biostudies-otherUnknown61Zainab Ashimiyu-AbdusalamJournal of chemical information and modeling1083-1094https://www.ebi.ac.uk/biostudies/studies/MODEL2405210006biostudies-other33629843Zainab Ashimiyu-AbdusalamMiquel Duran-FrigolafalseJiménez-Luna2021 - Coloring molecules for Caco-2 cell permeability<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 pCaco-2 cell permeability as the case for this model. MolGrad incorporates explainable features to facilitate interpretation of the predictions. This model has been trained using experimental data on the permeability of molecules across Caco2 cell membranes (Papp, cm s-1).</p><p><normal>Model Type:</normal> Predictive machine learning model.<br><normal>Model Relevance:</normal> Predicts Log10 of the Passive permeability in cm s-1.<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/eos1af5">https://github.com/ersilia-os/eos1af5</a></p><img src="https://www.ebi.ac.uk/biomodels/static-assets/images/ersilia-logo.png" alt="Ersilia Logo" width="150">2024-05-21T00:00:00Z2025-07-14T17:02:11.857Z2025-03-31T13:26:11.947ZMODEL24052100060010008000000933629843C154407topic_0154OBI_0200032BTO:0000195molgrad