MolPredictX: Online Biological Activity Predictions by Machine Learning Models
Marcus Tullius Scotti, Chonny Herrera‐Acevedo, Renata Priscila Barros de Menezes, Holli‐Joi Martin, Eugene N. Muratov, Ávilla Ítalo de Souza Silva, Emmanuella Faustino Albuquerque, Lucas Ferreira Calado, Ericsson Coy‐Barrera, Luciana Scotti
Abstract
Here we report the development of MolPredictX, an innovate and freely accessible web interface for biological activity predictions of query molecules. MolPredictX utilizes in-house QSAR models to provide 27 qualitative predictions (active or inactive), and quantitative probabilities for bioactivity against parasitic (Trypanosoma and Leishmania), viral (Dengue, Sars-CoV and Hepatitis C), pathogenic yeast (Candida albicans), bacterial (Salmonella enterica and Escherichia coli), and Alzheimer disease enzymes. In this article, we introduce the methodology and usability of this webtool, highlighting its potential role in the development of new drugs against a variety of diseases. MolPredictX is undergoing continuous development and is freely available at https://www.molpredictx.ufpb.br/.