Recent advances in (deep) machine learning, natural language processing, and information retrieval show great potential for enhancing the knowledge and processes in the fields of pharmacogenetics, pharmacogenomics, and pharmacoepidemiology. These techniques allow for the unprecedented analysis of large (unstructured) datasets that would otherwise be intractable, such as finding relevant patterns and clusters in the data being analyzed. From predicting treatment outcomes and guiding drug choice to prevent adverse reactions to drug discovery and repurposing, artificial intelligence holds great promise when it comes to the development of support systems to aid clinical decision making in the coming years.

This Research Topic is the second addition in the series and looks to expand on the original collection. We invite new contributions in the field of artificial intelligence (machine learning, natural language processing, and information retrieval) that can be applied to advance pharmacogenetics, pharmacogenomics, and pharmacoepidemiology.
The main goal is to gather novel methodologies, and examples of their translational use in clinical practice, as well as to identify the strengths and weaknesses of artificial intelligence in these fields.

In the second addition of this Research Topic, we welcome submissions of Original Research, Systematic Reviews, Methods, Clinical Trials, Case Reports, Data Reports and Brief Research Reports addressing the development, improvement, or examples of using methods or algorithms including. but not limited to:

• Data integration from diverse sources, and improvement of the inference of haplotypes and phenotypes, with a special focus on those inducing pharmacokinetic changes, generation of reactive metabolites, or those inducing adverse drug events.

• Prediction of drug-drug interactions and/or quantification of their dose-effect relationship.

• Acquisition of relevant pharmacogenetics and/or pharmacoepidemiology information from published sources or from clinical records by means of natural language processing.

• Managing large datasets useful in pharmacogenetics, such as DNA sequences obtained by next-generation sequencing, phenomics, transcriptomics, proteomics, or metabolomics.

• Improvement of risk/benefit assessment of drug use.

• Assessment of the probability of adverse drug effects in specific populations.

• Assessment of trends in drug use in specific populations.

Note to authors: Manuscripts will only be accepted for peer review if they adhere to the scope and requirements of the journal section.

Submit your idea

Impact

Frontiers in Pharmacology

Participating Journals

Impact