{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001565231,0.0001677299,0.0002762883,0.0009776006,0.0005613903,0.0002222313,0.001133753,0.00006981545,0.000002684641],"category_scores_gemma":[0.002874505,0.0001657473,0.00005992454,0.008649096,0.0001787081,0.000314031,0.0008338016,0.0004183983,0.00001364991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004836017,"about_ca_system_score_gemma":0.00009938185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000318393,"about_ca_topic_score_gemma":0.000006649971,"domain_scores_codex":[0.9978836,0.00009801075,0.0002528857,0.0009296038,0.0004242194,0.00041164],"domain_scores_gemma":[0.9989302,0.0002038327,0.0001462776,0.0002886181,0.0002634634,0.0001676059],"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":[0.00001563384,0.00002572856,0.0186373,0.00001963316,0.00006483987,0.000007581605,0.0007300888,0.338867,0.02760865,0.1009815,0.000006064122,0.513036],"study_design_scores_gemma":[0.0001947562,0.0002019849,0.0006885257,0.000006369175,0.00003187909,0.000007263519,0.00003578027,0.9836555,0.003121218,0.007684792,0.004186796,0.0001851333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06380326,0.0002359192,0.9062114,0.0288719,0.00002965783,0.0002754462,0.000001411782,0.0004629435,0.0001080372],"genre_scores_gemma":[0.7541744,0.000004145706,0.2449034,0.0008219972,0.00001540937,0.00005196894,0.000005117598,0.000008903586,0.00001464332],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6903711,"threshold_uncertainty_score":0.6758977,"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."}}