Mariya Popova

TL;DR: The ReLeaSE method is used to design chemical libraries with a bias toward structural complexity or toward compounds with maximal, minimal, or specific range of physical properties, such as melting point or hydrophobicity.

TL;DR: In this paper, the authors proposed a new computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution) based on deep and reinforcement learning approaches, which integrates two deep neural networks -generative and predictive -that are trained separately but employed jointly to generate novel targeted chemical libraries.

TL;DR: A crowdsourced benchmarking of the accuracy of machine learning (ML) algorithms at predicting kinase inhibitor potencies across multiple kinase families demonstrated that these models and their ensemble can improve the accuracies of experimental mapping efforts, especially for so far under-studied kinases.

TL;DR: A crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data finds the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays.

TL;DR: In this article, the authors carried out a crowdsourced benchmarking of the accuracy of machine learning (ML) algorithms at predicting kinase inhibitor potencies across multiple kinase families.