TY - GEN
T1 - A drug-induced liver injury prediction model using transcriptional response data with graph neural network
AU - Hwang, Doyeong
AU - Jeon, Minji
AU - Kang, Jaewoo
N1 - Funding Information:
This research was supported by the National Research Foundation of Korea [NRF-2016M3A9A7916996, NRF-2017R1A2A1A17069645]; and by the National IT Industry Promotion Agency grant funded by the Ministry of Science and ICT and Ministry of Health and Welfare [NO. C1202-18-1001, Development Project of the Precision Medicine Hospital Information System (P-HIS)].
PY - 2020/2/1
Y1 - 2020/2/1
N2 - Drug-Induced Liver Injury (Dili) is a major cause of failed drug candidates in clinical trials and withdrawal of approved drugs from the market. Therefore, machine learning-based Dili prediction can be key in increasing the success rate of drug discovery because drug candidates that are predicted to potentially induce liver injury can be rejected before clinical trials. However, existing Dili prediction models mainly focus on the chemical structures of drugs. Since we cannot determine whether a drug will cause liver injury based solely on its structure, Dili prediction based on the transcriptional effect of a drug on a cell is necessary. In this paper, we propose GLIT which is a model that uses transcriptional response data and chemical structures and can be used for drug-induced liver injury prediction. GLIT learns the embedding vectors of drug structures and drug-induced gene expression profiles using graph attention networks in a biological knowledge graph for predicting Dili. GLIT outperformed a baseline model that uses only drug structure information by 7% and 19.2% in terms of correct classification rate (CCR) and Matthews correlation coefficient (MCC), respectively. In addition, we conducted a literature survey to confirm whether the class labels of drugs, in the unknown Dili class, predicted by GLIT are correct.
AB - Drug-Induced Liver Injury (Dili) is a major cause of failed drug candidates in clinical trials and withdrawal of approved drugs from the market. Therefore, machine learning-based Dili prediction can be key in increasing the success rate of drug discovery because drug candidates that are predicted to potentially induce liver injury can be rejected before clinical trials. However, existing Dili prediction models mainly focus on the chemical structures of drugs. Since we cannot determine whether a drug will cause liver injury based solely on its structure, Dili prediction based on the transcriptional effect of a drug on a cell is necessary. In this paper, we propose GLIT which is a model that uses transcriptional response data and chemical structures and can be used for drug-induced liver injury prediction. GLIT learns the embedding vectors of drug structures and drug-induced gene expression profiles using graph attention networks in a biological knowledge graph for predicting Dili. GLIT outperformed a baseline model that uses only drug structure information by 7% and 19.2% in terms of correct classification rate (CCR) and Matthews correlation coefficient (MCC), respectively. In addition, we conducted a literature survey to confirm whether the class labels of drugs, in the unknown Dili class, predicted by GLIT are correct.
KW - Drug Discovery
KW - Drug induced Liver Injury
KW - Drug-induced Gene Expression Profiles
KW - Graph Neural Network
UR - http://www.scopus.com/inward/record.url?scp=85084350975&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084350975&partnerID=8YFLogxK
U2 - 10.1109/BigComp48618.2020.00-54
DO - 10.1109/BigComp48618.2020.00-54
M3 - Conference contribution
AN - SCOPUS:85084350975
SN - 9781728160344
T3 - Proceedings - 2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020
SP - 323
EP - 329
BT - Proceedings - 2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020
A2 - Lee, Wookey
A2 - Chen, Luonan
A2 - Moon, Yang-Sae
A2 - Bourgeois, Julien
A2 - Bennis, Mehdi
A2 - Li, Yu-Feng
A2 - Ha, Young-Guk
A2 - Kwon, Hyuk-Yoon
A2 - Cuzzocrea, Alfredo
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020
Y2 - 19 February 2020 through 22 February 2020
ER -