{"id":"W2935566373","doi":"10.1002/jrs.5608","title":"Optimized preprocessing and machine learning for quantitative Raman spectroscopy in biology","year":2019,"lang":"en","type":"preprint","venue":"Journal of Raman Spectroscopy","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Semiconductor Research Corporation","keywords":"Raman spectroscopy; Robustness (evolution); Preprocessor; Computer science; Artificial intelligence; Medical diagnosis; Machine learning; Process (computing); Set (abstract data type); Biological system; Optics; Biology; Physics","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":[0.00267562,0.001116597,0.0007183423,0.000945974,0.0005622601,0.0009311542,0.001087155,0.001099948,0.001510704],"category_scores_gemma":[0.006209408,0.0005261941,0.0009382488,0.0009608498,0.0008353987,0.001006306,0.0008003417,0.001785669,0.0007361282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009560753,"about_ca_system_score_gemma":0.001144777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002382864,"about_ca_topic_score_gemma":0.002273607,"domain_scores_codex":[0.9989707,0.0004065382,0.00005632843,0.000228061,0.0002661253,0.00007214251],"domain_scores_gemma":[0.9969383,0.001928543,0.0002659047,0.000322951,0.000491266,0.00005300377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002765531,0.000340213,0.002253978,0.0002452143,0.0001417973,0.00009038273,0.00009378386,0.6792455,0.06889253,0.01102814,0.002219942,0.235172],"study_design_scores_gemma":[0.000003270875,0.0000300022,0.0002336829,0.000004419226,0.00000540618,0.000007383018,0.000004590857,0.9893078,0.007480359,0.00243509,0.000479988,0.000008009896],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02066197,0.0002566585,0.9769841,0.0002448751,0.00004070205,0.00005525347,0.00008910177,0.001109101,0.0005582458],"genre_scores_gemma":[0.3125999,0.0002617869,0.6844802,0.0001856455,0.00006727214,0.0002657339,0.0004355611,0.000243888,0.001460068],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00267562,"threshold_uncertainty_score":0.0141502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02545766168058384,"score_gpt":0.3902677291017067,"score_spread":0.3648100674211229,"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."}}