{"id":"W4388410090","doi":"10.1101/2023.11.04.565620","title":"MiRGraph: A hybrid deep learning approach to identify microRNA-target interactions by integrating heterogeneous regulatory network and genomic sequences","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"microRNA; Computational biology; Transformer; ENCODE; Gene; Sequence labeling; Biology; Computer science; Artificial intelligence; Genetics; Engineering","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":[0.0004130337,0.001058695,0.0007366187,0.0009915833,0.0002607581,0.0004694654,0.001447126,0.0009374964,0.001468839],"category_scores_gemma":[0.0006514209,0.0004442245,0.0008421692,0.0007180787,0.0003640635,0.000828387,0.0008270067,0.0008308475,0.0004387083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007808246,"about_ca_system_score_gemma":0.0006923464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006445696,"about_ca_topic_score_gemma":0.01030632,"domain_scores_codex":[0.9997715,0.00004099256,0.000009146423,0.00009414877,0.00004695425,0.00003718441],"domain_scores_gemma":[0.9997804,0.00008872458,0.00003611376,0.0000314051,0.00004123991,0.00002217148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003834136,0.0003595934,0.005110338,0.0001728269,0.0003623132,0.0003304299,0.00007121155,0.7035468,0.0261566,0.006358176,0.008711029,0.2484373],"study_design_scores_gemma":[0.000005352995,0.00002102256,0.00017462,0.000002085523,0.00001004527,0.0000154404,0.000003647833,0.9966956,0.001362061,0.001356555,0.0003496105,0.000004016487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1072387,0.001137192,0.8795213,0.0003768985,0.00007010862,0.00008989746,0.001164148,0.008152639,0.002249129],"genre_scores_gemma":[0.7543235,0.0005017868,0.2326704,0.0005795908,0.00006605983,0.0001708081,0.004981149,0.0004274582,0.006279254],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006445696,"threshold_uncertainty_score":0.01281637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01188910806139436,"score_gpt":0.2382885310044065,"score_spread":0.2263994229430121,"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."}}