🧬 BEND Zero-shot prediction of expression variants (eQTL)

Predicting variant effects is a binary problem, where single-bp mutations are classified as either having an effect or not. Each variant is a genomic position with a mutation $x ∈ {A, C, G, T}$ and a label $y ∈ {0, 1}$ indicating whether it has an effect on gene expression (eQTL) or not (background variation). The adjacent 512 bp serve as context.

The data used was adapted from DeepSEA (Zhou & Troyanskaya, 2015)

As this is a zero-shot task, we used the cosine distance in embedding space between a variant nucleotide and its reference nucleotide as the prediction score in BEND.