Fast Identification of Adverse Drug Reactions (ADRs) of Digestive and Nervous Systems of Organic Drugs by In Silico Models.

Meimei Chen,Yuxing Gao,Zhaoyang Yang,Candong Li

doi:10.3390/molecules26040930

Abstract

This study aimed to discover concurrences of adverse drug reactions (ADRs) and derive models of the most frequent items of ADRs based on the SIDER database, which included 1430 marketed drugs and 5868 ADRs. First, common ADRs of organic drugs were manually reclassified according to side effects in the human system and followed by an association rule analysis, which found ADRs of digestive and nervous systems often occurred at the same time with a good association rule. Then, three algorithms, linear discriminant analysis (LDA), support vector machine (SVM) and deep learning, were used to derive models of ADRs of digestive and nervous systems based on 497 organic monomer drugs and to identify key structural features in defining these ADRs. The statistical results indicated that these kinds of QSAR models were good tools for screening ADRs of digestive and nervous systems, which gave the ROC AUC values of 81.5%, 98.9%, 91.5%, 69.5%, 78.4% and 78.8%, respectively. Then, these models were applied to investigate ADRs of 1536 organic compounds with four phase and zero rule-of-five (RO5) violations from the ChEMBL database. Based on the consensus ADRs’ predictions of models, 58.1% and 42.6% of compounds were predicted to cause these two ADRs, respectively, indicating the significance of initial assessment of ADRs in early drug discovery.

Highlights

According to the definition that an Adverse drug reactions (ADRs) is common if occurring at a frequency of greater than 10%, 566 organic drugs were identified as common ADR drugs after removing gold or ion compounds
deep learning (DL) enhanced the accuracy of descriptors in prediction of ADRs of digestive and nervous systems compared with linear discriminant analysis (LDA)
Three QSAR modeling algorithms, LDA, support vector machine (SVM) and DL, were successfully used to derive models of ADRs of digestive and nervous systems and identified key structural features in defining these ADRs of organic drugs based on 497 marketed organic monomer drugs

Summary

Introduction

Ibuprofen is the most commonly used and prescribed non-steroidal anti-inflammatory drug. It causes commonly reported side effects, including hemorrhage, vomiting, anemia, decreased hemoglobin, eosinophilia and hypertension [1,2]. Severe ADRs can induce drugs to be withdrawn from the market. Troglitazone, a drug for treatment of diabetes that decreases blood glucose significantly without body weight changes, was withdrawn from the market due to it causing the ADR of hepatic failure [3,4]. Valdecoxib, an anti-inflammatory drug, was withdrawn from the market due to ADRs of nervous and cardiovascular systems [2]

Objectives

Methods

Results

Conclusion