Related Experiment Video
Updated: Jul 6, 2025
Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro
Published on: January 31, 2022
InterDILI: interpretable prediction of drug-induced liver injury through permutation feature importance and attention
Soyeon Lee1,2, Sunyong Yoo3
1Department of ICT Convergence System Engineering, Chonnam National University, Gwangju, 61186, Republic of Korea.
Abstract:
Safety is one of the important factors constraining the distribution of clinical drugs on the market. Drug-induced liver injury (DILI) is the leading cause of safety problems produced by drug side effects. Therefore, the DILI risk of approved drugs and potential drug candidates should be assessed. Currently, in vivo and in vitro methods are used to test DILI risk, but both methods are labor-intensive, time-consuming, and expensive. To overcome these problems, many in silico methods for DILI prediction have been suggested. Previous studies have shown that DILI prediction models can be utilized as prescreening tools, and they achieved a good performance. However, there are still limitations in interpreting the prediction results. Therefore, this study focused on interpreting the model prediction to analyze which features could potentially cause DILI. For this, five publicly available datasets were collected to train and test the model. Then, various machine learning methods were applied using substructure and physicochemical descriptors as inputs and the DILI label as the output. The interpretation of feature importance was analyzed by recognizing the following general-to-specific patterns: (i) identifying general important features of the overall DILI predictions, and (ii) highlighting specific molecular substructures which were highly related to the DILI prediction for each compound. The results indicated that the model not only captured the previously known properties to be related to DILI but also proposed a new DILI potential substructural of physicochemical properties. The models for the DILI prediction achieved an area under the receiver operating characteristic (AUROC) of 0.88-0.97 and an area under the Precision-Recall curve (AUPRC) of 0.81-0.95. From this, we hope the proposed models can help identify the potential DILI risk of drug candidates at an early stage and offer valuable insights for drug development.
Insights
This study developed interpretable machine learning models to predict drug-induced liver injury (DILI). The models identify key molecular features, aiding early-stage DILI risk assessment in drug development.
Area of Science:
- Pharmacology
- Computational Chemistry
- Toxicology
Background:
- Drug-induced liver injury (DILI) is a major safety concern limiting drug distribution.
- Current in vivo and in vitro DILI assessment methods are costly and time-consuming.
- Interpreting DILI prediction models remains a challenge.
Purpose of the Study:
- To develop interpretable in silico models for predicting DILI risk.
- To identify specific molecular features and physicochemical properties associated with DILI.
- To aid early-stage identification of potential DILI risks in drug candidates.
Main Methods:
- Collected five public datasets for DILI prediction model training and testing.
- Applied machine learning methods using substructure and physicochemical descriptors as input.
- Analyzed feature importance to identify general and specific DILI-related molecular patterns.
Main Results:
- Achieved high performance with AUROC of 0.88-0.97 and AUPRC of 0.81-0.95.
- Identified known DILI-associated properties and proposed novel substructural features.
- Successfully interpreted model predictions to highlight DILI-related molecular substructures.
Conclusions:
- The developed interpretable models can effectively predict DILI risk.
- The findings offer valuable insights into DILI mechanisms and potential drug candidates.
- This approach facilitates early-stage DILI risk assessment in drug development.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:23Author Spotlight: Developing a Simple and Robust Hepatic Model for Pharmacological and Toxicological Applications
Published on: October 20, 2023
Related Concept Videos
01:07Physiological Pharmacokinetic Models: Incorporating Hepatic Transporter-Mediated Clearance
A recent model describes pravastatin's hepatobiliary excretion,...
01:16Drug Biotransformation: Overview
01:20Factors Affecting Dissolution: Drug Permeability, Stability and Stereochemistry
01:14Hepatic Drug Clearance: Role of Transporters
01:23Factors Affecting Protein-Drug Binding: Drug Interactions
Displacement interactions can have varying outcomes, ranging from toxicity to virtually...
01:15Factors Affecting Drug Distribution: Organ Perfusion Rate
Perfusion rate-limited distribution relies on the...