Generic placeholder image

Current Bioinformatics

Author(s): Tiantian Tang, Xiaofeng Gan, Li Zhou, Kexue Pu, Hong Wang, Weina Dai, Bo Zhou, Lingyun Mo and Yonghong Zhang*

DOI: 10.2174/1574893618666230316122534

DownloadDownload PDF Flyer Cite As
Exploring the Hepatotoxicity of Drugs through Machine Learning and Network Toxicological Methods

Page: [484 - 496] Pages: 13

  • * (Excluding Mailing and Handling)

Abstract

Background: The prediction of the drug-induced liver injury (DILI) of chemicals is still a key issue of the adverse drug reactions (ADRs) that needs to be solved urgently in drug development. The development of a novel method with good predictive capability and strong mechanism interpretation is still a focus topic in exploring the DILI.

Objective: With the help of systems biology and network analysis techniques, a class of descriptors that can reflect the influence of drug targets in the pathogenesis of DILI is established. Then a machine learning model with good predictive capability and strong mechanism interpretation is developed between these descriptors and the toxicity of DILI.

Methods: After overlapping the DILI disease module and the drug-target network, we developed novel descriptors according to the number of drug genes with different network overlapped distance parameters. The hepatotoxicity of drugs is predicted based on these novel descriptors and the classical molecular descriptors. Then the DILI mechanism interpretations of drugs are carried out with important network topological descriptors in the prediction model.

Results: First, we collected targets of drugs and DILI-related genes and developed 5 NT parameters (S, Nds=0, Nds=1, Nds=2, and Nds>2) based on their relationship with a DILI disease module. Then hepatotoxicity predicting models were established between the above NT parameters combined with molecular descriptors and drugs through the machine learning algorithms. We found that the NT parameters had a significant contribution in the model (ACCtraining set=0.71, AUCtraining set=0.76; ACCexternal set=0.79, AUCexternal set=0.83) developed by these descriptors within the applicability domain, especially for Nds=2, and Nds>2. Then, the DILI mechanism of acetaminophen (APAP) and gefitinib are explored based on their risk genes related to ds=2. There are 26 DILI risk genes in the regulation of cell death regulated with two steps by 5 APAP targets, and gefitinib regulated risk gene of CLDN1, EIF2B4, and AMIGO1 with two steps led to DILI which fell in the biological process of response to oxygen-containing compound, indicating that different drugs possibly induced liver injury through regulating different biological functions.

Conclusion: A novel method based on network strategies and machine learning algorithms successfully explored the DILI of drugs. The NT parameters had shown advantages in illustrating the DILI mechanism of chemicals according to the relationships between the drug targets and the DILI risk genes in the human interactome. It can provide a novel candidate of molecular descriptors for the predictions of other ADRs or even of the predictions of ADME/T activity.

Graphical Abstract

[1]
Segall MD, Barber C. Addressing toxicity risk when designing and selecting compounds in early drug discovery. Drug Discov Today 2014; 19(5): 688-93.
[http://dx.doi.org/10.1016/j.drudis.2014.01.006] [PMID: 24451294]
[2]
Rawson NSB. Drug safety: Withdrawn medications are only part of the picture. BMC Med 2016; 14(1): 28.
[http://dx.doi.org/10.1186/s12916-016-0579-5] [PMID: 26873482]
[3]
Andrade RJ, Chalasani N, Björnsson ES, et al. Drug-induced liver injury. Nat Rev Dis Primers 2019; 5(1): 58.
[http://dx.doi.org/10.1038/s41572-019-0105-0] [PMID: 31439850]
[4]
Zhang Y, Shi D, Abagyan R, Dai W, Dong M. Population scale retrospective analysis reveals potential risk of cholestasis in pregnant women taking omeprazole, lansoprazole, and amoxicillin. Interdiscip Sci 2019; 11(2): 273-81.
[http://dx.doi.org/10.1007/s12539-019-00335-w] [PMID: 31106388]
[5]
Poleksic A, Xie L, Wren J. Predicting serious rare adverse reactions of novel chemicals. Bioinformatics 2018; 34(16): 2835-42.
[http://dx.doi.org/10.1093/bioinformatics/bty193] [PMID: 29617731]
[6]
Sun J, Slavov S, Schnackenberg LK, et al. Identification of a metabolic biomarker panel in rats for prediction of acute and idiosyncratic hepatotoxicity. Comput Struct Biotechnol J 2014; 10(17): 78-89.
[http://dx.doi.org/10.1016/j.csbj.2014.08.001] [PMID: 25379137]
[7]
Garcia-Cortes M, Robles-Diaz M, Stephens C, Ortega-Alonso A, Lucena MI, Andrade RJ. Drug induced liver injury: An update. Arch Toxicol 2020; 94(10): 3381-407.
[http://dx.doi.org/10.1007/s00204-020-02885-1] [PMID: 32852569]
[8]
Jia X, Ciallella HL, Russo DP, Zhao L, James MH, Zhu H. Construction of a virtual opioid bioprofile: A data-driven qsar modeling study to identify new analgesic opioids. ACS Sustain Chem& Eng 2021; 9(10): 3909-19.
[http://dx.doi.org/10.1021/acssuschemeng.0c09139] [PMID: 34239782]
[9]
Li H, Sun J, Fan X, et al. Considerations and recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction. J Comput Aided Mol Des 2008; 22(11): 843-55.
[http://dx.doi.org/10.1007/s10822-008-9225-4] [PMID: 18574695]
[10]
Wan H, Ulander J. High-throughput p Ka screening and prediction amenable for ADME profiling. Expert Opin Drug Metab Toxicol 2006; 2(1): 139-55.
[http://dx.doi.org/10.1517/17425255.2.1.139] [PMID: 16863474]
[11]
Singla D, Dhanda SK, Chauhan JS, et al. Open source software and web services for designing therapeutic molecules. Curr Top Med Chem 2013; 13(10): 1172-91.
[http://dx.doi.org/10.2174/1568026611313100005] [PMID: 23647540]
[12]
Yap C, Li H, Ji Z, Chen Y. Regression methods for developing QSAR and QSPR models to predict compounds of specific pharmacodynamic, pharmacokinetic and toxicological properties. Mini Rev Med Chem 2007; 7(11): 1097-107.
[http://dx.doi.org/10.2174/138955707782331696] [PMID: 18045213]
[13]
Chen S, Xue D, Chuai G, Yang Q, Liu Q. FL-QSAR: A federated learning-based QSAR prototype for collaborative drug discovery. Bioinformatics 2021; 36(22-23): 5492-8.
[http://dx.doi.org/10.1093/bioinformatics/btaa1006] [PMID: 33289524]
[14]
Zhang YH, Xia ZN, Yan L, Liu SS. Prediction of placental barrier permeability: a model based on partial least squares variable selection procedure. Molecules 2015; 20(5): 8270-86.
[http://dx.doi.org/10.3390/molecules20058270] [PMID: 25961165]
[15]
Zhang YH, Xia ZN, Qin LT, Liu SS. Prediction of blood–brain partitioning: A model based on molecular electronegativity distance vector descriptors. J Mol Graph Model 2010; 29(2): 214-20.
[http://dx.doi.org/10.1016/j.jmgm.2010.06.006] [PMID: 20637670]
[16]
Chen M, Hong H, Fang H, et al. Quantitative structure-activity relationship models for predicting drug-induced liver injury based on FDA-approved drug labeling annotation and using a large collection of drugs. Toxicol Sci 2013; 136(1): 242-9.
[http://dx.doi.org/10.1093/toxsci/kft189] [PMID: 23997115]
[17]
Yap CW. PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints. J Comput Chem 2011; 32(7): 1466-74.
[http://dx.doi.org/10.1002/jcc.21707] [PMID: 21425294]
[18]
Moriwaki H, Tian YS, Kawashita N, Takagi T. Mordred: A molecular descriptor calculator. J Cheminform 2018; 10(1): 4.
[http://dx.doi.org/10.1186/s13321-018-0258-y] [PMID: 29411163]
[19]
Fernández-de Gortari E, García-Jacas CR, Martinez-Mayorga K, Medina-Franco JL. Database fingerprint (DFP): An approach to represent molecular databases. J Cheminform 2017; 9(1): 9.
[http://dx.doi.org/10.1186/s13321-017-0195-1] [PMID: 28224019]
[20]
Soufan O, Ba-Alawi W, Afeef M, Essack M, Kalnis P, Bajic VB. DRABAL: Novel method to mine large high-throughput screening assays using Bayesian active learning. J Cheminform 2016; 8(1): 64.
[http://dx.doi.org/10.1186/s13321-016-0177-8] [PMID: 27895719]
[21]
Ai H, Chen W, Zhang L, et al. Predicting drug-induced liver injury using ensemble learning methods and molecular fingerprints. Toxicol Sci 2018; 165(1): 100-7.
[http://dx.doi.org/10.1093/toxsci/kfy121] [PMID: 29788510]
[22]
Chen Y, Yang H, Wu Z, Liu G, Tang Y, Li W. Prediction of farnesoid X receptor disruptors with machine learning methods. Chem Res Toxicol 2018; 31(11): 1128-37.
[http://dx.doi.org/10.1021/acs.chemrestox.8b00162] [PMID: 30371063]
[23]
Zhu H, Rusyn I, Richard A, Tropsha A. Use of cell viability assay data improves the prediction accuracy of conventional quantitative structure-activity relationship models of animal carcinogenicity. Environ Health Perspect 2008; 116(4): 506-13.
[http://dx.doi.org/10.1289/ehp.10573] [PMID: 18414635]
[24]
Liu G, Yan X, Sedykh A, et al. Analysis of model PM2.5-induced inflammation and cytotoxicity by the combination of a virtual carbon nanoparticle library and computational modeling. Ecotoxicol Environ Saf 2020; 191: 110216.
[http://dx.doi.org/10.1016/j.ecoenv.2020.110216] [PMID: 31972454]
[25]
Wang W, Sedykh A, Sun H, et al. Predicting nano–bio interactions by integrating nanoparticle libraries and quantitative nanostructure activity relationship modeling. ACS Nano 2017; 11(12): 12641-9.
[http://dx.doi.org/10.1021/acsnano.7b07093] [PMID: 29149552]
[26]
Vo AH, Van Vleet TR, Gupta RR, Liguori MJ, Rao MS. An overview of machine learning and big data for drug toxicity evaluation. Chem Res Toxicol 2020; 33(1): 20-37.
[http://dx.doi.org/10.1021/acs.chemrestox.9b00227] [PMID: 31625725]
[27]
Guo Y, Zhao L, Zhang X, Zhu H. Using a hybrid read-across method to evaluate chemical toxicity based on chemical structure and biological data. Ecotoxicol Environ Saf 2019; 178: 178-87.
[http://dx.doi.org/10.1016/j.ecoenv.2019.04.019] [PMID: 31004930]
[28]
Menche J, Sharma A, Kitsak M, et al. Uncovering disease-disease relationships through the incomplete interactome. Science 2015; 347(6224): 1257601.
[http://dx.doi.org/10.1126/science.1257601] [PMID: 25700523]
[29]
Greene N, Fisk L, Naven RT, Note RR, Patel ML, Pelletier DJ. Developing structure-activity relationships for the prediction of hepatotoxicity. Chem Res Toxicol 2010; 23(7): 1215-22.
[http://dx.doi.org/10.1021/tx1000865] [PMID: 20553011]
[30]
Cataldo VD, Gibbons DL, Pérez-Soler R, Quintás-Cardama A. Treatment of non-small-cell lung cancer with erlotinib or gefitinib. N Engl J Med 2011; 364(10): 947-55.
[http://dx.doi.org/10.1056/NEJMct0807960] [PMID: 21388312]
[31]
Dai W, Tang T, Dai Z, Shi D, Mo L, Zhang Y. Probing the mechanism of hepatotoxicity of hexabromocyclododecanes through toxicological network analysis. Environ Sci Technol 2020; 54(23): 15235-45.
[http://dx.doi.org/10.1021/acs.est.0c03998] [PMID: 33190479]
[32]
Wang X, Shen Y, Wang S, et al. PharmMapper 2017 update: A web server for potential drug target identification with a comprehensive target pharmacophore database. Nucleic Acids Res 2017; 45(W1): W356-60.
[http://dx.doi.org/10.1093/nar/gkx374] [PMID: 28472422]
[33]
von Mering C, Jensen LJ, Snel B, et al. STRING: known and predicted protein-protein associations, integrated and transferred across organisms. Nucleic Acids Res 2004; 33(Database issue): D433-7.
[http://dx.doi.org/10.1093/nar/gki005] [PMID: 15608232]
[34]
Guney E, Menche J, Vidal M, Barábasi AL. Network-based in silico drug efficacy screening. Nat Commun 2016; 7(1): 10331.
[http://dx.doi.org/10.1038/ncomms10331] [PMID: 26831545]
[35]
Yang HF, Zhang XN, Li Y, Zhang YH, Xu Q, Wei DQ. Theoretical studies of intracellular concentration of micro-organisms’ metabolites. Sci Rep 2017; 7(1): 9048.
[http://dx.doi.org/10.1038/s41598-017-08793-2] [PMID: 28831069]
[36]
Noble WS. What is a support vector machine? Nat Biotechnol 2006; 24(12): 1565-7.
[http://dx.doi.org/10.1038/nbt1206-1565] [PMID: 17160063]
[37]
Che D, Liu Q, Rasheed K, Tao X. Decision tree and ensemble learning algorithms with their applications in bioinformatics. Adv Exp Med Biol 2011; 696: 191-9.
[http://dx.doi.org/10.1007/978-1-4419-7046-6_19] [PMID: 21431559]
[38]
Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP. Random forest: A classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci 2003; 43(6): 1947-58.
[http://dx.doi.org/10.1021/ci034160g] [PMID: 14632445]
[39]
Chen T, Guestrin C. XGBoost: A scalable tree boosting system. arXiv 2016.
[http://dx.doi.org/10.1145/2939672.2939785]
[40]
Swami A, Jain RJJMLR. Scikit-learn. Mach Learn Python 2013; 12(10): 2825-30.
[41]
Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006; 27(8): 861-74.
[http://dx.doi.org/10.1016/j.patrec.2005.10.010]
[42]
Wang Z, Yang H, Wu Z, et al. In silico prediction of blood-brain barrier permeability of compounds by machine learning and resampling methods. ChemMedChem 2018; 13(20): 2189-201.
[http://dx.doi.org/10.1002/cmdc.201800533] [PMID: 30110511]
[43]
Margulis E, Dagan-Wiener A, Ives RS, Jaffari S, Siems K, Niv MY. Intense bitterness of molecules: Machine learning for expediting drug discovery. Comput Struct Biotechnol J 2021; 19: 568-76.
[http://dx.doi.org/10.1016/j.csbj.2020.12.030] [PMID: 33510862]
[44]
Shi X, Wong YD, Li MZF, Palanisamy C, Chai C. A feature learning approach based on XGBoost for driving assessment and risk prediction. Accid Anal Prev 2019; 129: 170-9.
[http://dx.doi.org/10.1016/j.aap.2019.05.005] [PMID: 31154284]
[45]
Sang X, Xiao W, Zheng H, Yang Y, Liu T. HMMPred: Accurate prediction of dna-binding proteins based on HMM profiles and XGBOOST feature selection. Comput Math Methods Med 2020; 2020: 1-10.
[http://dx.doi.org/10.1155/2020/1384749] [PMID: 32300371]
[46]
Shen M, LeTiran A, Xiao Y, Golbraikh A, Kohn H, Tropsha A. Quantitative structure-activity relationship analysis of functionalized amino acid anticonvulsant agents using k nearest neighbor and simulated annealing PLS methods. J Med Chem 2002; 45(13): 2811-23.
[http://dx.doi.org/10.1021/jm010488u] [PMID: 12061883]
[47]
Iorga A, Dara L. Cell death in drug-induced liver injury. Adv Pharmacol 2019; 85: 31-74.
[http://dx.doi.org/10.1016/bs.apha.2019.01.006] [PMID: 31307591]
[48]
Chipuk JE, Green DR. PUMA cooperates with direct activator proteins to promote mitochondrial outer membrane permeabilization and apoptosis. Cell Cycle 2009; 8(17): 2692-6.
[http://dx.doi.org/10.4161/cc.8.17.9412] [PMID: 19652530]
[49]
Nakano K, Vousden KH. PUMA, a novel proapoptotic gene, is induced by p53. Mol Cell 2001; 7(3): 683-94.
[http://dx.doi.org/10.1016/S1097-2765(01)00214-3] [PMID: 11463392]
[50]
Lu L, Finegold MJ, Johnson RL. Hippo pathway coactivators Yap and Taz are required to coordinate mammalian liver regeneration. Exp Mol Med 2018; 50(1): e423.
[http://dx.doi.org/10.1038/emm.2017.205] [PMID: 29303509]
[51]
Teperino R, Aberger F, Esterbauer H, Riobo N, Pospisilik JA. Canonical and non-canonical Hedgehog signalling and the control of metabolism. Semin Cell Dev Biol 2014; 33: 81-92.
[http://dx.doi.org/10.1016/j.semcdb.2014.05.007] [PMID: 24862854]
[52]
Jin L, Huang H, Ni J, et al. Shh‐Yap signaling controls hepatic ductular reactions in CCl 4 ‐induced liver injury. Environ Toxicol 2021; 36(2): 194-203.
[http://dx.doi.org/10.1002/tox.23025] [PMID: 32996673]
[53]
Narendra D, Tanaka A, Suen DF, Youle RJ. Parkin is recruited selectively to impaired mitochondria and promotes their autophagy. J Cell Biol 2008; 183(5): 795-803.
[http://dx.doi.org/10.1083/jcb.200809125] [PMID: 19029340]
[54]
Wang H, Ni HM, Chao X, et al. Double deletion of PINK1 and Parkin impairs hepatic mitophagy and exacerbates acetaminophen-induced liver injury in mice. Redox Biol 2019; 22: 101148.
[http://dx.doi.org/10.1016/j.redox.2019.101148] [PMID: 30818124]
[55]
Zou GL, Zuo S, Lu S, et al. Bone morphogenetic protein-7 represses hepatic stellate cell activation and liver fibrosis via regulation of TGF-β/Smad signaling pathway. World J Gastroenterol 2019; 25(30): 4222-34.
[http://dx.doi.org/10.3748/wjg.v25.i30.4222] [PMID: 31435175]
[56]
Budak H, Ceylan H, Kocpinar EF, Gonul N, Erdogan O. Expression of glucose-6-phosphate dehydrogenase and 6-phosphogluconate dehydrogenase in oxidative stress induced by long-term iron toxicity in rat liver. J Biochem Mol Toxicol 2014; 28(5): 217-23.
[http://dx.doi.org/10.1002/jbt.21556] [PMID: 24599681]
[57]
Albano E. Alcohol, oxidative stress and free radical damage. Proc Nutr Soc 2006; 65(3): 278-90.
[http://dx.doi.org/10.1079/PNS2006496] [PMID: 16923312]
[58]
Németh Z, Szász AM, Tátrai P, et al. Claudin-1, -2, -3, -4, -7, -8, and -10 protein expression in biliary tract cancers. J Histochem Cytochem 2009; 57(2): 113-21.
[http://dx.doi.org/10.1369/jhc.2008.952291] [PMID: 18854598]
[59]
Grosse B, Cassio D, Yousef N, Bernardo C, Jacquemin E, Gonzales E. Claudin-1 involved in neonatal ichthyosis sclerosing cholangitis syndrome regulates hepatic paracellular permeability. Hepatology 2012; 55(4): 1249-59.
[http://dx.doi.org/10.1002/hep.24761] [PMID: 22030598]
[60]
Juntilla MM, Patil VD, Calamito M, Joshi RP, Birnbaum MJ, Koretzky GA. AKT1 and AKT2 maintain hematopoietic stem cell function by regulating reactive oxygen species. Blood 2010; 115(20): 4030-8.
[http://dx.doi.org/10.1182/blood-2009-09-241000] [PMID: 20354168]
[61]
Larson-Casey JL, Deshane JS, Ryan AJ, Thannickal VJ, Carter AB. Macrophage Akt1 kinase-mediated mitophagy modulates apoptosis resistance and pulmonary fibrosis. Immunity 2016; 44(3): 582-96.
[http://dx.doi.org/10.1016/j.immuni.2016.01.001] [PMID: 26921108]
[62]
Klaassen CD, Aleksunes LM. Xenobiotic, bile acid, and cholesterol transporters: Function and regulation. Pharmacol Rev 2010; 62(1): 1-96.
[http://dx.doi.org/10.1124/pr.109.002014] [PMID: 20103563]
[63]
Hao C, Ma X, Wang L, et al. Predicting the presence and mechanism of busulfan drug-drug interactions in hematopoietic stem cell transplantation using pharmacokinetic interaction network–based molecular structure similarity and network pharmacology. Eur J Clin Pharmacol 2021; 77(4): 595-605.
[http://dx.doi.org/10.1007/s00228-020-03034-4] [PMID: 33179758]
[64]
Jiménez-Torres C, Hernández-Kelly LC, Najimi M, Ortega A. Bisphenol A exposure disrupts aspartate transport in HepG2 cells. J Biochem Mol Toxicol 2020; 34(8): e22516.
[http://dx.doi.org/10.1002/jbt.22516] [PMID: 32363662]
[65]
Najimi M, Stéphenne X, Sempoux C, Sokal E. Regulation of hepatic EAAT-2 glutamate transporter expression in human liver cholestasis. World J Gastroenterol 2014; 20(6): 1554-64.
[http://dx.doi.org/10.3748/wjg.v20.i6.1554] [PMID: 24587631]
[66]
Zhou SL, Zhou ZJ, Hu ZQ, et al. Tumor-associated neutrophils recruit macrophages and t-regulatory cells to promote progression of hepatocellular carcinoma and resistance to sorafenib. Gastroenterology 2016; 150(7): 1646-1658.e17.
[http://dx.doi.org/10.1053/j.gastro.2016.02.040] [PMID: 26924089]
[67]
Yamada T, Dawson TM, Yanagawa T, Iijima M, Sesaki H. SQSTM1/p62 promotes mitochondrial ubiquitination independently of PINK1 and PRKN/parkin in mitophagy. Autophagy 2019; 15(11): 2012-8.
[http://dx.doi.org/10.1080/15548627.2019.1643185] [PMID: 31339428]
[68]
Bruening J, Lasswitz L, Banse P, et al. Hepatitis C virus enters liver cells using the CD81 receptor complex proteins calpain-5 and CBLB. PLoS Pathog 2018; 14(7): e1007111.
[http://dx.doi.org/10.1371/journal.ppat.1007111] [PMID: 30024968]
[69]
Alves Pedroso ML, Boldt ABW, Pereira-Ferrari L, et al. Mannan-binding lectin MBL2 gene polymorphism in chronic hepatitis C: association with the severity of liver fibrosis and response to interferon therapy. Clin Exp Immunol 2008; 152(2): 258-64.
[http://dx.doi.org/10.1111/j.1365-2249.2008.03614.x] [PMID: 18336595]
[70]
Collins GA, Goldberg AL. The Logic of the 26S Proteasome. Cell 2017; 169(5): 792-806.
[http://dx.doi.org/10.1016/j.cell.2017.04.023] [PMID: 28525752]
[71]
Wang Y, Liu Z, Shu S, Cai J, Tang C, Dong Z. AMPK/mTOR signaling in autophagy regulation during cisplatin-induced acute kidney injury. Front Physiol 2020; 11: 619730.
[http://dx.doi.org/10.3389/fphys.2020.619730] [PMID: 33391038]
[72]
Wang H, Zhang J, Lu Z, et al. Identification of potential therapeutic targets and mechanisms of COVID-19 through network analysis and screening of chemicals and herbal ingredients. Brief Bioinform 2021; 23(1): bbab 373.
[PMID: 34505138]