基于大鼠血清胆酸盐水平构建药物性肝损伤随机森林分类模型

doi:10.5246/jcps.2022.09.057

中国药学(英文版) ›› 2022, Vol. 31 ›› Issue (9): 677-688.DOI: 10.5246/jcps.2022.09.057

基于大鼠血清胆酸盐水平构建药物性肝损伤随机森林分类模型

靳永文¹, 席莉莉¹, 魏玉辉¹, 武新安¹^,²^,^*()

1. 兰州大学第一医院药剂科, 甘肃兰州 730000
2. 兰州大学药学院, 甘肃兰州 730000

收稿日期:2022-04-12 修回日期:2022-05-09 接受日期:2022-06-11 出版日期:2022-09-30 发布日期:2022-09-30
通讯作者: 武新安
作者简介:
+ Tel.: +86-13519318621, E-mail: wuxa@lzu.edu.cn
基金资助:
The Research Foundation of Education Bureau of Gansu Province, China (Grant No. 2020B-013); the Foundation of the First Hospital Lanzhou University (Grant No. ldyyyn2018-10), and the Engineering Research Centre of Prevention and Control for Clinical Medication Risk, Gansu Province.

Recognition of specific types of drug-induced liver injury using random forest algorithm: the importance of individual serum bile acid level

Yongwen Jin¹, Lili Xi¹, Yuhui Wei¹, Xinan Wu¹^,²^,^*()

1 Department of Pharmacy, the First Hospital of Lanzhou University, Lanzhou 730000, China
2 School of Pharmacy, Lanzhou University, Lanzhou 730000, China

Received:2022-04-12 Revised:2022-05-09 Accepted:2022-06-11 Online:2022-09-30 Published:2022-09-30
Contact: Xinan Wu

摘要/Abstract

摘要：

药物性肝损伤(DILI)与体内胆酸盐(BAs)稳态的失衡有关。然而, 胆酸盐与不同类型DILI的关联性尚不明确。本研究以17种胆酸盐为变量建立一种基于随机森林法(RF)的DILI分型评估模型, 探讨其在预测DILI分型中的价值。大鼠分别给予7种造模药物(异烟肼、对乙酰氨基酚、苄达赖氨酸、17α-炔雌醇、1-萘异硫氰酸酯、四环素和噻氯匹定)诱导肝细胞坏死型肝损、胆汁淤积型肝损伤和脂肪变性型肝损伤; 采用LC-MS/MS方法测定大鼠血清中17种胆酸盐含量; 建立RF分类模型; 通过抽一法(LOO)交互检验对所有BAs的预测能力权重进行重要性排序。结果表明RF模型具有较好的预测性能, LOO法验证、训练集和外部测试集的准确度分别为0.98、0.97和1.00; BAs的预测能力权重重要性排序为TUDCA > GUDCA > TCA > THDCA; RF模型对肝细胞坏死型、胆汁淤积型和脂肪变性型预测的特异性分别为0.94、1.00和1.00。以上结果提示不同类型DILI血清中BAs含量变化不同, 基于BAs含量变化建立的RF模型对DILI进行分类准确度较高。

关键词: 药物性肝损伤, 胆酸盐, 随机森林

Abstract:

Drug-induced liver injury (DILI) is associated with an imbalance in the homeostasis of bile salts (BAs). However, a clear connection between BAs and different types of DILI remains to be established. In the present study, random forest (RF) machine learning prediction systems were deployed with 17 individual BAs for categorizing DILI. BAs were analyzed via LC-MS/MS in the serum using the model of seven known hepatotoxins (isoniazid, acetaminophen, bendazac, 17α-ethinylestradiol, 1-naphthylisothiocyanate, tetracycline, and ticlopidine), which caused cholestasis, steatosis, and necrosis in rats. The RF model was validated via leave-one-out cross-validation. The importance of each individual BA with respect to prediction ability was determined. The RF model achieved the best prediction performance, producing accuracy values of 0.98, 0.97, and 1.00 for leave-one-out cross-validation, the training set, and the external test set, respectively. The order of descriptor’s importance was obtained, which was TUDCA > GUDCA > TCA > THDCA. The specificity values for necrosis, cholestasis, and steatosis were 0.94, 1.00, and 1.00, respectively. The results indicated the potential value of individual BA level in serum for categorizing DILI. The RF model in the present work was an inexpensive and readily available tool for categorizing DILI.

Key words: Drug-induced liver injury, Bile acids, Random forest

Supporting:

靳永文, 席莉莉, 魏玉辉, 武新安. 基于大鼠血清胆酸盐水平构建药物性肝损伤随机森林分类模型[J]. 中国药学(英文版), 2022, 31(9): 677-688.

Yongwen Jin, Lili Xi, Yuhui Wei, Xinan Wu. Recognition of specific types of drug-induced liver injury using random forest algorithm: the importance of individual serum bile acid level[J]. Journal of Chinese Pharmaceutical Sciences, 2022, 31(9): 677-688.

图/表 8

Table 1. The abbreviations of BAs.

Table 2. Hepatotoxins and their doses used in this study.

Table 3. Summary of toxicant and the clinical chemistry. The results are shown as mean ± SD (n = 8).

Figure 1. Photomicrography of liver sections. (A) Control group; (B) Isoniazid group; (C) Acetaminophen group; (D) Bendazac group; (E) 1-Naphthylisothiocyanate group; (F) 17α-Ethinylestradiol group; (G) Tetracycline group; (H) Ticlopidine group. Images of all groups were taken at × 400 magnification; black arrow indicates cell death and/or necrosis; red arrow indicates dilatation of the bile ducts; green arrow indicates fatty degeneration.

Figure 2. BA profile is significantly altered in the serum of rats following administration of various hepatotoxins. (a) Stack bar plot representing the proportion of unconjugated, glycine conjugated, and taurine conjugated BAs. (b) Stack bar plot representing the proportion of primary BAs and secondary BAs; (c) Heat map cells represent the fold change, defined as the ratio of the group means (n = 8), for a test group relative to its corresponding vehicle control. INH: isoniazid; APAP: acetaminophen; BDZ: Bendazac; TTC: tetracycline; TCP: ticlopidine; ANIT: 1-naphthylisothiocyanate; EE: 17α-ethinylestradiol.

Table 4. The performance of the built RF model based on internal and external validation.

Table 5. The performance of the best RF model.

Figure 3. The content change of TUDCA, GUDCA, TCA, and THDCA in the serum of rats following administration of various hepatotoxins. INH: isoniazid; APAP: acetaminophen; BDZ: bendazac; TTC: tetracycline; TCP: ticlopidine; ANIT: 1-naphthylisothiocyanate; EE: 17α-ethinylestradiol. *P < 0.05; **P < 0.01; ***P < 0.001 significantly different from the control group.

参考文献 34

[1]	Benichou, C. Criteria of drug-induced liver disorders: report of an International Consensus Meeting. J. Hepatol. 1990, 11, 272–276.
[2]	Sayuk, G.S.; Elwing, J.E.; Lisker-Melman, M. Hepatic glycogenosis: an underrecognized source of abnormal liver function tests? Dig. Dis. Sci. 2007, 52, 936–938.
[3]	Rautou, P.E.; Cazals-Hatem, D.; Moreau, R.; Francoz, C.; Feldmann, G.; Lebrec, D.; Ogier-Denis, É.; Bedossa, P.; Valla, D.; Durand, F. Acute liver cell damage in patients with anorexia nervosa: a possible role of starvation-induced hepatocyte autophagy. Gastroenterology. 2008, 135, 840–848.e3.
[4]	Browning, J.D.; Szczepaniak, L.S.; Dobbins, R.; Nuremberg, P.; Horton, J.D.; Cohen, J.C.; Grundy, S.M.; Hobbs, H.H. Prevalence of hepatic steatosis in an urban population in the United States: impact of ethnicity. Hepatology. 2004, 40, 1387–1395.
[5]	Chalasani, N.P.; Hayashi, P.H.; Bonkovsky, H.L.; Navarro, V.J.; Lee, W.M.; Fontana, R.J. ACG clinical guideline: the diagnosis and management of idiosyncratic drug-induced liver injury. Am. J. Gastroenterol. 2014, 109, 950–966.
[6]	Czaja, A.J. Drug-induced autoimmune-like hepatitis. Dig. Dis. Sci. 2011, 56, 958–976.
[7]	Luedde, T.; Kaplowitz, N.; Schwabe, R.F. Cell death and cell death responses in liver disease: mechanisms and clinical relevance. Gastroenterology. 2014, 147, 765–783.e4.
[8]	Chen, M.J.; Liu, C.; Wan, Y.; Yang, L.; Jiang, S.; Qian, D.W.; Duan, J.N. Enterohepatic circulation of bile acids and their emerging roles on glucolipid metabolism. Steroids. 2021, 165, 108757.
[9]	Li, M.; Cai, S.Y.; Boyer, J.L. Mechanisms of bile acid mediated inflammation in the liver. Mol. Aspects Med. 2017, 56, 45–53.
[10]	Pinto, C.; Giordano, D.M.; Maroni, L.; Marzioni, M. Role of inflammation and proinflammatory cytokines in cholangiocyte pathophysiology. Biochim. Biophys. Acta BBA Mol. Basis Dis. 2018, 1864, 1270–1278.
[11]	Chang, J.H.; Sangaraju, D.; Liu, N.; Jaochico, A.; Plise, E. Comprehensive evaluation of bile acid homeostasis in human hepatocyte co-culture in the presence of troglitazone, pioglitazone, and acetylsalicylic acid. Mol. Pharm. 2019, 16, 4230–4240.
[12]	Segev, N.; Harel, M.; Mannor, S.; Crammer, K.; El-Yaniv, R. Learn on source, refine on target: a model transfer learning framework with random forests. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 1811–1824.
[13]	Salem, G.A.; Shaban, A.; Diab, H.A.; Elsaghayer, W.A.; Mjedib, M.D.; Hnesh, A.M.; Sahu, R.P. Phoenix dactylifera protects against oxidative stress and hepatic injury induced by paracetamol intoxication in rats. Biomed. Pharmacother. 2018, 104, 366–374.
[14]	Gellin, B.; Modlin, J.F.; Breiman, R.F. Vaccines as tools for advancing more than public health: perspectives of a former director of the national vaccine program office. Clin. Infect Dis. 2001, 32, 283–288.
[15]	Hussein, M.A. Prophylactic effect of resveratrol against ethinylestradiol-induced liver cholestasis. J. Med. Food. 2013, 16, 246–254.
[16]	Wang, P.C.; Pradhan, K.; Zhong, X.B.; Ma, X.C. Isoniazid metabolism and hepatotoxicity. Acta Pharm. Sin. B. 2016, 6, 384–392.
[17]	Yamazaki, M.; Miyake, M.; Sato, H.; Masutomi, N.; Tsutsui, N.; Adam, K.P.; Alexander, D.C.; Lawton, K.A.; Milburn, M.V.; Ryals, J.A.; Wulff, J.E.; Guo, L.N. Perturbation of bile acid homeostasis is an early pathogenesis event of drug induced liver injury in rats. Toxicol. Appl. Pharmacol. 2013, 268, 79–89.
[18]	Alkiyumi, S.S.; Abdullah, M.A.; Alrashdi, A.S.; Salama, S.M.; Abdelwahab, S.I.; Hadi, A.H.A. Ipomoea aquatica extract shows protective action against thioacetamide-induced hepatotoxicity. Molecules. 2012, 17, 6146–6155.
[19]	Wagner, M.; Zollner, G.; Trauner, M. New molecular insights into the mechanisms of cholestasis. J. Hepatol. 2009, 51, 565–580.
[20]	Anderson, N.; Borlak, J. Molecular mechanisms and therapeutic targets in steatosis and steatohepatitis. Pharmacol. Rev. 2008, 60, 311–357.
[21]	Jaeschke, H.; McGill, M.R.; Ramachandran, A. Oxidant stress, mitochondria, and cell death mechanisms in drug-induced liver injury: lessons learned from acetaminophen hepatotoxicity. Drug Metab. Rev. 2012, 44, 88–106.
[22]	Younossi, Z.M.; Loomba, R.; Anstee, Q.M.; Rinella, M.E.; Bugianesi, E.; Marchesini, G.; Neuschwander-Tetri, B.A.; Serfaty, L.; Negro, F.; Caldwell, S.H.; Ratziu, V.; Corey, K.E.; Friedman, S.L.; Abdelmalek, M.F.; Harrison, S.A.; Sanyal, A.J.; Lavine, J.E.; Mathurin, P.; Charlton, M.R.; Goodman, Z.D.; Chalasani, N.P.; Kowdley, K.V.; George, J.; Lindor, K. Diagnostic modalities for nonalcoholic fatty liver disease, nonalcoholic steatohepatitis, and associated fibrosis. Hepatology. 2018, 68, 349–360.
[23]	Alnouti, Y.; Csanaky, I.L.; Klaassen, C.D. Quantitative-profiling of bile acids and their conjugates in mouse liver, bile, plasma, and urine using LC-MS/MS. J. Chromatogr. B. 2008, 873, 209–217.
[24]	Copple, B.; Jaeschke, H.; Klaassen, C. Oxidative stress and the pathogenesis of cholestasis. Semin. Liver Dis. 2010, 30, 195–204.
[25]	Rodrigues, C.M.P.; Solá, S.; Nan, Z.H.; Castro, R.E.; Ribeiro, P.S.; Low, W.C.; Steer, C.J. Tauroursodeoxycholic acid reduces apoptosis and protects against neurological injury after acute hemorrhagic stroke in rats. PNAS. 2003, 100, 6087–6092.
[26]	Hua, Y.N.; Kandadi, M.R.; Zhu, M.J.; Ren, J.; Sreejayan, N. Tauroursodeoxycholic acid attenuates lipid accumulation in endoplasmic reticulum–stressed macrophages. J. Cardiovasc. Pharmacol. 2010, 55, 49–55.
[27]	Woo, S.J.; Kim, J.H.; Yu, H.G. Ursodeoxycholic acid and tauroursodeoxycholic acid suppress choroidal neovascularization in a laser-treated rat model. J. Ocular Pharmacol. Ther. 2010, 26, 223–229.
[28]	Fernandes, A.; Vaz, A.R.; Falcão, A.S.; Silva, R.F.M.; Brito, M.A.; Brites, D. Glycoursodeoxycholic acid and interleukin-10 modulate the reactivity of rat cortical astrocytes to unconjugated bilirubin. J. Neuropathol. Exp. Neurol. 2007, 66, 789–798.
[29]	Brito, M.A.; Lima, S.; Fernandes, A.; Falcão, A.S.; Silva, R.F.M.; Butterfield, D.A.; Brites, D. Bilirubin injury to neurons: contribution of oxidative stress and rescue by glycoursodeoxycholic acid. NeuroToxicology. 2008, 29, 259–269.
[30]	Battson, M.L.; Lee, D.M.; Jarrell, D.K.; Hou, S.F.; Ecton, K.E.; Phan, A.B.; Gentile, C.L. Tauroursodeoxycholic acid reduces arterial stiffness and improves endothelial dysfunction in type 2 diabetic mice. J. Vasc. Res. 2017, 54, 280–287.
[31]	Hofmann, A.F. The continuing importance of bile acids in liver and intestinal disease. Arch. Intern. Med. 1999, 159, 2647.
[32]	Amaral J.D.; Xavier J.M.; Steer C.J.; Rodrigues C.M. The role of p53 in apoptosis. Discov. Med. 2010, 45, 145–152.
[33]	Wang, C.Y.; Li, L.; Guan, H.; Tong, S.; Liu, M.Q.; Liu, C.; Zhang, Z.Y.; Du, C.G.; Li, P.F. Effects of taurocholic acid on immunoregulation in mice. Int. Immunopharmacol. 2013, 15, 217–222.
[34]	Xu, Y.; Zhong, P.P.; Tao, Y.Y. Metabolic profiling of endogenous bile acids: a novel method to assess hepatoprotective effect of Tanreqing capsule on carbon-tetrachloride-induced liver injury in rats. Chin. J. Nat. Med. 2018, 16, 271–283.

基于大鼠血清胆酸盐水平构建药物性肝损伤随机森林分类模型

Recognition of specific types of drug-induced liver injury using random forest algorithm: the importance of individual serum bile acid level

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 34

相关文章 3

编辑推荐

Metrics

本文评价

[1]	沈洁, 杨凯, 孙彩华, 蒋程, 郑敏霞. 含何首乌的中成药致肝损伤的临床分析[J]. 中国药学(英文版), 2022, 31(4): 289-297.
[2]	靳永文, 饶志, 武艳芳, 张国强, 石阿茜, 魏玉辉, 武新安. 对乙酰氨基酚诱导的大鼠胆酸盐蓄积性肝损伤机制研究[J]. 中国药学(英文版), 2018, 27(7): 498-509.
[3]	李凤前, 胡晋红, 朱全刚. 大豆磷脂脂质载体与胆酸盐表面活性剂的体外相互作用[J]. , 2001, 10(3): 136-139.