{"id":"W4389463139","doi":"10.1101/2023.12.05.570178","title":"Joint Learning of Node Semantics and Graph Topology using a Transformer in the sparse network regime","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Interactome; Computer science; Graph; Gene ontology; Transformer; Semantics (computer science); Artificial intelligence; Machine learning; Network topology; Biological network; Interaction network; Theoretical computer science; Computational biology; Computer network; Gene; Biology","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":[0.0007370808,0.000599461,0.0005316655,0.0006663437,0.0002222749,0.0005415856,0.0008921436,0.0006884168,0.001345819],"category_scores_gemma":[0.003353755,0.0003225423,0.0005105656,0.000672615,0.0006795265,0.001604022,0.0009965037,0.001248196,0.0003445004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006614115,"about_ca_system_score_gemma":0.0004982786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004986474,"about_ca_topic_score_gemma":0.007572445,"domain_scores_codex":[0.999755,0.00009672533,0.000009567784,0.00007102337,0.00003674505,0.00003103038],"domain_scores_gemma":[0.9986758,0.0008637819,0.0001197903,0.0001307736,0.0001361461,0.0000737515],"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":[0.0001794087,0.0001181938,0.003358977,0.00006090753,0.00005295928,0.0001138007,0.00006168576,0.9002538,0.00423772,0.01222567,0.001964734,0.07737216],"study_design_scores_gemma":[0.00000189267,0.000007250803,0.00006737252,0.000001105597,0.000001816371,0.000005124524,0.000002565851,0.9971288,0.0002080908,0.002537594,0.00003728763,0.000001124462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2322103,0.0002581688,0.7627259,0.0006878339,0.00004386311,0.00004771131,0.0004509467,0.001039333,0.002535902],"genre_scores_gemma":[0.9617724,0.0001251861,0.03563193,0.0001110256,0.00002762934,0.00003531838,0.0006092177,0.00003981714,0.001647433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004986474,"threshold_uncertainty_score":0.009914875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02168280546614132,"score_gpt":0.2267946713815991,"score_spread":0.2051118659154578,"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."}}