{"id":"W4281555275","doi":"10.1101/2022.05.24.493339","title":"plASgraph - using graph neural networks to detect plasmid contigs from an assembly graph","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Universität Bielefeld; Simon Fraser University; Compute Canada","keywords":"Contig; Computer science; Graph; Software; Artificial intelligence; Plasmid; Artificial neural network; Sequence (biology); Genome; Data mining; Machine learning; Theoretical computer science; Biology; Genetics; Gene; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005800519,0.001057809,0.0004277052,0.003024433,0.000513808,0.001024592,0.00115837,0.0008678193,0.005829063],"category_scores_gemma":[0.003169451,0.000472383,0.0007671626,0.001359853,0.0003798139,0.001280808,0.001012165,0.0009003368,0.001786677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007701677,"about_ca_system_score_gemma":0.0006609392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007595327,"about_ca_topic_score_gemma":0.01254374,"domain_scores_codex":[0.9997286,0.0000340365,0.00001548917,0.0001225405,0.00007100822,0.00002831038],"domain_scores_gemma":[0.9988862,0.0005806058,0.0001297093,0.0001588801,0.0001907838,0.0000539526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006413218,0.0003005947,0.02559384,0.001147743,0.0003532877,0.000769653,0.0004103125,0.3207653,0.04157144,0.00942946,0.04071172,0.5583053],"study_design_scores_gemma":[0.00001821054,0.00003913052,0.002106523,0.00003632501,0.00002241366,0.00009634451,0.00005422465,0.9770916,0.006911345,0.008085562,0.005521417,0.00001693108],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1570486,0.0007920736,0.7268291,0.0006793371,0.0002071426,0.0002238957,0.01541964,0.09323372,0.005566555],"genre_scores_gemma":[0.3852265,0.0004644584,0.5692964,0.0003291861,0.00005458727,0.0002508844,0.03612624,0.003173336,0.005078495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007595327,"threshold_uncertainty_score":0.0195002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01500624398328653,"score_gpt":0.2319474719582211,"score_spread":0.2169412279749346,"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."}}