Creating the New from the Old: Combinatorial Libraries Generation with Machine-Learning-Based Compound Structure Optimization

Abstract

The growing computational abilities of various tools that are applied in the broadly understood field of computer-aided drug design have led to the extreme popularity of virtual screening in the search for new biologically active compounds. Most often, the source of such molecules consists of commercially available compound databases, but they can also be searched for within the libraries of structures generated in silico from existing ligands. Various computational combinatorial approaches are based solely on the chemical structure of compounds, using different types of substitutions for new molecules formation. In this study, the starting point for combinatorial library generation was the fingerprint referring to the optimal substructural composition in terms of the activity toward a considered target, which was obtained using a machine learning-based optimization procedure. The systematic enumeration of all possible connections between preferred substructures resulted in the formation of target-focused libraries of new potential ligands. The compounds were initially assessed by machine learning methods using a hashed fingerprint to represent molecules; the distribution of their physicochemical properties was also investigated, as well as their synthetic accessibility. The examination of various fingerprints and machine learning algorithms indicated that the Klekota-Roth fingerprint and support vector machine were an optimal combination for such experiments. This study was performed for 8 protein targets, and the obtained compound sets and their characterization are publically available at http://skandal.if-pan.krakow.pl/comb_lib/ .

Merging Ligand-Based and Structure-Based Methods in Drug Discovery: An Overview of Combined Virtual Screening Approaches

“…The design of target chemical libraries is actually an undertaking of increasing interest, as illustrated by a number of recent studies that have reported the implementation of artificial intelligence-based algorithms [ 63 , 64 , 65 , 183 , 184 , 185 , 186 ]. One of them is the development of ReLeaSE (Reinforcement Learning for Structural Evolution), which integrates a generative deep neural network with a predictive one into a joint framework for the design of novel compounds satisfying certain chemical requirements, as illustrated with the biased selection of compounds fulfilling a specific range of physical properties (i.e., melting temperature and lipophilicity) or inhibitory activity against the desired target protein (Janus protein kinase 2) [ 62 ].…”

ChemTS: an efficient python library for de novo molecular generation

“…Most computer-aided methods for molecular design build a molecule by a combination of predefined fragments (e.g. [ 6 ]). Recently, Ikebata et al [ 7 ] succeeded de novo molecular design using an engineered language model of SMILES representation of molecules [ 8 ].…”

Accelerating the discovery of materials for clean energy in the era of smart automation

“…This is required because if the enumeration of molecules was pursued, the libraries for certain applications would become too large for even searching and hence also for the prediction of properties. New generative models could be used to generate focused, smaller virtual libraries that have shifted property distributions tailored for targets 200,203 (Fig. 3).…”