{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537251,0.000590265,0.0005565879,0.0008768256,0.0004077705,0.001084565,0.001127262,0.0007202596,0.001799337],"category_scores_gemma":[0.003512298,0.0003122497,0.0004789332,0.001490491,0.0007561313,0.001639908,0.00189222,0.001206954,0.001077509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004957126,"about_ca_system_score_gemma":0.0006136619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009751948,"about_ca_topic_score_gemma":0.001317229,"domain_scores_codex":[0.9992164,0.0001550274,0.0000481639,0.0001318356,0.0003740783,0.00007451586],"domain_scores_gemma":[0.9986161,0.0005782809,0.0001399579,0.0004085907,0.0002015963,0.00005549597],"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":[0.00081236,0.0002044489,0.001324419,0.000381306,0.00004766509,0.0006516242,0.0008159095,0.296654,0.1587338,0.07314698,0.008659709,0.4585679],"study_design_scores_gemma":[0.00004562154,0.0001040859,0.0003498417,0.0000279507,0.00001233564,0.0002443894,0.0001115852,0.9056755,0.058238,0.02808971,0.007062335,0.00003865633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0354159,0.0002089356,0.9612088,0.0001966484,0.00004558912,0.00003934107,0.0003136237,0.001195064,0.001376127],"genre_scores_gemma":[0.2517938,0.0003402944,0.7420571,0.0002001419,0.00007294608,0.0002166367,0.001977347,0.0003666334,0.002975075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001799337,"threshold_uncertainty_score":0.006019413,"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."}}