{"id":"W1965359119","doi":"10.1186/1748-7188-6-23","title":"ReCoil - an algorithm for compression of extremely large datasets of dna data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data compression; Redundancy (engineering); Algorithm; Encoding (memory); Compression (physics); Volume (thermodynamics); Data compression ratio; Lossless compression; Compression ratio; Sequence (biology); Data mining; Image compression; Artificial intelligence; Biology; Physics","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":[0.0008489378,0.0002762186,0.0005499246,0.0001728805,0.00012429,0.00001830853,0.003465033,0.0002331923,0.00001888603],"category_scores_gemma":[0.00009244171,0.000237738,0.0001314069,0.0002248623,0.0001452841,0.0006397581,0.00168765,0.0001051811,0.000002009502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001440164,"about_ca_system_score_gemma":0.0001192105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001805842,"about_ca_topic_score_gemma":0.00001047737,"domain_scores_codex":[0.9974455,0.0001526333,0.0006684985,0.001025347,0.0001835088,0.000524572],"domain_scores_gemma":[0.9960935,0.0001504393,0.0004744501,0.002865464,0.0002608661,0.0001553289],"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":[0.00009039929,0.0007622934,0.00004454578,0.00008333278,0.0001451099,0.00001027696,0.0002190688,0.000002733669,0.06492332,0.02133523,0.002436023,0.9099477],"study_design_scores_gemma":[0.002650669,0.001888139,0.0001673259,0.00007153607,0.00007714093,0.00002476486,0.00004702355,0.7614823,0.1765105,0.01856839,0.03800045,0.0005117165],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001108476,0.0005476378,0.9819627,0.00002515713,0.0005691184,0.0006680499,0.01501331,0.00006090597,0.00004457804],"genre_scores_gemma":[0.008668174,0.00004512839,0.979298,0.0001145298,0.00008027116,0.00007087379,0.01168196,0.00003096976,0.00001008033],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9094359,"threshold_uncertainty_score":0.9694675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1004202575440594,"score_gpt":0.3489168214591663,"score_spread":0.2484965639151069,"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."}}