{"id":"W4399477115","doi":"10.1101/2024.06.09.598161","title":"pyRforest: A comprehensive R package for genomic data analysis featuring scikit-learn Random Forests in R","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"R package; Random forest; Computer science; Environmental science; Statistics; Mathematics; Artificial intelligence; 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":[0.005421665,0.004074495,0.003511887,0.004194688,0.00129559,0.0034077,0.004936242,0.001628129,0.07562898],"category_scores_gemma":[0.02515201,0.002505418,0.003985337,0.003608733,0.001438166,0.003675895,0.003927165,0.006239686,0.08503789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041321,"about_ca_system_score_gemma":0.004114139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003870917,"about_ca_topic_score_gemma":0.006069178,"domain_scores_codex":[0.9962064,0.001253655,0.0003370079,0.001031392,0.0008744737,0.0002969956],"domain_scores_gemma":[0.9925668,0.004611026,0.0007612657,0.00102222,0.00074822,0.0002903717],"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":[0.0004397756,0.0001096343,0.004563454,0.003638351,0.0009756452,0.0004408981,0.0003221703,0.02720188,0.004815812,0.01306863,0.8152849,0.1291389],"study_design_scores_gemma":[0.0006189822,0.0001665878,0.006047909,0.0009759759,0.0004491277,0.001029946,0.0001257289,0.1854512,0.01310095,0.12894,0.6626303,0.0004632833],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.002539127,0.001486496,0.5194507,0.0008306713,0.0005186796,0.0004390259,0.1234587,0.3458177,0.005458977],"genre_scores_gemma":[0.02791584,0.001435912,0.6323106,0.001653266,0.0003040705,0.003151344,0.1444806,0.1802169,0.008531509],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.07562898,"threshold_uncertainty_score":0.2530041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02584131881454406,"score_gpt":0.2709217220998116,"score_spread":0.2450804032852676,"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."}}