{"id":"W3093860449","doi":"10.3389/fmicb.2020.587306","title":"An Improved Sequencing-Based Bioinformatics Pipeline to Track the Distribution and Clonal Architecture of Proviral Integration Sites","year":2020,"lang":"en","type":"article","venue":"Frontiers in Microbiology","topic":"T-cell and Retrovirus Studies","field":"Immunology and Microbiology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Amis de l'Institut Bordet; Institut National Du Cancer","keywords":"Workflow; Pipeline (software); Computational biology; Computer science; Genome; DNA sequencing; Precision and recall; Biology; Data mining; Genetics; Database; Gene; Artificial intelligence","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":[0.003091909,0.001514302,0.001121886,0.001943884,0.001032562,0.001880622,0.001670679,0.0008369915,0.003623256],"category_scores_gemma":[0.005077382,0.0009089343,0.0014557,0.002213601,0.0004065671,0.00139556,0.001208914,0.002081576,0.00302792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001055285,"about_ca_system_score_gemma":0.00425238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006676096,"about_ca_topic_score_gemma":0.009829745,"domain_scores_codex":[0.9985442,0.0002098469,0.0001600286,0.0005016805,0.0004730138,0.0001112869],"domain_scores_gemma":[0.9980881,0.0004962029,0.0001829056,0.000306311,0.0007616543,0.0001649771],"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":[0.001210936,0.0005181778,0.01984553,0.0009867499,0.0004515045,0.000766759,0.0005978734,0.123264,0.365372,0.01116453,0.0476716,0.4281504],"study_design_scores_gemma":[0.000175471,0.0002557118,0.01322361,0.00006044403,0.0001450251,0.000367571,0.00008664501,0.8471527,0.08794741,0.01316056,0.03723109,0.0001938064],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03529314,0.0003283435,0.9221317,0.000492127,0.0001447276,0.0004713483,0.008510538,0.03131797,0.001310202],"genre_scores_gemma":[0.0599348,0.000230741,0.9154571,0.0002794161,0.00005455501,0.0005736779,0.01949533,0.002092774,0.001881593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006676096,"threshold_uncertainty_score":0.01635182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009424624325524742,"score_gpt":0.2134613844903403,"score_spread":0.2040367601648155,"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."}}