{"id":"W4289743973","doi":"10.48550/arxiv.1808.03227","title":"Identifying Protein-Protein Interaction using Tree LSTM and Structured\\n Attention","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Benchmark (surveying); Computer science; Tree (set theory); Artificial intelligence; Machine learning; Recurrent neural network; Recall; Feature (linguistics); Deep learning; Precision and recall; Artificial neural network; Pattern recognition (psychology); Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004163876,0.0006841184,0.0004639982,0.0002423744,0.0005204446,0.0002610294,0.0006119974,0.0009673035,0.0001294724],"category_scores_gemma":[0.0001489011,0.0008400813,0.0003103123,0.0002900826,0.0004062051,0.00007343887,0.001862496,0.0009581207,0.00004101855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002388591,"about_ca_system_score_gemma":0.0001727333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00018515,"about_ca_topic_score_gemma":0.0001325837,"domain_scores_codex":[0.9970443,0.0003393653,0.0005694432,0.001353625,0.0001475243,0.0005456901],"domain_scores_gemma":[0.9972574,0.00001399437,0.001096459,0.001050567,0.000348935,0.0002326649],"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":[0.001247732,0.0001973962,0.01659151,0.002499637,0.001199417,0.0001047233,0.0005497076,0.02852717,0.9403783,0.00347543,0.00008890755,0.005140069],"study_design_scores_gemma":[0.00357832,0.001120955,0.00937603,0.002512814,0.00108726,0.0001889643,0.001816021,0.8705207,0.0961629,0.007297134,0.003175865,0.003163056],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.873291,0.00009890802,0.1238766,0.00002034998,0.0005902667,0.0009653803,0.00002749326,0.00004032772,0.001089772],"genre_scores_gemma":[0.9919845,0.000153732,0.004872621,0.00002880153,0.0004499858,0.00000213431,0.0002254125,0.00006582175,0.002216952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8442154,"threshold_uncertainty_score":0.999405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05226849937284599,"score_gpt":0.2270449886930217,"score_spread":0.1747764893201758,"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."}}