E' per mercoledì 26 aprile alle 14. 30 il seminario di Monica Bianchini, per il ciclo AIM. Monica è professore associato al Dipartimento Ingegneria dell’informazione e scienze matematiche dell'Università di Siena.
Il titolo del talk è Graph Neural Networks in Drug Design: From discovering new molecules to predicting side-effects.
Di seguito l'abstract.
"This talk will introduce Graph Neural Networks (GNNs) as a powerful tool for the design and evaluation of new targeted drugs. Drug Discovery is a fundamental but expensive process to make new pharmacological products available for healthcare. The generation of molecular graphs is of particular interest for drug discovery, as it could provide a technique for designing large amounts of possible drug candidates. GNNs can be used as molecular graph generators, able to create new drug-like molecules from scratch, which can also be adapted to fit in specific pockets of the protein surface. Indeed, constrained generation allows for designing molecules with both the desired chemical and stereochemical properties, while their side-effects can be evaluated based on their molecular structure. Moreover, the introduction of Composite GNN(CGNN) models, designed for processing heterogeneous graphs has allowed the study of even more complex networks. With CGNNs, drug side-effects can be predicted based on a graph describing the interactions between drugs and human genes. Actually, a three-step chain can be devised, in which the graph generator constitutes the first step, aimed at producing a large pool of possible drug candidates. The drug candidates could then be screened for their drug-likeness, retaining only compounds with a high druggability score. Finally, the selected compounds can be evaluated, filtering out those with too many or too dangerous side-effects. In this way, discovering new drugs can be carried out as a total in-silico procedure, before clinical trials, saving costs in terms of time and money”.
Il seminario sarà trasmesso in streaming sul canale YouTube CNR IAC.
Qui il programma completo dei seminari.
