PMID- 36562724
OWN - NLM
STAT- MEDLINE
DCOM- 20230123
LR  - 20230215
IS  - 1477-4054 (Electronic)
IS  - 1467-5463 (Print)
IS  - 1467-5463 (Linking)
VI  - 24
IP  - 1
DP  - 2023 Jan 19
TI  - Improving therapeutic synergy score predictions with adverse effects using 
      multi-task heterogeneous network learning.
LID - 10.1093/bib/bbac564 [doi]
LID - bbac564
AB  - 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.
CI  - (c) The Author(s) 2022. Published by Oxford University Press.
FAU - Yue, Yang
AU  - Yue Y
AD  - School of Computer Science from the University of Birmingham, UK.
FAU - Liu, Yongxuan
AU  - Liu Y
AD  - State Key Laboratory of Agricultural Microbiology from Huazhong Agricultural 
      University, China.
FAU - Hao, Luoying
AU  - Hao L
AD  - School of Computer Science from the University of Birmingham, UK.
FAU - Lei, Huangshu
AU  - Lei H
AD  - YaoPharma Co., Ltd.
FAU - He, Shan
AU  - He S
AUID- ORCID: 0000-0003-1694-1465
AD  - School of Computer Science, the University of Birmingham, UK.
LA  - eng
PT  - Journal Article
PL  - England
TA  - Brief Bioinform
JT  - Briefings in bioinformatics
JID - 100912837
RN  - 0 (Drug Combinations)
SB  - IM
MH  - Humans
MH  - *Drug-Related Side Effects and Adverse Reactions
MH  - Drug Interactions
MH  - Drug Combinations
MH  - Machine Learning
PMC - PMC9851313
OTO - NOTNLM
OT  - biological networks
OT  - heterogeneous graph convolutional network
OT  - meta-path information aggregation for MoAs
OT  - multi-task learning
OT  - therapeutic synergy score prediction
EDAT- 2022/12/24 06:00
MHDA- 2023/01/24 06:00
PMCR- 2022/12/23
CRDT- 2022/12/23 10:22
PHST- 2022/09/14 00:00 [received]
PHST- 2022/10/31 00:00 [revised]
PHST- 2022/11/21 00:00 [accepted]
PHST- 2022/12/24 06:00 [pubmed]
PHST- 2023/01/24 06:00 [medline]
PHST- 2022/12/23 10:22 [entrez]
PHST- 2022/12/23 00:00 [pmc-release]
AID - 6958504 [pii]
AID - bbac564 [pii]
AID - 10.1093/bib/bbac564 [doi]
PST - ppublish
SO  - Brief Bioinform. 2023 Jan 19;24(1):bbac564. doi: 10.1093/bib/bbac564.