1
|
Segovia-Zafra A, Villanueva-Paz M, Serras AS, Matilla-Cabello G, Bodoque-García A, Di Zeo-Sánchez DE, Niu H, Álvarez-Álvarez I, Sanz-Villanueva L, Godec S, Milisav I, Bagnaninchi P, Andrade RJ, Lucena MI, Fernández-Checa JC, Cubero FJ, Miranda JP, Nelson LJ. Control compounds for preclinical drug-induced liver injury assessment: Consensus-driven systematic review by the ProEuroDILI network. J Hepatol 2024; 81:630-640. [PMID: 38703829 DOI: 10.1016/j.jhep.2024.04.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Revised: 04/10/2024] [Accepted: 04/21/2024] [Indexed: 05/06/2024]
Abstract
BACKGROUND & AIMS Idiosyncratic drug-induced liver injury (DILI) is a complex and unpredictable event caused by drugs, and herbal or dietary supplements. Early identification of human hepatotoxicity at preclinical stages remains a major challenge, in which the selection of validated in vitro systems and test drugs has a significant impact. In this systematic review, we analyzed the compounds used in hepatotoxicity assays and established a list of DILI-positive and -negative control drugs for validation of in vitro models of DILI, supported by literature and clinical evidence and endorsed by an expert committee from the COST Action ProEuroDILI Network (CA17112). METHODS Following 2020 PRISMA guidelines, original research articles focusing on DILI which used in vitro human models and performed at least one hepatotoxicity assay with positive and negative control compounds, were included. Bias of the studies was assessed by a modified 'Toxicological Data Reliability Assessment Tool'. RESULTS A total of 51 studies (out of 2,936) met the inclusion criteria, with 30 categorized as reliable without restrictions. Although there was a broad consensus on positive compounds, the selection of negative compounds lacked clarity. 2D monoculture, short exposure times and cytotoxicity endpoints were the most tested, although there was no consensus on drug concentrations. CONCLUSIONS Extensive analysis highlighted the lack of agreement on control compounds for in vitro DILI assessment. Following comprehensive in vitro and clinical data analysis together with input from the expert committee, an evidence-based consensus-driven list of 10 positive and negative control drugs for validation of in vitro models of DILI is proposed. IMPACT AND IMPLICATIONS Prediction of human toxicity early in the drug development process remains a major challenge, necessitating the development of more physiologically relevant liver models and careful selection of drug-induced liver injury (DILI)-positive and -negative control drugs to better predict the risk of DILI associated with new drug candidates. Thus, this systematic study has crucial implications for standardizing the validation of new in vitro models of DILI. By establishing a consensus-driven list of positive and negative control drugs, the study provides a scientifically justified framework for enhancing the consistency of preclinical testing, thereby addressing a significant challenge in early hepatotoxicity identification. Practically, these findings can guide researchers in evaluating safety profiles of new drugs, refining in vitro models, and informing regulatory agencies on potential improvements to regulatory guidelines, ensuring a more systematic and efficient approach to drug safety assessment.
Collapse
Affiliation(s)
- Antonio Segovia-Zafra
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain
| | - Marina Villanueva-Paz
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain
| | - Ana Sofia Serras
- Research Institute for Medicines (iMed.ULisboa), Faculty of Pharmacy, Universidade de Lisboa, Lisbon, Portugal
| | - Gonzalo Matilla-Cabello
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain
| | - Ana Bodoque-García
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain
| | - Daniel E Di Zeo-Sánchez
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain
| | - Hao Niu
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain
| | - Ismael Álvarez-Álvarez
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain
| | - Laura Sanz-Villanueva
- Immunology and Diabetes Unit, St Vincent's Institute, Fitzroy VIC, Australia; Department of Medicine, St Vincent's Hospital, University of Melbourne, Fitzroy, VIC, Australia
| | - Sergej Godec
- Department of Anaesthesiology and Surgical Intensive Care, University Medical Centre Ljubljana, Ljubljana, Slovenia; Institute of Pathophysiology, Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia
| | - Irina Milisav
- Institute of Pathophysiology, Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia; Laboratory of oxidative stress research, Faculty of Health Sciences, University of Ljubljana, Ljubljana, Slovenia
| | - Pierre Bagnaninchi
- Centre for Regenerative Medicine, Institute for Regeneration and Repair, University of Edinburgh, Edinburgh, Scotland, United Kingdom
| | - Raúl J Andrade
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain; Plataforma de Investigación Clínica y Ensayos Clínicos UICEC-IBIMA, Plataforma ISCIII de Investigación Clínica, Madrid, Spain
| | - M Isabel Lucena
- Servicios de Aparato Digestivo y Farmacología Clínica, Hospital Universitario Virgen de la Victoria, Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND, Universidad de Málaga, Málaga, Spain; Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain; Plataforma de Investigación Clínica y Ensayos Clínicos UICEC-IBIMA, Plataforma ISCIII de Investigación Clínica, Madrid, Spain.
| | - José C Fernández-Checa
- Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain; Department of Cell Death and Proliferation, Institute of Biomedical Research of Barcelona (IIBB), CSIC, Barcelona, Spain; Liver Unit, Hospital Clinic I Provincial de Barcelona, Barcelona, Spain; Instituto de Investigaciones Biomédicas August Pi i Sunyer (IDIBAPS), Barcelona, Spain; Department of Medicine, Keck School of Division of Gastrointestinal and Liver disease, University of Southern California, Los Angeles, CA, United States.
| | - Francisco Javier Cubero
- Centro de Investigación Biomédica en Red Enfermedades Hepáticas y Digestivas (CIBERehd), Madrid, Spain; Department of Immunology, Ophthalmology and ORL, Complutense University School of Medicine, Madrid, Spain; Health Research Institute Gregorio Marañón (IiSGM), Madrid, Spain
| | - Joana Paiva Miranda
- Research Institute for Medicines (iMed.ULisboa), Faculty of Pharmacy, Universidade de Lisboa, Lisbon, Portugal
| | - Leonard J Nelson
- Institute for Bioengineering, School of Engineering, Faraday Building, The University of Edinburgh, Scotland, United Kingdom
| |
Collapse
|
2
|
Yu SM, Zheng HC, Wang SC, Rong WY, Li P, Jing J, He TT, Li JH, Ding X, Wang RL. Salivary metabolites are promising noninvasive biomarkers of drug-induced liver injury. World J Gastroenterol 2024; 30:2454-2466. [PMID: 38764769 PMCID: PMC11099387 DOI: 10.3748/wjg.v30.i18.2454] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/20/2024] [Revised: 04/05/2024] [Accepted: 04/18/2024] [Indexed: 05/11/2024] Open
Abstract
BACKGROUND Drug-induced liver injury (DILI) is one of the most common adverse events of medication use, and its incidence is increasing. However, early detection of DILI is a crucial challenge due to a lack of biomarkers and noninvasive tests. AIM To identify salivary metabolic biomarkers of DILI for the future development of noninvasive diagnostic tools. METHODS Saliva samples from 31 DILI patients and 35 healthy controls (HCs) were subjected to untargeted metabolomics using ultrahigh-pressure liquid chromatography coupled with tandem mass spectrometry. Subsequent analyses, including partial least squares-discriminant analysis modeling, t tests and weighted metabolite coexpression network analysis (WMCNA), were conducted to identify key differentially expressed metabolites (DEMs) and metabolite sets. Furthermore, we utilized least absolute shrinkage and selection operato and random fores analyses for biomarker prediction. The use of each metabolite and metabolite set to detect DILI was evaluated with area under the receiver operating characteristic curves. RESULTS We found 247 differentially expressed salivary metabolites between the DILI group and the HC group. Using WMCNA, we identified a set of 8 DEMs closely related to liver injury for further prediction testing. Interestingly, the distinct separation of DILI patients and HCs was achieved with five metabolites, namely, 12-hydroxydodecanoic acid, 3-hydroxydecanoic acid, tetradecanedioic acid, hypoxanthine, and inosine (area under the curve: 0.733-1). CONCLUSION Salivary metabolomics revealed previously unreported metabolic alterations and diagnostic biomarkers in the saliva of DILI patients. Our study may provide a potentially feasible and noninvasive diagnostic method for DILI, but further validation is needed.
Collapse
Affiliation(s)
- Si-Miao Yu
- School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 100029, China
| | - Hao-Cheng Zheng
- School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 100029, China
| | - Si-Ci Wang
- School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 100029, China
| | - Wen-Ya Rong
- School of Traditional Chinese Medicine, Southern Medical University, Guangzhou 510515, Guangdong Province, China
| | - Ping Li
- School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 100029, China
| | - Jing Jing
- Department of Hepatology of Traditional Chinese Medicine, The Fifth Medical Center of PLA General Hospital, Beijing 100039, China
| | - Ting-Ting He
- Department of Hepatology of Traditional Chinese Medicine, The Fifth Medical Center of PLA General Hospital, Beijing 100039, China
| | - Jia-Hui Li
- The First Clinical Medical College, Henan University of Traditional Chinese Medicine, Zhengzhou 450000, Henan Province, China
| | - Xia Ding
- School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 100029, China
| | - Rui-Lin Wang
- Department of Hepatology of Traditional Chinese Medicine, The Fifth Medical Center of PLA General Hospital, Beijing 100039, China
| |
Collapse
|
3
|
Tran TTV, Surya Wibowo A, Tayara H, Chong KT. Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives. J Chem Inf Model 2023; 63:2628-2643. [PMID: 37125780 DOI: 10.1021/acs.jcim.3c00200] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/02/2023]
Abstract
Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.
Collapse
Affiliation(s)
- Thi Tuyet Van Tran
- Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
- Faculty of Information Technology, An Giang University, Long Xuyen 880000, Vietnam
- Vietnam National University - Ho Chi Minh City, Ho Chi Minh 700000, Vietnam
| | - Agung Surya Wibowo
- Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
- Department of Electrical Engineering, Telkom University, Bandung 40257, Indonesia
| | - Hilal Tayara
- School of International Engineering and Science, Jeonbuk National University, Jeonju 54896, Republic of Korea
| | - Kil To Chong
- Advances Electronics and Information Research Center, Jeonbuk National University, Jeonju 54896, Republic of Korea
| |
Collapse
|
4
|
Nukaga T, Takemura A, Endo Y, Uesawa Y, Ito K. Estimating drug-induced liver injury risk by in vitro molecular initiation response and pharmacokinetic parameters for during early drug development. Toxicol Res (Camb) 2023; 12:86-94. [PMID: 36866207 PMCID: PMC9972805 DOI: 10.1093/toxres/tfac083] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2022] [Revised: 11/02/2022] [Accepted: 12/02/2022] [Indexed: 01/10/2023] Open
Abstract
Drug-induced liver injury (DILI) is a major factor influencing new drug withdrawal; therefore, an appropriate toxicity assessment at the preclinical stage is required. Previous in silico models have been established using compound information listed in large data sources, thereby limiting the DILI risk prediction for new drugs. Herein, we first constructed a model to predict DILI risk based on a molecular initiating event (MIE) predicted by quantitative structure-activity relationships, admetSAR parameters (e.g. cytochrome P450 reactivity, plasma protein binding, and water-solubility), and clinical information (maximum daily dose [MDD] and reactive metabolite [RM]) for 186 compounds. The accuracy of the models using MIE, MDD, RM, and admetSAR alone were 43.2%, 47.3%, 77.0%, and 68.9%, while the "predicted MIE + admetSAR + MDD + RM" model's accuracy was 75.7%. The contribution of MIE to the overall prediction accuracy was little effect or rather worsening it. However, it was considered that MIE was a valuable parameter and that it contributed to detect high DILI risk compounds in the early development stage. We next examined the effect of stepwise changes in MDD on altering the DILI risk and estimating the maximum safety dose (MSD) for clinical use based on structural information, admetSAR, and MIE parameters because it is important to estimate the dose that could prevent the DILI onset in clinical conditions. Low-MSD compounds might increase the DILI risk, as these compounds were classified as "most-DILI concern" at low doses. In conclusion, MIE parameters were especially useful to check the DILI concern compounds and to prevent the underestimation of DILI risk in the early stage of drug development.
Collapse
Affiliation(s)
- Takumi Nukaga
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University, Inohana 1-8-1, Chuo-ku, Chiba 260-8675, Japan
| | - Akinori Takemura
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University, Inohana 1-8-1, Chuo-ku, Chiba 260-8675, Japan
| | - Yuka Endo
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University, Inohana 1-8-1, Chuo-ku, Chiba 260-8675, Japan
| | - Yoshihiro Uesawa
- Department of Medical Molecular Informatics, Meiji Pharmaceutical University, 2-522-1 Noshio, Kiyose, Tokyo 204-8588, Japan
| | - Kousei Ito
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University, Inohana 1-8-1, Chuo-ku, Chiba 260-8675, Japan
| |
Collapse
|
5
|
Lim S, Kim Y, Gu J, Lee S, Shin W, Kim S. Supervised chemical graph mining improves drug-induced liver injury prediction. iScience 2022; 26:105677. [PMID: 36654861 PMCID: PMC9840932 DOI: 10.1016/j.isci.2022.105677] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2022] [Revised: 11/11/2022] [Accepted: 11/23/2022] [Indexed: 12/27/2022] Open
Abstract
Drug-induced liver injury (DILI) is the main cause of drug failure in clinical trials. The characterization of toxic compounds in terms of chemical structure is important because compounds can be metabolized to toxic substances in the liver. Traditional machine learning approaches have had limited success in predicting DILI, and emerging deep graph neural network (GNN) models are yet powerful enough to predict DILI. In this study, we developed a completely different approach, supervised subgraph mining (SSM), a strategy to mine explicit subgraph features by iteratively updating individual graph transitions to maximize DILI fidelity. Our method outperformed previous methods including state-of-the-art GNN tools in classifying DILI on two different datasets: DILIst and TDC-benchmark. We also combined the subgraph features by using SMARTS-based frequent structural pattern matching and associated them with drugs' ATC code.
Collapse
Affiliation(s)
- Sangsoo Lim
- Bioinformatics Institute, Seoul National University, Gwanak-ro 1, Seoul 08826, South Korea
| | - Youngkuk Kim
- Department of Computer Science and Engineering, Seoul National University, Gwanak-ro 1, Seoul 08826, South Korea
| | - Jeonghyeon Gu
- Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-ro 1, Seoul 08826, South Korea
| | - Sunho Lee
- AIGENDRUG Co., Ltd., Gwanak-ro 1, Seoul 08826, South Korea
| | - Wonseok Shin
- Department of Computer Science and Engineering, Seoul National University, Gwanak-ro 1, Seoul 08826, South Korea
| | - Sun Kim
- Department of Computer Science and Engineering, Seoul National University, Gwanak-ro 1, Seoul 08826, South Korea
- Interdisciplinary Program in Artificial Intelligence, Seoul National University, Gwanak-ro 1, Seoul 08826, South Korea
- AIGENDRUG Co., Ltd., Gwanak-ro 1, Seoul 08826, South Korea
- Corresponding author
| |
Collapse
|
6
|
Takemura A, Ito K. In Vitro Assay System to Detect Drug-Induced Bile Acid-Dependent Cytotoxicity Using Hepatocytes. Methods Mol Biol 2022; 2544:119-127. [PMID: 36125714 DOI: 10.1007/978-1-0716-2557-6_8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Inhibition of bile acid excretion by drugs is a significant factor in the development of drug-induced cholestatic liver injury. We constructed a new in vitro assay system to detect bile acid-dependent cytotoxicity in hepatocytes. This cell-based system can assess the toxicity of the parent compound, as well as the contribution of metabolite(s). In addition, this system can utilize several types of hepatocytes (primary hepatocytes, hepatoma cell line, and induced pluripotent stem cell-induced hepatocytes). In this chapter, a method to detect drug-induced bile acid-dependent toxicity in hepatocytes is described.
Collapse
Affiliation(s)
- Akinori Takemura
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University, Chiba, Japan
| | - Kousei Ito
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University, Chiba, Japan.
| |
Collapse
|
7
|
Kralj T, Brouwer KLR, Creek DJ. Analytical and Omics-Based Advances in the Study of Drug-Induced Liver Injury. Toxicol Sci 2021; 183:1-13. [PMID: 34086958 PMCID: PMC8502468 DOI: 10.1093/toxsci/kfab069] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
Drug-induced liver injury (DILI) is a significant clinical issue, affecting 1-1.5 million patients annually, and remains a major challenge during drug development-toxicity and safety concerns are the second-highest reason for drug candidate failure. The future prevalence of DILI can be minimized by developing a greater understanding of the biological mechanisms behind DILI. Both qualitative and quantitative analytical techniques are vital to characterizing and investigating DILI. In vitro assays are capable of characterizing specific aspects of a drug's hepatotoxic nature and multiplexed assays are capable of characterizing and scoring a drug's association with DILI. However, an even deeper insight into the perturbations to biological pathways involved in the mechanisms of DILI can be gained through the use of omics-based analytical techniques: genomics, transcriptomics, proteomics, and metabolomics. These omics analytical techniques can offer qualitative and quantitative insight into genetic susceptibilities to DILI, the impact of drug treatment on gene expression, and the effect on protein and metabolite abundance. This review will discuss the analytical techniques that can be applied to characterize and investigate the biological mechanisms of DILI and potential predictive biomarkers.
Collapse
Affiliation(s)
- Thomas Kralj
- Drug Delivery, Disposition and Dynamics, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, Australia
| | - Kim L R Brouwer
- Division of Pharmacotherapy and Experimental Therapeutics, UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599-7569, USA
| | - Darren J Creek
- Drug Delivery, Disposition and Dynamics, Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC, Australia
| |
Collapse
|
8
|
Zhang J, Norinder U, Svensson F. Deep Learning-Based Conformal Prediction of Toxicity. J Chem Inf Model 2021; 61:2648-2657. [PMID: 34043352 DOI: 10.1021/acs.jcim.1c00208] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Predictive modeling for toxicity can help reduce risks in a range of applications and potentially serve as the basis for regulatory decisions. However, the utility of these predictions can be limited if the associated uncertainty is not adequately quantified. With recent studies showing great promise for deep learning-based models also for toxicity predictions, we investigate the combination of deep learning-based predictors with the conformal prediction framework to generate highly predictive models with well-defined uncertainties. We use a range of deep feedforward neural networks and graph neural networks in a conformal prediction setting and evaluate their performance on data from the Tox21 challenge. We also compare the results from the conformal predictors to those of the underlying machine learning models. The results indicate that highly predictive models can be obtained that result in very efficient conformal predictors even at high confidence levels. Taken together, our results highlight the utility of conformal predictors as a convenient way to deliver toxicity predictions with confidence, adding both statistical guarantees on the model performance as well as better predictions of the minority class compared to the underlying models.
Collapse
Affiliation(s)
- Jin Zhang
- Department of Drug Metabolism and Pharmacokinetics, Janssen Pharmaceutica NV, B-2340 Beerse, Belgium
| | - Ulf Norinder
- Department of Computer and Systems Sciences, Stockholm University, P.O. Box 7003, SE-164 07 Kista, Sweden.,Department of Pharmaceutical Biosciences, Uppsala University, P.O. Box 591, SE-751 24 Uppsala, Sweden.,MTM Research Centre, School of Science and Technology, Örebro University, SE-701 82 Örebro, Sweden
| | - Fredrik Svensson
- The Alzheimer's Research UK University College London Drug Discovery Institute, The Cruciform Building, Gower Street, London WC1E 6BT, U.K
| |
Collapse
|
9
|
Chen SS, Huang Y, Guo YM, Li SS, Shi Z, Niu M, Zou ZS, Xiao XH, Wang JB. Serum Metabolomic Analysis of Chronic Drug-Induced Liver Injury With or Without Cirrhosis. Front Med (Lausanne) 2021; 8:640799. [PMID: 33855035 PMCID: PMC8039323 DOI: 10.3389/fmed.2021.640799] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2020] [Accepted: 03/08/2021] [Indexed: 12/25/2022] Open
Abstract
Background: Chronic drug-induced liver injury (DILI) occurs in up to 20% of all DILI patients. It presents a chronic pattern with persistent or relapsed episodes and may even progress to cirrhosis. However, its underlying development mechanism is poorly understood. Aims: To find serum metabolite signatures of chronic DILI with or without cirrhosis, and to elucidate the underlying mechanism. Methods: Untargeted metabolomics coupled with pattern recognition approaches were used to profile and extract metabolite signatures from 83 chronic DILI patients, including 58 non-cirrhosis (NC) cases, 14 compensated cirrhosis (CC) cases, and 11 decompensated cirrhosis (DC) cases. Results: Of the 269 annotated metabolites associated with chronic DILI, metabolic fingerprints associated with cirrhosis (including 30 metabolites) and decompensation (including 25 metabolites), were identified. There was a significantly positive correlation between cirrhosis-associated fingerprint (eigenmetabolite) and the aspartate aminotransferase-to-platelet ratio index (APRI) (r = 0.315, P = 0.003). The efficacy of cirrhosis-associated eigenmetabolite coupled with APRI to identify cirrhosis from non-cirrhosis patients was significantly better than APRI alone [area under the curve (AUC) value 0.914 vs. 0.573]. The decompensation-associated fingerprint (eigenmetabolite) can effectively identify the compensation and decompensation periods (AUC value 0.954). The results of the metabolic fingerprint pathway analysis suggest that the blocked tricarboxylic acid cycle (TCA cycle) and intermediary metabolism, excessive accumulation of bile acids, and perturbed amino acid metabolism are potential mechanisms in the occurrence and development of chronic DILI-associated cirrhosis. Conclusions: The metabolomic fingerprints characterize different stages of chronic DILI progression and deepen the understanding of the metabolic reprogramming mechanism of chronic DILI progression to cirrhosis.
Collapse
Affiliation(s)
- Shuai-shuai Chen
- School of Pharmacy, Chengdu University of Traditional Chinese Medicine, Chengdu, China
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Ying Huang
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Yu-ming Guo
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Shan-shan Li
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Zhuo Shi
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Ming Niu
- Department of Poisoning Treatment, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Zheng-sheng Zou
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Xiao-he Xiao
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
| | - Jia-bo Wang
- Department of Liver Diseases, The Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China
- School of Traditional Chinese Medicine, Capital Medical University, Beijing, China
| |
Collapse
|
10
|
Takemura A, Ito K. [The trends in predicting drug-induced liver injury]. Nihon Yakurigaku Zasshi 2020; 155:401-405. [PMID: 33132258 DOI: 10.1254/fpj.20049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Abstract
Drug-induced liver injury (DILI) is the major reason for the discontinuation of new drug development and the withdrawal of drugs from the market. Hence, the evaluation systems which predict the onset of DILI in the pre-clinical stage are needed. To date, many researchers have conducted the mechanism of DILI, but the DILI prediction is poor because of the complexity of DILI. In this regard, based on the information obtained from basic research and clinical case, several pharmaceutical companies have been developed DILI prediction methods with high sensitivity and specificity by combining multiple targets. Another reason for low predictability is derived from the conventional culture method which causes a rapid decrease in hepatocyte function. To overcome these problems, the construction of a high-level in vitro evaluation system has been developed and applied to DILI evaluation. On the other hand, these in vitro evaluation methods require a lot of labor and cost so, in silico prediction methods have also been constructed in recent years. Based on this point, this article reviews the trends in DILI prediction systems in the non-clinical stage.
Collapse
Affiliation(s)
- Akinori Takemura
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University
| | - Kousei Ito
- Laboratory of Biopharmaceutics, Graduate School of Pharmaceutical Sciences, Chiba University
| |
Collapse
|
11
|
Semenova E, Williams DP, Afzal AM, Lazic SE. A Bayesian neural network for toxicity prediction. ACTA ACUST UNITED AC 2020. [DOI: 10.1016/j.comtox.2020.100133] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
|