A novel machine learning-based approach for the computational functional assessment of pharmacogenomic variants

Abstract

Background The field of pharmacogenomics focuses on the way a person’s genome affects his or her response to a certain dose of a specified medication. The main aim is to utilize this information to guide and personalize the treatment in a way that maximizes the clinical benefits and minimizes the risks for the patients, thus fulfilling the promises of personalized medicine. Technological advances in genome sequencing, combined with the development of improved computational methods for the efficient analysis of the huge amount of generated data, have allowed the fast and inexpensive sequencing of a patient’s genome, hence rendering its incorporation into clinical routine practice a realistic possibility. Methods This study exploited thoroughly characterized in functional level SNVs within genes involved in drug metabolism and transport, to train a classifier that would categorize novel variants according to their expected effect on protein functionality. This categorization is based on the available in silico prediction and/or conservation scores, which are selected with the use of recursive feature elimination process. Toward this end, information regarding 190 pharmacovariants was leveraged, alongside with 4 machine learning algorithms, namely AdaBoost, XGBoost, multinomial logistic regression, and random forest, of which the performance was assessed through 5-fold cross validation. Results All models achieved similar performance toward making informed conclusions, with RF model achieving the highest accuracy (85%, 95% CI: 0.79, 0.90), as well as improved overall performance (precision 85%, sensitivity 84%, specificity 94%) and being used for subsequent analyses. When applied on real world WGS data, the selected RF model identified 2 missense variants, expected to lead to decreased function proteins and 1 to increased. As expected, a greater number of variants were highlighted when the approach was used on NGS data derived from targeted resequencing of coding regions. Specifically, 71 variants (out of 156 with sufficient annotation information) were classified as to “Decreased function,” 41 variants as “No” function proteins, and 1 variant in “Increased function.” Conclusion Overall, the proposed RF-based classification model holds promise to lead to an extremely useful variant prioritization and act as a scoring tool with interesting clinical applications in the fields of pharmacogenomics and personalized medicine.

A paradigm shift in pharmacogenomics: From candidate polymorphisms to comprehensive sequencing

“…In contrast, APF performance on the disease‐associated drug transporter SLC10A1 (NTCP) was not higher than other algorithms 52 . Similar to APF, another machine learning‐based model was recently developed with good performance in prioritizing NGS‐derived pharmacogenomic variants 56 …”

“…52 Similar to APF, another machine learning-based model was recently developed with good performance in prioritizing NGS-derived pharmacogenomic variants. 56 Besides those prediction methods applicable to the entire pharmacogenome, several gene-specific predictors have been developed. The DPYD-specific variant classifier DPYD-Varifier was trained using in vitro functional data of 156 missense DPYD variants and achieved 85% of predictive accuracy.…”

“… 52 Similar to APF, another machine learning‐based model was recently developed with good performance in prioritizing NGS‐derived pharmacogenomic variants. 56 …”

Development of an extensive workflow for comprehensive clinical pharmacogenomic profiling: lessons from a pilot study on 100 whole exome sequencing data

“…Nevertheless, the workflow in this level for the current study brought many interesting outcomes for novel and/or not-annotated variants in our samples, which the interpretation and further analysis are still in progress. Today, computational assessments proved to be a promising approach for the translation of novel variants into healthcare [ 35 , 36 ].…”

Artificial intelligence in clinical pharmacology: A case study and scoping review of large language models and bioweapon potential

“…In the realm of clinical pharmacology, AI has become an indispensable tool, aiding in various tasks such as drug discovery, prediction of drug interactions, personalized medicine and pharmacovigilance. [8][9][10][11] Among the AI subfields, LLMs stand out for their ability to understand and generate humanlike text. Trained on vast amounts of textual data, LLMs such as Generative Pre-trained Transformers (GPT)-3 and GPT-4, developed by OpenAI, can generate meaningful and coherent text based on the provided input, making them a powerful tool for processing and interpreting large-scale biomedical literature and clinical records.…”