A CLIP-style model aligns protein surface point clouds with GO-derived captions and achieves roughly 60% Top-5 zero-shot retrieval on PDB and 36% on EMDB.
Multimodal large language models in health care: applications, challenges, and future outlook.JMIR, 2024
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.BM 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Aligning Proteins and Language: A Foundation Model for Protein Retrieval
A CLIP-style model aligns protein surface point clouds with GO-derived captions and achieves roughly 60% Top-5 zero-shot retrieval on PDB and 36% on EMDB.