Disease-related compound identification based on deeping learning method

Bin Yang; Wenzheng Bao; Jinglong Wang; Baitong Chen; Naoki Iwamori; Jiazi Chen; Yuehui Chen

doi:10.1038/s41598-022-24385-1

Disease-related compound identification based on deeping learning method

Sci Rep. 2022 Nov 29;12(1):20594. doi: 10.1038/s41598-022-24385-1.

Authors

Bin Yang¹, Wenzheng Bao², Jinglong Wang³, Baitong Chen⁴, Naoki Iwamori⁵, Jiazi Chen⁶, Yuehui Chen⁷

Affiliations

¹ School of Information Science and Engineering, Zaozhuang University, Zaozhuang, 277160, China.
² School of Information and Electrical Engineering, Xuzhou University of Technology, Xuzhou, 221018, China. baowz55555@126.com.
³ College of Food Science and Pharmaceutical Engineering, Zaozhuang University, Zaozhuang, 277160, China.
⁴ Xuzhou First People's Hospital, Xuzhou, 221000, China.
⁵ Laboratory of Zoology, Graduate School of Bioresource and Bioenvironmental Sciences, Kyushu University, Fukuoka-shi, Fukuoka, Japan.
⁶ Laboratory of Zoology, Graduate School of Bioresource and Bioenvironmental Sciences, Kyushu University, Fukuoka-shi, Fukuoka, Japan. chen.jiazi.767@s.kyushu-u.ac.jp.
⁷ School of Information Science and Engineering, University of Jinan, Jinan, China.

Abstract

Acute lung injury (ALI) is a serious respiratory disease, which can lead to acute respiratory failure or death. It is closely related to the pathogenesis of New Coronavirus pneumonia (COVID-19). Many researches showed that traditional Chinese medicine (TCM) had a good effect on its intervention, and network pharmacology could play a very important role. In order to construct "disease-gene-target-drug" interaction network more accurately, deep learning algorithm is utilized in this paper. Two ALI-related target genes (REAL and SATA3) are considered, and the active and inactive compounds of the two corresponding target genes are collected as training data, respectively. Molecular descriptors and molecular fingerprints are utilized to characterize each compound. Forest graph embedded deep feed forward network (forgeNet) is proposed to train. The experimental results show that forgeNet performs better than support vector machines (SVM), random forest (RF), logical regression (LR), Naive Bayes (NB), XGBoost, LightGBM and gcForest. forgeNet could identify 19 compounds in Erhuang decoction (EhD) and Dexamethasone (DXMS) more accurately.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Acute Lung Injury*
Algorithms
Bayes Theorem
COVID-19 Drug Treatment*
Humans
Respiratory Distress Syndrome*