{"id":"W4414754796","doi":"10.1093/nar/gkag335","title":"DNAi: an open-source AI tool for unbiased DNA fiber analysis","year":2025,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hôpital Maisonneuve-Rosemont; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Fiber; Annotation; Deep learning; Pattern recognition (psychology); DNA","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003335655,0.0001297318,0.0002432452,0.0007610093,0.0006613547,0.001484817,0.003618462,0.0001133417,0.0002464555],"category_scores_gemma":[0.0007933622,0.0001191463,0.00008858702,0.003503433,0.0001053637,0.0008688471,0.00119286,0.0004570003,0.0002146615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001046729,"about_ca_system_score_gemma":0.0002519768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003165869,"about_ca_topic_score_gemma":0.00006229703,"domain_scores_codex":[0.9971952,0.0005941982,0.000276832,0.0008216494,0.0005934511,0.0005186444],"domain_scores_gemma":[0.9969494,0.0005240656,0.00005304582,0.00188963,0.0004507079,0.0001331599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001559341,0.0005004964,0.009559576,0.00008159731,0.0003581019,0.000005304054,0.0007277345,0.000797111,0.004955474,0.1180504,0.121924,0.7428843],"study_design_scores_gemma":[0.0005841418,0.0001980945,0.03173369,0.00001409847,0.00003709169,6.338332e-7,0.00004773124,0.3688214,0.0006496924,0.002265183,0.5954734,0.000174822],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05800008,0.00004584468,0.9058065,0.01869908,0.00009784853,0.0009146437,0.00003043255,0.0003000764,0.01610554],"genre_scores_gemma":[0.9011527,0.00001079234,0.04496973,0.001577989,0.0001045665,0.0002616065,0.000252402,0.00002671836,0.05164347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8608367,"threshold_uncertainty_score":0.9995517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06455442467865942,"score_gpt":0.4114980527189616,"score_spread":0.3469436280403022,"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."}}