A review of molecular representation in the age of machine learning

Abstract

Research in chemistry increasingly requires interdisciplinary work prompted by, among other things, advances in computing, machine learning, and artificial intelligence. Everyone working with molecules, whether chemist or not, needs an understanding of the representation of molecules in a machinereadable format, as this is central to computational chemistry. Four classes of representations are introduced: string, connection table, feature-based, and computer-learned representations. Three of the most significant representations are simplified molecular-input line-entry system (SMILES), International Chemical Identifier (InChI), and the MDL molfile, of which SMILES was the first to successfully be used in conjunction with a variational autoencoder (VAE) to yield a continuous representation of molecules. This is noteworthy because a continuous representation allows for efficient navigation of the immensely large chemical space of possible molecules. Since 2018, when the first model of this type was published, considerable effort has been put into developing novel and improved methodologies. Most, if not all, researchers in the community make their work easily accessible on GitHub, though discussion of computation time and domain of applicability is often overlooked.Herein, we present questions for consideration in future work which we believe will make chemical VAEs even more accessible.

Understanding the charge dynamics in organic light-emitting diodes using convolutional neural network

“…In the field of molecular discovery based on machine learning, various methods of molecular fingerprint appropriately exhibiting structural and chemical properties of the given molecular structure have been recently proposed. 47,[54][55][56][57] As a fingerprint corresponding to the charge dynamics of OLEDs, we selected the modulus spectra of OLEDs depending on the DC voltage and AC frequency. In the case of conventional current density-voltage property, the information of the transit time of each organic layer, charge retardation, and charge accumulation were not separately extracted since these mechanisms commonly result in the change of resistance in devices.…”

Automated pH Adjustment Driven by Robotic Workflows and Active Machine Learning

“…Representing chemical compounds in a machine-readable format is considered a challenge in chemoinformatics due to its effect on different surrogate models and, thus, their predictive performance. 39 Previous literature has led to ambiguous outcomes on whether the addition of chemical information within low data regimes, such as the initialization of active-ML search strategies, is beneficial. 31,40 To learn more about featurization effects on this specific application, we compared two input feature sets.…”

ViSAS for Entering Chemical Space: Virtual Screening of Analog Series and Related Advances

“…[70] Structural representation is the most relevant feature in basically any chemoinformatics application, and computational study [73] and it is an area under constant research. [74] In virtual screening, defining the chemical space to be explored is crucial, as it defines the applicability domain that will be searched. In practice, it is common to conduct virtual screening campaigns focused on regions of the medicinally relevant chemical space.…”