{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Zhang Y"],"funding":["Key Technologies Research and Development Program","National Natural Science Foundation of China","National Key Research and Development Program of China"],"pagination":["101313"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12409376"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["15(8)"],"pubmed_abstract":["P-glycoprotein (P-gp) is a transmembrane protein widely involved in the absorption, distribution, metabolism, excretion, and toxicity (ADMET) of drugs within the human body. Accurate prediction of P-gp inhibitors and substrates is crucial for drug discovery and toxicological assessment. However, existing models rely on limited molecular information, leading to suboptimal model performance for predicting P-gp inhibitors and substrates. To overcome this challenge, we compiled an extensive dataset from public databases and literature, consisting of 5,943 P-gp inhibitors and 4,018 substrates, notable for their high quantity, quality, and structural uniqueness. In addition, we curated two external test sets to validate the model's generalization capability. Subsequently, we developed a multimod"],"journal":["Journal of pharmaceutical analysis"],"pubmed_title":["A multimodal contrastive learning framework for predicting P-glycoprotein substrates and inhibitors."],"pmcid":["PMC12409376"],"funding_grant_id":["2022YFF1203003","82373791"],"pubmed_authors":["Wu J","Zhang Y","Hou T","Kang Y"],"additional_accession":[]},"is_claimable":false,"name":"A multimodal contrastive learning framework for predicting P-glycoprotein substrates and inhibitors.","description":"P-glycoprotein (P-gp) is a transmembrane protein widely involved in the absorption, distribution, metabolism, excretion, and toxicity (ADMET) of drugs within the human body. Accurate prediction of P-gp inhibitors and substrates is crucial for drug discovery and toxicological assessment. However, existing models rely on limited molecular information, leading to suboptimal model performance for predicting P-gp inhibitors and substrates. To overcome this challenge, we compiled an extensive dataset from public databases and literature, consisting of 5,943 P-gp inhibitors and 4,018 substrates, notable for their high quantity, quality, and structural uniqueness. In addition, we curated two external test sets to validate the model's generalization capability. Subsequently, we developed a multimod","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Aug","modification":"2026-06-03T07:08:07.345Z","creation":"2026-05-29T03:05:47.718Z"},"accession":"S-EPMC12409376","cross_references":{"pubmed":["40919587"],"doi":["10.1016/j.jpha.2025.101313"]}}