biostudies-otherUnknown61Zainab Ashimiyu-AbdusalamJournal of chemical information and modeling1083-1094Homo sapienshttps://www.ebi.ac.uk/biostudies/studies/MODEL2405210003biostudies-other33629843Zainab Ashimiyu-AbdusalamMiquel Duran-FrigolafalseJiménez-Luna2021 - Coloring molecules for interaction with CYP3A4<p> By combining a Message-Passing Graph Neural Network (MPGNN) and a Forward fully connected Neural Network (FNN) with an integrated gradients explainable artificial intelligence (XAI) method, the authors developed MolGrad and tested it on a number of ADME predictive tasks such as metabolism as the case for this model. MolGrad incorporates explainable features to facilitate interpretation of the predictions. This model has been trained using a ChEMBL dataset of CYP450 3A4 inhibitors (0) and non-inhibitors (1).</p><p><normal>Model Type:</normal> Predictive machine learning model.<br><normal>Model Relevance:</normal> Probability that the molecule is metabolized by Cyp3A4.<br><normal>Model Encoded by:</normal> Miquel Duran-Frigola (Ersilia)<br><normal>Metadata Submitted in BioModels by:</normal> Zainab Ashimiyu-Abdusalam</p><p>Implementation of this model code by <a href="https://ersilia.io/">Ersilia</a> is available here: <br><a href="https://github.com/ersilia-os/eos96ia">https://github.com/ersilia-os/eos96ia</a></p><img src="https://www.ebi.ac.uk/biomodels/static-assets/images/ersilia-logo.png" alt="Ersilia Logo" width="150">2024-05-21T00:00:00Z2025-07-14T17:02:16.761Z2025-03-31T13:26:06.778ZMODEL2405210003STATO:0000274STATO:0000549STATO:00000310000009000230533629843NCIT:C91423NCIT:C16484NCIT:C16309NCIT:C176258NCIT:C24328NCIT:C17429C154407C45329NCIT:C19404topic_3336topic_0154topic_3474OBI_0200032CHEMINF:0000189606eos96ia