{"id":"W4323049029","doi":"10.1101/2023.02.28.530483","title":"Meta-Research: understudied genes are lost in a leaky pipeline between genome-wide assays and reporting of results","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Mitochondrial Function and Pathology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"Northwestern University; National Institutes of Health; Moderna; National Science Foundation","keywords":"Pipeline (software); Genome; Computational biology; Biology; Gene; Genetics; Data science; Computer science; Programming language","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":[0.1538951,0.001508797,0.003567924,0.01915406,0.002204394,0.01188332,0.00273362,0.001780042,0.005897808],"category_scores_gemma":[0.3549676,0.001159854,0.004673677,0.02783678,0.004058269,0.008702363,0.006511502,0.003002518,0.001265757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002594136,"about_ca_system_score_gemma":0.006424382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002361278,"about_ca_topic_score_gemma":0.004423325,"domain_scores_codex":[0.8748358,0.06763513,0.0186342,0.02006048,0.01668039,0.002153997],"domain_scores_gemma":[0.4331592,0.4249267,0.05759694,0.06638246,0.01436918,0.003565448],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002185493,0.000127145,0.4255643,0.03033677,0.03048312,0.001807076,0.01199485,0.001933369,0.01469222,0.04010563,0.0496672,0.3911029],"study_design_scores_gemma":[0.0004481346,0.0005353714,0.427462,0.01684344,0.03992546,0.003741671,0.007003089,0.007743069,0.02425533,0.215498,0.255674,0.0008703587],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2933493,0.1556658,0.3955605,0.07071364,0.004910296,0.001213239,0.04360612,0.009631647,0.02534948],"genre_scores_gemma":[0.8125981,0.01508975,0.1379149,0.01355776,0.001962512,0.001117035,0.01262006,0.002508473,0.002631338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8461049,"threshold_uncertainty_score":0.8138847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1827943943702337,"score_gpt":0.3221715309969006,"score_spread":0.1393771366266669,"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."}}