{"id":"W4225380763","doi":"10.1101/2022.04.22.487554","title":"GeneVector: Identification of transcriptional programs using dense vector representations defined by mutual information","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dimensionality reduction; Embedding; Curse of dimensionality; Computer science; Mutual information; Scalability; Computational biology; Leverage (statistics); Gene; Principal component analysis; Identification (biology); Feature vector; Artificial intelligence; Data mining; Biology; Genetics","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":[0.0003358667,0.0003505323,0.0003129693,0.000163508,0.0001958468,0.0001275363,0.000419306,0.0003890916,0.00004763502],"category_scores_gemma":[0.0001138631,0.0004326023,0.0002296908,0.0002840461,0.0001232526,0.00003889924,0.000163969,0.0003327538,0.000005506552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001340291,"about_ca_system_score_gemma":0.000506276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000150345,"about_ca_topic_score_gemma":0.000007202806,"domain_scores_codex":[0.9977034,0.0001510444,0.000838475,0.0005756529,0.0004235366,0.0003078422],"domain_scores_gemma":[0.9980355,0.00001405407,0.0005809428,0.000787217,0.000458515,0.0001237964],"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":[0.00009084948,0.0002485791,0.006611963,0.000196974,0.0001576847,0.000001172439,0.00002336075,0.0006805087,0.9915698,0.0001400234,0.0002733474,0.000005739291],"study_design_scores_gemma":[0.0007684454,0.0001450962,0.02134284,0.00005248949,0.0001924636,7.439986e-8,0.00002148344,0.001784933,0.9670724,0.000002231109,0.007980832,0.0006367723],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9761618,0.0007628669,0.01997332,0.00004220256,0.001048391,0.0006990617,0.001236897,0.00007079441,0.000004683375],"genre_scores_gemma":[0.9953907,0.0001417108,0.003808825,0.00006337676,0.0002057376,0.0002059834,0.0001102044,0.0000655924,0.000007827285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02449746,"threshold_uncertainty_score":0.9998126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01833423391209078,"score_gpt":0.2317764538433078,"score_spread":0.213442219931217,"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."}}