FANCY: fast estimation of privacy risk in functional genomics data

• DOI: 10.1093/bioinformatics/btaa661
• Publication Date: 2020-07-22T19:24:53Z
• Authors: Gamze Gürsoy; Charlotte M Brannon; Fabio C P Navarro; Mark Gerstein
• Keywords: Python; MIT License

Functional genomics data are becoming clinically actionable, raising privacy concerns. However, quantifying leakage via genotyping is difficult due to the heterogeneous nature of sequencing techniques. Thus, we present FANCY, a tool that rapidly estimates number leaking variants from raw RNA-Seq, ATAC-Seq and ChIP-Seq reads, without explicit genotyping. FANCY employs supervised regression using overall statistics as features provides an estimate risk before release.FANCY can predict cumulative SNVs with average 0.95 R2 for all independent test sets. We realize importance accurate prediction when leaked low. develop special version model, which make predictions higher accuracy low.A python MATLAB implementation well custom scripts generate be found at https://github.com/gersteinlab/FANCY. also provide jupyter notebooks so users optimize parameters in model based on their own data. An easy-to-use webserver takes inputs displays results fancy.gersteinlab.org.Supplementary available Bioinformatics online.