{"id":"W4223988818","doi":"10.1186/s12859-022-04667-1","title":"Deep clustering of small molecules at large-scale via variational autoencoder embedding and K-means","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Autoencoder; Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Principal component analysis; Cluster (spacecraft); Embedding; Similarity (geometry); Biological system; Data mining; Deep learning; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001245654,0.0001493616,0.000218807,0.000106197,0.0005167563,0.00008642166,0.0003920294,0.00004146254,0.001471269],"category_scores_gemma":[0.0001176531,0.0001441242,0.00004232681,0.0001652853,0.00009967728,0.0002355731,0.00111091,0.000107583,0.00004554351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008973251,"about_ca_system_score_gemma":0.00005839282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003190697,"about_ca_topic_score_gemma":0.0001015342,"domain_scores_codex":[0.9983258,0.0001229699,0.0005462985,0.0001917328,0.0004780849,0.0003351305],"domain_scores_gemma":[0.9990855,0.0001325962,0.0003797144,0.0002726912,0.00005123141,0.00007830219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002142123,0.00002458558,0.001514328,0.0001773238,0.000002440896,7.532095e-7,0.003657918,0.9891208,0.005037673,0.0003163484,0.00003805402,0.0000882978],"study_design_scores_gemma":[0.000306847,0.00006412793,0.002066231,0.0000131552,0.00001121281,0.00005967166,0.0006269441,0.9958841,0.0002421515,0.0001946033,0.0003611917,0.0001697476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01445876,0.00002655246,0.9838732,0.00004993544,0.0004319492,0.0001795693,0.00006588687,0.00007934407,0.0008348433],"genre_scores_gemma":[0.001588682,0.00000246694,0.9980189,0.0001548611,0.00003023867,0.0000247039,0.000025357,0.00001424804,0.0001405586],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01414572,"threshold_uncertainty_score":0.9994415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01183289589264877,"score_gpt":0.2411205728047431,"score_spread":0.2292876769120943,"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."}}