TY - JOUR
T1 - Comparison of target features for predicting drug-target interactions by deep neural network based on large-scale drug-induced transcriptome data
AU - Lee, Hanbi
AU - Kim, Wankyu
N1 - Funding Information:
Funding: This research was supported by the National Research Foundation of Korea (NRF-2017M3A9B3061843).
Publisher Copyright:
© 2019 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2019/8
Y1 - 2019/8
N2 - Uncovering drug-target interactions (DTIs) is pivotal to understand drug mode-of-action (MoA), avoid adverse drug reaction (ADR), and seek opportunities for drug repositioning (DR). For decades, in silico predictions for DTIs have largely depended on structural information of both targets and compounds, e.g., docking or ligand-based virtual screening. Recently, the application of deep neural network (DNN) is opening a new path to uncover novel DTIs for thousands of targets. One important question is which features for targets are most relevant to DTI prediction. As an early attempt to answer this question, we objectively compared three canonical target features extracted from: (i) the expression profiles by gene knockdown (GEPs); (ii) the protein–protein interaction network (PPI network); and (iii) the pathway membership (PM) of a target gene. For drug features, the large-scale drug-induced transcriptome dataset, or the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 dataset was used. All these features are closely related to protein function or drug MoA, of which utility is only sparsely investigated. In particular, few studies have compared the three types of target features in DNN-based DTI prediction under the same evaluation scheme. Among the three target features, the PM and the PPI network show similar performances superior to GEPs. DNN models based on both features consistently outperformed other machine learning methods such as naïve Bayes, random forest, or logistic regression.
AB - Uncovering drug-target interactions (DTIs) is pivotal to understand drug mode-of-action (MoA), avoid adverse drug reaction (ADR), and seek opportunities for drug repositioning (DR). For decades, in silico predictions for DTIs have largely depended on structural information of both targets and compounds, e.g., docking or ligand-based virtual screening. Recently, the application of deep neural network (DNN) is opening a new path to uncover novel DTIs for thousands of targets. One important question is which features for targets are most relevant to DTI prediction. As an early attempt to answer this question, we objectively compared three canonical target features extracted from: (i) the expression profiles by gene knockdown (GEPs); (ii) the protein–protein interaction network (PPI network); and (iii) the pathway membership (PM) of a target gene. For drug features, the large-scale drug-induced transcriptome dataset, or the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 dataset was used. All these features are closely related to protein function or drug MoA, of which utility is only sparsely investigated. In particular, few studies have compared the three types of target features in DNN-based DTI prediction under the same evaluation scheme. Among the three target features, the PM and the PPI network show similar performances superior to GEPs. DNN models based on both features consistently outperformed other machine learning methods such as naïve Bayes, random forest, or logistic regression.
KW - Deep neural network
KW - Drug repositioning
KW - Drug target interaction
KW - Drug-induced transcriptome data
UR - http://www.scopus.com/inward/record.url?scp=85070980123&partnerID=8YFLogxK
U2 - 10.3390/pharmaceutics11080377
DO - 10.3390/pharmaceutics11080377
M3 - Article
AN - SCOPUS:85070980123
SN - 1999-4923
VL - 11
JO - Pharmaceutics
JF - Pharmaceutics
IS - 8
M1 - 377
ER -