{"id":"W4414870790","doi":"10.1101/2025.10.03.680292","title":"A Convolutional Deep Learning Approach to identify DNA Sequences for Gene Prediction","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Pseudogene; Deep learning; Convolutional neural network; Human genome; Metric (unit); Genome; Gene; DNA sequencing; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004824799,0.000405606,0.0003896812,0.0002252515,0.0002523277,0.0001463049,0.0004921182,0.0005983121,0.000008282234],"category_scores_gemma":[0.0003462866,0.0004411976,0.000297454,0.0003402007,0.0001004519,0.00001342079,0.0004359871,0.0003421523,0.00001295526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001297442,"about_ca_system_score_gemma":0.0004882106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005363329,"about_ca_topic_score_gemma":0.000003360625,"domain_scores_codex":[0.9975763,0.0001008138,0.0004376509,0.001169155,0.0002747426,0.0004413273],"domain_scores_gemma":[0.9983043,0.00002062675,0.0002428355,0.0006369298,0.0005942842,0.0002010039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005920804,0.0000880978,0.002578166,0.0002266215,0.0003407242,0.000002043149,0.000006017318,0.005929988,0.9902321,0.0001765837,0.0003556078,0.000004803336],"study_design_scores_gemma":[0.0005449739,0.0002010948,0.02224379,0.0001763216,0.0004042929,5.430305e-8,0.00001514701,0.007131114,0.9490025,0.00001266857,0.01932833,0.0009396895],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8479856,0.002071826,0.147168,0.0001365874,0.0007324693,0.0009546514,0.0007482371,0.0001394328,0.00006326409],"genre_scores_gemma":[0.9837707,0.000281407,0.01398086,0.0002688058,0.0007803087,0.0007514283,0.00003144629,0.0000436709,0.00009133442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1357852,"threshold_uncertainty_score":0.999804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01358633984616219,"score_gpt":0.2462878785514192,"score_spread":0.232701538705257,"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."}}