Evaluation of Supervised Machine Learning Algorithms and Computational Structural Validation of Single Nucleotide Polymorphisms Related to Acute Liver Injury with Paracetamol.

Aims: To identify single nucleotide polymorphisms (SNPs) of paracetamol-metabolizing enzymes that can predict acute liver injury.

Background: Paracetamol is a commonly administered analgesic/antipyretic in critically ill and chronic renal failure patients and several SNPs influence the therapeutic and toxic effects.

Objective: To evaluate the role of machine learning algorithms (MLAs) and bioinformatics tools to delineate the predictor SNPs as well as to understand their molecular dynamics.

Methods: A cross-sectional study was undertaken by recruiting critically ill patients with chronic renal failure and administering intravenous paracetamol as a standard of care. Serum concentrations of paracetamol and the principal metabolites were estimated. Following SNPs were evaluated: . MLAs were used to identify the predictor genetic variable for acute liver failure. Bioinformatics tools such as Predict SNP2 and molecular docking (MD) were undertaken to evaluate the impact of the above SNPs with binding affinity to paracetamol.

Results: and genotypes were identified by MLAs to significantly predict hepatotoxicity. The predictSNP2 revealed that was highly deleterious in all the tools. MD revealed binding energy of -5.5 Kcal/mol, -6.9 Kcal/mol, and -6.8 Kcal/mol for , and against paracetamol. MD simulations revealed that and missense variants in affect the binding ability with paracetamol. In-silico techniques found that and are highly harmful. MD simulations revealed (A>G) had decreased binding energy with paracetamol than , and (A>T) and both have greater binding energy with paracetamol.

Conclusion: Polymorphisms in , and significantly influence paracetamol's clinical outcomes or binding affinity. Robust clinical studies are needed to identify these polymorphisms' clinical impact on the pharmacokinetics or pharmacodynamics of paracetamol.