{"id":"W2045949302","doi":"10.1038/nprot.2009.97","title":"Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt","year":2009,"lang":"en","type":"article","venue":"Nature Protocols","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4605,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Cancer Institute; Ontario Institute for Cancer Research; University of California, Santa Cruz","keywords":"Ensembl; Bioconductor; Computer science; Identifier; Computational biology; R package; Genomics; Data mining; Data integration; Genome; Data science; Biology; Gene; 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":[0.008947399,0.004157401,0.00537162,0.009213435,0.003085177,0.003739532,0.006524035,0.002050383,0.1214247],"category_scores_gemma":[0.02718917,0.0026524,0.003323582,0.01293424,0.0009504007,0.003557617,0.005474584,0.005173627,0.0931298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382134,"about_ca_system_score_gemma":0.005601751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004248708,"about_ca_topic_score_gemma":0.006270681,"domain_scores_codex":[0.9950402,0.001145054,0.0008008096,0.001712563,0.0008235711,0.0004778008],"domain_scores_gemma":[0.9887242,0.004269199,0.001231606,0.003546164,0.001429938,0.0007989003],"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":[0.001590918,0.000170842,0.003685394,0.005334612,0.0008272965,0.0003961251,0.0008698832,0.00150907,0.01228212,0.02127714,0.9004349,0.05162169],"study_design_scores_gemma":[0.0007275362,0.0001657456,0.009437721,0.0008963386,0.0008008403,0.0007177947,0.0002774774,0.009003683,0.02538405,0.05470356,0.897594,0.0002912342],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.002773369,0.0006416228,0.2201265,0.0005292886,0.0007480278,0.0005552851,0.5567527,0.2106906,0.007182495],"genre_scores_gemma":[0.01301477,0.0004974372,0.3494246,0.0005116481,0.0001485539,0.00453899,0.5686747,0.05729251,0.005896795],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1214247,"threshold_uncertainty_score":0.4062062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02574701164941351,"score_gpt":0.3351561014281086,"score_spread":0.3094090897786951,"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."}}