R.ROSETTA: an interpretable machine learning framework.

BACKGROUND: Machine learning involves strategies and algorithms that may assist bioinformatics analyses in terms of data mining and knowledge discovery. In several applications, viz. in Life Sciences, it is often more important to understand how a prediction was obtained rather than knowing what prediction was made. To this end so-called interpretable machine learning has been recently advocated. In this study, we implemented an interpretable machine learning package based on the rough set theory. An important aim of our work was provision of statistical properties of the models and their components. RESULTS: We present the R.ROSETTA package, which is an R wrapper of ROSETTA framework. The original ROSETTA functions have been improved and adapted to the R programming environment. The package allows for building and analyzing non-linear interpretable machine learning models. R.ROSETTA gathers combinatorial statistics via rule-based modelling for accessible and transparent results, well-suited for adoption within the greater scientific community. The package also provides statistics and visualization tools that facilitate minimization of analysis bias and noise. The R.ROSETTA package is freely available at https://github.com/komorowskilab/R.ROSETTA . To illustrate the usage of the package, we applied it to a transcriptome dataset from an autism case-control study. Our tool provided hypotheses for potential co-predictive mechanisms among features that discerned phenotype classes. These co-predictors represented neurodevelopmental and autism-related genes. CONCLUSIONS: R.ROSETTA provides new insights for interpretable machine learning analyses and knowledge-based systems. We demonstrated that our package facilitated detection of dependencies for autism-related genes. Although the sample application of R.ROSETTA illustrates transcriptome data analysis, the package can be used to analyze any data organized in decision tables.

Interpretable machine learning identifies paediatric Systemic Lupus Erythematosus subtypes based on gene expression data.

Transcriptomic analyses are commonly used to identify differentially expressed genes between patients and controls, or within individuals across disease courses. These methods, whilst effective, cannot encompass the combinatorial effects of genes driving disease. We applied rule-based machine learning (RBML) models and rule networks (RN) to an existing paediatric Systemic Lupus Erythematosus (SLE) blood expression dataset, with the goal of developing gene networks to separate low and high disease activity (DA1 and DA3). The resultant model had an 81% accuracy to distinguish between DA1 and DA3, with unsupervised hierarchical clustering revealing additional subgroups indicative of the immune axis involved or state of disease flare. These subgroups correlated with clinical variables, suggesting that the gene sets identified may further the understanding of gene networks that act in concert to drive disease progression. This included roles for genes (i) induced by interferons (IFI35 and OTOF), (ii) key to SLE cell types (KLRB1 encoding CD161), or (iii) with roles in autophagy and NF-κB pathway responses (CKAP4). As demonstrated here, RBML approaches have the potential to reveal novel gene patterns from within a heterogeneous disease, facilitating patient clinical and therapeutic stratification.

Potential of whole-genome sequencing-based pharmacogenetic profiling.

Pharmacogenetics represents a major driver of precision medicine, promising individualized drug selection and dosing. Traditionally, pharmacogenetic profiling has been performed using targeted genotyping that focuses on common/known variants. Recently, whole-genome sequencing (WGS) is emerging as a more comprehensive short-read next-generation sequencing approach, enabling both gene diagnostics and pharmacogenetic profiling, including rare/novel variants, in a single assay. Using the example of the pharmacogene CYP2D6, we demonstrate the potential of WGS-based pharmacogenetic profiling as well as emphasize the limitations of short-read next-generation sequencing. In the near future, we envision a shift toward long-read sequencing as the predominant method for gene diagnostics and pharmacogenetic profiling, providing unprecedented data quality and improving patient care.