{"id":"W4403203186","doi":"10.1093/bfgp/elae038","title":"<i>pyRforest</i> : a comprehensive R package for genomic data analysis featuring scikit-learn Random Forests in R","year":2024,"lang":"en","type":"article","venue":"Briefings in Functional Genomics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"Massey University; University of Otago","keywords":"Python (programming language); Random forest; Interpretability; Computer science; Visualization; R package; Data mining; Computational biology; Machine learning; Biology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003063982,0.0001711402,0.0002173301,0.000312101,0.00007292962,0.00009513559,0.0003036837,0.0001458723,0.00001876237],"category_scores_gemma":[0.00008137208,0.0001790784,0.0001245469,0.0005173014,0.00005294595,0.00001485503,0.0002435865,0.0001480529,0.00000845166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012628,"about_ca_system_score_gemma":0.0002596834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008705924,"about_ca_topic_score_gemma":0.0008527198,"domain_scores_codex":[0.9984893,0.00003961827,0.0003222268,0.0007640279,0.0001232346,0.0002615853],"domain_scores_gemma":[0.9991864,0.00006705593,0.00006874176,0.0005521663,0.00006805229,0.0000576095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002218688,0.0001480144,0.03402498,0.0002137508,0.0007522899,0.00001615011,0.0002395373,0.04800741,0.8545547,0.001067061,0.04841248,0.0103449],"study_design_scores_gemma":[0.003489377,0.00009447517,0.2672862,0.00006797748,0.0002247875,0.00002124673,0.000167252,0.03135624,0.0104884,0.0009789267,0.6852787,0.000546471],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9073682,0.005308908,0.08457182,0.001120214,0.0005326599,0.0005728395,0.0002539954,0.00002988947,0.0002414779],"genre_scores_gemma":[0.9932649,0.0004602605,0.001462246,0.0006605169,0.0003541234,0.0001215394,0.002842741,0.00004019773,0.0007934454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8440663,"threshold_uncertainty_score":0.7302606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03906415870514608,"score_gpt":0.2851587844403725,"score_spread":0.2460946257352264,"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."}}