{"id":"W4409154928","doi":"10.1371/journal.pcbi.1012904","title":"scTrans: Sparse attention powers fast and accurate cell type annotation in single-cell RNA-seq data","year":2025,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Annotation; Adaptability; Computer science; Generalization; Curse of dimensionality; Computational biology; Cluster analysis; RNA-Seq; Data type; Artificial intelligence; Data mining; Biology; Gene; Transcriptome; Mathematics; Genetics; Gene expression","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001174481,0.0001451002,0.0001504854,0.0001101039,0.00006038857,0.00002671323,0.0002051289,0.0001670502,0.000008766845],"category_scores_gemma":[0.00004103421,0.0001509022,0.00002718164,0.000166468,0.0001004522,0.00001261251,0.00008605048,0.0001026763,0.000008434318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001687034,"about_ca_system_score_gemma":0.00009523566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003328476,"about_ca_topic_score_gemma":0.00006252198,"domain_scores_codex":[0.9989249,0.00009666636,0.0002658516,0.0004661197,0.00006140055,0.0001851003],"domain_scores_gemma":[0.9995262,0.00005404558,0.00007172817,0.000202561,0.0001077355,0.00003771119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002059546,0.0003295334,0.0145159,0.0000574604,0.00003721554,0.000002234344,0.00004467129,0.002564988,0.9792126,0.0002191474,0.0002836939,0.002526534],"study_design_scores_gemma":[0.02113498,0.004446255,0.1262116,0.0004351573,0.0004627558,0.00003985732,0.0008866841,0.2838231,0.5212039,0.01459284,0.023648,0.003114854],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768992,0.000802489,0.02014331,0.0003306104,0.0002800281,0.0001976197,0.0001049687,0.00001602658,0.001225747],"genre_scores_gemma":[0.9926246,0.0001354932,0.002891883,0.0004118348,0.00005529217,0.000005213709,0.003684658,0.00001178506,0.0001791819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4580088,"threshold_uncertainty_score":0.6153613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03666320982266986,"score_gpt":0.268432528660476,"score_spread":0.2317693188378061,"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."}}