Beyond the Scope of Free-Wilson Analysis: Building Interpretable QSAR Models with Machine Learning Algorithms
Authors:
- Hongming ChenHCHongming Chen
- Lars CarlssonLCLars Carlsson
- Mats ErikssonMEMats Eriksson
- Peter VarkonyiPVPeter Varkonyi
- Ulf NorinderUNUlf Norinder
- Ingemar NilssonINIngemar Nilsson
- 12 June 2013
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 53 (6) , 1324-1336
Abstract
A novel methodology was developed to build Free-Wilson like local QSAR models by combining R-group signatures and the SVM algorithm. Unlike Free-Wilson analysis this method is able to make predictions for compounds with R-groups not present in a training set. Eleven public data sets were chosen as test cases for comparing the performance of our new method with several other traditional modeling strategies, including Free-Wilson analysis. Our results show that the R-group signature SVM models achieve better prediction accuracy compared with Free-Wilson analysis in general. Moreover, the predictions of R-group signature models are also comparable to the models using ECFP6 fingerprints and signatures for the whole compound. Most importantly, R-group contributions to the SVM model can be obtained by calculating the gradient for R-group signatures. For most of the studied data sets, a significant correlation with that of a corresponding Free-Wilson analysis is shown. These results suggest that the R-group contribution can be used to interpret bioactivity data and highlight that the R-group signature based SVM modeling method is as interpretable as Free-Wilson analysis. Hence the signature SVM model can be a useful modeling tool for any drug discovery project.Keywords
This publication has 34 references indexed in Scilit:
- Hypothesis driven drug design: improving quality and effectiveness of the design-make-test-analyse cycleDrug Discovery Today, 2012
- How to improve R&D productivity: the pharmaceutical industry's grand challengeNature Reviews Drug Discovery, 2010
- Making medicinal chemistry more effective—application of Lean Sigma to improve processes, speed and qualityDrug Discovery Today, 2009
- In Silico Prediction of Drug PropertiesCurrent Medicinal Chemistry, 2009
- Regression Methods for Developing QSAR and QSPR Models to Predict Compounds of Specific Pharmacodynamic, Pharmacokinetic and Toxicological PropertiesMini-Reviews in Medicinal Chemistry, 2007
- Artificial Intelligence Approaches for Rational Drug Design and DiscoveryCurrent Pharmaceutical Design, 2007
- Prediction of Compounds with Specific Pharmacodynamic, Pharmacokinetic or Toxicological Property by Statistical Learning MethodsMini-Reviews in Medicinal Chemistry, 2006
- Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agentsDrug Development Research, 2005
- Learning to improve the decision-making process in researchDrug Discovery Today, 2004
- Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteinsJournal of the American Chemical Society, 1988