S2ALM pretrains a 650M-parameter antibody language model on sequence and Foldseek 3Di structure tokens, reporting modest state-of-the-art gains across six antibody benchmarks.
Accurate prediction of antibody function and structure using bio-inspired antibody language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
S$^2$ALM: Sequence-Structure Pre-trained Large Language Model for Comprehensive Antibody Representation Learning
S2ALM pretrains a 650M-parameter antibody language model on sequence and Foldseek 3Di structure tokens, reporting modest state-of-the-art gains across six antibody benchmarks.