{"id":"W4389782977","doi":"10.7554/elife.93429.1","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":"","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":"Northwestern University; National Institutes of Health; Moderna; National Science Foundation","keywords":"Gene; Genome; Biology; 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":[0.1356251,0.001406144,0.003259429,0.01857923,0.00220362,0.01144557,0.002460073,0.001554429,0.006422328],"category_scores_gemma":[0.3367651,0.00109725,0.004246982,0.02917953,0.00395135,0.008942982,0.006178301,0.0028344,0.001293181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002585329,"about_ca_system_score_gemma":0.005854271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002649544,"about_ca_topic_score_gemma":0.004817732,"domain_scores_codex":[0.8940448,0.05764005,0.01447437,0.01758319,0.01435182,0.001905765],"domain_scores_gemma":[0.4598795,0.4083766,0.0550511,0.06012655,0.01303803,0.003528209],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001973314,0.0001103739,0.4360893,0.02532163,0.02483793,0.001782792,0.01151015,0.002011995,0.01288927,0.04562343,0.04828854,0.3895613],"study_design_scores_gemma":[0.0003800326,0.0004657088,0.4266932,0.01363687,0.03289675,0.003611252,0.006761773,0.008122047,0.02130735,0.2434557,0.2418894,0.0007797098],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3028291,0.1382913,0.400109,0.07041983,0.004623874,0.001060075,0.0440099,0.009835135,0.02882177],"genre_scores_gemma":[0.8346645,0.01316871,0.1221258,0.01151236,0.001703346,0.0008869679,0.01104614,0.002315338,0.002576783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8643749,"threshold_uncertainty_score":0.7172625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.298867354565667,"score_gpt":0.3688895209037612,"score_spread":0.07002216633809422,"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."}}