{"id":"W4416571000","doi":"10.1038/s41592-025-02939-1","title":"Helixer: ab initio prediction of primary eukaryotic gene models combining deep learning and a hidden Markov model","year":2025,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bureau de Coopération Interuniversitaire","funders":"German Network for Bioinformatics Infrastructure; Heinrich-Heine-Universität Düsseldorf; Forschungszentrum Jülich; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft","keywords":"Hidden Markov model; Gene prediction; Identification (biology); Deep learning; Genome; Annotation; Software; Gene Annotation; Genome project","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":[0.00107112,0.001298604,0.0008679343,0.0008613943,0.0005995893,0.001080743,0.001572989,0.001442704,0.005219534],"category_scores_gemma":[0.002780071,0.0007978597,0.001447849,0.0007562199,0.0004575575,0.001247172,0.001198652,0.001772909,0.002542226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007756674,"about_ca_system_score_gemma":0.001188653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003704457,"about_ca_topic_score_gemma":0.005841058,"domain_scores_codex":[0.9996235,0.0001044273,0.0000194886,0.0001206781,0.00009794525,0.000033833],"domain_scores_gemma":[0.9991776,0.0005329269,0.00005800514,0.0001129359,0.00007229397,0.00004622325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008569009,0.0002904092,0.004756005,0.0008785655,0.0005975068,0.0006396291,0.0003211038,0.6376556,0.05132131,0.02197532,0.04704258,0.233665],"study_design_scores_gemma":[0.00002264476,0.00003827921,0.0002095184,0.00001909211,0.00001553014,0.00006220787,0.00001716297,0.9833134,0.006039266,0.007172655,0.003075937,0.00001426259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03657269,0.0005767507,0.9055803,0.0003111695,0.0001492562,0.0000785639,0.004892624,0.0496201,0.002218475],"genre_scores_gemma":[0.2332496,0.0005984276,0.7423564,0.0003141054,0.00008013904,0.0002698907,0.01571783,0.003673159,0.003740387],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005219534,"threshold_uncertainty_score":0.017461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01426356486179845,"score_gpt":0.2989379692566936,"score_spread":0.2846744043948951,"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."}}