A new benchmark shows that genomic language models mostly fail to detect loss-of-function mutations in synthetic, evolutionarily implausible DNA, with accuracy tied to how likely the model finds the sequence.
Saprothub: Making protein modeling accessible to all biologists
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.QM 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences
A new benchmark shows that genomic language models mostly fail to detect loss-of-function mutations in synthetic, evolutionarily implausible DNA, with accuracy tied to how likely the model finds the sequence.