{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001367644,0.0001168599,0.0001855368,0.0000704784,0.00005838102,0.000003835304,0.0001631712,0.000141134,0.0000313776],"category_scores_gemma":[0.00005351384,0.0001094673,0.00008202854,0.0001630557,0.0001327717,3.541701e-7,0.000189729,0.00003627909,0.00007572032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005233699,"about_ca_system_score_gemma":0.00003010249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002711249,"about_ca_topic_score_gemma":0.0000158502,"domain_scores_codex":[0.9991083,0.00006038289,0.0002276226,0.000315285,0.00004405737,0.0002443301],"domain_scores_gemma":[0.9994802,0.00002642568,0.00009198524,0.000302031,0.00005941635,0.00003990789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003665183,0.00001446908,0.0110253,0.00001097064,0.00009229399,0.000001168256,0.0001464885,0.00006312178,0.9854397,0.0001307849,0.001388484,0.001650569],"study_design_scores_gemma":[0.001620859,0.001258227,0.3807704,0.00001007653,0.00006768113,0.00002609088,0.001313963,0.00009350829,0.3626126,0.004131776,0.2473811,0.0007137975],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964938,0.001108708,0.00007855437,0.0002436372,0.0002372106,0.0001448935,0.0001252569,0.000007923009,0.001560011],"genre_scores_gemma":[0.9974742,0.0008726905,0.0003262689,0.0001175616,0.0001526598,0.00002702137,0.0003631767,0.00001599017,0.00065041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6228271,"threshold_uncertainty_score":0.4463948,"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."}}