{"id":"W2800253090","doi":"10.1038/s41467-017-02480-6","title":"Optimal compressed representation of high throughput sequence data via light assembly","year":2018,"lang":"en","type":"article","venue":"Nature Communications","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Simons Institute for the Theory of Computing, University of California Berkeley; National Institutes of Health; National Science Foundation","keywords":"Sequence assembly; Computer science; Trie; Contig; Representation (politics); Data compression; Node (physics); Compression (physics); Algorithm; Compression ratio; Throughput; Reference genome; External Data Representation; Data structure; Theoretical computer science; Parallel computing; Genome; Artificial intelligence; Biology","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002947094,0.0001358765,0.0002064913,0.00009017819,0.0003887528,0.0001110338,0.009818682,0.0001903922,0.00001398777],"category_scores_gemma":[0.0001576422,0.0001220655,0.00003748393,0.0007476871,0.0002290586,0.001565058,0.006118424,0.0005140111,0.00002909928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002605752,"about_ca_system_score_gemma":0.00008910273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002489928,"about_ca_topic_score_gemma":0.00009925011,"domain_scores_codex":[0.998413,0.0002112736,0.000343211,0.0004820477,0.000364041,0.0001864621],"domain_scores_gemma":[0.988372,0.0003109419,0.0002679274,0.0105138,0.000468176,0.00006718647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007091156,0.001587198,0.001845037,0.00005904168,0.0003029646,0.00001246406,0.002938859,0.0004349048,0.157932,0.4940975,0.212634,0.1280851],"study_design_scores_gemma":[0.0005170185,0.0001202704,0.006794227,0.00008956649,0.00003431249,0.00002988557,0.00003763187,0.8438616,0.03149187,0.002410768,0.1142679,0.0003449171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003430165,0.001754865,0.9841625,0.007130468,0.0005786461,0.0002788691,0.0001630971,0.0002072778,0.002294079],"genre_scores_gemma":[0.5843073,0.0001547967,0.414835,0.0001677621,0.00007300147,0.000007386571,0.0004222527,0.000006618149,0.00002593769],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8434268,"threshold_uncertainty_score":0.9955387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07744304994520126,"score_gpt":0.3753275363313552,"score_spread":0.2978844863861539,"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."}}