Abstract
Rheumatoid arthritis (RA) affects millions world-wide. While anti-TNF treatment is widely used to reduce disease progression, treatment fails in ∼one-third of patients. No biomarker currently exists that identifies non-responders before treatment. A rigorous community-based assessment of the utility of SNP data for predicting anti-TNF treatment efficacy in RA patients was performed in the context of a DREAM Challenge (http://www.synapse.org/RA_Challenge). An open challenge framework enabled the comparative evaluation of predictions developed by 73 research groups using the most comprehensive available data and covering a wide range of state-of-the-art modelling methodologies. Despite a significant genetic heritability estimate of treatment non-response trait (h2=0.18, P value=0.02), no significant genetic contribution to prediction accuracy is observed. Results formally confirm the expectations of the rheumatology community that SNP information does not significantly improve predictive performance relative to standard clinical traits, thereby justifying a refocusing of future efforts on collection of other data.
Highlights
IntroductionGenetic information has not been found to provide clinically relevant predictions in many cases[8,9,10], the high-potential impact of successful genetic biomarkers and their potential to provide biological insights continues to inspire research inquiries in many fields including anti-TNF response
This study was performed as an open analytical challenge using the DREAM framework[11,12,13,14] (DREAM Challenges website; www.dreamchallenges. org) as a mechanism to test predictions developed across a variety of state-of-the-art methodologies
Challenge participants were provided with single-nucleotide polymorphism (SNP) data collected on 2,706 anti-TNF-treated Rheumatoid arthritis (RA) patients[6] (Supplementary Table 1) with which to develop predictive models of disease-modulating treatment response where treatment efficacy was measured using (a) the absolute change in disease activity score in 28 joints[15] (DAS28)
Summary
Genetic information has not been found to provide clinically relevant predictions in many cases[8,9,10], the high-potential impact of successful genetic biomarkers and their potential to provide biological insights continues to inspire research inquiries in many fields including anti-TNF response. To this aim, we perform a community-based empirical assessment of the contribution of common single-nucleotide polymorphism (SNP) data to predictions of anti-TNF treatment response in RA patients to formally assess their utility for clinical application. While the researchers are able to build predictive models that perform significantly better than random, formal evaluation from the best-performing teams show that common SNP variants do not meaningfully contribute to model performance within this study
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
