{"id":"W2290848280","doi":"10.1186/s12859-016-0970-4","title":"MetICA: independent component analysis for high-resolution mass-spectrometry based non-targeted metabolomics","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lallemand","keywords":"Independent component analysis; Overfitting; Principal component analysis; Metabolomics; Computer science; Component (thermodynamics); Data mining; Artificial intelligence; Pattern recognition (psychology); Bioinformatics; Biology; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002382443,0.002626485,0.001292308,0.002046269,0.0007426062,0.0017564,0.001614817,0.001761399,0.005392352],"category_scores_gemma":[0.006486656,0.0006723797,0.002459534,0.001683608,0.0007230751,0.000914091,0.001108051,0.003169475,0.003039798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006772791,"about_ca_system_score_gemma":0.00181919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004480555,"about_ca_topic_score_gemma":0.003984192,"domain_scores_codex":[0.9989102,0.0004132288,0.00008556271,0.0002052737,0.0003277906,0.00005790882],"domain_scores_gemma":[0.9980259,0.001235564,0.0001758786,0.0001486735,0.0003632706,0.00005085656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003244877,0.0001835024,0.001403679,0.001038975,0.0005863465,0.0004821074,0.0002393549,0.5180429,0.01677333,0.01907609,0.01535108,0.4264982],"study_design_scores_gemma":[0.00001974761,0.0000486647,0.0004880776,0.00004654294,0.00003379519,0.00008619055,0.00001536789,0.9833598,0.002536705,0.007628002,0.005703246,0.00003375657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001530607,0.0005280905,0.9938785,0.0001403383,0.00005915467,0.00007588624,0.0001722912,0.002989154,0.0006258984],"genre_scores_gemma":[0.09282797,0.001235794,0.8999813,0.000187203,0.0001614431,0.0009102509,0.001671205,0.000799433,0.002225429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005392352,"threshold_uncertainty_score":0.01803917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01337171532866286,"score_gpt":0.2361374865971329,"score_spread":0.2227657712684701,"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."}}