Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Jiménez-Luna2021 - Coloring molecules for for hERG blockade

ABSTRACT: 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 Pharmacokinetics predictive tasks with cardiotoxicity a case study for this model. MolGrad incorporates explainable features to facilitate interpretation of the predictions.In this model, they train MolGrad with a dataset of hERG channel blockers/non-blockers to predict the cardiotoxicity of small molecules (IC50 in hERG blockade). Model Relevance: Predicts hERG inhibition. Model Encoded by: Miquel Duran-Frigola (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos43at

SUBMITTER: Zainab Ashimiyu-Abdusalam

PROVIDER: MODEL2405210007 | BioModels | 2024-05-21

REPOSITORIES: BioModels

ACCESS DATA

Json Xml

Publications

Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment.

Jiménez-Luna José J Skalic Miha M Weskamp Nils N Schneider Gisbert G

Journal of chemical information and modeling 20210225 3

Graph neural networks are able to solve certain drug discovery tasks such as molecular property prediction and <i>de novo</i> molecule generation. However, these models are considered "black-box" and "hard-to-debug". This study aimed to improve modeling transparency for rational molecular design by applying the integrated gradients explainable artificial intelligence (XAI) approach for graph neural network models. Models were trained for predicting plasma protein binding, hERG channel inhibition ...[more]

PMID: 33629843

Similar Datasets

Jiménez-Luna2021 - Coloring molecules for plasma protein binding prediction

Project description: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 plasma protein binding prediction as the case for this model. MolGrad incorporates explainable features to facilitate interpretation of the predictions. In this model, they train MolGrad with data from a Plasma-protein binding assay (PPB) to predict the fraction bound in plasma of small molecules. Model Type: Predictive machine learning model. Model Relevance: Fraction of protein bound in plasma. Model Encoded by: Miquel Duran-Frigola (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos6ao8

2024-05-21 | MODEL2405210005 | BioModels

Jiménez-Luna2021 - Coloring molecules for interaction with CYP3A4

Project description: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). Model Type: Predictive machine learning model. Model Relevance: Probability that the molecule is metabolized by Cyp3A4. Model Encoded by: Miquel Duran-Frigola (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos96ia

2024-05-21 | MODEL2405210003 | BioModels

Jiménez-Luna2021 - Coloring molecules for Caco-2 cell permeability

Project description: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). Model Type: Predictive machine learning model. Model Relevance: Predicts Log10 of the Passive permeability in cm s-1. Model Encoded by: Miquel Duran-Frigola (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos1af5

2024-05-21 | MODEL2405210006 | BioModels

Karim2021 - CardioTox net: Ligand-based prediction of hERG blockade

Project description:A robust predictor for hERG channel blockade based on an ensemble of five deep learning models. The authors have collected a dataset from public sources, such as BindingDB and ChEMBL on hERG blockers and non-blockers. The cut-off for hERG blockade was set at IC50 Model Type: Predictive machine learning model. Model Relevance: Prediction of hERG blockade Model Encoded by: Miquel Duran-Frigola (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos2ta5

2024-07-18 | MODEL2407180003 | BioModels

Rahman2022 - High throughput antibacterial screening with machine learning.

Project description:Prediction of antimicrobial potential using a dataset of 29537 compounds screened against the antibiotic resistant pathogen Burkholderia cenocepacia. The model uses the Chemprop Direct Message Passing Neural Network (D-MPNN) and has an AUC score of 0.823 for the test set. It has been used to virtually screen the FDA approved drugs as well as a collection of natural product list (>200k compounds) with hit rates of 26% and 12% respectively. Model Type: Predictive machine learning model. Model Relevance: Probability that a compound inhibits bacterial pathogens with a focus on ESKAPE. Model Encoded by: Sarima Chiorlu (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos5xng

2024-04-22 | MODEL2404080002 | BioModels

Wong2024 - Discovery of a structural class of antibiotics with explainable deep learning

Project description:The authors use a large dataset (>30k) to train an explainable graph-based model to identify potential antibiotics with low cytotoxicity. The model uses a substructure-based approach to explore the chemical space. Using this method, they were able to screen 283 compounds and identify a candidate active against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci. Model Type: Predictive machine learning model. Model Relevance: The model predicts the probability of growth inhibition. Model Encoded by: Sarima Chiorlu (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos18ie

2024-05-08 | MODEL2405080002 | BioModels

Wong2024 - Cytotoxicity Prediction from Human Cell Lines

Project description:The authors use a large dataset (>30k) to train an explainable graph-based model to identify potential antibiotics with low cytotoxicity. The model uses a substructure-based approach to explore the chemical space. Using this method, they were able to screen 283 compounds and identify a candidate active against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci. Model Type: Predictive machine learning model. Model Relevance: Prediction of Human cytotoxicity endpoints. Model Encoded by: Sarima Chiorlu (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos42ez

2024-05-13 | MODEL2405130002 | BioModels

Kim2022 - BayeshERG: A deep learning model for predicting hERG channel blockers

Project description:BayeshERG is a predictor of small molecule-induced blockade of the hERG ion channel. To increase its predictive power, the authors pretrained a bayesian graph neural network with 300,000 molecules as a transfer learning exercise. The pretraining set was obtained from Du et al, 2015, and the fine tuning dataset is a collection of 14,322 molecules from public databases (8488 positives and 5834 negatives). The model was validated on external datasets and experimentally, from 12 selected compounds (>0.95 probability) one candidate showed strong hERG inhibition (IC 50 Model Type: Predictive machine learning model. Model Relevance: Prediction of hERG channel blockade probability br> Model Encoded by: Azycn (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos4tcc

2024-08-06 | MODEL2408060001 | BioModels

Siramshetty2020 - Assessment of rat liver microsomal stability with QSAR models.

Project description:Hepatic metabolic stability is key to ensure the drug attains the desired concentration in the body. The Rat Liver Microsomal (RLM) stability is a good approximation of a compound’s stability in the human body, and NCATS has collected a proprietary dataset of 20216 compounds with its associated RLM (in vitro half-life; unstable ≤30 min, stable >30 min) and used it to train a classifier based on an ensemble of several ML approaches (random forest, deep neural networks, graph convolutional neural networks and recurrent neural networks. Model Type: Predictive machine learning model. Model Relevance: Predicting the stability of a compound in RLM assay. Model Encoded by: Pauline (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos5505

2024-04-22 | MODEL2404220002 | BioModels

Prosit: Proteome-wide prediction of peptide tandem mass spectra by deep learning

Project description:In this study, we extended the ProteomeTools peptide library (PROPEL, see PXD004732 and PXD010595) to train a deep neural network resulting in chromatographic retention time and fragment ion intensity predictions for (tryptic) peptides that exceed the quality of the experimental data.

2019-05-30 | PXD010871 | Pride

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data