{"id":"W2081122436","doi":"10.1186/1471-2164-14-s1-s14","title":"Scoring relevancy of features based on combinatorial analysis of Lasso with application to lymphoma diagnosis","year":2013,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; Mitacs; National Institutes of Health; Michael Smith Health Research BC","keywords":"Overfitting; Feature selection; Computer science; Machine learning; Artificial intelligence; Bootstrapping (finance); Feature (linguistics); Data mining; Relevance (law); Lasso (programming language); Pattern recognition (psychology); Mathematics; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00006413792,0.000107975,0.000204089,0.0001032344,0.00002612908,0.00001012434,0.0001485099,0.00009132882,0.000004863832],"category_scores_gemma":[0.00003106147,0.0000980189,0.0001038395,0.0002359659,0.00002964978,0.000002018795,0.00002040573,0.0000251576,0.000002225014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002418655,"about_ca_system_score_gemma":0.00006397013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003053714,"about_ca_topic_score_gemma":0.0002791572,"domain_scores_codex":[0.9993356,0.00002307147,0.0001871738,0.0002327623,0.0001039015,0.0001175105],"domain_scores_gemma":[0.9993334,0.00003136961,0.0001091253,0.0003562618,0.0001150716,0.00005474758],"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":[0.0004127333,0.0003280907,0.16279,0.00004909276,0.0002289436,1.532294e-7,0.00006589714,0.02880026,0.8030733,0.0001897635,0.0001739607,0.003887858],"study_design_scores_gemma":[0.001043355,0.000590532,0.1049901,0.00001755946,0.0002581905,1.842983e-7,0.00003162602,0.002892285,0.8889264,0.00003921613,0.001027726,0.0001827936],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9871851,0.00005788562,0.01215081,0.00002500011,0.00008260201,0.0002659157,0.00002767717,0.000005103499,0.0001999452],"genre_scores_gemma":[0.9954792,0.00002294806,0.004155434,0.00007789853,0.0000729207,0.000067364,0.00008607693,0.00001700961,0.00002117669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08585314,"threshold_uncertainty_score":0.3997095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007693783872449654,"score_gpt":0.212304233643008,"score_spread":0.2046104497705584,"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."}}