Optimizing active learning for free energy calculations
James Thompson, W. Patrick Walters, Jianwen A. Feng et al. · Artificial Intelligence in the Life Sciences · 2022
While Relative Binding Free Energy (RBFE) calculations have become a mainstay in lead optimization programs, the computational expense of performing these calculations has limited their broader application. Active learning (AL), a machine learning method used to direct a search iteratively, has explored larger chemical libraries using RBFE calculations. While AL has been successfully applied, there has not been a systematic study of the impact of parameter settings on the performance of AL. To address this gap, we have generated an exhaustive dataset of RBFE calculations on 10,000 congeneric molecules. We used this dataset to explore the impact of several AL design choices, including the number of molecules sampled at each iteration, the method used to select an initial sample, the method used to build a machine learning model, and the acquisition function that defines the balance between exploration and exploitation in the search. Our studies demonstrated that the performance of AL is largely insensitive to the specific machine learning method and acquisition functions used. In our studies, the most significant factor impacting performance was the number of molecules sampled at each iteration where selecting too few molecules hurts performance. Under the best conditions, we were able to identify 75% of the 100 top scoring molecules by sampling only 6% of the dataset. We hope that the dataset of 10K molecules will provide the basis for future studies exploring additional AL strategies. The source code and supporting data for the work are available at https://github.com/google-research/google-research/tree/master/al_for_fep.
Cited by 59 works. doi:10.1016/j.ailsci.2022.100050
Authors
- W. Patrick Walters
- Jianwen A. Feng
- Nicolas A Pabon
- Hongcheng Xu
- Michael Maser
- Brian B Goldman
- Demetri T. Moustakas
- Molly Schmidt
- Forrest York
References
- Scikit-learn: Machine Learning in Python
- Comparison of simple potential functions for simulating liquid water
- Efficient estimation of free energy differences from Monte Carlo data
- Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling
- Improved side‐chain torsion potentials for the Amber ff99SB protein force field
- Fast, efficient generation of high‐quality atomic charges. AM1‐BCC model: II. Parameterization and validation
- Accurate and Reliable Prediction of Relative Ligand Binding Potency in Prospective Drug Discovery by Way of a Modern Free-Energy Calculation Protocol and Force Field
- Active Learning with Support Vector Machines in the Drug Discovery Process
- Extreme Gradient Boosting as a Method for Quantitative Structure–Activity Relationships
- Active-learning strategies in computer-assisted drug discovery