{"id":"W4413355637","doi":"10.1093/bib/bbaf428","title":"HiCat: a semi-supervised approach for cell type annotation","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Research Council Canada; Canada Research Chairs; Michael Smith Health Research BC; Alliance de recherche numérique du Canada; Western Canada Research Grid","keywords":"Computer science; Annotation; Artificial intelligence; Pipeline (software); Dimensionality reduction; Classifier (UML); Cluster analysis; Machine learning; Identification (biology); Scalability; Supervised learning; Benchmark (surveying); Unsupervised learning; Pattern recognition (psychology); Data mining; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001595665,0.0001307889,0.0001382444,0.00007869746,0.0000646063,0.00004002864,0.0001726492,0.0001834905,0.00000200398],"category_scores_gemma":[0.0000791827,0.0001328698,0.00006435934,0.0002018203,0.00004148553,0.000008608557,0.00003816075,0.00008104795,0.000002463413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001855717,"about_ca_system_score_gemma":0.00009977511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002773265,"about_ca_topic_score_gemma":0.000007206964,"domain_scores_codex":[0.9992272,0.0000111067,0.0003260165,0.000153878,0.00007178836,0.0002100425],"domain_scores_gemma":[0.9995773,0.00001743927,0.0000660843,0.0002102333,0.00009686287,0.0000320365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001647284,0.001503488,0.01172882,0.004722878,0.0001946087,0.000001758906,0.004112567,0.004758154,0.8303127,0.004498729,0.08095659,0.05556244],"study_design_scores_gemma":[0.007641048,0.0007362869,0.001935556,0.0001534408,0.00009510434,0.000008733919,0.0009072782,0.3982855,0.3873568,0.0008275103,0.2010067,0.001046124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4148454,0.0008322124,0.539581,0.0006051539,0.0004748628,0.001353358,0.00006434457,0.00006543534,0.0421782],"genre_scores_gemma":[0.8485598,0.0002275994,0.1440668,0.00444777,0.0000871843,0.00007028798,0.0009093524,0.0000277562,0.001603456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4429559,"threshold_uncertainty_score":0.5418274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01168797032225961,"score_gpt":0.2370859393686366,"score_spread":0.225397969046377,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}