{"id":"W3095617312","doi":"10.1093/bib/bbaa266","title":"TrimNet: learning molecular representation from triplet messages for biomedicine","year":2020,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Computer science; Biomedicine; Representation (politics); Graph; Feature learning; Artificial intelligence; Machine learning; Theoretical computer science; Property (philosophy); Bioinformatics","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":[0.000812709,0.0001910924,0.0003626868,0.0001076806,0.0001276223,0.0002088066,0.0004563337,0.0000947552,0.0003058096],"category_scores_gemma":[0.002456318,0.000176908,0.00005799126,0.0004332042,0.0001327269,0.0004452318,0.0001439161,0.0001707639,0.0001223597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003827956,"about_ca_system_score_gemma":0.00005458524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003535737,"about_ca_topic_score_gemma":0.000004438255,"domain_scores_codex":[0.9980347,0.00009865627,0.0007553193,0.0003159087,0.0004255187,0.0003698862],"domain_scores_gemma":[0.9988615,0.0003227826,0.0004019048,0.0002190552,0.00006904403,0.0001257489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001858847,0.00003034308,0.001606731,0.000245081,0.000008698076,0.00001296252,0.007705974,0.01946256,0.9599948,0.0005897908,0.004819793,0.005337401],"study_design_scores_gemma":[0.003061261,0.0003996057,0.002187929,0.0001612472,0.00003519292,0.000007706637,0.0009710892,0.6847984,0.2744024,0.001224915,0.03219967,0.0005506176],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6442567,0.0001214505,0.3418512,0.01097989,0.0004142751,0.0007661223,0.00006792618,0.0003175971,0.001224889],"genre_scores_gemma":[0.6013407,0.00004105911,0.3888506,0.008978472,0.000275887,0.00009204814,0.0002471089,0.00005303552,0.0001211794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6855924,"threshold_uncertainty_score":0.72141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02323441463107265,"score_gpt":0.2815302091960457,"score_spread":0.258295794564973,"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."}}