{"doi":"10.1093/bioinformatics/btad085","title":"Multimodal representation learning for predicting molecule–disease relations","abstract":"MOTIVATION: Predicting molecule-disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule-molecule, molecule-disease and disease-disease semantic dependencies can potentially improve prediction performance. METHODS: We introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule-disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects. RESULTS: We extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens. AVAILABILITY AND IMPLEMENTATION: The code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.","journal":"Bioinformatics","year":2023,"id":333109,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":23,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9545,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1060299,"name":"Xiang Zhang","orcid":"0009-0004-9025-414X","position":1,"is_corresponding":false},{"id":874839,"name":"Everett Rush","orcid":"0000-0002-5632-5723","position":2,"is_corresponding":false},{"id":515691,"name":"Vidul Ayakulangara Panickan","orcid":null,"position":3,"is_corresponding":false},{"id":1060300,"name":"Xingyu Li","orcid":"0000-0002-2946-5448","position":4,"is_corresponding":false},{"id":499601,"name":"Tianrun Cai","orcid":"0000-0001-5772-7460","position":5,"is_corresponding":false},{"id":465953,"name":"Doudou Zhou","orcid":"0000-0002-0830-2287","position":6,"is_corresponding":false},{"id":480530,"name":"Yuk‐Lam Ho","orcid":"0000-0003-3305-3830","position":7,"is_corresponding":false},{"id":808837,"name":"Lauren Costa","orcid":"0000-0001-7237-5336","position":8,"is_corresponding":false},{"id":16843,"name":"Edmon Begoli","orcid":"0000-0002-2173-3663","position":9,"is_corresponding":false},{"id":465955,"name":"Chuan Hong","orcid":"0000-0001-7056-9559","position":10,"is_corresponding":false},{"id":11341,"name":"J. Michael Gaziano","orcid":"0000-0002-5384-9767","position":11,"is_corresponding":false},{"id":11349,"name":"Kelly Cho","orcid":"0000-0003-1727-7076","position":12,"is_corresponding":false},{"id":311412,"name":"Junwei Lu","orcid":"0000-0003-3743-6855","position":13,"is_corresponding":false},{"id":350961,"name":"Katherine P. Liao","orcid":"0000-0002-4797-3200","position":14,"is_corresponding":false},{"id":29867,"name":"Marinka Zitnik","orcid":"0000-0001-8530-7228","position":15,"is_corresponding":false},{"id":322350,"name":"Tianxi Cai","orcid":"0000-0002-5379-2502","position":16,"is_corresponding":false},{"id":1051809,"name":"Jun Wen","orcid":"0000-0001-5067-2647","position":0,"is_corresponding":true}],"reference_count":48,"raw_metadata":null,"created_at":"2026-07-19T01:09:39.719497Z","pmid":"36805623","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}