{"entity": "researcher", "timestamp": "2026-08-22T07:48:27.594Z", "family": "Ostankovich", "given": "Vladislav", "initials": "V", "orcid": "0000-0001-7020-8825", "affiliations": ["Innopolis University, Innopolis, Russian Federation."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/b3a24a4ce6254b1aa5ee0ffc987b3b45.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/b3a24a4ce6254b1aa5ee0ffc987b3b45"}}, "publications": [{"entity": "publication", "iuid": "82fcc044a9424abea9804a6b4242c8a5", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/82fcc044a9424abea9804a6b4242c8a5.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/82fcc044a9424abea9804a6b4242c8a5"}}, "title": "Analysis of the Human Protein Atlas Weakly Supervised Single-Cell Classification competition.", "authors": [{"family": "Le", "given": "Trang", "initials": "T"}, {"family": "Winsnes", "given": "Casper F", "initials": "CF", "orcid": "0000-0002-0028-5865", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/edeb3bc6c95d4185bf2098bf1e4a5e3c.json"}}, {"family": "Axelsson", "given": "Ulrika", "initials": "U", "orcid": "0000-0002-0273-9306", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/5c60c73df0c445b38aabb5e91a118a2b.json"}}, {"family": "Xu", "given": "Hao", "initials": "H"}, {"family": "Mohanakrishnan Kaimal", "given": "Jayasankar", "initials": "J"}, {"family": "Mahdessian", "given": "Diana", "initials": "D"}, {"family": "Dai", "given": "Shubin", "initials": "S", "orcid": "0000-0001-6680-0500", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7f4835d5b16a400b9dd9aaff8a8d49f7.json"}}, {"family": "Makarov", "given": "Ilya S", "initials": "IS"}, {"family": "Ostankovich", "given": "Vladislav", "initials": "V", "orcid": "0000-0001-7020-8825", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/b3a24a4ce6254b1aa5ee0ffc987b3b45.json"}}, {"family": "Xu", "given": "Yang", "initials": "Y"}, {"family": "Benhamou", "given": "Eric", "initials": "E"}, {"family": "Henkel", "given": "Christof", "initials": "C", "orcid": "0000-0002-2913-3662", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2560edfc894b48b4849f28173e580861.json"}}, {"family": "Solovyev", "given": "Roman A", "initials": "RA", "orcid": "0000-0003-0312-452X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/6aee06b530294a58b87b0e0c40aa316d.json"}}, {"family": "Bani\u0107", "given": "Nikola", "initials": "N"}, {"family": "Bo\u0161njak", "given": "Vito", "initials": "V", "orcid": "0000-0003-3786-0592", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/14fb5bfa316e4fb48cb6afc00ccbb2dc.json"}}, {"family": "Bo\u0161njak", "given": "Ana", "initials": "A", "orcid": "0000-0002-3425-8363", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/58a2bdb9d5b94686a57238eddc685730.json"}}, {"family": "Mili\u010devi\u0107", "given": "Andrija", "initials": "A", "orcid": "0000-0001-7148-7651", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ffd8bc851170484c85db3c7699c3c49d.json"}}, {"family": "Ouyang", "given": "Wei", "initials": "W", "orcid": "0000-0002-0291-926X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/56f601e1d1c6448aab0c3a1e3cffdbfc.json"}}, {"family": "Lundberg", "given": "Emma", "initials": "E", "orcid": "0000-0001-7034-0850", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bb07e6d0122c4528a927c1fe922e3bc8.json"}}], "type": "journal article", "published": "2022-10-00", "journal": {"title": "Nat. Methods", "issn": "1548-7105", "volume": "19", "issue": "10", "pages": "1221-1229", "issn-l": "1548-7091"}, "abstract": "While spatial proteomics by fluorescence imaging has quickly become an essential discovery tool for researchers, fast and scalable methods to classify and embed single-cell protein distributions in such images are lacking. Here, we present the design and analysis of the results from the competition Human Protein Atlas - Single-Cell Classification hosted on the Kaggle platform. This represents a crowd-sourced competition to develop machine learning models trained on limited annotations to label single-cell protein patterns in fluorescent images. The particular challenges of this competition include class imbalance, weak labels and multi-label classification, prompting competitors to apply a wide range of approaches in their solutions. The winning models serve as the first subcellular omics tools that can annotate single-cell locations, extract single-cell features and capture cellular dynamics.", "doi": "10.1038/s41592-022-01606-z", "pmid": "36175767", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC9550622"}, {"db": "pii", "key": "10.1038/s41592-022-01606-z"}], "notes": [], "created": "2026-08-20T09:02:51.438Z", "modified": "2026-08-20T09:02:51.797Z"}]}