{"id":"W3092168132","doi":"10.1101/2020.10.09.327114","title":"Expanding the Galaxy’s reference data","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; BC Centre for Disease Control","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; National Institutes of Health; European Commission; Vlaamse regering; National Research Foundation; UK Research and Innovation; Cleveland Clinic","keywords":"Computer science; Galaxy; Task (project management); MIT License; Interface (matter); License; Reference data; Information retrieval; Database; Astrophysics; Physics; Systems engineering; Engineering; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.007620294,0.001910906,0.001950914,0.007462985,0.002173375,0.005453672,0.006870038,0.002260327,0.04123585],"category_scores_gemma":[0.02216418,0.001888955,0.002245789,0.01045046,0.001037877,0.004354346,0.008731679,0.004361968,0.07241244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002724787,"about_ca_system_score_gemma":0.004839447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03037519,"about_ca_topic_score_gemma":0.02831353,"domain_scores_codex":[0.9925768,0.001300332,0.0005921338,0.00187211,0.003011104,0.0006475475],"domain_scores_gemma":[0.9787709,0.001866231,0.000559972,0.01234654,0.005292492,0.001163853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000349645,0.00004304037,0.004167348,0.0006212658,0.0001935549,0.0002485259,0.0003967783,0.002710022,0.007955221,0.02097631,0.8859893,0.07634893],"study_design_scores_gemma":[0.00007066629,0.00002145326,0.002164285,0.0001267029,0.00005372682,0.0001048675,0.0000513673,0.002809784,0.00650547,0.008723781,0.9792976,0.00007038287],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01555898,0.002983193,0.197364,0.004075797,0.002062326,0.0002960618,0.398505,0.3148214,0.06433325],"genre_scores_gemma":[0.02938592,0.0007850834,0.141891,0.001475773,0.0002436135,0.0004514961,0.7672706,0.04519654,0.01330011],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04123585,"threshold_uncertainty_score":0.1379477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03816374138307518,"score_gpt":0.2607434311263169,"score_spread":0.2225796897432417,"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."}}