Some classes of problem are best solved by a specific class of machine learning model, due to the structure of the data (e.g. Deep Learning for computer vision).
Prediction of bacterial resistance/susceptibility to antimicrobials (from genotypic data) using Machine Learning methods is a problem that has started receiving interest in recent years.
The following paper (from 2017) analysed the then current literature and found that:
To date, there has not been a consensus about the optimal machine learning model to be used for AST genotype–phenotype prediction, as reflected by the diverse algorithms authors have implemented (Table 1).
- Machine learning: novel bioinformatics approaches for combating antimicrobial resistance
Macesica, Polubriaginof, Tatonettib (2017)
Has this changed in the past 2 years?
Is there now a consensus about which models are most effective?
References: Table 1 from paper: