{"id":"W4380084687","doi":"10.1186/s13059-023-02968-z","title":"Matchtigs: minimum plain text representation of k-mer sets","year":2023,"lang":"en","type":"article","venue":"Genome biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"H2020 European Research Council; Horizon 2020 Framework Programme; Academy of Finland","keywords":"Biology; k-mer; Representation (politics); Human genetics; Combinatorics; Genome Biology; Computational biology; Evolutionary biology; Genetics; Mathematics; Genomics; Genome; Gene","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":[0.0005877275,0.001507915,0.001296782,0.001589874,0.0007658657,0.002429266,0.002593063,0.001574875,0.0176015],"category_scores_gemma":[0.004960856,0.0007677389,0.001206776,0.002963121,0.0005448369,0.004015151,0.001977188,0.001456098,0.01120444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006759852,"about_ca_system_score_gemma":0.001076425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009895463,"about_ca_topic_score_gemma":0.001742612,"domain_scores_codex":[0.9989506,0.0001574162,0.000107561,0.0003027403,0.000356471,0.0001252919],"domain_scores_gemma":[0.9983436,0.0004885554,0.0001504597,0.000703712,0.0002314397,0.00008222579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00269844,0.0004293275,0.002324114,0.001406906,0.0001582359,0.0005433334,0.0005333057,0.0369525,0.1006536,0.02144145,0.08644916,0.7464095],"study_design_scores_gemma":[0.0005998528,0.0008448799,0.001806161,0.0001569893,0.0001138823,0.001260071,0.0005356111,0.7229044,0.1298842,0.06794193,0.07378369,0.0001683446],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05554991,0.000784736,0.8610807,0.0006343974,0.0003490238,0.0003914909,0.009695932,0.06476751,0.006746319],"genre_scores_gemma":[0.1313806,0.0003374376,0.834455,0.0002790491,0.0001339872,0.0005031758,0.0223732,0.003860852,0.006676781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0176015,"threshold_uncertainty_score":0.05888283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02207327219455207,"score_gpt":0.2846385252613501,"score_spread":0.262565253066798,"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."}}