{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001875893,0.00008155849,0.0001051971,0.0000144404,0.00006678186,0.00001559982,0.0002901209,0.0001111089,0.0000214994],"category_scores_gemma":[0.00006314051,0.00007067819,0.0000277468,0.00002852777,0.00001690945,0.000002958632,0.0002210398,0.00004056607,0.00001199207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004383149,"about_ca_system_score_gemma":0.00001398299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.680299e-7,"about_ca_topic_score_gemma":0.000007451907,"domain_scores_codex":[0.9992298,0.00003550609,0.0001170296,0.0003627173,0.00008171641,0.0001731749],"domain_scores_gemma":[0.9992642,0.000009486241,0.00004718229,0.000574763,0.00004480396,0.00005958559],"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":[0.00005257942,0.0005302735,0.0006215496,0.00002898707,0.0000639999,1.115706e-7,0.00002094789,0.000006606946,0.9626413,0.00002834591,0.007021436,0.02898384],"study_design_scores_gemma":[0.002850288,0.0007456958,0.003539202,0.00007823521,0.00008494453,0.000002883702,0.0001436883,0.2714438,0.3960837,0.0003129558,0.3241355,0.0005791341],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1250076,0.0003732752,0.8724144,0.0006034508,0.0001033188,0.0003895519,0.000231702,0.00003850153,0.0008383082],"genre_scores_gemma":[0.6757336,0.0004453857,0.3158451,0.001204845,0.0009299018,0.0002148269,0.003951276,0.00003665836,0.001638499],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5665576,"threshold_uncertainty_score":0.2882173,"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."}}