Controlled exploration of chemical space by machine learning of coarse-grained representations

Abstract

The size of chemical compound space is too large to be probed exhaustively. This leads high-throughput protocols to drastically subsample and results in sparse and non-uniform datasets. Rather than arbitrarily selecting compounds, we systematically explore chemical space according to the target property of interest. We first perform importance sampling by introducing a Markov chain Monte Carlo scheme across compounds. We then train an ML model on the sampled data to expand the region of chemical space probed. Our boosting procedure enhances the number of compounds by a factor 2 to 10, enabled by the ML model's coarse-grained representation, which both simplifies the structure-property relationship and reduces the size of chemical space. The ML model correctly recovers linear relationships between transfer free energies. These linear relationships correspond to features that are global to the dataset, marking the region of chemical space up to which predictions are reliable---a more robust alternative to the predictive variance. Bridging coarse-grained simulations with ML gives rise to an unprecedented database of drug-membrane insertion free energies for 1.3 million compounds.

arXiv comment9 pages, 5 figures

References in corpus (11)

• Canonical sampling through velocity-rescaling
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Statistically optimal analysis of samples from multiple equilibrium states
• Big Data of Materials Science - Critical Role of the Descriptor
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine learning prediction errors better than DFT accuracy
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Alchemical and structural distribution based representation for improved QML
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• In silico screening of drug-membrane thermodynamics reveals linear relations between bulk partitioning and the potential of mean force
• Efficient potential of mean force calculation from multiscale simulations: solute insertion in a lipid membrane

Cited by in corpus (6)

• Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
• Hydration free energies from kernel-based machine learning: Compound-database bias
• Differentiable Molecular Simulations for Control and Learning
• Resolution limit of data-driven coarse-grained models spanning chemical space
• Ab initio machine learning in chemical compound space
• Broad chemical transferability in structure-based coarse-graining