{"id":"W3100697461","doi":"10.1101/2020.11.16.385427","title":"Simplified and unified access to cancer proteogenomic data","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Pacific Northwest National Laboratory; National Cancer Institute; York University","keywords":"Computer science; Python (programming language); Consistency (knowledge bases); Data curation; Computational biology; R package; Raw data; Cancer; Proteogenomics; Data science; Biology; Bioinformatics; Genomics; Genome; Artificial intelligence; Genetics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005630095,0.001675323,0.001367922,0.004545374,0.001187018,0.004119598,0.002711565,0.0007200547,0.03190564],"category_scores_gemma":[0.01687549,0.001378683,0.001668072,0.006303492,0.0007681114,0.003027397,0.007339344,0.003541416,0.02719318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001153795,"about_ca_system_score_gemma":0.004403222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006900694,"about_ca_topic_score_gemma":0.008105533,"domain_scores_codex":[0.9963438,0.0006233873,0.0005521558,0.0008375081,0.001339745,0.0003033168],"domain_scores_gemma":[0.9920848,0.001352407,0.000327178,0.004340314,0.00139689,0.0004985264],"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":[0.001511468,0.0002133123,0.007507409,0.00118026,0.0003205451,0.000939446,0.0004667148,0.01119161,0.0164273,0.01908105,0.810078,0.1310828],"study_design_scores_gemma":[0.000557532,0.00008674656,0.01565593,0.0002646881,0.0001038801,0.001103245,0.000233621,0.05907832,0.03234862,0.05267186,0.8375667,0.0003288083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.008377762,0.0003155488,0.1851283,0.001150552,0.0004742669,0.0006116277,0.5777195,0.2170504,0.00917194],"genre_scores_gemma":[0.03676871,0.0004320304,0.1609401,0.0005741202,0.0001953593,0.001300624,0.7720967,0.02238598,0.005306378],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03190564,"threshold_uncertainty_score":0.1067351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03729794702730676,"score_gpt":0.2715256761579596,"score_spread":0.2342277291306528,"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."}}