{"id":"W3016820838","doi":"10.1088/2632-2153/ab8aa3","title":"A machine learning workflow for molecular analysis: application to melting points","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"","keywords":"Workflow; Computer science; Autoencoder; Molecular graph; Context (archaeology); Artificial intelligence; Cluster analysis; Machine learning; Representation (politics); Data mining; Graph; Theoretical computer science; Deep learning; Database","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":[0.003530727,0.001090807,0.0007920034,0.001675212,0.001045599,0.001741392,0.002261704,0.0009686984,0.005140767],"category_scores_gemma":[0.006053119,0.0005499088,0.001422498,0.0009374499,0.0009993265,0.001228187,0.001847211,0.001632333,0.002549608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001323496,"about_ca_system_score_gemma":0.002242534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003546805,"about_ca_topic_score_gemma":0.003760968,"domain_scores_codex":[0.9990243,0.000261031,0.0001061346,0.0002551014,0.000309711,0.00004377156],"domain_scores_gemma":[0.9969348,0.001336713,0.00019537,0.0007607187,0.0006275729,0.0001448082],"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":[0.0005779156,0.0003448029,0.005198198,0.0005697149,0.000236102,0.0007059433,0.0004899391,0.3745816,0.05239277,0.1132208,0.01795978,0.4337223],"study_design_scores_gemma":[0.0000204509,0.00001643733,0.000229937,0.00002083708,0.000006049836,0.00005687119,0.00001633834,0.9425051,0.01639991,0.03403778,0.006668215,0.00002211079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002156843,0.00002840641,0.9843305,0.00009015269,0.00001451062,0.00005802904,0.0003433636,0.01240739,0.000570946],"genre_scores_gemma":[0.04138051,0.0000661707,0.9558664,0.00006393442,0.00001068685,0.0001658382,0.0007666926,0.0009363903,0.000743424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005140767,"threshold_uncertainty_score":0.01867247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024595856869351,"score_gpt":0.2886374425979468,"score_spread":0.2783914840292533,"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."}}