 10.3389/fmolb.2020.00093 |
| Popis: | Protein-ligand binding affinity is a key pharmacodynamic endpoint in drug discovery. Sole reliance on experimental design, make, and test cycles is costly and time consuming, providing an opportunity for computational methods to assist. Herein, we present results comparing random forest and feed-forward neural network proteochemometric models for their ability to predict pIC50 measurements for held out generic Bemis-Murcko scaffolds. In addition, we assess the ability of conformal prediction to provide calibrated prediction intervals in both a retrospective and semi-prospective test using the recently released Grand Challenge 4 data set as an external test set. In total, random forest and deep neural network proteochemometric models show quality retrospective performance but suffer in the semi-prospective setting. However, the conformal predictor prediction intervals prove to be well calibrated both retrospectively and semi-prospectively showing that they can be used to guide hit discovery and lead optimization campaigns. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|