Single-Sequence, Structure Free Allosteric Residue Prediction with Protein Language Models
Kannan, G. R.; Hie, B.; Kim, P. S.
Show abstract
Large language models trained on protein amino acid sequences have shown the ability to learn general coevolutionary relationships at scale, which in turn contain useful structural and functional information. Here we show that attention maps, matrices of learned pairwise relationships between residues, also include information about allostery. This enables prediction of allosteric relationships with no task-specific training, requiring only a single input sequence and no structural information. Attention maps outperform state-of-the-art structure-based and sequence coevolution-based allosteric residue prediction models on a well-curated benchmark set of 24 allosteric proteins. For K-Ras, an allosterically regulated GTPase, attention maps correlate best with allosteric residues influencing binding identified in deep mutational scanning data. For the beta-2 adrenergic receptor, an allosterically regulated GPCR, attention maps correlate best when compared to experimental alanine-scanning mutational data identifying allosteric relationships influencing signaling. These results enable allosteric relationship prediction in a single-sequence, structure-free manner.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
"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.