{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004957917,0.0008673523,0.001369262,0.001781618,0.0005703692,0.001420415,0.001099944,0.001330411,0.001228201],"category_scores_gemma":[0.01344516,0.0005332101,0.001404842,0.001726333,0.00113411,0.001763722,0.001551743,0.001915145,0.0007710081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005022778,"about_ca_system_score_gemma":0.001011393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000466623,"about_ca_topic_score_gemma":0.0007923636,"domain_scores_codex":[0.9960691,0.001774687,0.0002129245,0.0007118213,0.00111633,0.0001152073],"domain_scores_gemma":[0.9912088,0.006435771,0.0004715151,0.001224205,0.000524783,0.0001350644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009590331,0.0008198392,0.02223188,0.001269105,0.0002911472,0.0006163924,0.0006201524,0.09331414,0.227688,0.01729611,0.001636959,0.6332572],"study_design_scores_gemma":[0.0001385103,0.0007131607,0.008536357,0.000139472,0.0002107633,0.0009852614,0.0002172882,0.7048096,0.2097509,0.06214013,0.01225108,0.0001074513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0274548,0.0002590851,0.9707413,0.0002862463,0.00001799328,0.0001340002,0.0001294869,0.0005796424,0.0003974152],"genre_scores_gemma":[0.1579798,0.0002830617,0.840076,0.0001813583,0.000031717,0.000469788,0.0004609287,0.0001021621,0.0004151598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004957917,"threshold_uncertainty_score":0.02622026,"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."}}