{"entity": "researcher", "timestamp": "2026-08-20T20:50:22.518Z", "family": "Nielsen", "given": "Henrik", "initials": "H", "orcid": "0000-0002-9412-9643", "affiliations": ["Department of Health Technology, Section for Bioinformatics, Technical University of Denmark, Kgs. Lyngby, Denmark. henni@dtu.dk."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/95aab73521844700a8137cfc2cb287b0.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/95aab73521844700a8137cfc2cb287b0"}}, "publications": [{"entity": "publication", "iuid": "d3c8b97f7d4647dc9088d1705ac540e7", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/d3c8b97f7d4647dc9088d1705ac540e7.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/d3c8b97f7d4647dc9088d1705ac540e7"}}, "title": "SignalP 6.0 achieves signal peptide prediction across all types using protein language models", "authors": [{"family": "Teufel", "given": "Felix", "initials": "F", "orcid": "0000-0003-1275-8065", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/5d5809964f694f7fb16e0745dbb645d5.json"}}, {"family": "Armenteros", "given": "Jos\u00e9 Juan Almagro", "initials": "JJA"}, {"family": "Johansen", "given": "Alexander Rosenberg", "initials": "AR"}, {"family": "G\u00edslason", "given": "Magn\u00fas Halld\u00f3r", "initials": "MH"}, {"family": "Pihl", "given": "Silas Irby", "initials": "SI"}, {"family": "Tsirigos", "given": "Konstantinos D", "initials": "KD", "orcid": "0000-0001-5280-1107", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/85e1896a52d04cb7b4475ebba4d17505.json"}}, {"family": "Winther", "given": "Ole", "initials": "O", "orcid": "0000-0002-1966-3205", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/9dea7f2a81d249cd99f8dec60f422770.json"}}, {"family": "Brunak", "given": "S\u00f8ren", "initials": "S"}, {"family": "von Heijne", "given": "Gunnar", "initials": "G", "orcid": "0000-0002-4490-8569", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/529a460e668a479ca7d9b9271375ef9f.json"}}, {"family": "Nielsen", "given": "Henrik", "initials": "H", "orcid": "0000-0002-9412-9643", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/95aab73521844700a8137cfc2cb287b0.json"}}], "type": "posted-content", "published": "2021-06-10", "journal": {"issn-l": null}, "abstract": null, "doi": "10.1101/2021.06.09.447770", "pmid": null, "labels": [], "xrefs": [], "notes": [], "created": "2026-08-20T10:04:45.794Z", "modified": "2026-08-20T10:04:45.920Z"}, {"entity": "publication", "iuid": "1747f563e3d0432b8c0965b609614d6b", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/1747f563e3d0432b8c0965b609614d6b.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/1747f563e3d0432b8c0965b609614d6b"}}, "title": "Detecting sequence signals in targeting peptides using deep learning.", "authors": [{"family": "Almagro Armenteros", "given": "Jose Juan", "initials": "JJ"}, {"family": "Salvatore", "given": "Marco", "initials": "M", "orcid": "0000-0001-5775-0417", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/cc13d7ecab9d4dc6b5330f387678a699.json"}}, {"family": "Emanuelsson", "given": "Olof", "initials": "O", "orcid": "0000-0002-8879-9245", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a51c22f2bc594fe3a349bec5363f394f.json"}}, {"family": "Winther", "given": "Ole", "initials": "O"}, {"family": "von Heijne", "given": "Gunnar", "initials": "G", "orcid": "0000-0002-4490-8569", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/529a460e668a479ca7d9b9271375ef9f.json"}}, {"family": "Elofsson", "given": "Arne", "initials": "A", "orcid": "0000-0002-7115-9751", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/248e70e81bd64f31a5f83e6e329bba95.json"}}, {"family": "Nielsen", "given": "Henrik", "initials": "H", "orcid": "0000-0002-9412-9643", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/95aab73521844700a8137cfc2cb287b0.json"}}], "type": "journal article", "published": "2019-10-00", "journal": {"title": "Life Sci. Alliance", "issn": "2575-1077", "volume": "2", "issue": "5", "issn-l": null}, "abstract": "In bioinformatics, machine learning methods have been used to predict features embedded in the sequences. In contrast to what is generally assumed, machine learning approaches can also provide new insights into the underlying biology. Here, we demonstrate this by presenting TargetP 2.0, a novel state-of-the-art method to identify N-terminal sorting signals, which direct proteins to the secretory pathway, mitochondria, and chloroplasts or other plastids. By examining the strongest signals from the attention layer in the network, we find that the second residue in the protein, that is, the one following the initial methionine, has a strong influence on the classification. We observe that two-thirds of chloroplast and thylakoid transit peptides have an alanine in position 2, compared with 20% in other plant proteins. We also note that in fungi and single-celled eukaryotes, less than 30% of the targeting peptides have an amino acid that allows the removal of the N-terminal methionine compared with 60% for the proteins without targeting peptide. The importance of this feature for predictions has not been highlighted before.", "doi": "10.26508/lsa.201900429", "pmid": "31570514", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC6769257"}, {"db": "pii", "key": "2/5/e201900429"}], "notes": [], "created": "2026-08-20T13:03:51.409Z", "modified": "2026-08-20T13:03:51.559Z"}, {"entity": "publication", "iuid": "ccefc040f04b48969c2df248758fa3a3", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/ccefc040f04b48969c2df248758fa3a3.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/ccefc040f04b48969c2df248758fa3a3"}}, "title": "A Brief History of Protein Sorting Prediction.", "authors": [{"family": "Nielsen", "given": "Henrik", "initials": "H", "orcid": "0000-0002-9412-9643", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/95aab73521844700a8137cfc2cb287b0.json"}}, {"family": "Tsirigos", "given": "Konstantinos D", "initials": "KD"}, {"family": "Brunak", "given": "S\u00f8ren", "initials": "S"}, {"family": "von Heijne", "given": "Gunnar", "initials": "G"}], "type": "journal article", "published": "2019-06-00", "journal": {"title": "Protein J", "issn": "1875-8355", "volume": "38", "issue": "3", "pages": "200-216", "issn-l": null}, "abstract": "Ever since the signal hypothesis was proposed in 1971, the exact nature of signal peptides has been a focus point of research. The prediction of signal peptides and protein subcellular location from amino acid sequences has been an important problem in bioinformatics since the dawn of this research field, involving many statistical and machine learning technologies. In this review, we provide a historical account of how position-weight matrices, artificial neural networks, hidden Markov models, support vector machines and, lately, deep learning techniques have been used in the attempts to predict where proteins go. Because the secretory pathway was the first one to be studied both experimentally and through bioinformatics, our main focus is on the historical development of prediction methods for signal peptides that target proteins for secretion; prediction methods to identify targeting signals for other cellular compartments are treated in less detail.", "doi": "10.1007/s10930-019-09838-3", "pmid": "31119599", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC6589146"}, {"db": "pii", "key": "10.1007/s10930-019-09838-3"}], "notes": [], "created": "2026-08-20T06:40:11.923Z", "modified": "2026-08-20T06:40:12.014Z"}]}