AUTHOR=Agraz Melih , Goksuluk Dincer , Zhang Peng , Choi Bum-Rak , Clements Richard T. , Choudhary Gaurav , Karniadakis George Em TITLE=ML-GAP: machine learning-enhanced genomic analysis pipeline using autoencoders and data augmentation JOURNAL=Frontiers in Genetics VOLUME=15 YEAR=2024 URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2024.1442759 DOI=10.3389/fgene.2024.1442759 ISSN=1664-8021 ABSTRACT=Introduction

The advent of RNA sequencing (RNA-Seq) has significantly advanced our understanding of the transcriptomic landscape, revealing intricate gene expression patterns across biological states and conditions. However, the complexity and volume of RNA-Seq data pose challenges in identifying differentially expressed genes (DEGs), critical for understanding the molecular basis of diseases like cancer.

Methods

We introduce a novel Machine Learning-Enhanced Genomic Data Analysis Pipeline (ML-GAP) that incorporates autoencoders and innovative data augmentation strategies, notably the MixUp method, to overcome these challenges. By creating synthetic training examples through a linear combination of input pairs and their labels, MixUp significantly enhances the model’s ability to generalize from the training data to unseen examples.

Results

Our results demonstrate the ML-GAP’s superiority in accuracy, efficiency, and insights, particularly crediting the MixUp method for its substantial contribution to the pipeline’s effectiveness, advancing greatly genomic data analysis and setting a new standard in the field.

Discussion

This, in turn, suggests that ML-GAP has the potential to perform more accurate detection of DEGs but also offers new avenues for therapeutic intervention and research. By integrating explainable artificial intelligence (XAI) techniques, ML-GAP ensures a transparent and interpretable analysis, highlighting the significance of identified genetic markers.