{"id":"W4283077104","doi":"10.2196/30890","title":"An Analysis of Different Distance-Linkage Methods for Clustering Gene Expression Data and Observing Pleiotropy: Empirical Study","year":2022,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Silhouette; Pleiotropy; Euclidean distance; Linkage (software); Complete linkage; Metric (unit); Data set; Set (abstract data type); Similarity (geometry); Data mining; Selection (genetic algorithm); Complete-linkage clustering; Computer science; Biology; Gene; Genetics; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Phenotype; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08804795,0.00151932,0.001204079,0.006891452,0.002203586,0.00222994,0.00265708,0.002379652,0.001045956],"category_scores_gemma":[0.2260586,0.0004567296,0.003118828,0.007084314,0.002366423,0.003688392,0.001547626,0.002585098,0.0002626732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00236761,"about_ca_system_score_gemma":0.001475514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008540595,"about_ca_topic_score_gemma":0.006597427,"domain_scores_codex":[0.9558263,0.03273898,0.001882457,0.003641047,0.005171365,0.0007398696],"domain_scores_gemma":[0.4553324,0.5034519,0.01103924,0.01316102,0.01548,0.001535463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001261054,0.0008769669,0.7858433,0.001070017,0.004384538,0.0004464868,0.002184817,0.1046255,0.0008898432,0.005986549,0.004142898,0.08828802],"study_design_scores_gemma":[0.0001492856,0.0007832824,0.2617247,0.0003366244,0.0008213536,0.000792999,0.002604807,0.7195929,0.001633037,0.00907856,0.002305378,0.0001771131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9177546,0.003870372,0.07506641,0.0008556399,0.00007943335,0.0002745707,0.0006332608,0.0002190146,0.001246762],"genre_scores_gemma":[0.9627292,0.0004967726,0.03487549,0.00007961857,0.00004644469,0.0001491437,0.001184451,0.0001028234,0.0003360895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08804795,"threshold_uncertainty_score":0.4656476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0326439277947011,"score_gpt":0.3553310898961504,"score_spread":0.3226871621014493,"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."}}