{"id":"W2784791781","doi":"10.1101/240515","title":"De novo profile generation based on sequence context specificity with the long short-term memory network","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Medical Science, University of Tokyo; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Sequence (biology); Context (archaeology); Computer science; Generator (circuit theory); Scalability; Similarity (geometry); Artificial intelligence; Computational biology; Bioinformatics; Power (physics); Biology; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009078896,0.0005354497,0.0003502165,0.00005588092,0.0005075779,0.0004378945,0.0009522594,0.0005532738,0.00003206126],"category_scores_gemma":[0.0001921951,0.0004222245,0.0001263009,0.00009122463,0.0002709012,0.00001226142,0.0003576236,0.0008728076,0.0000210245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432326,"about_ca_system_score_gemma":0.0008003735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002021138,"about_ca_topic_score_gemma":0.00003140457,"domain_scores_codex":[0.9977767,0.0002100689,0.0003579622,0.0007306746,0.0003702157,0.0005543137],"domain_scores_gemma":[0.996671,0.00003204537,0.0004917821,0.002288613,0.0003507798,0.0001658261],"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":[0.000384913,0.0001628579,0.05340754,0.0004773032,0.0002978559,0.0001053688,0.00002468986,0.05293364,0.8871075,0.0002171366,0.004818015,0.0000631619],"study_design_scores_gemma":[0.0009717568,0.0006407974,0.09802631,0.0007200218,0.0002115411,4.363993e-7,0.000005476315,0.07828489,0.8103964,5.338227e-7,0.008919503,0.001822292],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712,0.0003051368,0.02604898,0.0003649792,0.0005971132,0.001056971,0.0001374838,0.0001024238,0.0001868985],"genre_scores_gemma":[0.9909056,0.0000528792,0.006080128,0.0008071222,0.00180308,0.0002000398,0.00001135054,0.0001032612,0.00003658161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07671107,"threshold_uncertainty_score":0.999823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02028968337993811,"score_gpt":0.2449646485872867,"score_spread":0.2246749652073486,"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."}}