{"id":"W4396621369","doi":"10.1101/2024.04.30.591806","title":"ntEmbd: Deep learning embedding for nucleotide sequences","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institutes of Health; Canadian Institutes of Health Research; Genome British Columbia; Genome Canada","keywords":"Embedding; Artificial intelligence; Nucleotide; Deep learning; Computer science; Computational biology; Biology; Genetics; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004298136,0.001036387,0.0005336296,0.0006122342,0.0003279143,0.0008938105,0.001758084,0.001110095,0.007691599],"category_scores_gemma":[0.002405336,0.0005118689,0.0008026598,0.0006553359,0.0004557888,0.001408098,0.00155886,0.002542423,0.003279292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000771937,"about_ca_system_score_gemma":0.0008859792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004121196,"about_ca_topic_score_gemma":0.008643169,"domain_scores_codex":[0.9997622,0.00005233896,0.00001364237,0.00006101778,0.00008666357,0.00002422659],"domain_scores_gemma":[0.9996818,0.0001401846,0.00003021572,0.00007022452,0.00005154486,0.00002591292],"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":[0.0003681275,0.0002382368,0.002730002,0.000720925,0.000198928,0.0003335843,0.0002015069,0.357643,0.01874303,0.06072819,0.09408014,0.4640143],"study_design_scores_gemma":[0.00002950293,0.00003620026,0.0001656709,0.00003336047,0.000009533393,0.00007477278,0.00001675196,0.949366,0.00601538,0.03085724,0.0133802,0.00001545962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01008171,0.0007283653,0.9682819,0.0004548252,0.0001790559,0.00008331093,0.003657018,0.01362395,0.002909866],"genre_scores_gemma":[0.2143593,0.001205705,0.7488055,0.0007754734,0.00009941927,0.0008078463,0.0184746,0.002384304,0.01308778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007691599,"threshold_uncertainty_score":0.02573097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01224771977463973,"score_gpt":0.2670008472846836,"score_spread":0.2547531275100439,"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."}}