EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning

Yang Yue, Yongxuan Liu, Luoying Hao, Huangshu Lei, Shan He iD

Briefings in Bioinformatics · 2023

DOI: 10.1093/bib/bbac564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2023. Verfasst von Yang Yue und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science from the University of Birmingham, UK. Hauptthemen laut MEDLINE: Drug-Related Side Effects and Adverse Reactions. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug combinations could trigger pharmacological therapeutic effects (TEs) and adverse effects (AEs). Many computational methods have been developed to predict TEs, e.g. the therapeutic synergy scores of anti-cancer drug combinations, or AEs from drug–drug interactions. However, most of the methods treated the AEs and TEs predictions as two separate tasks, ignoring the potential mechanistic commonalities shared between them. Based on previous clinical observations, we hypothesized that by learning the shared mechanistic commonalities between AEs and TEs, we could learn the underlying MoAs (mechanisms of actions) and ultimately improve the accuracy of TE predictions. To test our hypothesis, we formulated the TE prediction problem as a multi-task heterogeneous network learning problem that performed TE and AE learning tasks simultaneously. To solve this problem, we proposed Muthene (multi-task heterogeneous network embedding) and evaluated it on our collected drug–drug interaction dataset with both TEs and AEs indications. Our experimental results showed that, by including the AE prediction as an auxiliary task, Muthene generated more accurate TE predictions than standard single-task learning methods, which supports our hypothesis. Using a drug pair Vincristine—Dasatinib as a case study, we demonstrated that our method not only provides a novel way of TE predictions but also helps us gain a deeper understanding of the MoAs of drug combinations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug-Related Side Effects and Adverse ReactionsHumansDrug InteractionsDrug CombinationsMachine Learning

Stichwörter der Autor:innen

biological networksheterogeneous graph convolutional networkmeta-path information aggregation for MoAsmulti-task learningtherapeutic synergy score prediction

Substanzen

Drug Combinations

Autor:innen und Institutionen

  • School of Computer Science from the University of Birmingham, UK.
  • State Key Laboratory of Agricultural Microbiology from Huazhong Agricultural University, China.
  • YaoPharma Co., Ltd.
  • School of Computer Science, the University of Birmingham, UK.

ORCID-Profile: Shan He

Zitieren

APA

Yue, Y., Liu, Y., Hao, L., Lei, H., & He, S. (2023). Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbac564

Vancouver

Yue Y, Liu Y, Hao L, Lei H, He S. Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning. Briefings in Bioinformatics. 2023. doi:10.1093/bib/bbac564

BibTeX
@article{Yue2023,
  author = {Yue, Yang and Liu, Yongxuan and Hao, Luoying and Lei, Huangshu and He, Shan},
  title = {Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  doi = {10.1093/bib/bbac564}
}
Kostenlos starten →