{"id":"W4386964872","doi":"10.1101/2023.09.19.558381","title":"Motif selection enables efficient sequence-based classification of non-coding RNA","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Computer science; Computation; Coding (social sciences); Artificial intelligence; Sequence (biology); Sequence motif; Non-coding RNA; Computational biology; Selection (genetic algorithm); Set (abstract data type); Annotation; Machine learning; Data mining; RNA; Biology; Algorithm; Mathematics; 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":[0.0003966302,0.0003936388,0.0003999382,0.0005128691,0.0002448075,0.0004538606,0.0006019096,0.0005704587,0.00133191],"category_scores_gemma":[0.001387701,0.000145239,0.0002879103,0.0003817509,0.000258171,0.0004273435,0.0003993317,0.0004578387,0.0009632825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001943245,"about_ca_system_score_gemma":0.0002849433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005245626,"about_ca_topic_score_gemma":0.0008608047,"domain_scores_codex":[0.9997167,0.00006122228,0.00001766856,0.0001010311,0.00007300229,0.00003030196],"domain_scores_gemma":[0.9994723,0.0001973907,0.00007609045,0.0000757459,0.0001258506,0.00005264573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004926852,0.000385003,0.00748153,0.0001879966,0.00004415123,0.0001968274,0.0000873247,0.05101776,0.5107513,0.004129237,0.003270095,0.421956],"study_design_scores_gemma":[0.00001562208,0.00005491485,0.001539435,0.000003895764,0.000006843123,0.0001062539,0.00001123421,0.921752,0.07342736,0.002359713,0.0007152025,0.000007517643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2837896,0.0002983647,0.7107766,0.0001447031,0.00004888903,0.000069077,0.0002119857,0.003018979,0.0016418],"genre_scores_gemma":[0.6257821,0.00008910269,0.370731,0.00007146689,0.00005073289,0.00007529248,0.0009113293,0.0001968604,0.00209195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00133191,"threshold_uncertainty_score":0.004455626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02971016052969001,"score_gpt":0.2449846987104002,"score_spread":0.2152745381807102,"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."}}