{"id":"W4388851247","doi":"10.1101/2023.11.20.567929","title":"scSemiProfiler: Advancing Large-scale Single-cell Studies through Semi-profiling with Deep Generative Models and Active Learning","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; McGill University Health Centre","funders":"","keywords":"Profiling (computer programming); Computer science; Scalability; Expansive; Generative grammar; Artificial intelligence; Deep learning; Deconvolution; Computational biology; Machine learning; Biology; Algorithm","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":[0.00231336,0.0008539553,0.000739233,0.0008145432,0.0003421424,0.001323168,0.001451082,0.001456152,0.00196896],"category_scores_gemma":[0.003369859,0.000683907,0.0009158977,0.0005639145,0.001103852,0.0009863987,0.001908688,0.002315344,0.0009836012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005129141,"about_ca_system_score_gemma":0.001045498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001378096,"about_ca_topic_score_gemma":0.002317232,"domain_scores_codex":[0.9995767,0.0001342255,0.00001477757,0.0001112968,0.0001274854,0.00003547994],"domain_scores_gemma":[0.9981235,0.001170507,0.0001564704,0.0002993469,0.0001308297,0.0001193629],"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":[0.0003727909,0.000176373,0.009453228,0.0004084943,0.0002402043,0.0004466442,0.0002855981,0.6802486,0.1535066,0.02738662,0.01155464,0.1159202],"study_design_scores_gemma":[0.00001147978,0.00001874384,0.0006056899,0.00001418896,0.000008858381,0.00005635159,0.00001498425,0.9666672,0.01679794,0.01374174,0.002043667,0.00001901764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01903253,0.0002116258,0.9753544,0.000239327,0.0000464282,0.00002953434,0.0005041303,0.003951091,0.0006309368],"genre_scores_gemma":[0.387187,0.0004571848,0.6052523,0.0004776435,0.00007351963,0.0002887217,0.002014998,0.001468766,0.0027798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00231336,"threshold_uncertainty_score":0.01223439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02704318795272774,"score_gpt":0.2403278573977704,"score_spread":0.2132846694450426,"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."}}