*Easter egg alert* NOT in the published paper. We also benchmarked Evo 2 and while it did better than other gLMs (consistent that scale can improve gLMs), it still falls short of a basic CNN trained using one-hot sequences and far short of supervised SOTA
@pkoo562.bsky.socialOur work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out!
genomebiology.biomedcentral.com/articles/10....
genomebiology.biomedcentral.com
Evaluating the representational power of pre-trained DNA language models for regulatory genomics - Genome Biology
Background The emergence of genomic language models (gLMs) offers an unsupervised approach to learning a wide diversity of cis-regulatory patterns in the non-coding genome without requiring labels of ...
