Protein structures are encoded as 400-bit hash codes with a graph neural network and contrastive learning, giving faster and more memory-efficient similarity search than real-valued vector methods.
Matt: local flexibility aids protein multiple structure alignment
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
-
Hashing for Protein Structure Similarity Search
Protein structures are encoded as 400-bit hash codes with a graph neural network and contrastive learning, giving faster and more memory-efficient similarity search than real-valued vector methods.