Researchers from Fondazione Gianni Benzi cooperated with the team of Dipartimento di Farmacia - Scienze del Farmaco at Università degli Studi di Bari to the article “TISBE: A Public Web Platform for the Consensus-Based Explainable Prediction of Developmental Toxicity” recently published on the Chemical Research in Toxicology journal.
The work describes TISBE (TIRESIA Improved on Structure-Based Explainability), a new public web platform for Developmental Toxicity predictions.
Developmental toxicity, in the framework of prenatal and neonatal health, is a highly complex endpoint. The lack of high-quality data as well as robust non-testing methods makes its understanding even more difficult. Thus, the application of new explainable alternative methods is of utmost importance.
Resulting from TIRESIA (Toxicology Intelligence and Regulatory Evaluations for Scientific and Industry Applications), TISBE implements four fundamental advancements for in silico analyses: a three times larger dataset, a transparent explainable artificial intelligence framework, a novel consensus classifier based on five independent machine learning models, and a new applicability domain method based on a double top-down approach for better estimating the prediction reliability.
TISBE is freely available at: https://prometheus.farmacia.uniba.it/tisbe
Read the article here.