EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal representation learning for predicting molecule–disease relations

Jun Wen iD, Xiang Zhang, Everett Rush, Vidul A Panickan, Xingyu Li, Tianrun Cai, Doudou Zhou, Yuk-Lam Ho, Lauren Costa, Edmon Begoli, Chuan Hong, J Michael Gaziano und 5 weitere

Bioinformatics · 2023

DOI: 10.1093/bioinformatics/btad085 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2023. Verfasst von Jun Wen und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA. Hauptthemen laut MEDLINE: Drug-Related Side Effects and Adverse Reactions. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United States Government, NIAMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug-Related Side Effects and Adverse ReactionsHumansDrug DevelopmentElectronic Health RecordsNeural Networks, ComputerPharmacovigilance

Autor:innen und Institutionen

  • Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA.
  • VA Boston Healthcare System, Boston, MA 02130, USA.
  • Department of Energy, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA.
  • Mass General Brigham, Boston, MA 02130, USA.
  • Department of Statistics, University of California, Davis, CA 95616, USA.
  • Department of Biostatistics and Bioinformatics, Duke University, Durham, NC 27708, USA.

ORCID-Profile: Jun Wen, Kelly Cho, Marinka Zitnik, Tianxi Cai

Förderung

  • United States Government
  • NIAMS NIH HHS

Zitieren

APA

Wen, J., Zhang, X., Rush, E., Panickan, V. A., Li, X., Cai, T., Zhou, D., Ho, Y. L., Costa, L., Begoli, E., Hong, C., Gaziano, J. M., Cho, K., Lu, J., Liao, K. P., Zitnik, M., & Cai, T. (2023). Multimodal representation learning for predicting molecule–disease relations. Bioinformatics. https://doi.org/10.1093/bioinformatics/btad085

Vancouver

Wen J, Zhang X, Rush E, Panickan VA, Li X, Cai T, et al. Multimodal representation learning for predicting molecule–disease relations. Bioinformatics. 2023. doi:10.1093/bioinformatics/btad085

BibTeX
@article{Wen2023,
  author = {Wen, Jun and Zhang, Xiang and Rush, Everett and Panickan, Vidul A and Li, Xingyu and Cai, Tianrun and Zhou, Doudou and Ho, Yuk-Lam and Costa, Lauren and Begoli, Edmon and Hong, Chuan and Gaziano, J Michael and Cho, Kelly and Lu, Junwei and Liao, Katherine P and Zitnik, Marinka and Cai, Tianxi},
  title = {Multimodal representation learning for predicting molecule–disease relations},
  journal = {Bioinformatics},
  year = {2023},
  doi = {10.1093/bioinformatics/btad085}
}
Kostenlos starten →