{"id":"W2084738599","doi":"10.1016/j.mbs.2003.11.002","title":"A model explaining the size distribution of gene and protein families","year":2004,"lang":"en","type":"article","venue":"Mathematical Biosciences","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Homogeneous; Simple (philosophy); Distribution (mathematics); Gene; Statistical physics; Protein family; Gene family; Exponential distribution; Power (physics); Genome; Mathematics; Biology; Evolutionary biology; Genetics; Statistics; Physics; Mathematical analysis","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":[0.002336159,0.0006819415,0.001239493,0.0018945,0.0009959457,0.002519369,0.003696957,0.003599175,0.00785768],"category_scores_gemma":[0.01068309,0.0007166977,0.0013096,0.001717569,0.002279248,0.005516367,0.001349429,0.001949246,0.001625316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002133895,"about_ca_system_score_gemma":0.00112573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003369673,"about_ca_topic_score_gemma":0.002037738,"domain_scores_codex":[0.9992971,0.0002171963,0.00002280277,0.0001774361,0.000144332,0.0001410854],"domain_scores_gemma":[0.9940007,0.004250067,0.0003955404,0.0004708963,0.0004829244,0.0003997415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005763932,0.00004264658,0.001767864,0.00006660281,0.00003478923,0.0002462811,0.0002494184,0.1346271,0.002387302,0.8471562,0.003761431,0.009602822],"study_design_scores_gemma":[0.00003330869,0.00001825366,0.0007580647,0.00001356104,0.0000167844,0.0002478343,0.00004185595,0.5373007,0.0002198347,0.4593848,0.001941427,0.00002353686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1893328,0.00123259,0.7754016,0.008792355,0.0001580787,0.00007790155,0.0009477139,0.0007635274,0.02329342],"genre_scores_gemma":[0.8974465,0.001702976,0.06785775,0.0008522195,0.000333765,0.0003255247,0.0008174447,0.0003054242,0.03035842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00785768,"threshold_uncertainty_score":0.02628654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0170554757090379,"score_gpt":0.237980081611961,"score_spread":0.2209246059029231,"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."}}