{"id":"W2020313378","doi":"10.1109/bibm.2011.105","title":"Employing Machine Learning Techniques for Data Enrichment: Increasing the Number of Samples for Effective Gene Expression Data Analysis","year":2011,"lang":"en","type":"article","venue":"","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Process (computing); Data mining; Independence (probability theory); Set (abstract data type); Machine learning; Probabilistic logic; Sample (material); Expression (computer science); Domain (mathematical analysis); Genetic algorithm; Artificial intelligence; Statistics; Mathematics","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":[0.00142212,0.0001679096,0.0002906662,0.00006495407,0.0001993298,0.00001809722,0.0009857718,0.0001039872,0.00003026307],"category_scores_gemma":[0.0003253089,0.0001164348,0.0001652163,0.0002335615,0.00006239642,0.00001300542,0.001096398,0.00005550487,3.517077e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008454665,"about_ca_system_score_gemma":0.00002388473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004253135,"about_ca_topic_score_gemma":0.0001578199,"domain_scores_codex":[0.9985411,0.0002009319,0.0002914175,0.0006376976,0.000113979,0.0002149026],"domain_scores_gemma":[0.9975577,0.0001687373,0.0002358466,0.00187364,0.0001216055,0.0000424477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003018322,0.00008730799,0.1979536,0.00004709646,0.002436207,1.965329e-7,0.00008372249,0.0001193934,0.7870319,0.00003801493,0.0005103298,0.0113903],"study_design_scores_gemma":[0.0002854234,0.00009461737,0.003752945,0.00001442465,0.001950349,0.000003667968,0.00008436206,0.01607812,0.9699537,0.0001260175,0.007439037,0.0002174094],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3084559,0.0007697195,0.6896369,0.00001529029,0.00001912614,0.0006387258,0.0003208078,0.00002585876,0.0001176136],"genre_scores_gemma":[0.7878995,0.0001041042,0.2063159,0.00002548665,0.000104354,0.00007775878,0.005376735,0.00002396383,0.00007220109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.483321,"threshold_uncertainty_score":0.4748075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04933694332252949,"score_gpt":0.3166905055451518,"score_spread":0.2673535622226223,"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."}}