{"id":"W4210522464","doi":"10.1177/00037028221077119","title":"Pushing the Limits of Surface-Enhanced Raman Spectroscopy (SERS) with Deep Learning: Identification of Multiple Species with Closely Related Molecular Structures","year":2022,"lang":"en","type":"article","venue":"Applied Spectroscopy","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Canada Foundation for Innovation; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Raman spectroscopy; Surface-enhanced Raman spectroscopy; Analyte; Chemistry; Molecule; Spectroscopy; Convolutional neural network; Identification (biology); Nanotechnology; Raman scattering; Biological system; Materials science; Artificial intelligence; Computer science; Biology; Chromatography; Optics; Organic chemistry; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002053197,0.001254269,0.0009985813,0.0006412162,0.000296686,0.00170696,0.001223733,0.001683736,0.0009327413],"category_scores_gemma":[0.003608203,0.0005431985,0.0006377973,0.0006981875,0.001560151,0.002713357,0.00159279,0.002766362,0.0005612184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000813572,"about_ca_system_score_gemma":0.0009154686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001562137,"about_ca_topic_score_gemma":0.00200334,"domain_scores_codex":[0.9989672,0.0002935634,0.00004663241,0.0002362095,0.0003734357,0.00008297625],"domain_scores_gemma":[0.9980043,0.001253105,0.0002135096,0.0002226473,0.0002309043,0.00007551657],"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":[0.0004200177,0.0004446977,0.008353109,0.001145721,0.0004934604,0.0003560278,0.0002853162,0.2060236,0.2051816,0.04747835,0.003043251,0.5267749],"study_design_scores_gemma":[0.00001844998,0.0002109749,0.001307961,0.00007930618,0.00003506755,0.0001561748,0.00005279798,0.9205753,0.04066723,0.03221635,0.004634471,0.00004602491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09776581,0.006427304,0.8881743,0.002007148,0.0001408747,0.00004177925,0.0001375836,0.0007923151,0.004513022],"genre_scores_gemma":[0.679559,0.004655167,0.3109131,0.0006566544,0.0001134903,0.0001022826,0.0002283522,0.0001134856,0.003658461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002053197,"threshold_uncertainty_score":0.01085848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007029623314442044,"score_gpt":0.2619674881751971,"score_spread":0.254937864860755,"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."}}