{"id":"W4392705522","doi":"10.7554/elife.93429.2","title":"Meta-Research: understudied genes are lost in a leaky pipeline between genome-wide assays and reporting of results","year":2024,"lang":"en","type":"preprint","venue":"eLife","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"","keywords":"Gene; Biology; Genome; Identification (biology); Selection (genetic algorithm); Computational biology; Pipeline (software); Genetics; Evolutionary biology; Computer science; Machine learning; Ecology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1295749,0.001495036,0.00328057,0.0184033,0.002417292,0.01108916,0.002855027,0.001651769,0.007107679],"category_scores_gemma":[0.334263,0.001198237,0.00447651,0.02830262,0.004096333,0.008924115,0.006455466,0.003014206,0.001398361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002796487,"about_ca_system_score_gemma":0.006765559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003415928,"about_ca_topic_score_gemma":0.006440357,"domain_scores_codex":[0.8986962,0.0551103,0.01326132,0.01786021,0.01313552,0.001936384],"domain_scores_gemma":[0.4814447,0.3966231,0.04958535,0.05596706,0.01290663,0.00347316],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001953741,0.000108327,0.3912558,0.03057569,0.02874985,0.002032403,0.01272023,0.002625698,0.01369395,0.05628898,0.06754887,0.3924465],"study_design_scores_gemma":[0.0004075286,0.0003807874,0.327921,0.01475701,0.03421611,0.003403766,0.006772046,0.009448097,0.02119822,0.2826776,0.2980297,0.0007880912],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2406415,0.1261176,0.45853,0.07559393,0.004850358,0.001075335,0.05262085,0.0110274,0.02954302],"genre_scores_gemma":[0.7890649,0.01443265,0.1602641,0.0123695,0.001758163,0.001139049,0.01484221,0.003145249,0.002984223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8704251,"threshold_uncertainty_score":0.6852657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2027141838984967,"score_gpt":0.3603626969721725,"score_spread":0.1576485130736758,"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."}}