{"id":"W3088588738","doi":"10.1021/acs.analchem.1c02178","title":"High-Throughput Molecular Imaging via Deep-Learning-Enabled Raman Spectroscopy","year":2021,"lang":"en","type":"preprint","venue":"Analytical Chemistry","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"H2020 European Research Council; Engineering and Physical Sciences Research Council; Royal Academy of Engineering; Wellcome Trust; Wellcome; H2020 Marie Skłodowska-Curie Actions; GlaxoSmithKline","keywords":"Raman spectroscopy; Hyperspectral imaging; Deep learning; Throughput; Artificial intelligence; Computer science; Chemical imaging; Noise reduction; Materials science; Pattern recognition (psychology); Nanotechnology; Optics; Physics; Telecommunications","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":[0.0008303457,0.001041731,0.0006713507,0.0006078392,0.0003012944,0.0009335637,0.001435764,0.001003718,0.002153254],"category_scores_gemma":[0.001344073,0.0005600781,0.0006581132,0.0006107129,0.0008319003,0.001904056,0.002164031,0.002377529,0.001188984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008329938,"about_ca_system_score_gemma":0.0008324617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001869011,"about_ca_topic_score_gemma":0.00341191,"domain_scores_codex":[0.9994981,0.00007452983,0.00001539539,0.0001222438,0.000227347,0.00006242601],"domain_scores_gemma":[0.9995319,0.000167837,0.0000432901,0.0001190894,0.0001014041,0.00003661587],"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":[0.0002320223,0.0003294841,0.002105428,0.0004918062,0.0001942913,0.0002408005,0.0001771615,0.29273,0.4556903,0.03415276,0.008901143,0.2047548],"study_design_scores_gemma":[0.00001124943,0.00003478521,0.0002995447,0.00001132571,0.000009009481,0.0000540474,0.00001319325,0.9273909,0.05838535,0.01050271,0.003269312,0.00001847952],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03835354,0.0005495263,0.9515983,0.0004893666,0.00006180379,0.00005271507,0.0004964428,0.004994636,0.003403736],"genre_scores_gemma":[0.3404476,0.001031291,0.6515667,0.0003069922,0.00006447315,0.0001529837,0.001601631,0.0005025816,0.004325644],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002153254,"threshold_uncertainty_score":0.007203341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00542234144586847,"score_gpt":0.2957394200166688,"score_spread":0.2903170785708003,"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."}}