Benchmarking and Testing Machine Learning Approaches with BARRA:CuRDa, a Curated RNA-Seq Database for Cancer Research

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• RNA sequencing (RNA-seq) is a key technology for global gene expression profiling.
• RNA-seq data analysis poses significant computational challenges.
• Machine learning (ML) is increasingly vital in biomedical research.

Purpose of the Study:

• To address the need for curated datasets in ML-driven bioinformatics.
• To provide a resource for developing and testing novel ML algorithms on RNA-seq data.

Main Methods:

• Development of a curated dataset from RNA-seq experiments.
• Application of state-of-the-art computational approaches for data preprocessing.
• Adaptation of data formats for seamless integration with ML protocols.

Main Results:

• A robust, ML-ready dataset for gene expression analysis.
• Demonstration of the dataset's utility in facilitating ML algorithm testing.
• Establishment of a standardized approach for RNA-seq data handling.

Conclusions:

• Curated, ML-adapted RNA-seq datasets are crucial for advancing bioinformatics.
• This resource will accelerate the development and validation of new computational tools.
• Facilitates the application of machine learning in understanding complex biological systems.