PROTOCOL: Late Interaction Retrieval for Protein Homolog Search
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916058078642176 |
|---|---|
| author | Cohn, Gabrielle Gumaste, Rohan Hoang, Minh Lakshman, Vihan |
| author_facet | Cohn, Gabrielle Gumaste, Rohan Hoang, Minh Lakshman, Vihan |
| contents | Protein homology search underlies function annotation, structure prediction, and evolutionary analysis, but remains challenging in the "twilight zone," where global sequence similarity is weak and classical alignment methods lose sensitivity. Protein language models provide context-aware representations that could improve alignment sensitivity in this regime. However, prior protein embedding-based retrieval pipelines often pool these representations into a single vector, potentially obscuring local motifs, domains, or conserved residues that reveal remote homology. We introduce ProtoCol, a model which represents proteins as sets of residue embeddings and uses ColBERT-style late interaction to test whether residue-level comparison improves homolog retrieval. ProtoCol encodes proteins independently, keeps candidate representations pre-computable, and scores candidates with MaxSim over residue embeddings. On SCOPe superfamily and Pfam clan benchmarks, ProtoCol outperforms sequence-composition, alignment-based, pooled PLM, and trained single-vector baselines, supporting late interaction as an effective retrieval layer for remote homology search. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29158 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PROTOCOL: Late Interaction Retrieval for Protein Homolog Search Cohn, Gabrielle Gumaste, Rohan Hoang, Minh Lakshman, Vihan Machine Learning Information Retrieval Biomolecules Protein homology search underlies function annotation, structure prediction, and evolutionary analysis, but remains challenging in the "twilight zone," where global sequence similarity is weak and classical alignment methods lose sensitivity. Protein language models provide context-aware representations that could improve alignment sensitivity in this regime. However, prior protein embedding-based retrieval pipelines often pool these representations into a single vector, potentially obscuring local motifs, domains, or conserved residues that reveal remote homology. We introduce ProtoCol, a model which represents proteins as sets of residue embeddings and uses ColBERT-style late interaction to test whether residue-level comparison improves homolog retrieval. ProtoCol encodes proteins independently, keeps candidate representations pre-computable, and scores candidates with MaxSim over residue embeddings. On SCOPe superfamily and Pfam clan benchmarks, ProtoCol outperforms sequence-composition, alignment-based, pooled PLM, and trained single-vector baselines, supporting late interaction as an effective retrieval layer for remote homology search. |
| title | PROTOCOL: Late Interaction Retrieval for Protein Homolog Search |
| topic | Machine Learning Information Retrieval Biomolecules |
| url | https://arxiv.org/abs/2605.29158 |