Advances in Computational Polypharmacology

Abstract

In drug discovery, polypharmacology encompasses the use of small molecules with defined multi‐target activity and in vivo effects resulting from multi‐target engagement. Multi‐target compounds are often efficacious in the treatment of complex diseases involving target and pathway networks, but might also elicit unwanted side effects. Computational approaches such as target prediction or multi‐target ligand design have been used to support polypharmacological drug discovery. In addition to efforts directed at the identification or design of new multi‐target compounds, other computational investigations have aimed to differentiate such compounds from potential false‐positives or explore the molecular basis of multi‐target activities. Herein, a concise overview of the field is provided and recent advances in computational polypharmacology through machine learning are discussed.

Calculation of exact Shapley values for support vector machines with Tanimoto kernel enables model interpretation

“…For both SVM and RF models, features present in active compounds determined their correct prediction, whereas the absence of these features was largely responsible for the correct prediction of random instances by RF. These results paralleled prior findings in multi-target activity predictions using RF and TreeExplainer (Feldmann et al, 2021;Feldmann and Bajorath, 2022). However, the comparison also revealed model-specific differences between the highly accurate SVM and RF classifiers.…”

Polypharmacology: promises and new drugs in 2022

“…Until the 1990s, this was impossible as a result of the lack of accurate and efficient testing methods [ 12 ]. Despite the continuous progress in the field of genomics and proteomics and the development of computational methods [ 40 ], it is still challenging nowadays to determine all the potential targets to which a molecule can possibly bind [ 8 ]. The molecular basis for the adverse effects of drugs with already well-established therapeutic position is being discovered in most cases spontaneously, often many years after the registration procedure has been completed.…”

Applications of Deep Learning for Drug Discovery Systems with BigData

“…Even when animal studies are successful, significant side effects often occur in human clinical trials [8]. Due to advances in medical science, research topics have shifted to complex diseases with unknown causes, and the hurdles of drug discovery are becoming higher by the year [9][10][11]. In addition, tightening pharmaceutical regulations, pressure to raise drug prices, and generic competition lead to an ever-widening innovation gap.…”