In:
PLOS ONE, Public Library of Science (PLoS), Vol. 18, No. 4 ( 2023-4-12), p. e0282042-
Abstract:
A computational approach to identifying drug–target interactions (DTIs) is a credible strategy for accelerating drug development and understanding the mechanisms of action of small molecules. However, current methods to predict DTIs have mainly focused on identifying simple interactions, requiring further experiments to understand mechanism of drug. Here, we propose AI-DTI, a novel method that predicts activatory and inhibitory DTIs by combining the mol2vec and genetically perturbed transcriptomes. We trained the model on large-scale DTIs with MoA and found that our model outperformed a previous model that predicted activatory and inhibitory DTIs. Data augmentation of target feature vectors enabled the model to predict DTIs for a wide druggable targets. Our method achieved substantial performance in an independent dataset where the target was unseen in the training set and a high-throughput screening dataset where positive and negative samples were explicitly defined. Also, our method successfully rediscovered approximately half of the DTIs for drugs used in the treatment of COVID-19. These results indicate that AI-DTI is a practically useful tool for guiding drug discovery processes and generating plausible hypotheses that can reveal unknown mechanisms of drug action.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0282042
DOI:
10.1371/journal.pone.0282042.g001
DOI:
10.1371/journal.pone.0282042.g002
DOI:
10.1371/journal.pone.0282042.g003
DOI:
10.1371/journal.pone.0282042.g004
DOI:
10.1371/journal.pone.0282042.t001
DOI:
10.1371/journal.pone.0282042.t002
DOI:
10.1371/journal.pone.0282042.t003
DOI:
10.1371/journal.pone.0282042.t004
DOI:
10.1371/journal.pone.0282042.t005
DOI:
10.1371/journal.pone.0282042.s001
DOI:
10.1371/journal.pone.0282042.s002
DOI:
10.1371/journal.pone.0282042.s003
DOI:
10.1371/journal.pone.0282042.s004
DOI:
10.1371/journal.pone.0282042.s005
DOI:
10.1371/journal.pone.0282042.s006
DOI:
10.1371/journal.pone.0282042.s007
DOI:
10.1371/journal.pone.0282042.s008
DOI:
10.1371/journal.pone.0282042.s009
DOI:
10.1371/journal.pone.0282042.s010
DOI:
10.1371/journal.pone.0282042.s011
DOI:
10.1371/journal.pone.0282042.s012
DOI:
10.1371/journal.pone.0282042.s013
DOI:
10.1371/journal.pone.0282042.r001
DOI:
10.1371/journal.pone.0282042.r002
DOI:
10.1371/journal.pone.0282042.r003
DOI:
10.1371/journal.pone.0282042.r004
DOI:
10.1371/journal.pone.0282042.r005
DOI:
10.1371/journal.pone.0282042.r006
DOI:
10.1371/journal.pone.0282042.r007
DOI:
10.1371/journal.pone.0282042.r008
DOI:
10.1371/journal.pone.0282042.r009
DOI:
10.1371/journal.pone.0282042.r010
DOI:
10.1371/journal.pone.0282042.r011
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2023
detail.hit.zdb_id:
2267670-3
Permalink