Robert McCoy Vernon

This paper shows that protein language models can better annotate metagenomic proteins when trained on curated data, enabling retrieval of diverse enzyme candidates from billions of sequences.

This study analyzes how biological concepts are encoded in protein language models across their layers and finds that complexity increases with depth, with pretraining data and compute having a greater impact than parameter scaling.

The paper identifies a novel TUBB mutation linked to both ciliopathy and tubulinopathy brain features, showing it impairs ciliogenesis by altering microtubule dynamics.

This paper introduces AMPLIFY, a protein language model that achieves better performance with less training cost by improving data quality and architecture, challenging the need for scaling.