Update 2024-drug-induced-liver-injury-integrating-in-vivo-vitro-data.md

content/publication/2024-drug-induced-liver-injury-integrating-in-vivo-vitro-data.md

@@ -1,15 +1,15 @@
 +++
 bibtex_type = "article"
-author="Seal S, Williams DP, Hosseini-Gerami L, Spjuth O, and Bender A."
+author="Seal S, Williams DP, Hosseini-Gerami L, Mahael M, Carpenter AE, Spjuth O, and Bender A."
 title="Improved Early Detection of Drug-Induced Liver Injury by Integrating Predicted in vivo and in vitro Data"
-journal="bioRxiv"
+journal="Chemical Research in Toxicology"
 year="2024"
-date="2024-02-12T00:00:00+01:55"
-volume="2024.01.10.575128"
+date="2024-07-09T00:00:00+01:55"
+volume="Online ahead of print"
 number=""
-preprint = true
+preprint = false
 pages=""
-abstract="Drug-induced liver injury (DILI) presents a significant challenge in drug discovery, often leading to clinical trial failures and necessitating drug withdrawals. In this study, we introduce a novel method for DILI prediction that first predicts eleven proxy-DILI labels and then uses them as features in addition to chemical structural features to predict DILI. The features include in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) data, in vivo (e.g., preclinical rat hepatotoxicity studies) data, pharmacokinetic parameters of maximum concentration, structural fingerprints, and physicochemical parameters. We trained DILI-prediction models on 1020 compounds from the DILIst dataset and tested on a held-out external test set of 255 compounds from DILIst dataset. The best model, DILIPredictor, attained a balanced accuracy of 70% and an LR+ score of 7.21. This model enabled the early detection of 26 toxic compounds compared to models using only structural features (4.62 LR+ score). Using feature interpretation from DILIPredictor, we were able to identify the chemical substructures causing DILI as well as differentiate cases DILI is caused by compounds in animals but not in humans. For example, DILIPredictor correctly recognized 2-butoxyethanol as non-toxic in humans despite its hepatotoxicity in mice models. Overall, the DILIPredictor model improves the detection of compounds causing DILI with an improved differentiation between animal and human sensitivity as well as the potential for mechanism evaluation. DILIPredictor is publicly available at https://broad.io/DILIPredictor for use via web interface and with all code available for download."
-doi="10.1101/2024.01.10.575128"
+abstract="Drug-induced liver injury (DILI) has been a significant challenge in drug discovery, often leading to clinical trial failures and necessitating drug withdrawals. Over the last decade, the existing suite of in vitro proxy-DILI assays has generally improved at identifying compounds with hepatotoxicity. However, there is considerable interest in enhancing the in silico prediction of DILI because it allows for evaluating large sets of compounds more quickly and cost-effectively, particularly in the early stages of projects. In this study, we aim to study ML models for DILI prediction that first predict nine proxy-DILI labels and then use them as features in addition to chemical structural features to predict DILI. The features include in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) data, in vivo (e.g., preclinical rat hepatotoxicity studies) data, pharmacokinetic parameters of maximum concentration, structural fingerprints, and physicochemical parameters. We trained DILI-prediction models on 888 compounds from the DILI data set (composed of DILIst and DILIrank) and tested them on a held-out external test set of 223 compounds from the DILI data set. The best model, DILIPredictor, attained an AUC-ROC of 0.79. This model enabled the detection of the top 25 toxic compounds (2.68 LR+, positive likelihood ratio) compared to models using only structural features (1.65 LR+ score). Using feature interpretation from DILIPredictor, we identified the chemical substructures causing DILI and differentiated cases of DILI caused by compounds in animals but not in humans. For example, DILIPredictor correctly recognized 2-butoxyethanol as nontoxic in humans despite its hepatotoxicity in mice models. Overall, the DILIPredictor model improves the detection of compounds causing DILI with an improved differentiation between animal and human sensitivity and the potential for mechanism evaluation. DILIPredictor required only chemical structures as input for prediction and is publicly available at https://broad.io/DILIPredictor for use via web interface and with all code available for download."
+doi="10.1021/acs.chemrestox.4c00015"
 url_html=""
 +++