Integrating Drug’s Mode of Action into Quantitative Structure–Activity Relationships for Improved Prediction of Drug-Induced Liver Injury

Abstract

Drug-induced liver injury (DILI) is complex in mechanism. Different drugs could undergo different mechanisms but result in the same DILI type while the same drug could lead to different DILI types via different mechanisms. Therefore, predicting a drug’s potential for DILI should take its underlying mechanisms into consideration. To achieve that, we constructed a novel approach by incorporating drug’s Mode of Action (MOA) into Quantitative Structure-Activity Relationship (QSAR) modeling. This MOA-DILI approach was examined using a dataset of 333 drugs. The drugs were first grouped according to their MOA profiles (positive or negative in each MOA) based on the Tox21 qHTS assays. QSAR models for individual MOA assays were developed and subsequently combined to obtain the MOA-DILI model. A hold-out testing strategy (222 drugs for training and 111 drugs as a test set) was employed, which yielded the predictive accuracy of 0.711. For comparison, the MOA-DILI model was directly compared with the standard QSAR approach using the same hold-out strategy, and the QSAR model yielded an accuracy of 0.662. To minimize the random chance in splitting training/test sets, the hold-out testing process was repeated 1000 times, and the observed difference in prediction accuracy between MOA-DILI and QSARs was statistically significant (P-value<0.0001). Out of 17 MOAs used, 4 assays (i.e., antioxidant response elements, PPAR-gamma, estrogen receptor, and thyroid receptor assays) contributed most to the improved prediction of the MOA-DILI model over QSARs. In conclusion, the MOA-DILI approach has the potential to significantly improve predictive outcomes and to reveal complex relationships between MOAs and DILI, all of which would be helpful in developing DILI predictive models in drug screening and for risk assessment of industrial chemicals.

Applicability Domains Enhance Application of PPARγ Agonist Classifiers Trained by Drug-like Compounds to Environmental Chemicals

“…With different ADs, the non-3D Mordred descriptors-based and MACCS keys based classifiers achieved average AUCs over 0.86 (Table ), which is comparable to the CV AUCs of previously reported Tox21-databased classifiers. ,, Exceptionally, the ECFP4 fingerprints-based classifiers performed much worse on the compounds selected by AD MACCS_Keys {1, 0.69} than on all 40 compounds of the EHT set. ECFP4 fingerprints theoretically can describe an unlimited number of specific fragment patterns, which were developed specifically for structure–activity modeling .…”

Can Transcriptomic Profiles from Cancer Cell Lines Be Used for Toxicity Assessment?

“…DILI is a complex clinical end point and poses a challenge to the pharmaceutical industry and to regulatory agencies due to inadequate methods of prediction. − Many DILI prediction models have been developed on the basis of information such as chemical structures, − toxicogenomics profiles, and high-throughput screening (HTS) assays . These models have improved DILI management to some extent.…”

Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets

“…In predictive toxicology, AI and Machine Learning (ML) also have been widely investigated for chemical risk assessment and drug safety evaluation. In the past decades, our group developed numerous predictive toxicology approaches and tools in this area, particularly for drug-induced liver injury (DILI) − and toxicogenomics. − The combination of high throughput screening and ML has also become an important direction in predictive toxicology. − For instance, the Tox21 project has screened over 10,000 chemical compounds via robotic automated high-throughput in vitro assays to measure corresponding bioactivities, an unprecedented achievement which provided millions of chemical bioactivity profiles and data points. , …”