AUTHOR=Rychkov Dmitry , Neely Jessica , Oskotsky Tomiko , Yu Steven , Perlmutter Noah , Nititham Joanne , Carvidi Alexander , Krueger Melissa , Gross Andrew , Criswell Lindsey A. , Ashouri Judith F. , Sirota Marina 

TITLE=Cross-Tissue Transcriptomic Analysis Leveraging Machine Learning Approaches Identifies New Biomarkers for Rheumatoid Arthritis

JOURNAL=Frontiers in Immunology

VOLUME=12

YEAR=2021

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2021.638066

DOI=10.3389/fimmu.2021.638066

ISSN=1664-3224

ABSTRACT=<p>There is an urgent need to identify biomarkers for diagnosis and disease activity monitoring in rheumatoid arthritis (RA). We leveraged publicly available microarray gene expression data in the NCBI GEO database for whole blood (N=1,885) and synovial (N=284) tissues from RA patients and healthy controls. We developed a robust machine learning feature selection pipeline with validation on five independent datasets culminating in 13 genes: <italic>TNFAIP6</italic>, <italic>S100A8</italic>, <italic>TNFSF10</italic>, <italic>DRAM1</italic>, <italic>LY96</italic>, <italic>QPCT</italic>, <italic>KYNU</italic>, <italic>ENTPD1</italic>, <italic>CLIC1</italic>, <italic>ATP6V0E1</italic>, <italic>HSP90AB1</italic>, <italic>NCL</italic> and <italic>CIRBP</italic> which define the RA score and demonstrate its clinical utility: the score tracks the disease activity DAS28 (p = 7e-9), distinguishes osteoarthritis (OA) from RA (OR 0.57, p = 8e-10) and polyJIA from healthy controls (OR 1.15, p = 2e-4) and monitors treatment effect in RA (p = 2e-4). Finally, the immunoblotting analysis of six proteins on an independent cohort confirmed two proteins, <italic>TNFAIP6</italic>/TSG6 and <italic>HSP90AB1</italic>/HSP90.</p>