{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Sanchez JE"],"funding":["Division of Materials Research","NIGMS NIH HHS"],"pagination":["4190-4199"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC8482801"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["61(9)"],"pubmed_abstract":["Signaling bias is a feature of many G protein-coupled receptor (GPCR) targeting drugs with potential clinical implications. Whether it is therapeutically advantageous for a drug to be G protein biased or β-arrestin biased depends on the context of the signaling pathway. Here, we explored GPCR ligands that exhibit biased signaling to gain insights into scaffolds and pharmacophores that lead to bias. More specifically, we considered BiasDB, a database containing information about GPCR biased ligands, and focused our analysis on ligands which show either a G protein or β-arrestin bias. Five different machine learning models were trained on these ligands using 15 different sets of features. Molecular fragments which were important for training the models were analyzed. Two of these fragments ("],"journal":["Journal of chemical information and modeling"],"pubmed_title":["BiasNet: A Model to Predict Ligand Bias Toward GPCR Signaling."],"pmcid":["PMC8482801"],"funding_grant_id":["TL4 GM118971","RL5 GM118969","DMR-1827745","UL1 GM118970"],"pubmed_authors":["Garcia JD","Allen WJ","Sirimulla S","Franco J","Sanchez JE","Kc GB"],"additional_accession":[]},"is_claimable":false,"name":"BiasNet: A Model to Predict Ligand Bias Toward GPCR Signaling.","description":"Signaling bias is a feature of many G protein-coupled receptor (GPCR) targeting drugs with potential clinical implications. Whether it is therapeutically advantageous for a drug to be G protein biased or β-arrestin biased depends on the context of the signaling pathway. Here, we explored GPCR ligands that exhibit biased signaling to gain insights into scaffolds and pharmacophores that lead to bias. More specifically, we considered BiasDB, a database containing information about GPCR biased ligands, and focused our analysis on ligands which show either a G protein or β-arrestin bias. Five different machine learning models were trained on these ligands using 15 different sets of features. Molecular fragments which were important for training the models were analyzed. Two of these fragments (","dates":{"release":"2021-01-01T00:00:00Z","publication":"2021 Sep","modification":"2025-04-18T20:58:29.913Z","creation":"2025-04-07T08:56:28.247Z"},"accession":"S-EPMC8482801","cross_references":{"pubmed":["34397210"],"doi":["10.1021/acs.jcim.1c00317"]}}