Gal Passi

11/RaCoon is fully open-source with a public web server. Try it → evaluate variant pathogenicity with interpretable, residue-aware probabilities. bio3d.cs.huji.ac.il/webserver/raco… Presenting the RaCoon poster at the EMBO workshop this week: embl.org/about/info/cou…

10/Why does this matter? Miscalibrated probabilities = inconsistent evidence for clinical classification (and you may also improve AUROC😎).

1/Missense variant effect predictors (VEPs) are very accurate but are they trustworthy? Not if their probability outputs aren’t calibrated. @SapirAmittai @DinaSchneidman

We finally show that our identified variants (red) are found in close spatial proximity to other established deleterious variants (green). Providing compelling evidence that specific variants in the genes CART and HSD17B4 (presented) are likely to interfere with protein function.

7/8 We show that alterations in these genes, both in expression and by somatic mutations significantly affect BC survival.

1/8 Excited to share our new paper on @BriefingBioinfo using protein variant effect predictors to discover predisposing genes for hereditary breast cancer. academic.oup.com/bib/article/25… @DinaSchneidman @LinialMichal