We trained DEDAL, an algorithm based on deep-learning language models, to generate pairwise alignments of protein sequences taking into account the sequence-specific context of amino acid substitutions or gaps. DEDAL improved the alignment correctness on remote homologs by up to threefold and the discrimination of remote homologs from evolutionarily unrelated sequences.
References
Jumper, J. B. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021). This paper describes Alphafold2, the state-of-the-art method for protein structure prediction for multiple sequence alignments.
Smith, T. F. & Waterman, M. S. Identification of common molecular subsequences. J. Mol. Biol. 147, 195–197 (1981). This paper introduces the classical Smith–Waterman algorithm for pairwise sequence alignment.
Altschul, S. et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 25, 3389–3402 (1997). This paper presents the most widely used heuristic variant of the Smith–Waterman algorithm.
Devlin, J. et al. BERT: pre-training of deep bidirectional transformers for language understanding. Proc. NAACL-HLT 1, 4171–4186 (2019). This paper proposes BERT, a technique for unsupervised pretraining of language models.
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: Llinares-López, F., Berthet, Q., Blondel, M., Teboul, O. & Vert, J.-P. Deep embedding and alignment of protein sequences. Nat. Methods https://doi.org/10.1038/s41592-022-01700-2 (2022).
Rights and permissions
About this article
Cite this article
Deep-learning language models help to improve protein sequence alignment. Nat Methods 20, 40–41 (2023). https://doi.org/10.1038/s41592-022-01707-9
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41592-022-01707-9
- Springer Nature America, Inc.