Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908402208210944 |
|---|---|
| author | Weitzman, Ruben Groth, Peter Mørch Van Niekerk, Lood Otani, Aoi Gal, Yarin Marks, Debora Notin, Pascal |
| author_facet | Weitzman, Ruben Groth, Peter Mørch Van Niekerk, Lood Otani, Aoi Gal, Yarin Marks, Debora Notin, Pascal |
| contents | Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein interactions. Traditional workflows have relied on a two-step process: first retrieving homologs via Multiple Sequence Alignments (MSA), then training models on one or more of these alignments. However, MSA-based retrieval is computationally expensive, struggles with highly divergent sequences or complex insertions & deletions patterns, and operates independently of the downstream modeling objective. We introduce Protriever, an end-to-end differentiable framework that learns to retrieve relevant homologs while simultaneously training for the target task. When applied to protein fitness prediction, Protriever achieves state-of-the-art performance compared to sequence-based models that rely on MSA-based homolog retrieval, while being two orders of magnitude faster through efficient vector search. Protriever is both architecture- and task-agnostic, and can flexibly adapt to different retrieval strategies and protein databases at inference time -- offering a scalable alternative to alignment-centric approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08954 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction Weitzman, Ruben Groth, Peter Mørch Van Niekerk, Lood Otani, Aoi Gal, Yarin Marks, Debora Notin, Pascal Quantitative Methods Machine Learning Biomolecules Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein interactions. Traditional workflows have relied on a two-step process: first retrieving homologs via Multiple Sequence Alignments (MSA), then training models on one or more of these alignments. However, MSA-based retrieval is computationally expensive, struggles with highly divergent sequences or complex insertions & deletions patterns, and operates independently of the downstream modeling objective. We introduce Protriever, an end-to-end differentiable framework that learns to retrieve relevant homologs while simultaneously training for the target task. When applied to protein fitness prediction, Protriever achieves state-of-the-art performance compared to sequence-based models that rely on MSA-based homolog retrieval, while being two orders of magnitude faster through efficient vector search. Protriever is both architecture- and task-agnostic, and can flexibly adapt to different retrieval strategies and protein databases at inference time -- offering a scalable alternative to alignment-centric approaches. |
| title | Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction |
| topic | Quantitative Methods Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2506.08954 |