The Promise of AI for DILI Prediction

Vall, Andreu; Sabnis, Yogesh; Shi, Jiye; Class, Reiner; Hochreiter, Sepp; Klambauer, Günter

doi:10.3389/frai.2021.638410

Cited by 41 publications

(37 citation statements)

References 81 publications

(169 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, only the two milder levels of fibrosis were included in the selection, as severe fibrosis was observed rarely. While we focus on the described definition of adverse histopathological findings in this study, the difficulty in summarising a complex phenotype such as DILI into a binary classification, adverse or not adverse, is well established [27, 28] and is also demonstrated by the discrepancies between DILI classifications from DILIst, DILIrank and those derived by Sutherland et al based on the TG-GATEs data (S1). We are aware that also broader or more targeted phenotypes might be of interest, and we hence provide a Shiny app where results for alternative definitions of adverse and non-adverse histopathology groups can be explored.…”

Section: Resultsmentioning

confidence: 99%

Deriving time-concordant event cascades from gene expression data: A case study for Drug-Induced Liver Injury (DILI)

Liu

Han

Munoz-Muriedas³

et al. 2021

Preprint

View full text Add to dashboard Cite

Adverse event pathogenesis is often a complex process which compromises multiple events ranging from the molecular to the phenotypic level. Adverse Outcome Pathways (AOPs) aim to formalize this as temporal sequences of events, in which event relationships should be supported by causal evidence according to the tailored Bradford-Hill criteria. One of the criteria is whether events are consistently observed in a certain temporal order and, in this work, we study this time concordance between gene expression- and histopathology-derived events as data-driven means to generate hypotheses on potentially causal mechanisms. As a case study, we analysed liver data from repeat-dose studies in rats from the TG-GATEs database which comprises measurements across eight timepoints, ranging from 3 hours to 4 weeks post-treatment. We identified time concordant pathway- and transcription factor (TF)- level events preceding adverse histopathology, which serves as surrogate readout for Drug-Induced Liver Injury (DILI). Among known events in DILI, we found some to change strongly before adverse histopathology, e.g. fatty acid beta oxidation, while others were more confident, e.g. bile acid recycling, or frequent, e.g. ATF4-mediated stress response, further characterizing their mechanistic roles. Moreover, we used the temporal order of TF expression and regulon activity to separate induced TFs, such as Cebpa, from post-transcriptionally activated ones, e.g. Srebf2, and subsequently combined this with known functional interactions (TF-target or protein-protein) to derive detailed gene-regulatory mechanisms, such as Hnf4a-dependent Cebpa expression. We additionally evaluate which time concordant events show sustained or increasing activation over time, as this time dependence is favourable for biomarker development, and identify pathways indicating dyslipidaemia, and a decrease in Hnf1a and Hnf4a indicating deteriorating liver function. At the same, time also potentially novel events are identified such as Sox13 which shows a more significant time dependence and -concordance than many known TFs in liver injury. Overall, we demonstrate how time-resolved transcriptomics can derive and support mechanistic hypotheses by quantifying time concordance and how this can be combined with prior causal knowledge, with the aim of both understanding mechanisms of toxicity, as well as potential applications to the AOP framework. We make our results available in the form of a Shiny app (https://github.com/anikaliu/DILICascades_App), which allows users to query events of interest in more detail.

show abstract

Section: Resultsmentioning

confidence: 99%

Deriving time-concordant event cascades from gene expression data: A case study for Drug-Induced Liver Injury (DILI)

Liu

Han

Munoz-Muriedas³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…New efforts to detect biomarkers of injured and necrotic hepatocytes seem promising, as it is important to identify APAP-induced acute liver injury patients at an early stage when lifesaving medical and surgical therapies can be provided. Going forward, AI approaches to predicting DILI could improve our understanding of the underlying mechanisms and our ability to anticipate hepatotoxicity for clinical applications [ 32 ].…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

et al. 2022

View full text Add to dashboard Cite

Although drug-induced liver injury (DILI) is a major target of the pharmaceutical industry, we currently lack an efficient model for evaluating liver toxicity in the early stage of its development. Recent progress in artificial intelligence-based deep learning technology promises to improve the accuracy and robustness of current toxicity prediction models. Mask region-based CNN (Mask R-CNN) is a detection-based segmentation model that has been used for developing algorithms. In the present study, we applied a Mask R-CNN algorithm to detect and predict acute hepatic injury lesions induced by acetaminophen (APAP) in Sprague-Dawley rats. To accomplish this, we trained, validated, and tested the model for various hepatic lesions, including necrosis, inflammation, infiltration, and portal triad. We confirmed the model performance at the whole-slide image (WSI) level. The training, validating, and testing processes, which were performed using tile images, yielded an overall model accuracy of 96.44%. For confirmation, we compared the model’s predictions for 25 WSIs at 20× magnification with annotated lesion areas determined by an accredited toxicologic pathologist. In individual WSIs, the expert-annotated lesion areas of necrosis, inflammation, and infiltration tended to be comparable with the values predicted by the algorithm. The overall predictions showed a high correlation with the annotated area. The R square values were 0.9953, 0.9610, and 0.9445 for necrosis, inflammation plus infiltration, and portal triad, respectively. The present study shows that the Mask R-CNN algorithm is a useful tool for detecting and predicting hepatic lesions in non-clinical studies. This new algorithm might be widely useful for predicting liver lesions in non-clinical and clinical settings.

show abstract

“…Advanced organ-on-a-chip and 3D models replicating the gut-liver axis with added microbiota components could represent the right direction for future interdisciplinary research in the DILI field [ 345 , 346 , 347 , 348 ]. Moreover, the implementation of in silico prediction models, machine learning methods, and the development of comprehensive databases could further assist in selecting better and safer candidates for drug development, and predicting, with high accuracy, potential DILI [ 349 , 350 , 351 , 352 ].…”

Section: Concluding Remarks and Future Perspectivesmentioning

confidence: 99%

Mitochondria as the Target of Hepatotoxicity and Drug-Induced Liver Injury: Molecular Mechanisms and Detection Methods

Mihajlovic

Vinken

2022

IJMS

View full text Add to dashboard Cite

One of the major mechanisms of drug-induced liver injury includes mitochondrial perturbation and dysfunction. This is not a surprise, given that mitochondria are essential organelles in most cells, which are responsible for energy homeostasis and the regulation of cellular metabolism. Drug-induced mitochondrial dysfunction can be influenced by various factors and conditions, such as genetic predisposition, the presence of metabolic disorders and obesity, viral infections, as well as drugs. Despite the fact that many methods have been developed for studying mitochondrial function, there is still a need for advanced and integrative models and approaches more closely resembling liver physiology, which would take into account predisposing factors. This could reduce the costs of drug development by the early prediction of potential mitochondrial toxicity during pre-clinical tests and, especially, prevent serious complications observed in clinical settings.

show abstract

The Promise of AI for DILI Prediction

Cited by 41 publications

References 81 publications

Deriving time-concordant event cascades from gene expression data: A case study for Drug-Induced Liver Injury (DILI)

Deriving time-concordant event cascades from gene expression data: A case study for Drug-Induced Liver Injury (DILI)

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

Mitochondria as the Target of Hepatotoxicity and Drug-Induced Liver Injury: Molecular Mechanisms and Detection Methods

Contact Info

Product

Resources

About