{"id":"W1992487663","doi":"10.1371/journal.pone.0091315","title":"Parallel Clustering Algorithm for Large-Scale Biological Data Sets","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Specialized Research Fund for the Doctoral Program of Higher Education of China; University of California, Irvine; Science and Technology Commission of Shanghai Municipality; Major Research Plan; National Natural Science Foundation of China; McMaster University","keywords":"Affinity propagation; Cluster analysis; Computer science; Bottleneck; Speedup; Algorithm; Similarity (geometry); Biological data; Parallel algorithm; Data mining; Scale (ratio); Canopy clustering algorithm; Parallel computing; Correlation clustering; Bioinformatics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.001197322,0.001255788,0.001392241,0.002944937,0.002295386,0.001264549,0.00239133,0.001153814,0.003318771],"category_scores_gemma":[0.00313251,0.0006494766,0.001972205,0.003992813,0.0007146203,0.00161138,0.001845745,0.001503959,0.002168556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00138871,"about_ca_system_score_gemma":0.00295143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009795044,"about_ca_topic_score_gemma":0.008850914,"domain_scores_codex":[0.9984475,0.000178897,0.0001419337,0.0004289101,0.000683245,0.0001196539],"domain_scores_gemma":[0.9986869,0.0002555909,0.0001242338,0.000275788,0.0005833246,0.00007413749],"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":[0.0003744743,0.0002032768,0.003466798,0.0003524598,0.000416438,0.0003273691,0.0003485584,0.3938832,0.01624035,0.02463767,0.01541935,0.5443301],"study_design_scores_gemma":[0.00005246414,0.00003314234,0.0005743701,0.000008407305,0.00003394224,0.0001474433,0.00004099975,0.9721247,0.003779518,0.01824987,0.00493647,0.00001870105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006134319,0.0001944439,0.9902505,0.0001488304,0.00006963794,0.0001141255,0.0001284643,0.00202501,0.000934737],"genre_scores_gemma":[0.07827862,0.00028351,0.9164231,0.0001027024,0.0001030586,0.0005589843,0.001009376,0.0002860847,0.002954591],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009795044,"threshold_uncertainty_score":0.01947606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08818269471788112,"score_gpt":0.2930610795257316,"score_spread":0.2048783848078505,"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."}}