To handle increasingly large protein databases, a new ultrafast, highly sensitive method — Dense Homolog Retriever (DHR) — detects remote homologs using dense retrieval and protein language models. Its alignment-free nature makes it much faster than traditional approaches, and the newly found remote homologs benefit our understanding of protein evolution, structure and function.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 print issues and online access
$209.00 per year
only $17.42 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
References
Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021). This paper proposed AlphaFold2, a deep learning model to predict protein structure accurately.
Buchfink, B. et al. Fast and sensitive protein alignment using DIAMOND. Nat. Methods 12, 59–60 (2015). This paper introduced an alignment algorithm that can achieve high sensitivity while being much faster than the gold standards.
Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123–1130 (2023). This paper proposed a protein language model trained on a large scale and a structure prediction model that uses only a single sequence.
Alexander, L. et al. Protein target highlights in CASP15: analysis of models by structure providers. Proteins 91, 1571–1599 (2023). This paper presented CASP, a challenge aiming at establishing the current state of the art in protein structure prediction.
Mirdita, M. et al. ColabFold: making protein folding accessible to all. Nat. Methods 19, 679–682 (2022). This paper proposed an accelerated method and an accessible platform for protein structure prediction.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Hong, L. et al. Fast, sensitive detection of protein homologs using deep dense retrieval. Nat. Biotechnol. https://doi.org/10.1038/s41587-024-02353-6 (2024).
Rights and permissions
About this article
Cite this article
Protein language model enables fast and sensitive remote homolog detection. Nat Biotechnol (2024). https://doi.org/10.1038/s41587-024-02359-0
Published:
DOI: https://doi.org/10.1038/s41587-024-02359-0
