{"id":"W2537748973","doi":"10.1101/080127","title":"Using predictive specificity to determine when gene set analysis is biologically meaningful","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institutes of Health","keywords":"Correctness; Robustness (evolution); Computer science; Set (abstract data type); Benchmark (surveying); Data mining; Computational biology; Machine learning; Artificial intelligence; Gene; Biology; Algorithm; Genetics; 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":[],"consensus_categories":[],"category_scores_codex":[0.02298218,0.001532558,0.001480375,0.007644872,0.00115004,0.00451522,0.001802145,0.002287289,0.003656153],"category_scores_gemma":[0.1064795,0.0006347156,0.001697438,0.003324314,0.003134517,0.002588656,0.002906768,0.002823791,0.001448337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00113937,"about_ca_system_score_gemma":0.001064407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001431941,"about_ca_topic_score_gemma":0.001562968,"domain_scores_codex":[0.9850211,0.005754035,0.001276112,0.002967885,0.004199478,0.0007814091],"domain_scores_gemma":[0.8864366,0.08727086,0.007739478,0.0098283,0.007323266,0.001401472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002865395,0.0003218935,0.5291632,0.001860851,0.002159741,0.0009468572,0.0008091955,0.1235615,0.08983563,0.02500401,0.007256957,0.2162146],"study_design_scores_gemma":[0.0001051891,0.0005222999,0.08735672,0.0003877195,0.001044285,0.001198256,0.0004449403,0.6763029,0.1539402,0.07163373,0.006829654,0.0002340622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3810863,0.002362764,0.5904604,0.001347171,0.0003489659,0.0002896847,0.002951348,0.007917532,0.01323588],"genre_scores_gemma":[0.9283046,0.0002053802,0.06832024,0.0003457174,0.00008779125,0.0001194741,0.001438817,0.0005109499,0.0006670299],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02298218,"threshold_uncertainty_score":0.1215428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02598435940091448,"score_gpt":0.2379848466280033,"score_spread":0.2120004872270888,"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."}}