{"id":"W4403597831","doi":"10.1093/bioinformatics/btae634","title":"PONYTA: prioritization of phenotype-related genes from mouse KO events using PU learning on a biological network","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Seoul National University; National Research Foundation","keywords":"False positive paradox; Cutoff; Phenotype; Transcriptome; Computational biology; Gene; Benchmark (surveying); Biology; Prioritization; Gene regulatory network; Computer science; Genetics; Gene expression; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002516524,0.0002017893,0.0002126186,0.00005751566,0.0001013215,0.00004695477,0.0001702251,0.0003273572,0.00002799905],"category_scores_gemma":[0.00004021423,0.0001695091,0.0001221077,0.0001828725,0.00005725773,0.00001504364,0.0001309935,0.0001888468,0.00003908794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002692096,"about_ca_system_score_gemma":0.0000762366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001161901,"about_ca_topic_score_gemma":0.000003211448,"domain_scores_codex":[0.9987605,0.00004017586,0.0006026556,0.0001646742,0.0001503164,0.0002817342],"domain_scores_gemma":[0.9994048,0.00003500697,0.0001928312,0.0002386489,0.00005748195,0.00007118042],"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":[0.0007682625,0.0003898364,0.01144518,0.0009455581,0.002244081,0.00001603944,0.003772581,0.4128492,0.2858039,0.01111328,0.01074674,0.2599052],"study_design_scores_gemma":[0.001186443,0.001001313,0.001582771,0.0005367343,0.0001206247,0.00002168944,0.0005310504,0.9329091,0.01368495,0.00233361,0.04514295,0.0009487104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9583658,0.002986559,0.03592541,0.00003271958,0.0006999214,0.0003129792,0.00007640159,0.00007042309,0.001529803],"genre_scores_gemma":[0.9826708,0.001061979,0.01463273,0.0001303807,0.0004066712,0.000004915356,0.0008456267,0.00003095637,0.0002159542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5200599,"threshold_uncertainty_score":0.6912381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01584083837139865,"score_gpt":0.2421163900166619,"score_spread":0.2262755516452633,"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."}}