{"id":"W4281294657","doi":"10.1093/bioadv/vbac038","title":"HPiP: an R/Bioconductor package for predicting host–pathogen protein–protein interactions from protein sequences using ensemble machine learning approach","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bioconductor; Computational biology; Host (biology); Computer science; Machine learning; Biology; Artificial intelligence; Bioinformatics; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005742109,0.0003691276,0.0003284999,0.0001066472,0.001064487,0.000164112,0.0005136307,0.0001283379,0.00004148663],"category_scores_gemma":[0.0001035684,0.0003561415,0.0001667688,0.0001857778,0.0001036051,0.000140528,0.000387826,0.0004317624,0.000003588523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008417245,"about_ca_system_score_gemma":0.0001697215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007704384,"about_ca_topic_score_gemma":0.00003821586,"domain_scores_codex":[0.9978566,0.0001192306,0.000775796,0.0003949685,0.0003106626,0.0005427746],"domain_scores_gemma":[0.9985042,0.0000222243,0.0007038929,0.0004914235,0.0001158186,0.0001624526],"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":[0.0001942445,0.0001284765,0.0002319635,0.0002277158,0.0001114054,0.000001294688,0.001022759,0.007641193,0.9813974,0.0002881229,0.0000348294,0.008720581],"study_design_scores_gemma":[0.001804831,0.001831928,0.00002301838,0.0001473499,0.00009259778,0.00006447453,0.008155259,0.6424904,0.2240887,0.001682168,0.1182478,0.001371473],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8389117,0.00137704,0.1551065,0.00003804989,0.0002514637,0.002471104,0.001049257,0.00007908525,0.0007158038],"genre_scores_gemma":[0.7985603,0.00002535343,0.1968652,0.00010061,0.0004060914,0.0008567967,0.002597019,0.00005974856,0.0005289033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7573088,"threshold_uncertainty_score":0.9998891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02130643004791029,"score_gpt":0.2605602040231485,"score_spread":0.2392537739752382,"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."}}