A user-driven machine learning approach for RNA-based sample discrimination and hierarchical classification

Tashifa Imtiaz; Jina Nanayakkara; Alexis Fang; Danny Jomaa; Harrison Mayotte; Simona Damiani; Fiza Javed; Tristan Jones; Emily Kaczmarek; Flourish Omolara Adebayo; Uroosa Imtiaz; Yiheng Li; Richard Zhang; Parvin Mousavi; Neil Renwick; Kathrin Tyryshkin

doi:10.1016/j.xpro.2023.102661

A user-driven machine learning approach for RNA-based sample discrimination and hierarchical classification

STAR Protoc. 2023 Oct 27;4(4):102661. doi: 10.1016/j.xpro.2023.102661. Online ahead of print.

Authors

Affiliations

¹ Laboratory of Translational RNA Biology, Department of Pathology and Molecular Medicine, Queen's University, 88 Stuart St, Kingston, ON K7L 3N6, Canada. Electronic address: [email protected].
² Laboratory of Translational RNA Biology, Department of Pathology and Molecular Medicine, Queen's University, 88 Stuart St, Kingston, ON K7L 3N6, Canada.
³ School of Medicine, Faculty of Health Sciences, Queen's University, 80 Barrie St, Kingston, ON K7L 3N6, Canada.
⁴ Medical Informatics Laboratory, School of Computing, Queen's University, 557 Goodwin Hall, Kingston, ON K7L 2N8, Canada.
⁵ School of Computing, Queen's University, 557 Goodwin Hall, Kingston, ON K7L 2N8, Canada.
⁶ Laboratory of Translational RNA Biology, Department of Pathology and Molecular Medicine, Queen's University, 88 Stuart St, Kingston, ON K7L 3N6, Canada; School of Computing, Queen's University, 557 Goodwin Hall, Kingston, ON K7L 2N8, Canada. Electronic address: [email protected].

Abstract

RNA-based sample discrimination and classification can be used to provide biological insights and/or distinguish between clinical groups. However, finding informative differences between sample groups can be challenging due to the multidimensional and noisy nature of sequencing data. Here, we apply a machine learning approach for hierarchical discrimination and classification of samples with high-dimensional miRNA expression data. Our protocol comprises data preprocessing, unsupervised learning, feature selection, and machine-learning-based hierarchical classification, alongside open-source MATLAB code.

Keywords: Bioinformatics; Gene Expression; RNAseq; Sequence Analysis; Sequencing.