Back

Recovering genomes and phenotypes using allele-specific gene expression

Gursoy, G.; Lu, N.; Wagner, S.; Gerstein, M.

2020-11-12 bioinformatics
10.1101/2020.11.11.377978 bioRxiv
Show abstract

With the recent increase in RNA sequencing efforts using large cohorts of individuals, studying allele-specific gene expression is becoming increasingly important. Here, we report that, despite not containing explicit variant information, a list of allele-specific gene names of an individual is enough to recover key variants and link the individual back to their genome or phenotype. This creates a privacy conundrum.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.