Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure

نویسندگان

چکیده

Abstract Background Drug-induced liver injury (DILI) is a major safety concern characterized by complex and diverse pathogenesis. In order to identify DILI early in drug development, better understanding of the models with predictivity are urgently needed. One approach this regard silico which aim at predicting risk based on compound structure. However, these do not yet show sufficient predictive performance or interpretability be useful for decision making themselves, former partially stemming from underlying problem labeling vivo compounds meaningful way generating machine learning models. Results As part Critical Assessment Massive Data Analysis (CAMDA) “CMap Drug Safety Challenge” 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based were generated using binarized DILIrank annotations. Support Vector Machine (SVM) Random Forest (RF) classifiers showed comparable previously published mean balanced accuracy over 5-fold LOCO-CV inside 10-fold training scheme 0.759 ± 0.027 when an external test set. used predicted protein targets as descriptors, we identified most information-rich proteins agreed mechanisms action toxicity nonsteroidal anti-inflammatory drugs (NSAIDs), one important classes causing DILI, stress response via TP53 biotransformation. addition, multiple involved xenobiotic metabolism could novel DILI-related off-targets, such CLK1 DYRK2. Moreover, derived potential structural alerts high precision, including furan hydrazine derivatives; however, all present approved specific indicating need consider quantitative variables dose. Conclusion Using descriptors fingerprints targets, prediction built previous literature. insights pathways statistically (and potentially causally) linked inferred new related adverse endpoint.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Letter of support for drug-induced liver injury (DILI) biomarker

The objectives of DILI WP3 were to qualify one or a set of new biomarkers with respect to: an early or earlier diagnosis of DILI as compared to current diagnostic rules the ability to predict DILI outcome, with particular emphasis on severe DILI/acute liver failure the prognosis and monitoring of progression and regression of DILI the differentiation between patients who incur true drug-induced...

متن کامل

The rediscovery of HepG2 cells for prediction of drug induced liver injury (DILI)

In the past HepG2 cells have been considered to show only little similarity to primary human hepatocytes (Godoy et al., 2013; Hewitt et al., 2007). However, recently it has become clear that the phenotype of HepG2 cells strongly depends on culture conditions. In a recent study, Ramaiahgari et al. (2014) cultivated HepG2 cells in spheroids. In this culture system the cells stopped proliferation ...

متن کامل

Setting Clinical Exposure Levels of Concern for Drug-Induced Liver Injury (DILI) Using Mechanistic in vitro Assays.

Severe drug-induced liver injury (DILI) remains a major safety issue due to its frequency of occurrence, idiosyncratic nature, poor prognosis, and diverse underlying mechanisms. Numerous experimental approaches have been published to improve human DILI prediction with modest success. A retrospective analysis of 125 drugs (70 = most-DILI, 55 = no-DILI) from the Food and Drug Administration Liver...

متن کامل

Recurrent drug-induced liver injury (DILI) with ciprofloxacin and amoxicillin/clavulanic.

Ciprofloxacin and amoxicillin/clavulanic are two widely used antibiotics due to their high efficacy and few side effects. While the percentage of hepatotoxicity of these antibiotics is low, their frequent use has led to a progressive increase in the number of cases. Both antibiotics have been associated with a wide variety of hepatotoxic reactions, from a slight rise of transaminases to fulmina...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Biology Direct

سال: 2021

ISSN: ['1745-6150']

DOI: https://doi.org/10.1186/s13062-020-00285-0