{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000436685,0.0008284638,0.000789464,0.0001289065,0.0004614892,0.000159666,0.0003496223,0.000677194,0.00000316149],"category_scores_gemma":[0.0001245773,0.0008136384,0.0001589555,0.0002862946,0.0002403656,0.00004511875,0.0006951095,0.0009685206,0.000006759151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001643652,"about_ca_system_score_gemma":0.0003182747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002495031,"about_ca_topic_score_gemma":0.00004221047,"domain_scores_codex":[0.9963737,0.0002056582,0.0005119863,0.001697526,0.000343351,0.0008677925],"domain_scores_gemma":[0.9978662,0.00006564669,0.000429241,0.0007651475,0.0006620666,0.0002117127],"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":[0.0001735311,0.0001391261,0.003372519,0.0005107104,0.0004360572,0.00003135985,0.0002664276,0.0141628,0.9808217,0.00003692521,0.00004383985,0.00000499233],"study_design_scores_gemma":[0.001107054,0.0003694216,0.0003224289,0.0004436354,0.0002178929,9.017737e-8,0.0004175459,0.006801676,0.9887795,0.00001631486,0.0004243873,0.00110004],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9196576,0.008351537,0.07004894,0.00007043682,0.0006395936,0.000748765,0.0001888909,0.0002603123,0.00003391117],"genre_scores_gemma":[0.95652,0.004479856,0.03758663,0.0001875939,0.0006449395,0.0002212702,0.000009806236,0.0002954538,0.00005444761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0368624,"threshold_uncertainty_score":0.9994314,"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."}}