{"id":"W4411293183","doi":"10.1101/2025.06.12.659409","title":"Planetary-scale metagenomic search reveals new patterns of CRISPR targeting","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"CRISPR; Metagenomics; Scale (ratio); Computational biology; Biology; Computer science; Evolutionary biology; Geography; Genetics; Cartography; 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":[0.001138642,0.0004528828,0.0008027794,0.00158415,0.0005843869,0.001428927,0.0005766136,0.0006402657,0.001802267],"category_scores_gemma":[0.003375927,0.0003055979,0.001153134,0.002002379,0.0005397368,0.0007675882,0.001131966,0.000724283,0.0005818102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004329322,"about_ca_system_score_gemma":0.0005680261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001715335,"about_ca_topic_score_gemma":0.002908942,"domain_scores_codex":[0.99927,0.0001459767,0.00005385749,0.0003259305,0.0001247865,0.00007934542],"domain_scores_gemma":[0.9989966,0.0004446603,0.0001309364,0.0002224062,0.0001195821,0.0000859787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001797504,0.0004302436,0.5906129,0.001702851,0.002722621,0.001718176,0.0009551745,0.1650791,0.1536431,0.00783614,0.01130402,0.06219825],"study_design_scores_gemma":[0.0001962373,0.0003899408,0.3150624,0.0001152154,0.0007781176,0.001006746,0.001907486,0.6038339,0.03729392,0.02203529,0.01723103,0.0001496922],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9839372,0.0006686472,0.007338073,0.0002965325,0.00003382264,0.00001565682,0.005085194,0.0009295384,0.001695385],"genre_scores_gemma":[0.9788079,0.0001620752,0.01176333,0.0001458063,0.00001503497,0.00001943823,0.008689547,0.0001911931,0.000205563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001802267,"threshold_uncertainty_score":0.006029189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009871112128427641,"score_gpt":0.2563908705413629,"score_spread":0.2465197584129353,"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."}}