Molecular representations for machine learning applications in chemistry

Abstract

Machine learning (ML) methods enable computers to address problems by learning from existing data. Such applications are becoming commonplace in molecular sciences. Interest in applying ML techniques across chemical compound space, from predicting properties to designing molecules and materials is in the surge. Especially, ML models have started to accelerate computational chemistry, and are often as accurate as state‐of‐the‐art electronic/atomistic models. Being an integral part of the ML architecture, representation of a molecular entity, uniquely encoded, plays a crucial role to what extent an ML model would be accurately predicting the desired property. This review aims to demonstrate a hierarchy of representations which has been introduced, to capture all degrees of freedom of a molecule or an atom the best, to map the quantum mechanical properties. We discuss their diverse applications how they have been instrumental in harnessing the growing field of ML accelerated computational modeling.

Toward a Mobility-Preserving Coarse-Grained Model: A Data-Driven Approach

“…However, when we would have data from multiple molecules, we would not necessarily need to restrict ourselves to the input features used in this work. We can choose from a zoo of molecule featurization techniques − developed in recent years.…”

The applications of machine learning to predict the forming of chemically stable amorphous solid dispersions prepared by hot-melt extrusion

“…To convert API and excipient molecules into computer-readable formats, multiple molecular representation methods, including extended-connectivity fingerprints (ECFP) and 2D molecular descriptors, were applied ( Jiang et al, 2022 ). Molecular descriptors contained physical and chemical properties of the APIs and excipients were generated by computer ( Raghunathan and Priyakumar, 2022 ). Some published literature compared the model's predictive performance using different molecular representation methods and found that ECFP-based models outperformed 2D molecular descriptors-based ones ( Dong et al, 2021 ).…”

New venues in electron density analysis

“…This is generally done in the form of atomic environment vectors (AEVs), which contain the desired information in a computer-understandable manner. Thus, a lot of effort has been made in recent years within the scientific community to develop suitable featurization approaches 100,101 such as the Bag of Bonds scheme, 36 Coulomb matrices, 46,102 Atom Centered Symmetry Functions (ACSF), 103,104 along with its many different flavors, [105][106][107] or the more recent Gaussian moments, 108 which would ultimately allow for the construction of reliable ML approaches. Despite being rigorous and useful, most strategies still recover little to no information about the actual chemistry, and are usually focused on encoding the radial and angular environments and the chemical composition of the system, just to mimic the external potential without further chemical insight.…”