Cargando…
Multimodal representation learning for predicting molecule–disease relations
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 M...
Autores principales: | , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9940625/ https://www.ncbi.nlm.nih.gov/pubmed/36805623 http://dx.doi.org/10.1093/bioinformatics/btad085 |
_version_ | 1784891122029428736 |
---|---|
author | Wen, Jun Zhang, Xiang Rush, Everett Panickan, Vidul A Li, Xingyu Cai, Tianrun Zhou, Doudou Ho, Yuk-Lam Costa, Lauren Begoli, Edmon Hong, Chuan Gaziano, J Michael Cho, Kelly Lu, Junwei Liao, Katherine P Zitnik, Marinka Cai, Tianxi |
author_facet | Wen, Jun Zhang, Xiang Rush, Everett Panickan, Vidul A Li, Xingyu Cai, Tianrun Zhou, Doudou Ho, Yuk-Lam Costa, Lauren Begoli, Edmon Hong, Chuan Gaziano, J Michael Cho, Kelly Lu, Junwei Liao, Katherine P Zitnik, Marinka Cai, Tianxi |
author_sort | Wen, Jun |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9940625 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-99406252023-02-21 Multimodal representation learning for predicting molecule–disease relations Wen, Jun Zhang, Xiang Rush, Everett Panickan, Vidul A Li, Xingyu Cai, Tianrun Zhou, Doudou Ho, Yuk-Lam Costa, Lauren Begoli, Edmon Hong, Chuan Gaziano, J Michael Cho, Kelly Lu, Junwei Liao, Katherine P Zitnik, Marinka Cai, Tianxi Bioinformatics Original Paper 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. Oxford University Press 2023-02-10 /pmc/articles/PMC9940625/ /pubmed/36805623 http://dx.doi.org/10.1093/bioinformatics/btad085 Text en © The Author(s) 2023. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Original Paper Wen, Jun Zhang, Xiang Rush, Everett Panickan, Vidul A Li, Xingyu Cai, Tianrun Zhou, Doudou Ho, Yuk-Lam Costa, Lauren Begoli, Edmon Hong, Chuan Gaziano, J Michael Cho, Kelly Lu, Junwei Liao, Katherine P Zitnik, Marinka Cai, Tianxi Multimodal representation learning for predicting molecule–disease relations |
title | Multimodal representation learning for predicting molecule–disease relations |
title_full | Multimodal representation learning for predicting molecule–disease relations |
title_fullStr | Multimodal representation learning for predicting molecule–disease relations |
title_full_unstemmed | Multimodal representation learning for predicting molecule–disease relations |
title_short | Multimodal representation learning for predicting molecule–disease relations |
title_sort | multimodal representation learning for predicting molecule–disease relations |
topic | Original Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9940625/ https://www.ncbi.nlm.nih.gov/pubmed/36805623 http://dx.doi.org/10.1093/bioinformatics/btad085 |
work_keys_str_mv | AT wenjun multimodalrepresentationlearningforpredictingmoleculediseaserelations AT zhangxiang multimodalrepresentationlearningforpredictingmoleculediseaserelations AT rusheverett multimodalrepresentationlearningforpredictingmoleculediseaserelations AT panickanvidula multimodalrepresentationlearningforpredictingmoleculediseaserelations AT lixingyu multimodalrepresentationlearningforpredictingmoleculediseaserelations AT caitianrun multimodalrepresentationlearningforpredictingmoleculediseaserelations AT zhoudoudou multimodalrepresentationlearningforpredictingmoleculediseaserelations AT hoyuklam multimodalrepresentationlearningforpredictingmoleculediseaserelations AT costalauren multimodalrepresentationlearningforpredictingmoleculediseaserelations AT begoliedmon multimodalrepresentationlearningforpredictingmoleculediseaserelations AT hongchuan multimodalrepresentationlearningforpredictingmoleculediseaserelations AT gazianojmichael multimodalrepresentationlearningforpredictingmoleculediseaserelations AT chokelly multimodalrepresentationlearningforpredictingmoleculediseaserelations AT lujunwei multimodalrepresentationlearningforpredictingmoleculediseaserelations AT liaokatherinep multimodalrepresentationlearningforpredictingmoleculediseaserelations AT zitnikmarinka multimodalrepresentationlearningforpredictingmoleculediseaserelations AT caitianxi multimodalrepresentationlearningforpredictingmoleculediseaserelations |