Impact of Artificial Intelligence on Compound Discovery, Design, and Synthesis

Abstract

As in other areas, artificial intelligence (AI) is heavily promoted in different scientific fields, including chemistry. Although chemistry traditionally tends to be a conservative field and slower than others to adapt new concepts, AI is increasingly being investigated across chemical disciplines. In medicinal chemistry, supported by computer-aided drug design and cheminformatics, computational methods have long been employed to aid in the search for and optimization of active compounds. We are currently witnessing a multitude of AI-related publications in the medicinal-chemistry-relevant literature and anticipate that the numbers will further increase. Often, advances through AI promoted in such reports are difficult to reconcile or remain questionable, which hampers the acceptance of computational work in interdisciplinary environments. Herein we attempt to highlight selected investigations in which AI has shown promise to impact medicinal chemistry in areas such as compound design and synthesis.

Feasibility and application of machine learning enabled fast screening of poly-beta-amino-esters for cartilage therapies

“…Machine learning (ML) based regression techniques are becoming wide spread in many areas of data analysis in the chemical 11,12 and pharmaceutical sector [13][14][15][16] ; they have recently been employed in drug development [17][18][19] , diagnostic 20 , treatment algorithm optimisation 21 , drug repurposing 2,22 and material discovery 23,24 ; however such applications are still quite limited despite being very promising 25,26 . Another application of ML technologies in drug discovery is during compound screening or hit/lead generation and optimization enabling a virtual screening platform that offers a quicker and cheaper alternative to classic testing of large compounds libraries 27,28 ; virtual screening can be generally classified in ligand-based or structure-based 28 .…”

A transfer learning approach for reaction discovery in small data situations using generative model

“…With the rapid advances in the field of deep learning (DL), there have been notable applications focused on addressing the challenges in molecular design ( LeCun et al., 2015 ; Butler et al., 2018 ; Sun et al., 2019 ; Griffiths and Hernández-Lobato, 2020 ; Li et al., 2021 ). The use of DL for molecular discovery can broadly be categorized into reaction outcome prediction and molecule generation ( Gomez-Bombarelli et al., 2018 ; Miljkovic et al., 2021 ; Walters and Barzilay, 2021 ). The predictive DL models, consisting of multiple hidden layers, have been used for predictions of molecular properties as well as the yield/selectivities of reactions ( Schwaller et al., 2021 ; Senior et al., 2020 ; Singh and Sunoj, 2022 ).…”

The Optimal Permeation of Cyclic Boronates to Cross the Outer Membrane via the Porin Pathway

“…Another approach for predicting the permeability of compounds would be the use of artificial intelligence algorithms, which are becoming very popular in drug discovery [ 34 ]. However, these methods require a large set of data and this conflicts in some way with the difficulty in measuring permeation [ 23 ].…”