{"id":"W3186675810","doi":"10.1101/2021.07.26.453767","title":"Using topic modeling to detect cellular crosstalk in scRNA-seq","year":2021,"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":"Institute of Infection and Immunity","funders":"","keywords":"Computer science; Population; Cluster analysis; Latent Dirichlet allocation; Ranking (information retrieval); Computational biology; Artificial intelligence; Topic model; Biology","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":[0.0003773139,0.0005464537,0.0005327053,0.0002044057,0.0001276588,0.0002814639,0.0005352632,0.0007885084,0.0000183116],"category_scores_gemma":[0.0001391035,0.0006638678,0.0002312776,0.000338744,0.0000544052,0.00001115875,0.000569394,0.000577832,0.000007327777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000178979,"about_ca_system_score_gemma":0.0006825709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000432546,"about_ca_topic_score_gemma":0.00008150176,"domain_scores_codex":[0.9971284,0.0001223221,0.0005821888,0.001254481,0.0002659525,0.0006467055],"domain_scores_gemma":[0.9980794,0.00000852434,0.0001402899,0.001183034,0.0003245775,0.0002641728],"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":[0.00004160384,0.00006912222,0.003391839,0.0001758205,0.0000645726,0.00007618037,0.00001257259,0.02116545,0.9749823,0.00000836123,0.000007906583,0.000004243032],"study_design_scores_gemma":[0.000514202,0.00005815753,0.001668837,0.0003475153,0.00005167019,3.99237e-8,0.000006459646,0.01422482,0.9816868,0.00000143844,0.0005921996,0.0008478428],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9242077,0.002223389,0.07180633,0.00003705722,0.001162432,0.0004470994,0.00005290876,0.00005608169,0.000007002732],"genre_scores_gemma":[0.9777156,0.0001878879,0.02102417,0.0002821782,0.0005844978,0.00005655652,0.000001843878,0.0001403304,0.000006976335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05350786,"threshold_uncertainty_score":0.9995813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02859558220589347,"score_gpt":0.2382790119949464,"score_spread":0.2096834297890529,"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."}}