Machine Learning to Identify Interaction of Single-Nucleotide Polymorphisms as a Risk Factor for Chronic Drug-Induced Liver Injury

Abstract

Drug-induced liver injury (DILI) is a major cause of drug development failure and drug withdrawal from the market after approval. The identification of human risk factors associated with susceptibility to DILI is of paramount importance. Increasing evidence suggests that genetic variants may lead to inter-individual differences in drug response; however, individual single-nucleotide polymorphisms (SNPs) usually have limited power to predict human phenotypes such as DILI. In this study, we aim to identify appropriate statistical methods to investigate gene–gene and/or gene–environment interactions that impact DILI susceptibility. Three machine learning approaches, including Multivariate Adaptive Regression Splines (MARS), Multifactor Dimensionality Reduction (MDR), and logistic regression, were used. The simulation study suggested that all three methods were robust and could identify the known SNP–SNP interaction when up to 4% of genotypes were randomly permutated. When applied to a real-life DILI chronicity dataset, both MARS and MDR, but not logistic regression, identified combined genetic variants having better associations with DILI chronicity in comparison to the use of individual SNPs. Furthermore, a simple decision tree model using the SNPs identified by MARS and MDR was developed to predict DILI chronicity, with fair performance. Our study suggests that machine learning approaches may help identify gene–gene interactions as potential risk factors for better assessing complicated diseases such as DILI chronicity.

Novel progressive deep learning algorithm for uncovering multiple single nucleotide polymorphism interactions to predict paclitaxel clearance in patients with nonsmall cell lung cancer

“…The results showed that 1184 combinations and strategies achieved the highest fitness function value of 99.99. Conversely, when SNPS are randomly combined, there is a one in two [ 6 ] chance that the calculated result is the highest fitness function value, which is substantially lower than the value achieved using our mined results. These findings suggest there is a robust correlation between the mined SNP combinations, strategies, and paclitaxel clearance, and also underscore the efficacy of the GEP‐CSI data mining algorithm.…”

“…Such integration can elucidate the possible influences of SNPs on a phenotype, thereby refining the precision of the analysis. However, alternative techniques such as machine‐learning algorithms may offer a robust mechanism to discern intricate interplays between variables [ 5 , 6 ].…”

Artificial intelligence applied to omics data in liver diseases: Enhancing clinical predictions

“…The inclusion criteria set out to specifically predict DILI, as diagnosed by liver biopsy, was met by one study which utilized genomics data. The study by Moore et al employed three ML algorithms, multivariate adaptive regression splines (MARS), multifactor dimensionality reduction (MDR), and LR, with the aim of investigating single-nucleotide polymorphisms (SNPs) (Moore et al, 2021 ). The effect of SNP-SNP interactions on DILI susceptibility as well as their ability to predict DILI chronicity were observed.…”