{"id":"W2972918700","doi":"10.3390/pr7090614","title":"A Comparison of Clustering and Prediction Methods for Identifying Key Chemical–Biological Features Affecting Bioreactor Performance","year":2019,"lang":"en","type":"article","venue":"Processes","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Hierarchical clustering; Random forest; Computer science; Outcome (game theory); Data mining; Artificial intelligence; Machine learning; Feature selection; Biochemical engineering; Bioreactor; Set (abstract data type); Mathematics; Engineering; Biology","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":[0.0001464752,0.0001177361,0.0002994614,0.00004028253,0.00005649045,0.0000310219,0.0001098577,0.0001163042,0.00008161648],"category_scores_gemma":[0.0004991255,0.000095446,0.0000407436,0.0001902653,0.0000384392,0.0001438926,0.00006280029,0.0001085922,6.121145e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002979836,"about_ca_system_score_gemma":0.00001654122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009527049,"about_ca_topic_score_gemma":0.000002326204,"domain_scores_codex":[0.9993052,0.000006866303,0.0002088455,0.0002410809,0.00007480954,0.0001631274],"domain_scores_gemma":[0.9991841,0.0004299327,0.0001674674,0.00009749644,0.00008777538,0.00003323543],"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":[0.00006616439,0.000052032,0.1224747,0.005410747,0.00005350531,3.046202e-8,0.0005571708,0.000006823223,0.8666623,0.000002911496,0.00001109727,0.004702441],"study_design_scores_gemma":[0.0002448346,0.00005740404,0.001275338,0.0001005997,0.00007565184,0.000004984481,0.001296497,0.001950731,0.994712,0.00003393473,0.0001447052,0.0001033173],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845191,0.006807894,0.007337175,0.000007311792,0.00003848538,0.00008793873,0.000008790602,0.00006691665,0.001126392],"genre_scores_gemma":[0.9834881,0.0003077055,0.0159901,0.000006245419,0.00006620563,0.00002276137,0.00001644218,0.000010605,0.0000917704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1280497,"threshold_uncertainty_score":0.3892175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06544163702627569,"score_gpt":0.4064067179162489,"score_spread":0.3409650808899732,"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."}}