{"entity": "researcher", "timestamp": "2026-08-20T21:13:12.542Z", "family": "Andreeva", "given": "Antonina", "initials": "A", "orcid": "0000-0002-0450-0091", "affiliations": ["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Hinxton, UK."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/c3c34ecb82054acfa7ead18dd8882f39.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/c3c34ecb82054acfa7ead18dd8882f39"}}, "publications": [{"entity": "publication", "iuid": "97815495d9ee4b1f9a78796452b64b1c", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/97815495d9ee4b1f9a78796452b64b1c.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/97815495d9ee4b1f9a78796452b64b1c"}}, "title": "The Pfam protein families database: embracing AI/ML.", "authors": [{"family": "Paysan-Lafosse", "given": "Typhaine", "initials": "T", "orcid": "0000-0001-5663-0894", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/9d642d6394c34f2b971ecb3f78a21523.json"}}, {"family": "Andreeva", "given": "Antonina", "initials": "A", "orcid": "0000-0002-0450-0091", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/c3c34ecb82054acfa7ead18dd8882f39.json"}}, {"family": "Blum", "given": "Matthias", "initials": "M", "orcid": "0000-0001-5773-4724", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/0b436424abf44aef98754474725ce9ab.json"}}, {"family": "Chuguransky", "given": "Sara Rocio", "initials": "SR", "orcid": "0000-0002-0520-0736", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/fb030e06c24947be8ff47fd830aa8b79.json"}}, {"family": "Grego", "given": "Tiago", "initials": "T"}, {"family": "Pinto", "given": "Beatriz Lazaro", "initials": "BL"}, {"family": "Salazar", "given": "Gustavo A", "initials": "GA", "orcid": "0000-0001-9208-4966", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ece1cf77fb0a44a7ae45dde5f96b62dd.json"}}, {"family": "Bileschi", "given": "Maxwell L", "initials": "ML"}, {"family": "Llinares-L\u00f3pez", "given": "Felipe", "initials": "F"}, {"family": "Meng-Papaxanthos", "given": "Laetitia", "initials": "L", "orcid": "0000-0002-0521-621X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/73b656807bdd4768887044006838042b.json"}}, {"family": "Colwell", "given": "Lucy J", "initials": "LJ"}, {"family": "Grishin", "given": "Nick V", "initials": "NV"}, {"family": "Schaeffer", "given": "R Dustin", "initials": "RD", "orcid": "0000-0001-6502-1425", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/b30d38ae15d94115b87f21c3ecf64b8e.json"}}, {"family": "Clementel", "given": "Damiano", "initials": "D"}, {"family": "Tosatto", "given": "Silvio C E", "initials": "SCE", "orcid": "0000-0003-4525-7793", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/152b8eca864e44f1954ee4952c60aa0d.json"}}, {"family": "Sonnhammer", "given": "Erik", "initials": "E"}, {"family": "Wood", "given": "Valerie", "initials": "V", "orcid": "0000-0001-6330-7526", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/8e02cbfbedcc47e2be70b605ebb04c6c.json"}}, {"family": "Bateman", "given": "Alex", "initials": "A", "orcid": "0000-0002-6982-4660", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/01e1775e560147c2b7c40e1ba7d95a4e.json"}}], "type": "journal article", "published": "2025-01-06", "journal": {"title": "Nucleic Acids Res.", "issn": "1362-4962", "volume": "53", "issue": "D1", "pages": "D523-D534", "issn-l": "0305-1048"}, "abstract": "The Pfam protein families database is a comprehensive collection of protein domains and families used for genome annotation and protein structure and function analysis (https://www.ebi.ac.uk/interpro/). This update describes major developments in Pfam since 2020, including decommissioning the Pfam website and integration with InterPro, harmonization with the ECOD structural classification, and expanded curation of metagenomic, microprotein and repeat-containing families. We highlight how AlphaFold structure predictions are being leveraged to refine domain boundaries and identify new domains. New families discovered through large-scale sequence similarity analysis of AlphaFold models are described. We also detail the development of Pfam-N, which uses deep learning to expand family coverage, achieving an 8.8% increase in UniProtKB coverage compared to standard Pfam. We discuss plans for more frequent Pfam releases integrated with InterPro and the potential for artificial intelligence to further assist curation. Despite recent advances, many protein families remain to be classified, and Pfam continues working toward comprehensive coverage of the protein universe.", "doi": "10.1093/nar/gkae997", "pmid": "39540428", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC11701544"}, {"db": "pii", "key": "7900195"}], "notes": [], "created": "2026-08-20T09:50:10.510Z", "modified": "2026-08-20T09:50:10.866Z"}, {"entity": "publication", "iuid": "e0d872b5ec224de6822fcf82082b759a", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/e0d872b5ec224de6822fcf82082b759a.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/e0d872b5ec224de6822fcf82082b759a"}}, "title": "Uncovering new families and folds in the natural protein universe.", "authors": [{"family": "Durairaj", "given": "Janani", "initials": "J", "orcid": "0000-0002-1698-4556", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bbc37e3024a34e18b93c50bd7ce6c3a7.json"}}, {"family": "Waterhouse", "given": "Andrew M", "initials": "AM", "orcid": "0009-0004-5717-6063", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/acfd68ed308a4b39971d70a1d48adc09.json"}}, {"family": "Mets", "given": "Toomas", "initials": "T"}, {"family": "Brodiazhenko", "given": "Tetiana", "initials": "T"}, {"family": "Abdullah", "given": "Minhal", "initials": "M", "orcid": "0000-0002-6018-314X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1c8fb279f2df41d2a5d86e7afbab9592.json"}}, {"family": "Studer", "given": "Gabriel", "initials": "G"}, {"family": "Tauriello", "given": "Gerardo", "initials": "G", "orcid": "0000-0002-5921-7007", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/f2bb2e6461c040f59429b6d8bd838523.json"}}, {"family": "Akdel", "given": "Mehmet", "initials": "M"}, {"family": "Andreeva", "given": "Antonina", "initials": "A", "orcid": "0000-0002-0450-0091", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/c3c34ecb82054acfa7ead18dd8882f39.json"}}, {"family": "Bateman", "given": "Alex", "initials": "A", "orcid": "0000-0002-6982-4660", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/01e1775e560147c2b7c40e1ba7d95a4e.json"}}, {"family": "Tenson", "given": "Tanel", "initials": "T", "orcid": "0000-0002-0260-3601", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/44fd1d5f2b4f43c0a2067d75306c85ed.json"}}, {"family": "Hauryliuk", "given": "Vasili", "initials": "V", "orcid": "0000-0003-2389-5057", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1884d638ebd34b34bcabc105ca2f4092.json"}}, {"family": "Schwede", "given": "Torsten", "initials": "T", "orcid": "0000-0003-2715-335X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ce9338dc4e0f41c0b756280291b43516.json"}}, {"family": "Pereira", "given": "Joana", "initials": "J", "orcid": "0000-0002-5588-6588", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/18123de080c84f7fba8ca71f1f294773.json"}}], "type": "journal article", "published": "2023-10-00", "journal": {"title": "Nature", "issn": "1476-4687", "volume": "622", "issue": "7983", "pages": "646-653", "issn-l": "0028-0836"}, "abstract": "We are now entering a new era in protein sequence and structure annotation, with hundreds of millions of predicted protein structures made available through the AlphaFold database1. These models cover nearly all proteins that are known, including those challenging to annotate for function or putative biological role using standard homology-based approaches. In this study, we examine the extent to which the AlphaFold database has structurally illuminated this 'dark matter' of the natural protein universe at high predicted accuracy. We further describe the protein diversity that these models cover as an annotated interactive sequence similarity network, accessible at https://uniprot3d.org/atlas/AFDB90v4 . By searching for novelties from sequence, structure and semantic perspectives, we uncovered the \u03b2-flower fold, added several protein families to Pfam database2 and experimentally demonstrated that one of these belongs to a new superfamily of translation-targeting toxin-antitoxin systems, TumE-TumA. This work underscores the value of large-scale efforts in identifying, annotating and prioritizing new protein families. By leveraging the recent deep learning revolution in protein bioinformatics, we can now shed light into uncharted areas of the protein universe at an unprecedented scale, paving the way to innovations in life sciences and biotechnology.", "doi": "10.1038/s41586-023-06622-3", "pmid": "37704037", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC10584680"}, {"db": "pii", "key": "10.1038/s41586-023-06622-3"}], "notes": [], "created": "2026-08-20T08:58:40.431Z", "modified": "2026-08-20T08:58:40.772Z"}, {"entity": "publication", "iuid": "740732b7f155421d92f9a2674081defb", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/740732b7f155421d92f9a2674081defb.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/740732b7f155421d92f9a2674081defb"}}, "title": "What is hidden in the darkness? Deep-learning assisted large-scale protein family curation uncovers novel protein families and folds", "authors": [{"family": "Durairaj", "given": "Janani", "initials": "J", "orcid": "0000-0002-1698-4556", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bbc37e3024a34e18b93c50bd7ce6c3a7.json"}}, {"family": "Waterhouse", "given": "Andrew M", "initials": "AM"}, {"family": "Mets", "given": "Toomas", "initials": "T", "orcid": "0000-0002-6796-7000", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7dbceebe30234575b3575ef4f44c0511.json"}}, {"family": "Brodiazhenko", "given": "Tetiana", "initials": "T"}, {"family": "Abdullah", "given": "Minhal", "initials": "M", "orcid": "0000-0002-6018-314X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1c8fb279f2df41d2a5d86e7afbab9592.json"}}, {"family": "Studer", "given": "Gabriel", "initials": "G", "orcid": "0000-0003-0462-1456", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a063e4b2d8284a1486037652aa35b11b.json"}}, {"family": "Akdel", "given": "Mehmet", "initials": "M", "orcid": "0000-0002-6092-3494", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/adcc39b269804e179cbea223cc8dc83d.json"}}, {"family": "Andreeva", "given": "Antonina", "initials": "A", "orcid": "0000-0002-0450-0091", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/c3c34ecb82054acfa7ead18dd8882f39.json"}}, {"family": "Bateman", "given": "Alex", "initials": "A", "orcid": "0000-0002-6982-4660", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/01e1775e560147c2b7c40e1ba7d95a4e.json"}}, {"family": "Tenson", "given": "Tanel", "initials": "T", "orcid": "0000-0002-0260-3601", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/44fd1d5f2b4f43c0a2067d75306c85ed.json"}}, {"family": "Hauryliuk", "given": "Vasili", "initials": "V", "orcid": "0000-0003-2389-5057", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1884d638ebd34b34bcabc105ca2f4092.json"}}, {"family": "Schwede", "given": "Torsten", "initials": "T", "orcid": "0000-0003-2715-335X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ce9338dc4e0f41c0b756280291b43516.json"}}, {"family": "Pereira", "given": "Joana", "initials": "J", "orcid": "0000-0002-5588-6588", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/18123de080c84f7fba8ca71f1f294773.json"}}], "type": "posted-content", "published": "2023-03-15", "journal": {"issn-l": null}, "abstract": null, "doi": "10.1101/2023.03.14.532539", "pmid": null, "labels": [], "xrefs": [], "notes": [], "created": "2026-08-20T10:44:24.617Z", "modified": "2026-08-20T10:44:24.767Z"}]}