Congratulations to the Structural Bioinformatics group of GRIB awarded in the Rheumatoid Arthritis Responder Challenge

The researchers of the Structural Bioinformatics group of GRIB, led by Baldo Oliva, recently participated in Subchallenge 2 of the RA Responder challenge in which participants had to identify individuals most likely to fail response to antiTNF therapy as defined by EULAR category.  There was a tie for best predictions between Team SBI and Team GuanLab. The top predictions submitted by these two teams were statistically indistinguishable.  The prediction of SBI group was done by using Gaussian processes for regression based on specific SNP dosages. Both teams predicted with an auc_ROC of 0.62 and an auc_PR of 0.51. The description of the SBI group method, as well as code, can be found here. The results of this work has been presentad at the Seventh Annual RECOMB/ISCB Conference.

The RA Responder Challege is one of the DREAM Challenges that pose fundamental questions about systems biology and translational medicine. Designed and run by a community of researchers from a variety of organizations, the challenges invite participants to propose solutions — fostering collaboration and building communities in the process. Expertise and institutional support are provided by Sage Bionetworks, along with the infrastructure to host challenges via their Synapse platform. Together, we share a vision allowing individuals and groups to collaborate openly so that the  “wisdom of the crowd” provides the greatest impact on science and human health.