scholarly journals A New Structure-Activity Relationship (SAR) Model for Predicting Drug-Induced Liver Injury, Based on Statistical and Expert-Based Structural Alerts

2016 ◽  
Vol 7 ◽  
Author(s):  
Fabiola Pizzo ◽  
Anna Lombardo ◽  
Alberto Manganaro ◽  
Emilio Benfenati
Keyword(s):  
Liver Injury ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Drug Induced ◽  
Drug Induced Liver Injury ◽  
Structure Activity ◽  
Sar Model ◽  
Structural Alerts

scholarly journals Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Anika Liu ◽  
Moritz Walter ◽  
Peter Wright ◽  
Aleksandra Bartosik ◽  
Daniela Dolciami ◽  
...  
Keyword(s):  
Liver Injury ◽  
Chemical Structure ◽  
Prediction Models ◽  
Safety Concern ◽  
Predictive Performance ◽  
Support Vector ◽  
Drug Induced ◽  
Protein Targets ◽  
Drug Induced Liver Injury ◽  
Structural Alerts

Abstract Background Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models. Results As part of the Critical Assessment of Massive Data Analysis (CAMDA) “CMap Drug Safety Challenge” 2019 (http://camda2019.bioinf.jku.at), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose. Conclusion Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.

scholarly journals Prediction and mechanistic analysis of Drug-Induced Liver Injury (DILI) based on chemical structure

2020 ◽  
Author(s):  
Anika Liu ◽  
Moritz Walter ◽  
Peter Wright ◽  
Aleksandra Maria Bartosik ◽  
Daniela Dolciami ◽  
...  
Keyword(s):  
Liver Injury ◽  
Chemical Structure ◽  
Prediction Models ◽  
Safety Concern ◽  
Predictive Performance ◽  
Support Vector ◽  
Drug Induced ◽  
Protein Targets ◽  
Drug Induced Liver Injury ◽  
Structural Alerts

Abstract Background: Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models.Results: As part of the Critical Assessment of Massive Data Analysis (CAMDA) “CMap Drug Safety Challenge” 2019 (http://papers.camda.info/), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold cross-validation inside a 10-fold training scheme of 0.759±0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, and the previously established stress response pathways mediated by mitochondria, p38 MAPK and TP53. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DDR2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose.Conclusion: Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.

scholarly journals Structure-Activity Relationship (SAR) and in vitro Predictions of Mutagenic and Carcinogenic Activities of Ixodicidal Ethyl-Carbamates

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
María G. Prado-Ochoa ◽  
Maribel Strassburger-Madrigal ◽  
Rafael Camacho-Carranza ◽  
Jesús J. Espinosa-Aguirre ◽  
Ana M. Velázquez-Sánchez ◽  
...  
Keyword(s):  
Mutagenic Activity ◽  
Metabolic Activation ◽  
Structure Activity Relationship ◽  
Test System ◽  
Egg Laying ◽  
Activity Relationship ◽  
Structure Activity ◽  
Structural Alerts ◽  
Sar Analysis

Ethyl-4-bromophenyl-carbamate (LQM 919) and Ethyl-4-chlorophenyl-carbamate (LQM 996) are compounds that inhibit egg-laying and hatching of tick larvae that are resistant to conventional ixodicides. The structure-activity relationship (SAR) to get the endpoint predictions of mutagenicity and carcinogenicity of the LQM 919 and LQM 996 was performed and the absence of mutagenicity was confirmed by Ames test. SAR analysis show no structural alerts indicating the ability of ethyl-carbamates to bind biomolecules or estrogen receptors. Endpoint of mutagenicity with and without metabolic activation showed that the ethyl-carbamates were negative (p <0.05) for mutagenicity induction in strains TA97, TA98, TA102, TA1535, TA1537 and TA1538 of Salmonella typhimurium. Pre-incubation with different ethyl-carbamate concentrations did not increase the number of spontaneously reverting colonies; moreover, the compounds did not induce a concentration-dependent increase in the number of reverting colonies in any of the strains used. This confirmed the absence of mutagenic activity in this test system. Exogenous metabolic activation did not modify these observations; suggesting that no metabolites with mutagenic activity were present. The endpoint of carcinogenicity in rats were negative for LQM 919 (p <0.05,) and LQM 996 (p <0.001). The results of the present study strongly suggest that ethyl-carbamates do not represent a risk for cancer in mammals.

Sign in / Sign up

Export Citation Format

Share Document