{"id":"W4414106964","doi":"10.1016/j.csbj.2025.09.002","title":"Pantheon-DNA: Versatile encoding-decoding system with integrated adaptive NGS preprocessing algorithms for DNA data storage","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Lenovo Group; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Preprocessor; Pipeline (software); Decodes; Scalability; Cluster analysis; Robustness (evolution); Error detection and correction; Indel; DNA sequencing","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":[0.0002394601,0.000183571,0.000211418,0.0001016784,0.0005202718,0.00008978701,0.0003723915,0.0002549541,0.00000244953],"category_scores_gemma":[0.0001075808,0.0001226022,0.00004046632,0.0001512938,0.0002441868,0.00001759866,0.0002746993,0.0002545326,4.080328e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000036689,"about_ca_system_score_gemma":0.0001318978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002704953,"about_ca_topic_score_gemma":0.000002682181,"domain_scores_codex":[0.9989063,0.00004546339,0.0002630767,0.0004583384,0.00008733842,0.0002395249],"domain_scores_gemma":[0.9993543,0.00006901818,0.0001799236,0.0001596998,0.0001860442,0.00005102811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003545707,0.0001165618,0.0101088,0.0005485811,0.002247046,0.0001382766,0.0003248674,0.0236271,0.3263848,0.03523086,0.003292708,0.5944347],"study_design_scores_gemma":[0.003426964,0.00174962,0.006981143,0.0006222212,0.0001600937,0.00187465,0.002967367,0.9260921,0.04325092,0.008782611,0.003285985,0.0008062974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6479389,0.0005406496,0.3505202,0.0004972084,0.000183652,0.0001484678,0.00005355111,0.00005584577,0.00006156253],"genre_scores_gemma":[0.9683775,0.00001937001,0.03119204,0.00009945402,0.0001223084,0.000003736857,0.0001447697,0.000008976459,0.00003179574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.902465,"threshold_uncertainty_score":0.4999571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02337901571674043,"score_gpt":0.2755321386105961,"score_spread":0.2521531228938557,"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."}}