{"id":"W4226097900","doi":"10.1093/bib/bbac155","title":"RNMFLP: Predicting circRNA–disease associations based on robust nonnegative matrix factorization and label propagation","year":2022,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"National Natural Science Foundation of China","keywords":"Non-negative matrix factorization; Factorization; Computer science; Matrix decomposition; Matrix (chemical analysis); Mathematics; Artificial intelligence; Algorithm; Chemistry; Physics","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":[0.003076088,0.001516382,0.001044642,0.001823658,0.0007115612,0.0009655774,0.001401203,0.001709496,0.001691384],"category_scores_gemma":[0.006423974,0.0004885258,0.001686818,0.001127411,0.0007391569,0.001258907,0.001028037,0.001957242,0.0008158502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006967458,"about_ca_system_score_gemma":0.001291269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006249919,"about_ca_topic_score_gemma":0.006764732,"domain_scores_codex":[0.998899,0.0003845736,0.00006135876,0.0003156769,0.0002435478,0.00009590974],"domain_scores_gemma":[0.9970459,0.001849064,0.0003752884,0.0001770888,0.0004375778,0.0001151053],"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":[0.0005921293,0.0003638157,0.01562044,0.0004726363,0.0004517188,0.0005163457,0.0002575943,0.3403143,0.02908307,0.008544962,0.01674629,0.5870367],"study_design_scores_gemma":[0.00001929459,0.00004207002,0.0005266858,0.00001149743,0.00002094736,0.00007982589,0.00001009931,0.9934684,0.001630447,0.003378286,0.000795391,0.00001703651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01408171,0.0004866531,0.9830744,0.0002625825,0.00008590167,0.00008625622,0.0003051654,0.001279685,0.0003376443],"genre_scores_gemma":[0.2306217,0.0006242381,0.7632059,0.0004433042,0.0002795183,0.0003728463,0.002215948,0.0002292603,0.002007182],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006249919,"threshold_uncertainty_score":0.01626813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01325040169376098,"score_gpt":0.2458305388229346,"score_spread":0.2325801371291736,"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."}}