{"id":"W4399439607","doi":"10.1021/acs.jcim.4c00378","title":"Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention","year":2024,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Canada Foundation for Innovation; Ontario Research Foundation","keywords":"Infrared spectroscopy; Transformer; Graph; Computer science; Infrared; Chemistry; Theoretical computer science; Engineering; Physics; Optics; Organic chemistry; Electrical engineering","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":[0.0002748067,0.0001275707,0.0001571597,0.0001585012,0.00004260103,0.00009148799,0.0001181354,0.0001698158,0.00005336903],"category_scores_gemma":[0.00003652312,0.000101721,0.0001907274,0.0001425892,0.0001063757,0.00007729372,0.00003851853,0.0002608461,0.000001881166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004976444,"about_ca_system_score_gemma":0.00007831259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004134959,"about_ca_topic_score_gemma":5.877409e-8,"domain_scores_codex":[0.9987696,0.00001283666,0.000540358,0.0001093499,0.0003645535,0.0002032466],"domain_scores_gemma":[0.9995769,0.000008914439,0.00007754446,0.00006333063,0.0001010292,0.0001722671],"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":[0.0001835424,0.00002916254,0.000005797937,0.00005792569,0.00005045673,0.000002041461,0.00005117106,0.00002538167,0.9955462,0.000115322,0.0008330585,0.003099919],"study_design_scores_gemma":[0.0005459805,0.0002104172,0.000001302081,0.0001352931,0.00003014768,0.0001446781,0.0001367505,0.038475,0.9486068,0.0005318793,0.01103915,0.0001425967],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9085524,0.001632429,0.08811475,0.0001633209,0.0001389272,0.00009205555,0.000008353268,0.00002070649,0.001277032],"genre_scores_gemma":[0.9936907,0.001148991,0.004629424,0.0001112185,0.0003384472,0.000003408147,0.00004709322,0.00001023292,0.00002047127],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08513828,"threshold_uncertainty_score":0.4148061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01934558366495329,"score_gpt":0.3270124235612999,"score_spread":0.3076668398963466,"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."}}