Transparency in Modeling through Careful Application of OECD’s QSAR/QSPR Principles via a Curated Water Solubility Data Set
- 6 March 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in Chemical Research in Toxicology
- Vol. 36 (3) , 465-478
Abstract
The need for careful assembly, training, and validation of quantitative structure-activity/property models (QSAR/QSPR) is more significant than ever as data sets become larger and sophisticated machine learning tools become increasingly ubiquitous and accessible to the scientific community. Regulatory agencies such as the United States Environmental Protection Agency must carefully scrutinize each aspect of a resulting QSAR/QSPR model to determine its potential use in environmental exposure and hazard assessment. Herein, we revisit the goals of the Organisation for Economic Cooperation and Development (OECD) in our application and discuss the validation principles for structure-activity models. We apply these principles to a model for predicting water solubility of organic compounds derived using random forest regression, a common machine learning approach in the QSA/PR literature. Using public sources, we carefully assembled and curated a data set consisting of 10,200 unique chemical structures with associated water solubility measurements. This data set was then used as a focal narrative to methodically consider the OECD's QSA/PR principles and how they can be applied to random forests. Despite some expert, mechanistically informed supervision of descriptor selection to enhance model interpretability, we achieved a model of water solubility with comparable performance to previously published models (5-fold cross validated performance 0.81 R2 and 0.98 RMSE). We hope this work will catalyze a necessary conversation around the importance of cautiously modernizing and explicitly leveraging OECD principles while pursuing state-of-the-art machine learning approaches to derive QSA/PR models suitable for regulatory consideration.Keywords
Funding Information
- U.S. Environmental Protection Agency
This publication has 32 references indexed in Scilit:
- Does Rational Selection of Training and Test Sets Improve the Outcome of QSAR Modeling?Journal of Chemical Information and Modeling, 2012
- Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical informationJournal of Computer-Aided Molecular Design, 2011
- PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprintsJournal of Computational Chemistry, 2010
- Trust, But Verify: On the Importance of Chemical Structure Curation in Cheminformatics and QSAR Modeling ResearchJournal of Chemical Information and Modeling, 2010
- How not to develop a quantitative structure–activity or structure–property relationship (QSAR/QSPR)SAR and QSAR in Environmental Research, 2009
- A Hierarchical Clustering Methodology for the Estimation of ToxicityToxicology Mechanisms and Methods, 2008
- Predicting aqueous solubility from structureDrug Discovery Today, 2005
- Guidelines for developing and using quantitative structure-activity relationshipsEnvironmental Toxicology and Chemistry, 2003
- Temperature and pressure dependence of hydrogen bond strength: A perturbation molecular orbital approachThe Journal of Chemical Physics, 1998
- Characterization of molecular branchingJournal of the American Chemical Society, 1975