{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:46:30Z","timestamp":1792806390723,"version":"4.5.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:00:00Z","timestamp":1776124800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:00:00Z","timestamp":1776124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Biotechnol"],"DOI":"10.1038\/s41587-026-03095-3","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T09:04:56Z","timestamp":1776157496000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Fast and accurate multiple-protein-sequence alignment at scale with FAMSA2"],"prefix":"10.1038","author":[{"given":"Adam","family":"Gudy\u015b","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8096-3776","authenticated-orcid":false,"given":"Andrzej","family":"Zielezinski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1461-0988","authenticated-orcid":false,"given":"Cedric","family":"Notredame","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9496-733X","authenticated-orcid":false,"given":"Sebastian","family":"Deorowicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,14]]},"reference":[{"key":"3095_CR1","doi-asserted-by":"publisher","first-page":"997","DOI":"10.3390\/biology12070997","volume":"12","author":"H Satam","year":"2023","unstructured":"Satam, H. et al. Next-generation sequencing technology: current trends and advancements. Biology 12, 997 (2023).","journal-title":"Biology"},{"key":"3095_CR2","doi-asserted-by":"publisher","first-page":"4325","DOI":"10.1073\/pnas.1720115115","volume":"115","author":"HA Lewin","year":"2018","unstructured":"Lewin, H. A. et al. Earth BioGenome Project: sequencing life for the future of life. Proc. Natl Acad. Sci. USA 115, 4325\u20134333 (2018).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"3095_CR3","doi-asserted-by":"publisher","first-page":"D753","DOI":"10.1093\/nar\/gkac1080","volume":"51","author":"L Richardson","year":"2023","unstructured":"Richardson, L. et al. MGnify: the microbiome sequence data analysis resource in 2023. Nucleic Acids Res. 51, D753\u2013D759 (2023).","journal-title":"Nucleic Acids Res."},{"key":"3095_CR4","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","volume":"18","author":"B Buchfink","year":"2021","unstructured":"Buchfink, B., Reuter, K. & Drost, H.-G. Sensitive protein alignments at tree-of-life scale using DIAMOND. Nat. Methods 18, 366\u2013368 (2021).","journal-title":"Nat. Methods"},{"key":"3095_CR5","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","volume":"35","author":"M Steinegger","year":"2017","unstructured":"Steinegger, M. & S\u00f6ding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026\u20131028 (2017).","journal-title":"Nat. Biotechnol."},{"key":"3095_CR6","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1038\/s41586-023-06583-7","volume":"622","author":"GA Pavlopoulos","year":"2023","unstructured":"Pavlopoulos, G. A. et al. Unraveling the functional dark matter through global metagenomics. Nature 622, 594\u2013602 (2023).","journal-title":"Nature"},{"key":"3095_CR7","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493\u2013500 (2024).","journal-title":"Nature"},{"key":"3095_CR8","doi-asserted-by":"publisher","first-page":"D439","DOI":"10.1093\/nar\/gkab1061","volume":"50","author":"M Varadi","year":"2022","unstructured":"Varadi, M. et al. AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res. 50, D439\u2013D444 (2022).","journal-title":"Nucleic Acids Res."},{"key":"3095_CR9","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1038\/s41586-023-06510-w","volume":"622","author":"I Barrio-Hernandez","year":"2023","unstructured":"Barrio-Hernandez, I. et al. Clustering predicted structures at the scale of the known protein universe. Nature 622, 637\u2013645 (2023).","journal-title":"Nature"},{"key":"3095_CR10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34630-w","volume":"13","author":"RC Edgar","year":"2022","unstructured":"Edgar, R. C. Muscle5: High-accuracy alignment ensembles enable unbiased assessments of sequence homology and phylogeny. Nat. Commun. 13, 6968 (2022).","journal-title":"Nat. Commun."},{"key":"3095_CR11","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1038\/s41587-019-0333-6","volume":"37","author":"E Garriga","year":"2019","unstructured":"Garriga, E. et al. Large multiple sequence alignments with a root-to-leaf regressive method. Nat. Biotechnol. 37, 1466\u20131470 (2019).","journal-title":"Nat. Biotechnol."},{"key":"3095_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/msb.2011.75","volume":"7","author":"F Sievers","year":"2011","unstructured":"Sievers, F. et al. Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega. Mol. Syst. Biol. 7, 539 (2011).","journal-title":"Mol. Syst. Biol."},{"key":"3095_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/srep33964","volume":"6","author":"S Deorowicz","year":"2016","unstructured":"Deorowicz, S., Debudaj-Grabysz, A. & Gudy\u015b, A. FAMSA: fast and accurate multiple sequence alignment of huge protein families. Sci. Rep. 6, 33964 (2016).","journal-title":"Sci. Rep."},{"key":"3095_CR14","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1126\/science.ads6733","volume":"391","author":"CLM Gilchrist","year":"2026","unstructured":"Gilchrist, C. L. M., Mirdita, M. & Steinegger, M. Multiple protein structure alignment at scale with FoldMason. Science 391, 485\u2013488 (2026).","journal-title":"Science"},{"key":"3095_CR15","doi-asserted-by":"publisher","first-page":"10556","DOI":"10.1073\/pnas.1405628111","volume":"111","author":"K Boyce","year":"2014","unstructured":"Boyce, K., Sievers, F. & Higgins, D. G. Simple chained guide trees give high-quality protein multiple sequence alignments. Proc. Natl Acad. Sci. USA 111, 10556\u201310561 (2014).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"3095_CR16","doi-asserted-by":"publisher","first-page":"E99","DOI":"10.1073\/pnas.1417526112","volume":"112","author":"G Tan","year":"2015","unstructured":"Tan, G., Gil, M., L\u00f6ytynoja, A. P., Goldman, N. & Dessimoz, C. Simple chained guide trees give poorer multiple sequence alignments than inferred trees in simulation and phylogenetic benchmarks. Proc. Natl Acad. Sci. USA 112, E99\u2013E100 (2015).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"3095_CR17","doi-asserted-by":"crossref","unstructured":"Schubert, E. & Rousseeuw, P. J. Faster k-medoids clustering: improving the PAM, CLARA, and CLARANS algorithms. In Proc. 12th International Similarity Search and Applications Conference (eds Amato, G. et al.) 171\u2013187 (Springer, 2019).","DOI":"10.1007\/978-3-030-32047-8_16"},{"key":"3095_CR18","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1093\/bioinformatics\/btl592","volume":"23","author":"K Katoh","year":"2007","unstructured":"Katoh, K. & Toh, H. PartTree: an algorithm to build an approximate tree from a large number of unaligned sequences. Bioinformatics 23, 372\u2013374 (2007).","journal-title":"Bioinformatics"},{"key":"3095_CR19","unstructured":"Kaufman, L. & Rousseeuw, P. J. Finding Groups in Data: An Introduction to Cluster Analysis 1st edn (John Wiley & Sons, 2009)."},{"key":"3095_CR20","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/TKDE.2002.1033770","volume":"14","author":"RT Ng","year":"2002","unstructured":"Ng, R. T. & Han, J. CLARANS: a method for clustering objects for spatial data mining. IEEE Trans. Knowl. Data Eng. 14, 1003\u20131016 (2002).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"3095_CR21","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1002\/j.1538-7305.1957.tb01515.x","volume":"36","author":"RC Prim","year":"1957","unstructured":"Prim, R. C. Shortest connection networks and some generalizations. Bell Syst. Tech. J. 36, 1389\u20131401 (1957).","journal-title":"Bell Syst. Tech. J."},{"key":"3095_CR22","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.1093\/bioinformatics\/btp348","volume":"25","author":"S Capella-Guti\u00e9rrez","year":"2009","unstructured":"Capella-Guti\u00e9rrez, S., Silla-Mart\u00ednez, J. M. & Gabald\u00f3n, T. trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses. Bioinformatics 25, 1972\u20131973 (2009).","journal-title":"Bioinformatics"},{"key":"3095_CR23","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.1093\/bioinformatics\/btz795","volume":"36","author":"T Lassmann","year":"2019","unstructured":"Lassmann, T. Kalign 3: multiple sequence alignment of large data sets. Bioinformatics 36, 1928\u20131929 (2019).","journal-title":"Bioinformatics"},{"key":"3095_CR24","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1093\/bioinformatics\/btaa992","volume":"37","author":"V Smirnov","year":"2021","unstructured":"Smirnov, V. & Warnow, T. MAGUS: multiple sequence alignment using graph clustering. Bioinformatics 37, 1666\u20131672 (2021).","journal-title":"Bioinformatics"},{"key":"3095_CR25","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1093\/molbev\/mst010","volume":"30","author":"K Katoh","year":"2013","unstructured":"Katoh, K. & Standley, D. M. MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Mol. Biol. Evol. 30, 772\u2013780 (2013).","journal-title":"Mol. Biol. Evol."},{"key":"3095_CR26","doi-asserted-by":"publisher","first-page":"btad007","DOI":"10.1093\/bioinformatics\/btad007","volume":"39","author":"M Park","year":"2023","unstructured":"Park, M., Ivanovic, S., Chu, G., Shen, C. & Warnow, T. UPP2: fast and accurate alignment of datasets with fragmentary sequences. Bioinformatics 39, btad007 (2023).","journal-title":"Bioinformatics"},{"key":"3095_CR27","doi-asserted-by":"publisher","first-page":"D203","DOI":"10.1093\/nar\/gkh027","volume":"32","author":"LA Stebbings","year":"2004","unstructured":"Stebbings, L. A. & Mizuguchi, K. HOMSTRAD: recent developments of the Homologous Protein Structure Alignment Database. Nucleic Acids Res. 32, D203\u2013D207 (2004).","journal-title":"Nucleic Acids Res."},{"key":"3095_CR28","doi-asserted-by":"publisher","first-page":"D412","DOI":"10.1093\/nar\/gkaa913","volume":"49","author":"J Mistry","year":"2021","unstructured":"Mistry, J. et al. Pfam: the protein families database in 2021. Nucleic Acids Res. 49, D412\u2013D419 (2021).","journal-title":"Nucleic Acids Res."},{"key":"3095_CR29","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1038\/s41576-020-0233-0","volume":"21","author":"P Kapli","year":"2020","unstructured":"Kapli, P., Yang, Z. & Telford, M. J. Phylogenetic tree building in the genomic age. Nat. Rev. Genet. 21, 428\u2013444 (2020).","journal-title":"Nat. Rev. Genet."},{"key":"3095_CR30","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msac092","volume":"39","author":"N Ly-Trong","year":"2022","unstructured":"Ly-Trong, N., Naser-Khdour, S., Lanfear, R. & Minh, B. Q. AliSim: a fast and versatile phylogenetic sequence simulator for the genomic era. Mol. Biol. Evol. 39, msac092 (2022).","journal-title":"Mol. Biol. Evol."},{"key":"3095_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-024-55264-0","volume":"16","author":"A Baltzis","year":"2025","unstructured":"Baltzis, A. et al. multistrap: boosting phylogenetic analyses with structural information. Nat. Commun. 16, 1\u201314 (2025).","journal-title":"Nat. Commun."},{"key":"3095_CR32","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1093\/molbev\/msv150","volume":"32","author":"V Lefort","year":"2015","unstructured":"Lefort, V., Desper, R. & Gascuel, O. FastME 2.0: a comprehensive, accurate, and fast distance-based phylogeny inference program. Mol. Biol. Evol. 32, 2798\u20132800 (2015).","journal-title":"Mol. Biol. Evol."},{"key":"3095_CR33","doi-asserted-by":"publisher","unstructured":"Gudy\u015b, A., Deorowicz, S. & Zielezinski, A. extHomFam v37.0: structural benchmark for protein multiple sequence alignments. Zenodo https:\/\/doi.org\/10.5281\/zenodo.6524236 (2025).","DOI":"10.5281\/zenodo.6524236"},{"key":"3095_CR34","doi-asserted-by":"publisher","unstructured":"Deorowicz, S., Gudy\u015b, A. & Zielezinski, A. extHomFam-mix-sep v37.0: structural benchmark for protein multiple sequence alignments (downsampled the largest 121 families). Zenodo https:\/\/doi.org\/10.5281\/zenodo.18418209 (2026).","DOI":"10.5281\/zenodo.18418209"},{"key":"3095_CR35","doi-asserted-by":"publisher","unstructured":"Zielezinski, A., Gudy\u015b, A. & Deorowicz, S. afdb_clusters v1.0: AlphaFold-derived structure-based dataset for benchmarking MSA tools. Zenodo https:\/\/doi.org\/10.5281\/zenodo.16082638 (2025).","DOI":"10.5281\/zenodo.16082638"},{"key":"3095_CR36","doi-asserted-by":"publisher","unstructured":"Zielezinski, A., Gudy\u015b, A. & Deorowicz, S. simulated_msa v1.0: simulated multiple sequence alignments with known phylogenies for benchmarking MSA tools. Zenodo https:\/\/doi.org\/10.5281\/zenodo.15971352 (2025).","DOI":"10.5281\/zenodo.15971352"},{"key":"3095_CR37","doi-asserted-by":"publisher","unstructured":"Zielezinski, A., Gudy\u015b, A. & Deorowicz, S. active_sites v1.0: enzyme domain sequences with annotated active sites from Pfam v37.1 for benchmarking MSA tools. Zenodo https:\/\/doi.org\/10.5281\/zenodo.16023626 (2025).","DOI":"10.5281\/zenodo.16023626"},{"key":"3095_CR38","doi-asserted-by":"publisher","unstructured":"Deorowicz, S., Gudy\u015b, A. & Zielezinski, A. famsa2_tuning_dataset v1.0: reference protein multiple sequence alignments for tuning the dissimilarity measure in FAMSA2. Zenodo https:\/\/doi.org\/10.5281\/zenodo.18412132 (2026).","DOI":"10.5281\/zenodo.18412132"}],"container-title":["Nature Biotechnology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41587-026-03095-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41587-026-03095-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41587-026-03095-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T09:05:00Z","timestamp":1776157500000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41587-026-03095-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,14]]},"references-count":38,"alternative-id":["3095"],"URL":"https:\/\/doi.org\/10.1038\/s41587-026-03095-3","relation":{},"ISSN":["1087-0156","1546-1696"],"issn-type":[{"value":"1087-0156","type":"print"},{"value":"1546-1696","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,14]]},"assertion":[{"value":"21 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}