Gene expression modelling across multiple cell-lines with MapReduce

TL;DR

This paper presents a scalable MapReduce-based method for gene expression modeling that efficiently analyzes large multi-cell line datasets, revealing invariant relationships between histone modifications and transcription.

Contribution

It introduces a parallelized MapReduce framework for gene expression modeling, enabling analysis of large datasets across multiple cell lines and demonstrating its effectiveness.

Findings

Histone modifications and transcription relationships are lineage, tissue, and karyotype-invariant.

Models trained on non-cancerous data can predict cancerous gene expression accurately.

The approach scales efficiently to large, multi-cell line datasets.

Abstract

With the wealth of high-throughput sequencing data generated by recent large-scale consortia, predictive gene expression modelling has become an important tool for integrative analysis of transcriptomic and epigenetic data. However, sequencing data-sets are characteristically large, and previously modelling frameworks are typically inefficient and unable to leverage multi-core or distributed processing architectures. In this study, we detail an efficient and parallelised MapReduce implementation of gene expression modelling. We leverage the computational efficiency of this framework to provide an integrative analysis of over fifty histone modification data-sets across a variety of cancerous and non-cancerous cell-lines. Our results demonstrate that the genome-wide relationships between histone modifications and mRNA transcription are lineage, tissue and karyotype-invariant, and that models trained on matched epigenetic/transcriptomic data from non-cancerous cell-lines are able to predict cancerous expression with equivalent genome-wide fidelity.