The development and application of in silico models for drug induced liver injury

被引:31
|
作者
Li, Xiao [1 ,2 ]
Chen, Yaojie [1 ]
Song, Xinrui [1 ]
Zhang, Yuan [1 ]
Li, Huanhuan [1 ]
Zhao, Yong [1 ,2 ]
机构
[1] Beijing Beike Deyuan Biopharm Technol Co Ltd, 7 Fengxian Rd, Beijing 100094, Peoples R China
[2] Beijing Acad Sci & Technol, Beijing Comp Ctr, Beijing Key Lab Cloud Comp Key Technol & Applicat, 7 Fengxian Rd, Beijing 100094, Peoples R China
关键词
MOLECULAR-BASIS; KNOWLEDGE-BASE; PREDICTION; TOXICITY; CARCINOGENICITY; HEPATOTOXICITY; CHEMICALS; INSIGHTS; ALERTS;
D O I
10.1039/c7ra12957b
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Drug-induced liver injury (DILI), caused by drugs, herbal agents or nutritional supplements, is a major issue for patients and the pharmaceutical industry. It has been a leading cause of clinical trials failure and withdrawal of FDA approval. In this research, we focused on in silico estimation of chemical DILI potential on humans based on structurally diverse organic chemicals. We developed a series of binary classification models using five different machine learning methods and eight different feature reduction methods. The model, developed with the support vector machine (SVM) and the MACCS fingerprint, performed best both on the test set and external validation. It achieved a prediction accuracy of 80.39% on the test set and 82.78% on external validation. We made this model available at http://opensource.vslead.com/. The user can freely predict the DILI potential of molecules. Furthermore, we analyzed the difference of distributions of 12 key physical-chemical properties between DILI-positive and DILI-negative compounds and 20 privileged substructures responsible for DILI were identified from the Klekota-Roth fingerprint. Moreover, since traditional Chinese medicine (TCM)-induced liver injury is also one of the major concerns among the toxic effects, we evaluated the DILI potential of TCM ingredients using the MACCS_SVM model developed in this study. We hope the model and privileged substructures could be useful complementary tools for chemical DILI evaluation.
引用
收藏
页码:8101 / 8111
页数:11
相关论文
共 50 条
  • [1] Applications of In Silico Models to Predict Drug-Induced Liver Injury
    Lin, Jiaying
    Li, Min
    Mak, Wenyao
    Shi, Yufei
    Zhu, Xiao
    Tang, Zhijia
    He, Qingfeng
    Xiang, Xiaoqiang
    TOXICS, 2022, 10 (12)
  • [2] In silico models for drug-induced liver injury - current status
    Przybylak, Katarzyna R.
    Cronin, Mark T. D.
    EXPERT OPINION ON DRUG METABOLISM & TOXICOLOGY, 2012, 8 (02) : 201 - 217
  • [3] In silico assessment of drug-induced liver injury in humans
    Yang, C.
    Thakkar, S.
    Mostrag, A.
    Gombar, V.
    Bienfait, B.
    Rathman, J. F.
    Tong, W.
    TOXICOLOGY LETTERS, 2016, 258 : S118 - S118
  • [4] Animal models of drug-induced liver injury
    McGill, Mitchell R.
    Jaeschke, Hartmut
    BIOCHIMICA ET BIOPHYSICA ACTA-MOLECULAR BASIS OF DISEASE, 2019, 1865 (05): : 1031 - 1039
  • [5] Models of Idiosyncratic Drug-Induced Liver Injury
    Yokoi, Tsuyoshi
    Oda, Shingo
    ANNUAL REVIEW OF PHARMACOLOGY AND TOXICOLOGY, VOL 61, 2021, 2021, 61 : 247 - 268
  • [6] miRNAs and their application in drug-induced liver injury
    Wang, Yuping
    Chen, Tao
    Tong, Weida
    BIOMARKERS IN MEDICINE, 2014, 8 (02) : 161 - 172
  • [7] In silico weight of evidence assessment of drug-induced liver injury in humans
    Yang, Chihae
    Rathman, James
    Mostrag, Aleksandra
    Thakkar, Shraddha
    Tong, Weida
    Vitcheva, Vessela
    TOXICOLOGY LETTERS, 2017, 280 : S284 - S285
  • [8] In-silico approach for drug induced liver injury prediction: Recent advances
    Saini, Neha
    Bakshi, Shikha
    Sharma, Sadhna
    TOXICOLOGY LETTERS, 2018, 295 : 288 - 295
  • [9] In Silico Prediction of Drug-Induced Liver Injury Based on Adverse Drug Reaction Reports
    Zhu, Xiang-Wei
    Li, Shao-Jing
    TOXICOLOGICAL SCIENCES, 2017, 158 (02) : 391 - 400
  • [10] Drug-Induced Liver Injury and Individual Cell Models
    Benesic, Andreas
    Gerbes, Alexander L.
    DIGESTIVE DISEASES, 2015, 33 (04) : 486 - 491