SaferWorldbyDesign Webinar: in silico Mutagenicity Prediction: a Journey

in silico Mutagenicity Prediction: a Journey

Assessing a molecule's mutagenicity is an important activity in the drug discovery and development process. Traditional assessment methods, such as the Ames test, require (i) that the corresponding molecule is already synthesized, (ii) extensive and expensive experiments. In this context, the use of in silico tools for the analysis and prediction of mutagenicity outcomes present a compelling alternative. During this webinar, we present an overview of the different approaches that are available to assist medicinal chemists in performing in silico prediction of mutagenicity, ranging from expert systems to machine learning models. Furthermore, there is a constant pursuit to increase the accuracy of the prediction tools. In this direction, we will highlight our recent work, which improved the accuracy of models by focusing on the selection of better descriptors (structural as well as functional). The results of our analysis showed that by doing the proper feature selection, the accuracy of models can be increased across the board.

Presenter: Nicolas K. Shinada (SBX Corporation) 

Nicolas K. Shinada graduated from Paris-Cité University (France) with a Master in Bioinformatics (2015) and a Ph.D. degree in Structural Biology and Cheminformatics (2019) under the supervision of Alexandre de Brevern and Peter Schmidtke. His research involved the analysis of camelid antibody structures and large-scale processing of protein-ligand molecular interactions. After finishing his degree, he moved to Japan to join SBX Corporation as a research engineer and transitioned to a data scientist role. His work covers the representation of the molecule, as well as properties calculation and prediction in collaboration with high-profile pharmaceutical companies.