{"id":"W4392190154","doi":"10.1101/2024.02.21.581497","title":"A highly scalable approach to topic modelling in single-cell data by approximate pseudobulk projection","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Scalability; Preprocessor; Probabilistic logic; Projection (relational algebra); Representation (politics); Data mining; Theoretical computer science; Artificial intelligence; Algorithm; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003266255,0.00128375,0.002281284,0.001604795,0.0008550028,0.002639025,0.003161756,0.001770682,0.002898555],"category_scores_gemma":[0.00922798,0.001225061,0.002339697,0.003137453,0.001130626,0.002413353,0.003007442,0.003354317,0.002414837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001251714,"about_ca_system_score_gemma":0.00223935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01184494,"about_ca_topic_score_gemma":0.01354763,"domain_scores_codex":[0.9981239,0.0007101079,0.00009607773,0.0004796183,0.0004240539,0.0001662506],"domain_scores_gemma":[0.9953069,0.00302699,0.0002025243,0.0006762814,0.000594667,0.0001925443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004774826,0.0001896176,0.00372236,0.0004513275,0.0003861424,0.0003620049,0.0005435198,0.681703,0.02273068,0.0363893,0.01340738,0.2396372],"study_design_scores_gemma":[0.000005467195,0.00000604009,0.0001571177,0.000003794915,0.000004896324,0.00001836919,0.00001629478,0.9888816,0.0006050915,0.00968774,0.0006053559,0.000008199346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003250221,0.0001146219,0.995351,0.00009571656,0.00002094898,0.00002409934,0.00017042,0.0008514591,0.0001215357],"genre_scores_gemma":[0.1351851,0.0004727872,0.8569703,0.000274083,0.0001945527,0.0005456728,0.003169632,0.000849176,0.0023386],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01184494,"threshold_uncertainty_score":0.023552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02987459943069743,"score_gpt":0.2195691386022869,"score_spread":0.1896945391715894,"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."}}