mikropml: User-Friendly R Package for Supervised Machine Learning Pipelines.

Area of Science:

• Computational Biology
• Bioinformatics
• Data Science

Background:

• Machine learning (ML) is crucial for classification and prediction across diverse fields like healthcare and economics.
• Implementing ML pipelines, encompassing preprocessing, model selection, and evaluation, presents significant challenges in terms of time, complexity, and user-friendliness.

Purpose of the Study:

• To present mikropml, an R package designed to simplify the implementation of machine learning pipelines.
• To provide an accessible tool for researchers and practitioners to build and evaluate ML models.

Main Methods:

• The mikropml package offers an easy-to-use interface for constructing ML pipelines.
• It supports various ML algorithms including regression, support vector machines, decision trees, random forest, and gradient-boosted trees.

Main Results:

• mikropml facilitates the creation and execution of ML pipelines with reduced complexity.
• The package integrates seamlessly into existing R workflows.

Conclusions:

• mikropml democratizes the use of machine learning by simplifying pipeline implementation.
• The R package is readily available on GitHub, CRAN, and conda for widespread adoption.