{"id":"W4400674289","doi":"10.1038/s41467-024-50150-1","title":"scSemiProfiler: Advancing large-scale single-cell studies through semi-profiling with deep generative models and active learning","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec-Société et Culture; Government of Canada","keywords":"Profiling (computer programming); Computer science; Scalability; Expansive; Computational biology; Generative grammar; Deep learning; Deconvolution; Artificial intelligence; Machine learning; Biology; Algorithm","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":[0.0001478609,0.0002047791,0.0001861381,0.00004284336,0.0004570306,0.00006589213,0.0002903899,0.0002610853,0.000001912416],"category_scores_gemma":[0.00004650064,0.0001742578,0.00005972735,0.0001806512,0.0001741857,0.00003475401,0.0002561068,0.0008543571,0.000001632857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000437078,"about_ca_system_score_gemma":0.00006625323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005067237,"about_ca_topic_score_gemma":0.0003986699,"domain_scores_codex":[0.9989577,0.0001232833,0.000170615,0.0003897687,0.0001109054,0.0002477256],"domain_scores_gemma":[0.9990144,0.0001083518,0.00005682586,0.0005724622,0.0001970824,0.00005088933],"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":[0.00009222737,0.0001894043,0.0009487491,0.0001317374,0.0003383731,0.000003943881,0.006868212,0.004342563,0.9817778,0.001966955,0.0003864874,0.002953485],"study_design_scores_gemma":[0.001163564,0.0006202584,0.00004954982,0.0003588549,0.000277785,0.00004297413,0.01535777,0.07397909,0.859276,0.001545662,0.04645706,0.0008714391],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4870386,0.4052619,0.09464624,0.001523396,0.0003982729,0.0006836012,0.0001297884,0.0002134701,0.0101047],"genre_scores_gemma":[0.9324109,0.01090733,0.05551474,0.0002799581,0.000114184,0.00004950776,0.0003225324,0.0000442536,0.0003565916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4453723,"threshold_uncertainty_score":0.7106025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02703485611255669,"score_gpt":0.2965456397250976,"score_spread":0.2695107836125409,"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."}}