@article {Wang110734, author = {Qingguo Wang and Joshua Armenia and Chao Zhang and Alexander V. Penson and Ed Reznik and Liguo Zhang and Angelica Ochoa and Benjamin E. Gross and Christine A. Iacobuzio-Donahue and Doron Betel and Barry S. Taylor and Jianjiong Gao and Nikolaus Schultz}, title = {Enabling cross-study analysis of RNA-Sequencing data}, elocation-id = {110734}, year = {2017}, doi = {10.1101/110734}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Driven by the recent advances of next generation sequencing (NGS) technologies and an urgent need to decode complex human diseases, a multitude of large-scale studies were conducted recently that have resulted in an unprecedented volume of whole transcriptome sequencing (RNA-seq) data. While these data offer new opportunities to identify the mechanisms underlying disease, the comparison of data from different sources poses a great challenge, due to differences in sample and data processing. Here, we present a pipeline that processes and unifies RNA-seq data from different studies, which includes uniform realignment and gene expression quantification as well as batch effect removal. We find that uniform alignment and quantification is not sufficient when combining RNA-seq data from different sources and that the removal of other batch effects is essential to facilitate data comparison. We have processed data from the Genotype Tissue Expression project (GTEx) and The Cancer Genome Atlas (TCGA) and have successfully corrected for study-specific biases, enabling comparative analysis across studies. The normalized data are available for download via GitHub (at https://github.com/mskcc/RNAseqDB).}, URL = {https://www.biorxiv.org/content/early/2017/02/27/110734}, eprint = {https://www.biorxiv.org/content/early/2017/02/27/110734.full.pdf}, journal = {bioRxiv} }