{"id":"W2888136048","doi":"10.1145/3233547.3233717","title":"Choosing Non-redundant Representative Subsets Of Protein Sequence Data Sets Using Submodular Optimization","year":2018,"lang":"en","type":"article","venue":"","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Submodular set function; Computer science; Optimization problem; Disjoint sets; Selection (genetic algorithm); Data mining; Sequence (biology); Redundancy (engineering); Preprocessor; Set (abstract data type); Mathematics; Algorithm; Mathematical optimization; Artificial intelligence; Biology; Combinatorics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005285216,0.002096455,0.003197242,0.001588115,0.0006582211,0.001664495,0.002106021,0.001447962,0.001842706],"category_scores_gemma":[0.007222078,0.0009245225,0.001798234,0.001965429,0.001286318,0.001740197,0.001911309,0.00208992,0.0005361215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001334494,"about_ca_system_score_gemma":0.002622742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002091608,"about_ca_topic_score_gemma":0.002498975,"domain_scores_codex":[0.9976916,0.001237065,0.0001025112,0.0004314158,0.0003841309,0.0001531771],"domain_scores_gemma":[0.9954828,0.003347814,0.0003413766,0.0002482935,0.0004016864,0.0001780364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000179422,0.0001857213,0.001148178,0.0002484164,0.0001645903,0.0001131873,0.00009254588,0.91361,0.003409973,0.007645226,0.002915256,0.07028747],"study_design_scores_gemma":[0.00002120509,0.00006911745,0.0001096487,0.00001154101,0.00001355889,0.00002247991,0.00002203973,0.991104,0.0006440689,0.007487461,0.0004867396,0.000008188327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02040698,0.0004392368,0.9770422,0.0003711409,0.0000257397,0.0001816796,0.0002305621,0.0004599303,0.0008424986],"genre_scores_gemma":[0.2710332,0.0005033623,0.7225158,0.0007604003,0.0001064035,0.001110171,0.001823297,0.0002914063,0.001856098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005285216,"threshold_uncertainty_score":0.02795124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1608780064708306,"score_gpt":0.368667685748764,"score_spread":0.2077896792779334,"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."}}