{"meta":{"query_hash":"eea82c7c0fa1","filters":{"venue":"Statistical Applications in Genetics and Molecular Biology"},"cohort_total":49,"direct_labels_cover":0,"predictions_cover":49,"exported":49,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/eea82c7c0fa1","api":"https://metacan.xera.ac/api/v1/cohort?venue=Statistical+Applications+in+Genetics+and+Molecular+Biology"},"results":[{"id":"W106150465","doi":"10.2202/1544-6115.1410","title":"Testing for Gene-Gene Interaction with AMMI Models","year":2010,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Ammi; Gene interaction; Biplot; Main effect; Interaction; Gene–environment interaction; Computational biology; Additive genetic effects; Biology; Multiplicative function; Genetics; Gene; Trait; Mixed model; Computer science; Mathematics; Genotype; Statistics; Heritability","score_opus":0.016352267092203384,"score_gpt":0.285890504062962,"score_spread":0.2695382369707586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W106150465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45863074,0.00015161297,0.5401613,0.000049316193,0.00003440953,0.00030868992,0.0002412369,0.0000066799516,0.0004159993],"genre_scores_gemma":[0.79229385,0.00003704741,0.20684335,0.00012237857,0.000056305806,0.00012525058,0.00049137796,0.0000116198735,0.000018825749],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914175,0.000020194919,0.0001654498,0.0004042856,0.00004455623,0.00022378519],"domain_scores_gemma":[0.9994967,0.00005640357,0.000051549745,0.00020630828,0.00010119759,0.00008786409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098914745,0.00013718466,0.00012851921,0.0000485823,0.000100277524,0.000023233786,0.00011580361,0.0001401882,0.000003782912],"category_scores_gemma":[0.000047028254,0.000121093915,0.000021591288,0.00006904734,0.00015157372,0.000001610093,0.000071277784,0.00009895101,0.0000010053235],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040723873,0.000058050664,0.0044556856,0.000013604079,0.000021865324,0.0000012366856,0.000014176488,0.00022024059,0.9630667,0.024396792,0.000046032306,0.0076649003],"study_design_scores_gemma":[0.0040523163,0.00392353,0.023292642,0.00003053075,0.00023351553,0.0002458009,0.00039021723,0.018451188,0.7160097,0.1364121,0.09513681,0.0018216851],"about_ca_topic_score_codex":0.000026765376,"about_ca_topic_score_gemma":0.00005096587,"teacher_disagreement_score":0.3336631,"about_ca_system_score_codex":0.0000032736743,"about_ca_system_score_gemma":0.000040859803,"threshold_uncertainty_score":0.49380666},"labels":[],"label_agreement":null},{"id":"W129429178","doi":"10.1515/sagmb-2014-0033","title":"Testing genotypes-phenotype relationships using permutation tests on association rules","year":2015,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Permutation (music); Association (psychology); Genotype; Phenotype; Genetics; Statistics; Biology; Computational biology; Mathematics; Psychology; Gene","score_opus":0.05919948829962234,"score_gpt":0.33482303618062387,"score_spread":0.2756235478810015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129429178","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062180355,0.0001694092,0.93630725,0.00025503332,0.00003335525,0.00025079207,0.000091828944,0.000039585895,0.0006723845],"genre_scores_gemma":[0.38301048,0.000008770488,0.61663383,0.00009293417,0.00002357181,0.00007464586,0.00014199062,0.000007800464,0.0000060010266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893314,0.00011343828,0.0002427647,0.00038882214,0.000118342796,0.00020351977],"domain_scores_gemma":[0.9988586,0.00047285756,0.00010081532,0.00030039612,0.00015681874,0.00011053783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003694758,0.00011029468,0.00011783381,0.00010037878,0.0001402368,0.000069691036,0.00022109832,0.00010395952,0.0000010252921],"category_scores_gemma":[0.00054735213,0.00011070686,0.000010597946,0.00035955582,0.00005584434,0.000038858117,0.00011080654,0.0001565374,0.00002167516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018212734,0.00008748969,0.011314934,0.0000061239325,0.000009581974,0.0000022970673,0.00013359069,0.0006468386,0.004172294,0.92017907,0.00005462112,0.06339133],"study_design_scores_gemma":[0.00044962254,0.000208416,0.07716059,0.000013452899,0.00003156579,0.000010641461,0.000065791544,0.39879027,0.0004566656,0.518001,0.004447208,0.00036477693],"about_ca_topic_score_codex":0.00004694272,"about_ca_topic_score_gemma":0.000010428241,"teacher_disagreement_score":0.40217808,"about_ca_system_score_codex":0.000102504,"about_ca_system_score_gemma":0.00009557184,"threshold_uncertainty_score":0.45144945},"labels":[],"label_agreement":null},{"id":"W146638925","doi":"10.1515/1544-6115.1779","title":"Hessian Calculation for Phylogenetic Likelihood based on the Pruning Algorithm and its Applications","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Hessian matrix; Computation; Pruning; Algorithm; Tree (set theory); Mathematics; Likelihood function; Restricted maximum likelihood; Inference; Computer science; Maximum likelihood; Model selection; Mathematical optimization; Matrix (chemical analysis); Newton's method; Applied mathematics; Estimation theory; Statistics; Artificial intelligence; Combinatorics; Nonlinear system","score_opus":0.011170475214458023,"score_gpt":0.28856232222371786,"score_spread":0.27739184700925984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W146638925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091054074,0.005856961,0.90066725,0.00037552527,0.000031525564,0.0014797667,0.00033681077,0.0000041201406,0.00019398623],"genre_scores_gemma":[0.95074815,0.0003960206,0.04620797,0.00047241905,0.000112956484,0.0017849342,0.00024477867,0.000024183853,0.0000085740685],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989135,0.00007314547,0.00022591454,0.00038305888,0.000056756395,0.00034758748],"domain_scores_gemma":[0.99931496,0.00017096696,0.000063355954,0.0002706481,0.000066031775,0.000114047354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022525144,0.000181887,0.00014903545,0.000051296145,0.00019827574,0.00001776681,0.00012153681,0.00013721599,0.000002290477],"category_scores_gemma":[0.000052171057,0.00014765652,0.000032403805,0.00009578583,0.00016686971,6.0874294e-7,0.00009121793,0.000076798235,0.0000014094022],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045716086,0.00038142136,0.014093031,0.00008410347,0.00011948408,3.5651698e-7,0.000110260364,0.0003967256,0.49266592,0.31311062,0.000106418105,0.17888594],"study_design_scores_gemma":[0.004507861,0.0026213024,0.17617871,0.000052180032,0.0005052176,0.000031859534,0.00049592304,0.11286117,0.17151837,0.096131474,0.4324016,0.0026943176],"about_ca_topic_score_codex":0.0000036993313,"about_ca_topic_score_gemma":0.000005573064,"teacher_disagreement_score":0.85969406,"about_ca_system_score_codex":0.000009784869,"about_ca_system_score_gemma":0.00003317901,"threshold_uncertainty_score":0.6021258},"labels":[],"label_agreement":null},{"id":"W1485154922","doi":"10.2202/1544-6115.1289","title":"Pattern Classification of Phylogeny Signals","year":2008,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Concatenation (mathematics); Phylogenetics; Phylogenetic tree; Entropy (arrow of time); Pattern recognition (psychology); Artificial intelligence; Computer science; Computational biology; Mathematics; Data mining; Gene; Biology; Genetics; Combinatorics; Physics","score_opus":0.017931865034605084,"score_gpt":0.3085976421761609,"score_spread":0.29066577714155584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1485154922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4373236,0.00097249646,0.56090844,0.000067189896,0.000019052944,0.00023499987,0.000069509115,0.0000040909513,0.00040059508],"genre_scores_gemma":[0.99192995,0.0008998807,0.0064218566,0.00014059883,0.000030542156,0.00018329054,0.00035380494,0.0000136367635,0.00002645927],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901,0.00007698923,0.0002988801,0.00038001648,0.00007352586,0.00016055508],"domain_scores_gemma":[0.99939984,0.00002562381,0.00009523463,0.00032525245,0.00008291666,0.00007113692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090214686,0.00011820774,0.000146939,0.00008116364,0.000052043888,0.0000037095215,0.00013897338,0.00014472276,0.000014569722],"category_scores_gemma":[0.000033700693,0.00011406601,0.00002977205,0.00013626974,0.00030251485,0.0000010230717,0.0000694176,0.000063846084,0.0000024465955],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011382762,0.000079387355,0.021229722,0.000011764102,0.000011419517,6.1996565e-7,0.000021967744,0.000015162845,0.9522551,0.010621502,0.00013701852,0.01560498],"study_design_scores_gemma":[0.0010822718,0.00053284183,0.35893524,0.000012640129,0.00003284881,0.00002689355,0.00014378225,0.0009260715,0.5777205,0.0142847095,0.045807593,0.00049461244],"about_ca_topic_score_codex":0.000009819972,"about_ca_topic_score_gemma":0.000007835166,"teacher_disagreement_score":0.5546063,"about_ca_system_score_codex":0.000007121935,"about_ca_system_score_gemma":0.00005625176,"threshold_uncertainty_score":0.4651477},"labels":[],"label_agreement":null},{"id":"W1489518784","doi":"10.2202/1544-6115.1298","title":"A Composite-Conditional-Likelihood Approach for Gene Mapping Based on Linkage Disequilibrium in Windows of Marker Loci","year":2008,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Linkage disequilibrium; Genetics; Locus (genetics); Biology; Single-nucleotide polymorphism; Association mapping; Genetic marker; Haplotype; Statistics; Mathematics; Algorithm; Allele; Gene; Genotype","score_opus":0.012891548595144143,"score_gpt":0.25739314203235947,"score_spread":0.24450159343721534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489518784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36431423,0.0003349226,0.63356405,0.00006176447,0.000010588278,0.0004715773,0.00081238215,0.0000035287142,0.00042694053],"genre_scores_gemma":[0.9129797,0.000120996716,0.083724566,0.00021983313,0.000024324803,0.00014671311,0.0027586776,0.000010909237,0.0000142576],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989221,0.00005985282,0.00028266764,0.0004199378,0.0000707521,0.00024470672],"domain_scores_gemma":[0.9995231,0.000066410896,0.00006616226,0.00021234494,0.000055654327,0.00007635135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012903493,0.00014969871,0.00021637407,0.00011180532,0.00006284983,0.000005732718,0.00013509825,0.00015738467,0.0000062845065],"category_scores_gemma":[0.00003531007,0.00014867085,0.0000493207,0.00010425504,0.0002296536,9.2340514e-7,0.00006771944,0.00007401044,6.051734e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025547878,0.0008875797,0.10784363,0.00018248915,0.00006341131,0.000009483667,0.00007036653,0.0031306243,0.8686747,0.016874598,0.00032478716,0.001682883],"study_design_scores_gemma":[0.012132768,0.00340196,0.6196346,0.00007943518,0.00014932912,0.00007772489,0.00030490386,0.10335363,0.18438299,0.038428452,0.03581925,0.002234949],"about_ca_topic_score_codex":0.00001071193,"about_ca_topic_score_gemma":0.0000027222538,"teacher_disagreement_score":0.68429166,"about_ca_system_score_codex":0.000007949001,"about_ca_system_score_gemma":0.000056032768,"threshold_uncertainty_score":0.60626215},"labels":[],"label_agreement":null},{"id":"W1497520349","doi":"10.2202/1544-6115.1151","title":"Hierarchical Inverse Gaussian Models and Multiple Testing: Application to Gene Expression Data","year":2005,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Inverse Gaussian distribution; Computational biology; Expression (computer science); Computer science; Gaussian; Mathematics; Statistics; Biology; Physics; Mathematical analysis","score_opus":0.03209668385080837,"score_gpt":0.32657705499584017,"score_spread":0.2944803711450318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1497520349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11629076,0.0006858354,0.88143647,0.0005269399,0.000015124246,0.000581922,0.00021514304,0.000013243941,0.00023454794],"genre_scores_gemma":[0.747953,0.00024408568,0.250051,0.00046020886,0.0000751932,0.00020565829,0.0009767263,0.00001858457,0.000015535934],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984404,0.000078480894,0.00028986647,0.00085794966,0.00008443795,0.0002488995],"domain_scores_gemma":[0.9988368,0.000051172225,0.000059587594,0.0007656216,0.000059175083,0.00022763594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015962392,0.0001733157,0.00015098404,0.00009557286,0.00009674008,0.000024192324,0.000296808,0.00017730742,0.0000030798915],"category_scores_gemma":[0.00010993718,0.00016621644,0.000012344351,0.00017169034,0.00017529014,0.0000053129365,0.0004978033,0.00011097216,0.0000040185787],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029170275,0.00007775467,0.0029449447,0.000009594631,0.0000065390054,3.7543703e-7,0.000026392821,0.0006619412,0.93441623,0.00814084,0.00028806983,0.053398144],"study_design_scores_gemma":[0.0024619706,0.00059297786,0.01702929,0.000035482957,0.00007133868,0.000040642364,0.00017241159,0.21600097,0.4528075,0.044132985,0.26533937,0.0013150492],"about_ca_topic_score_codex":0.000015889846,"about_ca_topic_score_gemma":0.000055596134,"teacher_disagreement_score":0.63166225,"about_ca_system_score_codex":0.000013433762,"about_ca_system_score_gemma":0.000052167044,"threshold_uncertainty_score":0.67781097},"labels":[],"label_agreement":null},{"id":"W1647270943","doi":"10.1515/1544-6115.1807","title":"Estimators of the local false discovery rate designed for small numbers of tests","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; False discovery rate; Bayes' theorem; Parametric statistics; Feature (linguistics); Negative binomial distribution; Binomial distribution; Prior probability","score_opus":0.1852363415391905,"score_gpt":0.5019122555711589,"score_spread":0.31667591403196843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1647270943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07222192,0.00016120545,0.9260218,0.000055287226,0.000062077605,0.0008882987,0.0005220931,0.0000050676117,0.00006223723],"genre_scores_gemma":[0.46389118,0.000015506455,0.53587705,0.000033420085,0.000012067531,0.0001501528,0.00000583561,0.000011143916,0.0000036432843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838763,0.0003891768,0.0006805419,0.0002209939,0.000068354544,0.00025331756],"domain_scores_gemma":[0.98246074,0.016806178,0.00021159781,0.000353795,0.00008454233,0.00008316676],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010257534,0.00013041182,0.00040541176,0.00003623965,0.000034559373,0.0000050542308,0.00019766025,0.00014612709,0.0000061980845],"category_scores_gemma":[0.0093452465,0.000092663955,0.00006359824,0.00015707812,0.00085997273,0.0000079533975,0.00011915104,0.000095452815,4.2955585e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030417901,0.00018769395,0.0065938607,0.00012315229,0.000029223316,1.2252258e-7,0.000027119875,0.000008707602,0.017254034,0.9667095,0.000022066015,0.009014116],"study_design_scores_gemma":[0.0004229254,0.00011035614,0.00599828,0.000017479919,0.00009973707,0.0000011039228,0.000029689698,0.00032985487,0.028954972,0.96376187,0.0001672416,0.00010648917],"about_ca_topic_score_codex":0.000011385034,"about_ca_topic_score_gemma":0.000009012882,"teacher_disagreement_score":0.39166927,"about_ca_system_score_codex":0.0000139072345,"about_ca_system_score_gemma":0.000046514677,"threshold_uncertainty_score":0.9989995},"labels":[],"label_agreement":null},{"id":"W168874597","doi":"10.1515/sagmb-2013-0035","title":"Estimation of weighted log partial area under the ROC curve and its application to MicroRNA expression data","year":2013,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistic; Receiver operating characteristic; microRNA; Ranking (information retrieval); Computer science; Data mining; Rank (graph theory); Expression (computer science); Variance (accounting); Coding (social sciences); Mathematics; Statistics; Computational biology; Algorithm; Artificial intelligence; Biology; Genetics","score_opus":0.012875139461111284,"score_gpt":0.30076401849011586,"score_spread":0.28788887902900456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W168874597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42761865,0.0009097184,0.5703297,0.00024336665,0.000008685733,0.0006949709,0.0001752509,0.0000034246768,0.000016197979],"genre_scores_gemma":[0.97877353,0.00015807612,0.018866334,0.0001518009,0.000023789959,0.00036091972,0.0016470499,0.00001389467,0.000004575464],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989206,0.000085802494,0.00028670646,0.00047426188,0.00006577171,0.00016686053],"domain_scores_gemma":[0.9991262,0.000052239127,0.000089985784,0.0005558121,0.00008360889,0.00009214435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001260729,0.00013204674,0.00013000915,0.000046459165,0.00006401425,0.000016405193,0.00024055966,0.000131964,0.000009654598],"category_scores_gemma":[0.000051125742,0.0001059315,0.000013206584,0.00011300567,0.00015570714,0.0000042325028,0.00034505787,0.000059913426,0.0000045387264],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013909089,0.0000500156,0.0005404905,0.000017955766,0.000014047938,8.904594e-8,0.000012858579,0.0003131347,0.9723224,0.013987632,0.00012064944,0.012606792],"study_design_scores_gemma":[0.00076390064,0.00025584642,0.03491554,0.000024498258,0.00008499427,0.000011262643,0.000091882255,0.10374888,0.81413746,0.03767949,0.007818929,0.0004673177],"about_ca_topic_score_codex":0.000020572657,"about_ca_topic_score_gemma":0.000013516235,"teacher_disagreement_score":0.5514634,"about_ca_system_score_codex":0.000007901082,"about_ca_system_score_gemma":0.000033275337,"threshold_uncertainty_score":0.43197608},"labels":[],"label_agreement":null},{"id":"W1967827763","doi":"10.2202/1544-6115.1406","title":"Sparse Canonical Correlation Analysis with Application to Genomic Data Integration","year":2009,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":351,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Canonical correlation; Interpretability; Multivariate statistics; Correlation; Feature selection; Mathematics; Variable (mathematics); Multivariate analysis; Statistics; Data mining; Computer science; Artificial intelligence","score_opus":0.011641527765839902,"score_gpt":0.31727430992254274,"score_spread":0.30563278215670286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967827763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10557842,0.00031972173,0.8927634,0.0004005783,0.000012267978,0.00053086394,0.00012949048,0.000009498585,0.0002557784],"genre_scores_gemma":[0.9446864,0.0001395787,0.050392434,0.00051183417,0.000038450602,0.00017127149,0.004029954,0.000011104637,0.000018946952],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986243,0.000069594884,0.00027859627,0.0007447324,0.00008569614,0.00019705464],"domain_scores_gemma":[0.998877,0.000019694735,0.000076857454,0.0008152878,0.000078381345,0.00013276192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015019748,0.00015434054,0.00017390962,0.00017462172,0.000065691725,0.000025417088,0.0002802066,0.00014378542,0.000006222986],"category_scores_gemma":[0.00003439376,0.00013719416,0.000021009218,0.000503482,0.00008884055,0.000003247243,0.00010979676,0.00009095197,0.000004637919],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013870839,0.00015007234,0.011182487,0.000004246129,0.00007268831,7.936789e-7,0.0000341223,0.0022397754,0.8388838,0.05724917,0.00018492223,0.089859225],"study_design_scores_gemma":[0.0022910926,0.0030195285,0.69853973,0.000022958116,0.0009301742,0.000023356683,0.000284157,0.07314452,0.06044634,0.024181271,0.13544334,0.0016735442],"about_ca_topic_score_codex":0.000026408568,"about_ca_topic_score_gemma":0.0002258291,"teacher_disagreement_score":0.8423709,"about_ca_system_score_codex":0.000022885662,"about_ca_system_score_gemma":0.0000735633,"threshold_uncertainty_score":0.55946153},"labels":[],"label_agreement":null},{"id":"W1980353549","doi":"10.2202/1544-6115.1711","title":"Principal Components of Heritability for High Dimension Quantitative Traits and General Pedigrees","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Principal component analysis; Heritability; Pedigree chart; Variance (accounting); Estimator; Statistics; Context (archaeology); Dimension (graph theory); Linear discriminant analysis; Mathematics; Econometrics; Computer science; Biology; Genetics","score_opus":0.021060826109587708,"score_gpt":0.33405240768445055,"score_spread":0.31299158157486284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980353549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73624694,0.0014316568,0.26153463,0.000060260594,0.000022599008,0.00039103575,0.00027854476,0.00000232886,0.000031982614],"genre_scores_gemma":[0.82208085,0.0002295939,0.17698686,0.000063895575,0.000031864907,0.00015900828,0.00043191639,0.000010369949,0.000005625475],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99891895,0.00012118507,0.00032769266,0.00031378813,0.000041246305,0.00027713986],"domain_scores_gemma":[0.9994508,0.00014164954,0.00009586043,0.00013049696,0.000083058025,0.0000981307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029590123,0.00013242573,0.00024072746,0.000039643797,0.000057899044,0.0000036427746,0.00007206923,0.00017130013,0.0000023647358],"category_scores_gemma":[0.00016260143,0.00012394144,0.000027513555,0.000054551165,0.00030979415,0.0000016484183,0.00010878921,0.00005425091,3.3612767e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055991008,0.0002116995,0.13979559,0.000047280533,0.000052410775,8.655706e-8,0.000087771965,0.000035723366,0.64999926,0.20428747,0.000038872564,0.005387853],"study_design_scores_gemma":[0.00086169003,0.0006756408,0.9531442,0.000004732334,0.000054548906,0.000004976114,0.000110925255,0.0007457825,0.01179219,0.02878888,0.0035530315,0.0002634047],"about_ca_topic_score_codex":0.000039854473,"about_ca_topic_score_gemma":0.000027512684,"teacher_disagreement_score":0.8133486,"about_ca_system_score_codex":0.0000079472375,"about_ca_system_score_gemma":0.000020037542,"threshold_uncertainty_score":0.50541854},"labels":[],"label_agreement":null},{"id":"W1982030926","doi":"10.2202/1544-6115.1261","title":"Estimating Number of Clusters Based on a General Similarity Matrix with Application to Microarray Data","year":2008,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Similarity (geometry); Data mining; Computer science; Selection (genetic algorithm); Set (abstract data type); A priori and a posteriori; Data set; Model selection; Matrix (chemical analysis); Determining the number of clusters in a data set; Artificial intelligence; Correlation clustering; CURE data clustering algorithm","score_opus":0.013888677644903851,"score_gpt":0.3370596504591929,"score_spread":0.323170972814289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982030926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19917727,0.00007228394,0.7997012,0.0001831674,0.000014900871,0.00043411108,0.00021932113,0.0000055977694,0.00019216075],"genre_scores_gemma":[0.6997311,0.000026327847,0.29870325,0.0003224735,0.000029233934,0.00018181223,0.000977983,0.000014800943,0.000013016322],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987733,0.00006847914,0.0002649145,0.00061246625,0.00009697716,0.00018389837],"domain_scores_gemma":[0.99891603,0.000031194442,0.00008692467,0.0007834006,0.000078066114,0.000104362276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001180994,0.00014857147,0.0001630071,0.00006857177,0.000070998714,0.0000067173523,0.00027757278,0.00012108665,0.000006132022],"category_scores_gemma":[0.00004170742,0.00013291453,0.000016343072,0.00018891525,0.00020266717,0.0000016246032,0.0001355605,0.00007977006,0.0000027608119],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002328143,0.0003229432,0.031574354,0.000054845717,0.00003031928,0.0000023963337,0.00004255694,0.009230218,0.93517846,0.010833131,0.0006240071,0.011873972],"study_design_scores_gemma":[0.0060171066,0.0026669155,0.079537444,0.0001072503,0.00018845875,0.00011826162,0.00017418654,0.41258904,0.38106272,0.008609525,0.10663711,0.0022919723],"about_ca_topic_score_codex":0.000023662606,"about_ca_topic_score_gemma":0.000016420994,"teacher_disagreement_score":0.5541157,"about_ca_system_score_codex":0.000011949652,"about_ca_system_score_gemma":0.0000905788,"threshold_uncertainty_score":0.5420097},"labels":[],"label_agreement":null},{"id":"W1988729528","doi":"10.2202/1544-6115.1231","title":"Examining Protein Structure and Similarities by Spectral Analysis Technique","year":2006,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Envelope (radar); Phylogenetic tree; Similarity (geometry); Categorical variable; Pattern recognition (psychology); Covariance; Spectral envelope; Tree (set theory); Spectral analysis; Mathematics; Computer science; Artificial intelligence; Biological system; Algorithm; Computational biology; Biology; Physics; Statistics; Speech recognition; Genetics; Combinatorics; Gene","score_opus":0.0042200096214464414,"score_gpt":0.25289519485412526,"score_spread":0.2486751852326788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988729528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5646086,0.0013803822,0.4332054,0.00005415033,0.0000027299493,0.0002478877,0.00031918284,0.000005468687,0.0001762477],"genre_scores_gemma":[0.96343195,0.00013219897,0.034683697,0.000083983854,0.000024426094,0.00016344897,0.0014221178,0.000010918696,0.000047267207],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990056,0.000054773835,0.00022102933,0.00045209876,0.000052847136,0.00021361058],"domain_scores_gemma":[0.99963266,0.000018248758,0.00004890474,0.00020760551,0.000034129247,0.00005846121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007104426,0.00015276033,0.00019585919,0.00010268475,0.00006452771,0.000025339705,0.000091519054,0.00017921561,0.000012348557],"category_scores_gemma":[0.000018417875,0.00014290765,0.000029173092,0.00023725364,0.0003152862,0.0000017175361,0.00008287654,0.00009309875,2.621311e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006455861,0.000029676563,0.019145384,0.000009960921,0.000063486616,0.000001955247,0.000003590946,0.00003681271,0.96114004,0.018276915,0.000046631718,0.0012390692],"study_design_scores_gemma":[0.00047156593,0.00047478772,0.026807848,0.000007035683,0.00037771187,0.000016048758,0.00009103474,0.0008446801,0.82964444,0.12914592,0.01141541,0.00070351764],"about_ca_topic_score_codex":0.00016143135,"about_ca_topic_score_gemma":0.00016600122,"teacher_disagreement_score":0.39882338,"about_ca_system_score_codex":0.000007554758,"about_ca_system_score_gemma":0.000017992379,"threshold_uncertainty_score":0.5827605},"labels":[],"label_agreement":null},{"id":"W1992991918","doi":"10.2202/1544-6115.1322","title":"Calculating Confidence Intervals for Prediction Error in Microarray Classification Using Resampling","year":2008,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Confidence interval; Resampling; Statistics; Robust confidence intervals; Percentile; Confidence distribution; Coverage probability; Point estimation; Nominal level; CDF-based nonparametric confidence interval; Sample size determination; Mathematics; Credible interval; Inference; Computer science; Artificial intelligence","score_opus":0.05684221735365688,"score_gpt":0.3714190284896959,"score_spread":0.31457681113603897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992991918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3773086,0.0005351378,0.6214483,0.000056717545,0.000032327524,0.00045206666,0.00010755016,0.0000050698673,0.00005423326],"genre_scores_gemma":[0.9326146,0.00026570025,0.06596796,0.0001122434,0.000047678153,0.00040099423,0.00055877795,0.000018062618,0.000013956265],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869657,0.00008198156,0.00040031414,0.0005344415,0.000058425772,0.0002282628],"domain_scores_gemma":[0.9994255,0.00004845772,0.000100166035,0.00026889323,0.000090160225,0.000066875335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019349561,0.00013716788,0.0001563292,0.00011931555,0.00010414555,0.000011099834,0.00011955609,0.00018772567,0.000003323551],"category_scores_gemma":[0.00011480141,0.00014347403,0.000031373478,0.00015683095,0.0002003456,0.0000028844493,0.000058139907,0.00009035143,5.55041e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033953504,0.00005124649,0.018613134,0.000019974534,0.0000074151703,5.14065e-7,0.000051051797,0.00034594667,0.9633288,0.015020376,0.000029996418,0.0024976232],"study_design_scores_gemma":[0.0049469555,0.0010189387,0.3070055,0.00015606098,0.00009537046,0.00011025256,0.00096687704,0.13146126,0.46564734,0.052209947,0.034875598,0.0015059101],"about_ca_topic_score_codex":0.000023757131,"about_ca_topic_score_gemma":0.000024927218,"teacher_disagreement_score":0.5554803,"about_ca_system_score_codex":0.000032971257,"about_ca_system_score_gemma":0.00008176504,"threshold_uncertainty_score":0.58507013},"labels":[],"label_agreement":null},{"id":"W1994687716","doi":"10.2202/1544-6115.1140","title":"Continuous Covariates in Genetic Association Studies of Case-Parent Triads: Gene and Gene-Environment Interaction Effects, Population Stratification, and Power Analysis","year":2005,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Multinomial logistic regression; Covariate; Statistics; Population stratification; Categorical variable; Multinomial distribution; Logistic regression; Econometrics; Mathematics; Population; Inference; Multinomial probit; Missing data; Logistic model tree; Computer science; Biology; Genetics; Genotype; Demography; Artificial intelligence","score_opus":0.007811834463553979,"score_gpt":0.29568025228899264,"score_spread":0.28786841782543865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994687716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.772548,0.0061839814,0.22068457,0.0000664437,0.000018889641,0.0004092021,0.00007476295,0.0000026891503,0.000011440228],"genre_scores_gemma":[0.878393,0.0013441725,0.119807206,0.000042063806,0.000021345737,0.00012852957,0.00024700825,0.0000094436455,0.0000072484445],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871194,0.00015937895,0.0004512896,0.00044179705,0.000067911045,0.00016765486],"domain_scores_gemma":[0.99935746,0.0001677396,0.000164693,0.00019854371,0.000053564134,0.000058011494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019572032,0.00015721827,0.00028904705,0.00012715936,0.000049483373,0.0000128399015,0.000052548796,0.00016096553,0.0000036156878],"category_scores_gemma":[0.00010364341,0.00015630288,0.000026189571,0.00012700286,0.00013937273,0.0000029435264,0.00007084144,0.000076837016,3.647304e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012346797,0.0005393824,0.6112032,0.00013126945,0.0011458799,0.0000074359955,0.00073016825,0.008392346,0.27095565,0.05345955,0.000028916815,0.053282756],"study_design_scores_gemma":[0.0011439226,0.0005933953,0.9610341,0.000010087396,0.0004907835,0.00004192546,0.00029604303,0.0011873103,0.017268743,0.017048584,0.000543347,0.00034175155],"about_ca_topic_score_codex":0.00006530901,"about_ca_topic_score_gemma":0.00017005202,"teacher_disagreement_score":0.34983093,"about_ca_system_score_codex":0.000035743356,"about_ca_system_score_gemma":0.000014442242,"threshold_uncertainty_score":0.6373846},"labels":[],"label_agreement":null},{"id":"W2004846882","doi":"10.2202/1544-6115.1330","title":"Correcting the Estimated Level of Differential Expression for Gene Selection Bias: Application to a Microarray Study","year":2008,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Ranking (information retrieval); Statistics; Expression (computer science); Smoothing; Microarray analysis techniques; Mathematics; Gene; Biology; Gene expression; Computational biology; Computer science; Genetics; Artificial intelligence","score_opus":0.05901533924471216,"score_gpt":0.3565840099581038,"score_spread":0.29756867071339166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004846882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46718907,0.00010886111,0.5316997,0.000033524106,0.000021669077,0.0008647596,0.00007218528,0.000003923714,0.000006259247],"genre_scores_gemma":[0.9660033,0.00004544553,0.032079503,0.000067372275,0.00004409063,0.0014322883,0.00028869754,0.000017465822,0.000021859549],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988707,0.00009964824,0.00032456734,0.0004548232,0.00007419735,0.00017608331],"domain_scores_gemma":[0.9993259,0.000060595165,0.0001120234,0.0002948798,0.00014155045,0.000065074986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014115944,0.00013757066,0.00015763227,0.00007995032,0.00016076636,0.000008138999,0.00016403402,0.0001094109,0.0000027631788],"category_scores_gemma":[0.00009622361,0.0001093985,0.00003116102,0.00020078279,0.00012163324,0.0000012320328,0.00008884417,0.000066384855,6.952718e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072658484,0.00018276459,0.012389396,0.0000088310135,0.000014298096,9.127472e-8,0.0001143269,0.00017913093,0.9748711,0.00064276427,0.00010668339,0.011417937],"study_design_scores_gemma":[0.00076688715,0.0006017129,0.0444432,0.0000065665818,0.000030534105,0.000016258246,0.00023549187,0.00163098,0.94898164,0.0009146269,0.0021742296,0.00019785632],"about_ca_topic_score_codex":0.00003176669,"about_ca_topic_score_gemma":0.000039740575,"teacher_disagreement_score":0.49962023,"about_ca_system_score_codex":0.000012524933,"about_ca_system_score_gemma":0.000052565316,"threshold_uncertainty_score":0.44611412},"labels":[],"label_agreement":null},{"id":"W2005834841","doi":"10.1515/sagmb-2013-0023","title":"A data-smoothing approach to explore and test gene-environment interaction in case-parent trios","year":2014,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Simon Fraser University","funders":"","keywords":"Trait; Smoothing; Statistical hypothesis testing; Gene–environment interaction; Gene; Computational biology; Econometrics; Computer science; Statistics; Genetics; Psychology; Biology; Mathematics","score_opus":0.04238394522881148,"score_gpt":0.3090808315913631,"score_spread":0.2666968863625516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005834841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59301746,0.00038151554,0.40559047,0.00009427829,0.000016553437,0.0003138878,0.0002650645,0.0000039942515,0.0003167404],"genre_scores_gemma":[0.9480685,0.00038969275,0.050445586,0.00021567552,0.00003193164,0.0000813719,0.0007465931,0.000009164398,0.000011511481],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989126,0.00006520388,0.00021220968,0.00056374096,0.000047578957,0.00019867044],"domain_scores_gemma":[0.999442,0.00007004673,0.00003660189,0.00032957326,0.000013776076,0.00010802578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019058555,0.00013350786,0.00014975366,0.00007305266,0.0000630471,0.000023410332,0.00013963215,0.00010527044,0.000002773212],"category_scores_gemma":[0.00010076621,0.00012963249,0.000010905048,0.000056230998,0.00008996837,0.0000017180342,0.00032745447,0.00008475211,0.0000022014735],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013745019,0.0014577725,0.13348264,0.0002011272,0.00010569283,0.00007591701,0.0008952272,0.0021395162,0.6797725,0.033110067,0.0008805994,0.14774151],"study_design_scores_gemma":[0.0067159003,0.004372617,0.12373538,0.0001125149,0.00030178975,0.001837206,0.005918814,0.06959778,0.02966689,0.018253796,0.73597836,0.0035089345],"about_ca_topic_score_codex":0.00004877131,"about_ca_topic_score_gemma":0.000036446894,"teacher_disagreement_score":0.73509777,"about_ca_system_score_codex":0.000008286109,"about_ca_system_score_gemma":0.000012145826,"threshold_uncertainty_score":0.52862597},"labels":[],"label_agreement":null},{"id":"W2010805470","doi":"10.1515/sagmb-2013-0066","title":"Robustness of the linear mixed effects model to error distribution assumptions and the consequences for genome-wide association studies","year":2014,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Medical Research Council; University of Bristol; Australian Government; Wellcome Trust","keywords":"Heteroscedasticity; Statistics; Random effects model; Type I and type II errors; Mixed model; Mathematics; Robustness (evolution); Linear model; Econometrics; Standard error; Genome-wide association study; Inference; Computer science; Genetics; Biology; Medicine; Single-nucleotide polymorphism; Artificial intelligence","score_opus":0.016383479548913643,"score_gpt":0.324614360187526,"score_spread":0.30823088063861237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010805470","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3227715,0.000689662,0.6736233,0.0019723235,0.000039670776,0.00067434734,0.00021838718,0.0000021809906,0.000008590802],"genre_scores_gemma":[0.9540387,0.00041581283,0.044014588,0.00052966014,0.000036750986,0.00068489125,0.00024807153,0.000008921005,0.000022599637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988398,0.00029839025,0.000305043,0.00029750078,0.0000553038,0.00020398421],"domain_scores_gemma":[0.99825704,0.0011341169,0.00014816353,0.00023547301,0.00017879333,0.00004642028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006781513,0.00011990067,0.00024945027,0.000022873748,0.00015961137,0.000006931353,0.0001410191,0.00015117083,3.0805154e-7],"category_scores_gemma":[0.0032313673,0.00007930085,0.00004592601,0.00009525823,0.00048842514,9.2612726e-7,0.00014713842,0.000068626374,2.4099273e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026538636,0.0002859535,0.15121649,0.00033238667,0.0007575538,1.7930174e-7,0.00043399518,0.14391378,0.1453105,0.545386,0.0025879727,0.009509804],"study_design_scores_gemma":[0.006658344,0.0012902617,0.30238774,0.000056957695,0.0008388085,0.0000072642174,0.00065211445,0.29444036,0.023078064,0.34416866,0.025303913,0.0011175205],"about_ca_topic_score_codex":0.0000076065458,"about_ca_topic_score_gemma":0.000059264592,"teacher_disagreement_score":0.6312672,"about_ca_system_score_codex":0.000023243936,"about_ca_system_score_gemma":0.000035454676,"threshold_uncertainty_score":0.3868482},"labels":[],"label_agreement":null},{"id":"W2014699424","doi":"10.1515/sagmb-2012-0044","title":"Imputing genotypes using regularized generalized linear regression models","year":2014,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; University of Toronto","funders":"","keywords":"Imputation (statistics); Missing data; International HapMap Project; Computer science; Statistics; Data mining; Context (archaeology); Mathematics; Single-nucleotide polymorphism; Genotype; Biology; Genetics","score_opus":0.013541119235238236,"score_gpt":0.30505275334210674,"score_spread":0.29151163410686853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014699424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31409493,0.0009757167,0.6842615,0.000033174583,0.00003768353,0.00025968856,0.00003531975,0.000008726976,0.00029322834],"genre_scores_gemma":[0.53650075,0.000101226295,0.46288112,0.00014535866,0.00008563615,0.000041521384,0.00020303561,0.000021706326,0.000019654159],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984759,0.00017997871,0.00034070437,0.0005874481,0.00008115017,0.00033481067],"domain_scores_gemma":[0.9992494,0.00004648211,0.0000868918,0.00041904996,0.00007135829,0.00012684488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002110895,0.00022038585,0.0002388015,0.000065118526,0.00011848738,0.000015544209,0.00019512181,0.00025624532,0.0000074882437],"category_scores_gemma":[0.0000621501,0.00019962317,0.000043407224,0.00010719594,0.0002591955,0.0000016757932,0.00019703183,0.00012029327,0.0000016798325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004338325,0.00007217278,0.0011550094,0.00002331571,0.000031695414,4.273113e-7,0.000035483135,0.0061142417,0.48802558,0.48735088,0.000024198658,0.017123636],"study_design_scores_gemma":[0.0024234178,0.0007873322,0.006804274,0.000032769083,0.00012271239,0.0000363115,0.00006226895,0.119409814,0.054664247,0.798308,0.01632602,0.0010228367],"about_ca_topic_score_codex":0.000026821323,"about_ca_topic_score_gemma":0.000010292792,"teacher_disagreement_score":0.43336132,"about_ca_system_score_codex":0.0000099695435,"about_ca_system_score_gemma":0.000051404586,"threshold_uncertainty_score":0.8140397},"labels":[],"label_agreement":null},{"id":"W2038019245","doi":"10.2202/1544-6115.1713","title":"A Family-Based Probabilistic Method for Capturing De Novo Mutations from High-Throughput Short-Read Sequencing Data","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Genetics; DNA sequencing; Biology; Selection (genetic algorithm); Mendelian inheritance; Mutation rate; Mutation; Computational biology; Genome; Population; Human genome; Throughput; Genomics; Computer science; Gene; Artificial intelligence","score_opus":0.03463663899362284,"score_gpt":0.35826484661819835,"score_spread":0.3236282076245755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038019245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2508347,0.0016879817,0.7432857,0.000060474962,0.000037894788,0.0005318513,0.0035197756,0.000007783816,0.00003380619],"genre_scores_gemma":[0.5877025,0.000053788797,0.40467462,0.00023219168,0.000081466365,0.0003196795,0.0069125094,0.000020671983,0.0000025646084],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857247,0.00009655166,0.0002896681,0.00057890103,0.000053931297,0.00040850314],"domain_scores_gemma":[0.9989146,0.00018012719,0.00005095274,0.0006101619,0.00007009134,0.0001740685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023795853,0.00018660018,0.0001939633,0.00005070167,0.0001040238,0.000023632614,0.0002736729,0.0001744599,0.000005780981],"category_scores_gemma":[0.00017342516,0.00018494755,0.000035218072,0.00007816124,0.00017001713,0.0000030085603,0.00019975277,0.00008067721,0.0000011964967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006745562,0.0003125579,0.008527252,0.00008567766,0.0001343754,0.000005683439,0.000085109714,0.0021418075,0.9039914,0.063692495,0.0000832545,0.02087295],"study_design_scores_gemma":[0.007315824,0.0015865621,0.09278796,0.00011029266,0.002060527,0.0001255764,0.0015047748,0.16266353,0.20692669,0.3973169,0.12294405,0.004657312],"about_ca_topic_score_codex":0.0001988308,"about_ca_topic_score_gemma":0.00008179643,"teacher_disagreement_score":0.6970647,"about_ca_system_score_codex":0.00003628663,"about_ca_system_score_gemma":0.00019687241,"threshold_uncertainty_score":0.7541942},"labels":[],"label_agreement":null},{"id":"W2047329948","doi":"10.2202/1544-6115.1641","title":"Linear Combination Test for Hierarchical Gene Set Analysis","year":2011,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Estimator; Covariance matrix; Set (abstract data type); Covariance; Computer science; Computational biology; Test statistic; Algorithm; Mathematics; Statistical hypothesis testing; Biology; Statistics","score_opus":0.020301324429671502,"score_gpt":0.32386893084780605,"score_spread":0.3035676064181345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047329948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09680556,0.00042075463,0.9015904,0.00008366991,0.000023398945,0.0004593972,0.00031393516,0.000007891502,0.00029498668],"genre_scores_gemma":[0.9089698,0.00028872243,0.08811009,0.00017924808,0.000033353463,0.0005357973,0.0018312777,0.000015107919,0.000036589736],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989444,0.000055309447,0.0002623745,0.0004804168,0.00005368788,0.00020382991],"domain_scores_gemma":[0.9993718,0.000052274198,0.00006488987,0.0003170329,0.00009513363,0.00009886058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013700109,0.0001323031,0.00016354256,0.0001442035,0.000068794005,0.000008555203,0.00014562295,0.00017207056,0.000015331481],"category_scores_gemma":[0.00008660889,0.0001278869,0.0000550841,0.0002652299,0.00017968813,0.000001160095,0.00007359091,0.00006843158,0.0000016942037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007554019,0.00037901037,0.036429174,0.000023169852,0.00015475274,9.204918e-7,0.00007522228,0.000033535493,0.81846225,0.13229729,0.00022643662,0.011842659],"study_design_scores_gemma":[0.00290745,0.002049455,0.16461234,0.000007777541,0.000647935,0.000010443584,0.00017871478,0.011397822,0.6048244,0.13573031,0.076538935,0.0010944166],"about_ca_topic_score_codex":0.000009981031,"about_ca_topic_score_gemma":0.00001899678,"teacher_disagreement_score":0.8134803,"about_ca_system_score_codex":0.000009106648,"about_ca_system_score_gemma":0.000040389266,"threshold_uncertainty_score":0.5215077},"labels":[],"label_agreement":null},{"id":"W2056036270","doi":"10.2202/1544-6115.1759","title":"Special Issue on Computational Statistical Methods for Genomics and Systems Biology","year":2012,"lang":"en","type":"editorial","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Genomics; Computational genomics; Systems biology; Computational biology; Genome Biology; Biology; Statistical analysis; Data science; Computer science; Genome; Genetics; Mathematics; Statistics","score_opus":0.014237265647260806,"score_gpt":0.38634272780498746,"score_spread":0.37210546215772666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056036270","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014333075,0.003842324,0.9463216,0.00008022605,0.044059705,0.0011751659,0.003912368,0.000009357779,0.00045592693],"genre_scores_gemma":[0.0035692614,0.0044654994,0.43879434,0.0003632081,0.5101623,0.0029129668,0.03928852,0.0001758532,0.00026808356],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997591,0.00034034217,0.00054650544,0.0009827887,0.000104176026,0.00043516577],"domain_scores_gemma":[0.99822545,0.0007747112,0.0001957478,0.00039524442,0.00019643696,0.00021243132],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004511933,0.00037709085,0.00047164096,0.00015349782,0.00012468973,0.000048629754,0.00022404183,0.0010357373,0.000020315512],"category_scores_gemma":[0.0003702923,0.00036722905,0.00004663057,0.00008524339,0.00044040428,0.0000015744085,0.00018067713,0.00030703255,0.0000047982685],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025386238,0.00026006738,0.00015553218,0.00025667323,0.00016529483,8.4467473e-7,0.000044000924,0.00016877498,0.05309611,0.24231751,0.54865193,0.15462936],"study_design_scores_gemma":[0.0006338645,0.0004628115,0.0001313162,0.000010692126,0.000070168724,0.0000025008103,0.000026784382,0.00076552294,0.00058741897,0.017463112,0.9794625,0.0003832743],"about_ca_topic_score_codex":0.000012370564,"about_ca_topic_score_gemma":0.0000047394224,"teacher_disagreement_score":0.50752723,"about_ca_system_score_codex":0.000048910424,"about_ca_system_score_gemma":0.00021277655,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W2056379515","doi":"10.2202/1544-6115.1714","title":"Adjusting for Spurious Gene-by-Environment Interaction Using Case-Parent Triads","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Spurious relationship; Locus (genetics); Sibling; Gene–environment interaction; Population stratification; Population; Econometrics; Genetics; Genotype; Statistics; Computer science; Psychology; Biology; Gene; Developmental psychology; Mathematics; Medicine; Environmental health; Single-nucleotide polymorphism","score_opus":0.026975429280990868,"score_gpt":0.3507347520915877,"score_spread":0.32375932281059683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056379515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4420222,0.0019568922,0.55528927,0.000041510524,0.000054252403,0.00038469632,0.00021754645,0.0000035642943,0.000030049901],"genre_scores_gemma":[0.8735441,0.00037501723,0.12461045,0.00014716297,0.00011938597,0.0003201935,0.00084906426,0.000022412902,0.000012242736],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986429,0.00012916562,0.00037480527,0.0003925532,0.000042103067,0.00041844533],"domain_scores_gemma":[0.9993682,0.00011053186,0.0001193931,0.0002335732,0.000036989473,0.00013133213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003222337,0.0001733791,0.00020800882,0.000051047045,0.00012995813,0.00001034996,0.00008200739,0.00021915448,0.000008446814],"category_scores_gemma":[0.00011149256,0.00017519496,0.000046002653,0.000055162993,0.00012784787,0.0000020634927,0.00010619233,0.000088372406,0.0000019738875],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067019544,0.00045649704,0.08287379,0.00004828826,0.0001570655,0.000005313306,0.00011810431,0.0012770917,0.86642414,0.010743254,0.00065293245,0.037176467],"study_design_scores_gemma":[0.011632853,0.004575544,0.05118835,0.000053357035,0.0015272619,0.0029710913,0.0032997173,0.064591676,0.2212538,0.050113525,0.5833642,0.005428616],"about_ca_topic_score_codex":0.00004460565,"about_ca_topic_score_gemma":0.000011886219,"teacher_disagreement_score":0.6451704,"about_ca_system_score_codex":0.000041817024,"about_ca_system_score_gemma":0.000025611113,"threshold_uncertainty_score":0.7144243},"labels":[],"label_agreement":null},{"id":"W2068181458","doi":"10.1515/sagmb-2012-0070","title":"A novel method for analyzing genetic association with longitudinal phenotypes","year":2013,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Biological Sciences","funders":"National Institute of General Medical Sciences; National Institute on Drug Abuse; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Framingham Heart Study; SNP; Genetic association; Statistical power; Trait; Bayesian probability; False discovery rate; Genome-wide association study; Replicate; Statistics; Statistical hypothesis testing; Quantitative trait locus; Biology; Disease; Computational biology; Genetics; Computer science; Single-nucleotide polymorphism; Genotype; Framingham Risk Score; Mathematics; Gene; Medicine; Internal medicine","score_opus":0.010934520757845833,"score_gpt":0.3158189965437446,"score_spread":0.3048844757858988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068181458","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12295332,0.0006206843,0.8750823,0.0003274723,0.000020981637,0.00075267814,0.00012451406,0.0000071316254,0.00011092998],"genre_scores_gemma":[0.39731437,0.00012518383,0.60102874,0.00020787252,0.00005467903,0.0008663913,0.00033515942,0.000020205143,0.000047404374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985704,0.00009222173,0.00033234153,0.0005517872,0.00006293256,0.00039031496],"domain_scores_gemma":[0.99909747,0.00020919449,0.00014343926,0.00025189322,0.0001975636,0.00010042771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002686524,0.00018459235,0.0002543748,0.000073353134,0.00010084027,0.00002617324,0.00013277387,0.00024234882,0.000018197494],"category_scores_gemma":[0.00019634019,0.0001635986,0.000041280902,0.00013642984,0.00009505124,0.0000019429272,0.000077258956,0.00009310872,0.000003899761],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037282494,0.00020046534,0.54356384,0.00003801674,0.00024405774,5.411324e-7,0.00003866153,0.0010412884,0.38799736,0.023880498,0.00044069684,0.04251733],"study_design_scores_gemma":[0.0032551247,0.0017978348,0.8640391,0.000016557071,0.00032059627,0.00004395828,0.00018533037,0.016712686,0.010646569,0.073181435,0.028578911,0.0012218539],"about_ca_topic_score_codex":0.00013141715,"about_ca_topic_score_gemma":0.00012530082,"teacher_disagreement_score":0.37735078,"about_ca_system_score_codex":0.000033423214,"about_ca_system_score_gemma":0.000058038106,"threshold_uncertainty_score":0.6671357},"labels":[],"label_agreement":null},{"id":"W2070009349","doi":"10.1515/sagmb-2013-0003","title":"Simple estimators of false discovery rates given as few as one or two p-values without strong parametric assumptions","year":2013,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; False discovery rate; Prior probability; Nonparametric statistics; Parametric statistics; Bayes' theorem; Generality; Simple (philosophy)","score_opus":0.1952700356856978,"score_gpt":0.5447426637159445,"score_spread":0.3494726280302467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070009349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18229286,0.00018343072,0.81540394,0.00012819638,0.00003422585,0.0012009289,0.00042558063,0.000023191957,0.00030763302],"genre_scores_gemma":[0.45035484,0.00013959233,0.5489141,0.000061567574,0.000021783513,0.00041574996,0.000038814702,0.000023431383,0.000030104848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735606,0.00051721674,0.0010073506,0.0005534485,0.00018865308,0.0003772679],"domain_scores_gemma":[0.9846549,0.014195635,0.00026131293,0.0005272445,0.00016704554,0.00019384487],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005988909,0.00024619492,0.0007199027,0.00017023286,0.00008127269,0.00005461562,0.00026776077,0.00019583564,0.00028411165],"category_scores_gemma":[0.015726045,0.00019921744,0.00006206827,0.00041784908,0.00082368666,0.000030933206,0.00020629607,0.00023824793,0.00003864176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036526748,0.0004078904,0.008506908,0.00009156366,0.000093269584,0.0000028367515,0.000022045035,0.000023637887,0.0046487357,0.96976787,0.00007261889,0.01632612],"study_design_scores_gemma":[0.0006736972,0.0004117796,0.0059990995,0.000023354882,0.00013873931,0.000004261906,0.00007389746,0.0018315007,0.0032142377,0.9872182,0.00017965927,0.00023156106],"about_ca_topic_score_codex":0.00020879583,"about_ca_topic_score_gemma":0.000020956977,"teacher_disagreement_score":0.268062,"about_ca_system_score_codex":0.000029569359,"about_ca_system_score_gemma":0.0001016904,"threshold_uncertainty_score":0.9925649},"labels":[],"label_agreement":null},{"id":"W2090537645","doi":"10.2202/1544-6115.1436","title":"A Bayesian Analysis Strategy for Cross-Study Translation of Gene Expression Biomarkers","year":2009,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"National Cancer Institute","keywords":"Computational biology; Multivariate statistics; Gene expression profiling; Bayesian probability; Computer science; Biology; Bioinformatics; Gene expression; Data mining; Gene; Artificial intelligence; Machine learning; Genetics","score_opus":0.016680353521724214,"score_gpt":0.35851177622644487,"score_spread":0.34183142270472067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090537645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25200158,0.00068924384,0.74643505,0.000032729895,0.000010006835,0.0006126802,0.00013815767,0.00000402246,0.00007649268],"genre_scores_gemma":[0.952247,0.000097368626,0.04655803,0.000043236527,0.00001866538,0.00023143881,0.00078715134,0.00000902435,0.000008041491],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998838,0.00007734637,0.00036673126,0.00047856866,0.00006802489,0.00017134055],"domain_scores_gemma":[0.9993762,0.000029596042,0.00010266442,0.0003278091,0.000091117116,0.000072636314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015961414,0.00013531167,0.00020001609,0.00016302022,0.00005739673,0.000014796837,0.00012948803,0.00014828779,0.0000060076445],"category_scores_gemma":[0.000023766916,0.0001277624,0.00006426391,0.0003032978,0.00011313027,0.0000017852526,0.0000181285,0.00004335041,1.539664e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010154186,0.0002477287,0.0136553915,0.000008942228,0.00008396991,2.5945442e-7,0.000039353246,0.00070574833,0.96024984,0.0023703363,0.00001670222,0.022520196],"study_design_scores_gemma":[0.0025694568,0.0022949409,0.15605351,0.0000069661037,0.00037613857,0.0000021559972,0.00035646357,0.005890272,0.81460536,0.013935833,0.00338874,0.00052013417],"about_ca_topic_score_codex":0.000006344423,"about_ca_topic_score_gemma":0.000015055184,"teacher_disagreement_score":0.70024544,"about_ca_system_score_codex":0.000006966921,"about_ca_system_score_gemma":0.00003798687,"threshold_uncertainty_score":0.52099997},"labels":[],"label_agreement":null},{"id":"W2140183618","doi":"10.2202/1544-6115.1569","title":"Information Metrics in Genetic Epidemiology","year":2011,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Multiple Sclerosis Society; National Multiple Sclerosis Society; Mitacs; U.S. Department of Defense; National Institutes of Health; National Science Foundation","keywords":"Computer science; Probabilistic logic; Context (archaeology); Relation (database); Interpretation (philosophy); Contrast (vision); Multinomial distribution; Genetic epidemiology; Data mining; Data science; Machine learning; Artificial intelligence; Econometrics; Mathematics; Biology; Genetics; Gene","score_opus":0.02503040580955535,"score_gpt":0.3209507100143086,"score_spread":0.29592030420475324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140183618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18506026,0.0019205066,0.8109405,0.000072909286,0.000049450093,0.00042078533,0.00004873337,0.000007577278,0.0014792519],"genre_scores_gemma":[0.93043834,0.0011200126,0.06729936,0.00048319035,0.000019787498,0.00032514357,0.00029328727,0.00001082627,0.0000100281395],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99875134,0.00015726312,0.00045926686,0.0003132963,0.000045809462,0.0002730459],"domain_scores_gemma":[0.9993843,0.000047880832,0.000094635354,0.00032245915,0.000054956436,0.00009579214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024535964,0.00014242675,0.0001813692,0.0002392103,0.000033515622,0.0000059759905,0.00016856876,0.00022408017,0.000020377645],"category_scores_gemma":[0.00019195954,0.00013880516,0.000025012856,0.00029371455,0.00018519709,0.000003253098,0.00010874565,0.0001107665,0.000007588725],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010580592,0.00028206164,0.4789042,0.000052638894,0.00003258763,0.0000031051622,0.0003058664,0.000090668516,0.106164165,0.25879484,0.0003253121,0.15493873],"study_design_scores_gemma":[0.0016221033,0.00066341046,0.70058376,0.000013926367,0.000027280643,0.000022384185,0.00044007332,0.0010955355,0.028936977,0.16240342,0.10346109,0.0007300293],"about_ca_topic_score_codex":0.000045382687,"about_ca_topic_score_gemma":0.00004627784,"teacher_disagreement_score":0.74537814,"about_ca_system_score_codex":0.000016637161,"about_ca_system_score_gemma":0.000050679417,"threshold_uncertainty_score":0.566031},"labels":[],"label_agreement":null},{"id":"W2197585008","doi":"10.1515/1544-6115.1760","title":"An Integrated Hierarchical Bayesian Model for Multivariate eQTL Mapping","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Clinical Research Institute","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research","keywords":"Multivariate statistics; Bayesian probability; Computer science; Bayesian hierarchical modeling; Artificial intelligence; Multivariate analysis; Data mining; Mathematics; Statistics; Machine learning; Bayesian inference","score_opus":0.018681557394560094,"score_gpt":0.3105318896602877,"score_spread":0.29185033226572765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197585008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088635154,0.00045705136,0.90975666,0.00006435274,0.00003027834,0.00037320677,0.00054171326,0.000009460663,0.00013210409],"genre_scores_gemma":[0.7824324,0.0000972589,0.21611135,0.00021969595,0.000056838282,0.000114127215,0.0009273713,0.000012570804,0.000028412858],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989101,0.0000650034,0.00021871438,0.00037634003,0.000047575766,0.0003822356],"domain_scores_gemma":[0.99942327,0.000044873643,0.000043030777,0.00023324284,0.000055055523,0.00020052807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019739453,0.00016169962,0.00016419399,0.00006604338,0.000108360495,0.000019740877,0.00015321004,0.0001912107,0.000007094799],"category_scores_gemma":[0.000062584186,0.00015073964,0.000034072607,0.000068372516,0.00015569723,0.0000023085136,0.000081076236,0.00008785578,0.0000011336247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000916279,0.00047537498,0.018401215,0.000051950563,0.00006673306,9.5076405e-7,0.00026586844,0.0010030086,0.78535223,0.16498291,0.00027450602,0.02903361],"study_design_scores_gemma":[0.0037008976,0.0017853031,0.029329706,0.00004889499,0.0001932655,0.00004568146,0.0010326777,0.6803252,0.034544915,0.08671774,0.15998508,0.002290645],"about_ca_topic_score_codex":0.000016989414,"about_ca_topic_score_gemma":0.0000098339915,"teacher_disagreement_score":0.75080734,"about_ca_system_score_codex":0.000007107106,"about_ca_system_score_gemma":0.000040456554,"threshold_uncertainty_score":0.6146984},"labels":[],"label_agreement":null},{"id":"W2200221635","doi":"10.2202/1544-6115.1620","title":"A Robust Statistical Method to Detect Null Alleles in Microsatellite and SNP Datasets in Both Panmictic and Inbred Populations","year":2011,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Inbreeding; Biology; Panmixia; Null allele; Genetics; Allele; Null (SQL); Population; Microsatellite; Statistics; Mathematics; Computer science; Data mining; Gene","score_opus":0.04170293006541853,"score_gpt":0.33296973950270214,"score_spread":0.2912668094372836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2200221635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25513142,0.0014894744,0.7419903,0.000044509623,0.00001457735,0.00052003993,0.0007208001,0.0000039184956,0.00008495708],"genre_scores_gemma":[0.4596674,0.00019511407,0.5393727,0.00013356331,0.000009093837,0.00012876488,0.00047671492,0.000013524896,0.0000031472957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9983817,0.00018789378,0.00038666071,0.0006632862,0.000050632647,0.00032987344],"domain_scores_gemma":[0.9994032,0.00008536719,0.000043863118,0.00027976005,0.000022170989,0.0001656657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022174946,0.00020480272,0.00024447872,0.00013734795,0.000047155318,0.000017253473,0.00013068649,0.00019491247,0.000010325742],"category_scores_gemma":[0.0000785202,0.00020830435,0.00001202056,0.00015129091,0.0002628924,0.000002343348,0.00021210285,0.0001434346,0.000001255497],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030503314,0.00044595066,0.10738076,0.00013125432,0.00006550615,0.000018937351,0.00080360565,0.00051995035,0.19225876,0.5585036,0.00012624981,0.13944039],"study_design_scores_gemma":[0.0010304234,0.00063631515,0.8130281,0.000017440194,0.000039273993,0.000035582787,0.000138745,0.0004929339,0.0033810218,0.17694083,0.0037850335,0.00047430705],"about_ca_topic_score_codex":0.0002466896,"about_ca_topic_score_gemma":0.0009972014,"teacher_disagreement_score":0.70564735,"about_ca_system_score_codex":0.000010979627,"about_ca_system_score_gemma":0.000039607232,"threshold_uncertainty_score":0.8494405},"labels":[],"label_agreement":null},{"id":"W2204121744","doi":"10.2202/1544-6115.1626","title":"Large Sample Approximations of Probabilities of Correct Evolutionary Tree Estimation and Biases of Maximum Likelihood Estimation","year":2011,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Mathematics; Tree (set theory); Sequence (biology); Statistics; Algorithm; Maximum likelihood; Combinatorics","score_opus":0.01604528567905189,"score_gpt":0.27348485234130654,"score_spread":0.25743956666225465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204121744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49621275,0.0014345803,0.5013102,0.000009085816,0.000011337069,0.00029758448,0.0006091456,0.00000123937,0.00011402805],"genre_scores_gemma":[0.76891327,0.00036397926,0.23034552,0.0000074991985,0.000004276014,0.0000863591,0.00027080058,0.0000073071596,9.880305e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999105,0.00005550337,0.00039868386,0.0002472577,0.00005238852,0.00014116178],"domain_scores_gemma":[0.99935126,0.000116209616,0.00015228914,0.00021428282,0.00012689213,0.000039062426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012585074,0.00011513073,0.00021707827,0.00007968532,0.00003592935,0.0000019819174,0.00008150963,0.000099637226,0.0000047277385],"category_scores_gemma":[0.00020880738,0.00011257352,0.000028703711,0.00009751742,0.00041311517,0.00000101977,0.00011404389,0.000036065554,1.1696108e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013628228,0.00089373963,0.07834557,0.0004751342,0.0001846502,3.7757601e-7,0.0011245842,0.00044989254,0.55472994,0.28978637,0.00003152333,0.073841974],"study_design_scores_gemma":[0.0011458654,0.0015804104,0.13988522,0.00004706624,0.00015709046,0.000009432787,0.00070297864,0.018771267,0.21232548,0.62461025,0.00037527672,0.00038964607],"about_ca_topic_score_codex":0.000068733156,"about_ca_topic_score_gemma":0.00004986253,"teacher_disagreement_score":0.34240443,"about_ca_system_score_codex":0.0000047081226,"about_ca_system_score_gemma":0.000049120146,"threshold_uncertainty_score":0.45906147},"labels":[],"label_agreement":null},{"id":"W2206438750","doi":"10.2202/1544-6115.1270","title":"Case-Control Inference of Interaction between Genetic and Nongenetic Risk Factors under Assumptions on Their Distribution","year":2007,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Inference; Estimator; Statistical inference; Econometrics; Logistic regression; Conditional independence; Covariate; Independence (probability theory); Statistics; Genetic model; Mathematics; Computer science; Artificial intelligence; Biology","score_opus":0.01723949161786159,"score_gpt":0.32697539084434335,"score_spread":0.30973589922648176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206438750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51225466,0.00027933277,0.48675624,0.000017132472,0.000017901823,0.00020757242,0.00043139976,0.0000032987818,0.000032444776],"genre_scores_gemma":[0.9954996,0.00052325864,0.0033066508,0.000039074974,0.000037607366,0.000062110645,0.00051415886,0.000013968043,0.0000035456194],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988193,0.00011933777,0.0003577958,0.00043096417,0.00006339246,0.00020921798],"domain_scores_gemma":[0.9991736,0.00020431535,0.00014320281,0.00028931838,0.00007713378,0.00011242722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018105826,0.00017144368,0.00017903365,0.00009396889,0.00009173445,0.000012655624,0.00008672973,0.000201938,0.000006124461],"category_scores_gemma":[0.00007953003,0.0001513075,0.000031532483,0.00012686233,0.00024524762,0.0000018980937,0.00005791741,0.0001382168,8.009343e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010097103,0.00023075801,0.32728028,0.00003891494,0.00013444173,0.000005976619,0.000094260955,0.0006971403,0.5425646,0.028836912,0.00002618233,0.0999896],"study_design_scores_gemma":[0.0008309791,0.00065311237,0.89080226,0.000013117612,0.000106209845,0.00003111238,0.0003110437,0.0006985071,0.09173402,0.012046433,0.002435806,0.0003374106],"about_ca_topic_score_codex":0.000039299135,"about_ca_topic_score_gemma":0.000054031087,"teacher_disagreement_score":0.563522,"about_ca_system_score_codex":0.000019161515,"about_ca_system_score_gemma":0.00002928601,"threshold_uncertainty_score":0.6170141},"labels":[],"label_agreement":null},{"id":"W2237023490","doi":"10.2202/1544-6115.1417","title":"A Multivariate Growth Curve Model for Ranking Genes in Replicated Time Course Microarray Data","year":2009,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Multivariate statistics; Ranking (information retrieval); Time point; Inference; Computer science; Statistics; Expression (computer science); Mathematics; Data mining; Artificial intelligence","score_opus":0.023125501762366774,"score_gpt":0.34872595219207553,"score_spread":0.32560045042970875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237023490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045529816,0.001972719,0.9505072,0.0005251112,0.000016905326,0.00081892894,0.0005121938,0.000010746439,0.000106362386],"genre_scores_gemma":[0.90276635,0.00058374385,0.092494205,0.00043359952,0.000037386882,0.0002885518,0.0033302233,0.000020639705,0.00004528298],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843234,0.00007422114,0.00034666597,0.00080936635,0.000055459106,0.00028196178],"domain_scores_gemma":[0.9990188,0.000035729707,0.00008477585,0.00069040345,0.000088175744,0.00008214634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025495133,0.00017425197,0.00019734887,0.000080963524,0.000059602145,0.000019135216,0.00034934128,0.00020297192,0.0000031598224],"category_scores_gemma":[0.00008256695,0.00017203853,0.00002521499,0.00015220225,0.000119422344,0.0000029190546,0.00012846905,0.000088096196,0.0000016003124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006518982,0.00015979915,0.00089234207,0.000010532373,0.000013150664,5.667783e-7,0.000021452104,0.00022138878,0.965755,0.016059432,0.0002861518,0.016515037],"study_design_scores_gemma":[0.005912773,0.00081280514,0.0244283,0.000049264185,0.00014531698,0.000018996263,0.0000861469,0.5508565,0.22731055,0.15775421,0.031093566,0.0015315772],"about_ca_topic_score_codex":0.000011735581,"about_ca_topic_score_gemma":0.00002098872,"teacher_disagreement_score":0.85801303,"about_ca_system_score_codex":0.0000132726755,"about_ca_system_score_gemma":0.00009115403,"threshold_uncertainty_score":0.7015528},"labels":[],"label_agreement":null},{"id":"W2265464824","doi":"10.1515/1544-6115.1818","title":"An Order Estimation Based Approach to Identify Response Genes for Microarray Time Course Data","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Gene; Context (archaeology); Microarray analysis techniques; Biology; Microarray; Computational biology; DNA microarray; Gene regulatory network; Genetics; Genome; Gene expression","score_opus":0.024981340043627853,"score_gpt":0.3885976204653775,"score_spread":0.36361628042174965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2265464824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08199245,0.00096018903,0.9153803,0.000195447,0.000036028247,0.00078259007,0.0005934348,0.000009847779,0.000049725408],"genre_scores_gemma":[0.6313656,0.000032634274,0.36227778,0.00037371952,0.00006553184,0.00056903006,0.0052695633,0.00002332404,0.000022793665],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863183,0.00017468375,0.0002469654,0.0005857149,0.00006848323,0.0002923112],"domain_scores_gemma":[0.99874234,0.00005418596,0.000059879683,0.0008412525,0.00010414887,0.00019819033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050313154,0.00015592833,0.00014134384,0.000079797115,0.000086828026,0.000027873084,0.0003310602,0.00017134508,0.0000074877166],"category_scores_gemma":[0.00011741365,0.00015281161,0.000017793116,0.00016221528,0.000117764066,0.000005133379,0.00011392917,0.00005258315,0.00000619129],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015322998,0.00029773507,0.0010061752,0.000015111724,0.000013304269,6.034685e-8,0.00001981124,0.0005021137,0.978436,0.003530769,0.000764877,0.015260833],"study_design_scores_gemma":[0.0027278643,0.0012440241,0.052259896,0.000018228413,0.00021849453,0.000016242338,0.00025297268,0.11921939,0.39553842,0.0044154716,0.42263842,0.0014505956],"about_ca_topic_score_codex":0.000003706542,"about_ca_topic_score_gemma":0.0000022300464,"teacher_disagreement_score":0.58289754,"about_ca_system_score_codex":0.000012100133,"about_ca_system_score_gemma":0.00009992717,"threshold_uncertainty_score":0.62314767},"labels":[],"label_agreement":null},{"id":"W2292733224","doi":"10.1515/sagmb-2014-0098","title":"Using informative Multinomial-Dirichlet prior in a t-mixture with reversible jump estimation of nucleosome positions for genome-wide profiling","year":2015,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Canadian Institutes of Health Research","keywords":"Multinomial distribution; Dirichlet distribution; Profiling (computer programming); Jump; Mathematics; Genome; Mixture model; Statistics; Computational biology; Biology; Econometrics; Computer science; Statistical physics; Genetics; Physics","score_opus":0.023026727306635755,"score_gpt":0.33038312067648096,"score_spread":0.3073563933698452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292733224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032298867,0.000145491,0.96647966,0.00009735275,0.0000102962895,0.000787913,0.00008437706,0.000007915529,0.00008811955],"genre_scores_gemma":[0.29796708,0.0000079867095,0.7018098,0.00006160942,0.0000036112451,0.00009557926,0.00004890861,0.0000043802875,0.0000010422672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992352,0.00006155129,0.0002598989,0.00022921043,0.000052419364,0.00016168269],"domain_scores_gemma":[0.99939513,0.00014314496,0.000089685935,0.00018731854,0.00011696547,0.00006776433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021415303,0.00009481222,0.00017251166,0.00013280631,0.000039774975,0.00001668006,0.00015120058,0.000080908176,2.9244026e-7],"category_scores_gemma":[0.000068642585,0.000082630984,0.000013447435,0.00026572606,0.00010351823,0.00004240124,0.000076126926,0.00007807074,2.440513e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034281664,0.00011505429,0.0013845727,0.00007525482,0.000017938944,0.000002128728,0.00078547327,0.0042284904,0.0144298365,0.96006465,0.0000052586506,0.01885709],"study_design_scores_gemma":[0.001159044,0.00031775545,0.0027033703,0.000025404619,0.000025635216,0.000009647087,0.00006597632,0.6737052,0.0075924895,0.31394738,0.00021799772,0.00023006994],"about_ca_topic_score_codex":0.00001404157,"about_ca_topic_score_gemma":0.0000070432175,"teacher_disagreement_score":0.66947675,"about_ca_system_score_codex":0.00003267294,"about_ca_system_score_gemma":0.000111560505,"threshold_uncertainty_score":0.33695936},"labels":[],"label_agreement":null},{"id":"W2322448335","doi":"10.1515/sagmb-2015-0056","title":"On the validity of within-nuclear-family genetic association analysis in samples of extended families","year":2015,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Canadian Institutes of Health Research","keywords":"Nuclear family; Estimator; Inference; Statistics; Logistic regression; Variance (accounting); Econometrics; Linkage (software); Mathematics; Genetics; Biology; Computer science; Artificial intelligence; Gene","score_opus":0.024373241857033618,"score_gpt":0.3070305004537845,"score_spread":0.2826572585967509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322448335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92517287,0.00046043194,0.073389165,0.00014569981,0.000023116192,0.00027762228,0.00022542373,0.0000023694597,0.00030332952],"genre_scores_gemma":[0.9763203,0.0002894634,0.022984328,0.00015945737,0.000011603882,0.00006563952,0.00015388179,0.000010187848,0.000005137563],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984025,0.00038754003,0.00054114556,0.00033407044,0.00013091303,0.00020386963],"domain_scores_gemma":[0.9988031,0.00034488324,0.0002574326,0.00034337252,0.00019256002,0.00005869873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088171114,0.00013106293,0.00033147886,0.00014798691,0.000029657256,0.000004774661,0.00017873014,0.00020955538,0.000004040982],"category_scores_gemma":[0.0010912562,0.00010664886,0.00006072141,0.000380474,0.00022054887,6.44017e-7,0.00010238217,0.0001023667,9.701498e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068566245,0.000392138,0.7488014,0.00002010867,0.00037885812,0.0000010902712,0.00030665018,0.007202885,0.09030378,0.1499272,0.0003608301,0.0022364596],"study_design_scores_gemma":[0.00061834126,0.0006512262,0.89606905,0.0000050028048,0.00018544584,9.778394e-7,0.0006533302,0.0028864811,0.0042079967,0.09326159,0.0012344406,0.00022611886],"about_ca_topic_score_codex":0.00014439193,"about_ca_topic_score_gemma":0.00029777328,"teacher_disagreement_score":0.14726761,"about_ca_system_score_codex":0.00003693519,"about_ca_system_score_gemma":0.00008427105,"threshold_uncertainty_score":0.43490145},"labels":[],"label_agreement":null},{"id":"W2326733347","doi":"10.1515/sagmb-2014-0100","title":"Corrigendum to: Simple estimators of false discovery rates given as few as one or two p-values without strong parametric assumptions","year":2015,"lang":"en","type":"erratum","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; University of Ottawa","funders":"","keywords":"Estimator; Simple (philosophy); Parametric statistics; Econometrics; Mathematics; Statistics; Parametric model; Applied mathematics; Philosophy; Epistemology","score_opus":0.2888264089124639,"score_gpt":0.5600055300892997,"score_spread":0.27117912117683574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326733347","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001735363,0.0008944273,0.9860369,0.0001581772,0.0013639237,0.0023861425,0.0053609065,0.000042906133,0.0020212447],"genre_scores_gemma":[0.009787979,0.0007723893,0.98365945,0.00017826843,0.00027213848,0.00097401283,0.00090008083,0.00013291126,0.0033227922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951372,0.00092467136,0.0017375541,0.0011238777,0.00044706248,0.0006295929],"domain_scores_gemma":[0.98823553,0.009242403,0.0006081534,0.001036025,0.00040224913,0.00047566352],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013351877,0.0005651056,0.0017635787,0.00041906655,0.00010405186,0.00007927635,0.00059994153,0.0007444074,0.00015556139],"category_scores_gemma":[0.039098416,0.00048334306,0.00012107509,0.00076973904,0.00095764967,0.00002157516,0.0005189156,0.00081618695,0.00004158635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019678807,0.00084055634,0.0010201052,0.00046260495,0.00035915154,0.000022968468,0.000062546584,0.000028694072,0.00048764516,0.93189466,0.048488323,0.016135985],"study_design_scores_gemma":[0.0007458485,0.0009592973,0.0003860261,0.000114474846,0.0004924745,0.000008181403,0.0000765575,0.00084691553,0.00038795458,0.97510517,0.020333895,0.00054323155],"about_ca_topic_score_codex":0.00020063801,"about_ca_topic_score_gemma":0.00009064991,"teacher_disagreement_score":0.04321051,"about_ca_system_score_codex":0.00010965162,"about_ca_system_score_gemma":0.0006464718,"threshold_uncertainty_score":0.9997618},"labels":[],"label_agreement":null},{"id":"W2400442575","doi":"10.1515/sagmb-2015-0026","title":"Identification of consistent functional genetic modules","year":2016,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Identification (biology); Computational biology; Computer science; Biological system; Biology","score_opus":0.009952392029068407,"score_gpt":0.2809339686172485,"score_spread":0.2709815765881801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400442575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2851525,0.0009148665,0.7133333,0.00015612935,0.000034690645,0.00020792286,0.000103539234,0.0000039521283,0.000093098664],"genre_scores_gemma":[0.9910761,0.00072140584,0.007714781,0.00006630157,0.00003049977,0.00020669545,0.00010701558,0.000011991954,0.000065194035],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895865,0.00006709792,0.00036200063,0.00039293276,0.000073614174,0.00014573007],"domain_scores_gemma":[0.9993702,0.00003444488,0.00010726676,0.00032333884,0.0000997059,0.00006500832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009992593,0.00010836525,0.00011991622,0.00008103942,0.00003510918,0.000006097605,0.000105119325,0.00011730447,0.000017503924],"category_scores_gemma":[0.000057505622,0.00008399429,0.000029759312,0.000096191055,0.0002995829,0.0000012671594,0.00007138855,0.000032509222,0.0000033737601],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018370476,0.000051665837,0.0073805256,0.000009690585,0.000012932919,1.9700849e-7,0.0000041857015,0.000016328562,0.91198516,0.053282604,0.00009108346,0.027147258],"study_design_scores_gemma":[0.0009825533,0.00024100709,0.1916741,0.000014817925,0.000034176694,0.0000102682425,0.000050723524,0.00021441416,0.73551524,0.048619315,0.02233924,0.00030417016],"about_ca_topic_score_codex":0.0000029952835,"about_ca_topic_score_gemma":0.0000060202196,"teacher_disagreement_score":0.7059236,"about_ca_system_score_codex":0.000010696701,"about_ca_system_score_gemma":0.00004310085,"threshold_uncertainty_score":0.34251878},"labels":[],"label_agreement":null},{"id":"W2408772186","doi":"10.1515/sagmb-2015-0057","title":"Using persistent homology and dynamical distances to analyze protein binding","year":2016,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; University of Alberta; Compute Canada","keywords":"Persistent homology; Persistence (discontinuity); Topological data analysis; Persistence length; Homology (biology); Barcode; Protein structure; Allosteric regulation","score_opus":0.01578656115812315,"score_gpt":0.3068789397904513,"score_spread":0.2910923786323281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408772186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22707191,0.00038258225,0.77151966,0.0007366574,0.000007846951,0.00015272897,0.00008884203,0.000008156857,0.00003162842],"genre_scores_gemma":[0.7643294,0.000058418085,0.23547122,0.000062100415,0.0000051958477,0.00004997125,0.000011243566,0.0000024198328,0.000010060267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990204,0.0000663291,0.00018111475,0.00045709088,0.000054416665,0.00022066542],"domain_scores_gemma":[0.9994596,0.00012839366,0.00003148737,0.00022496811,0.000028529903,0.00012698538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000108684064,0.00009233097,0.00016213825,0.00017272265,0.00006704604,0.00002736817,0.00023089316,0.000066131484,0.000007403759],"category_scores_gemma":[0.000079194724,0.000060578055,0.00002107251,0.00045056536,0.00024798824,0.000015858346,0.00030463657,0.00004534872,0.0000034015095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029116272,0.00004067667,0.0032792054,0.00000462487,0.000020075964,0.000005916003,0.000013583719,0.0000098868,0.050199337,0.87052184,0.0000033907822,0.07589855],"study_design_scores_gemma":[0.0013252823,0.0014662409,0.035498522,0.000047139198,0.00016050729,0.00006707983,0.00014491516,0.047915187,0.0054719364,0.8836037,0.02294382,0.001355686],"about_ca_topic_score_codex":0.000026117614,"about_ca_topic_score_gemma":0.000017117178,"teacher_disagreement_score":0.53725743,"about_ca_system_score_codex":0.000022877311,"about_ca_system_score_gemma":0.000013814174,"threshold_uncertainty_score":0.24703014},"labels":[],"label_agreement":null},{"id":"W2505409898","doi":"10.2202/1544-6115.1295","title":"Multiple Testing Issues in Discriminating Compound-Related Peaks and Chromatograms from High Frequency Noise, Spikes and Solvent-Based Noise in LC - MS Data Sets","year":2007,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"","keywords":"False positive paradox; Noise (video); Chromatography; Sample (material); Chemistry; Pattern recognition (psychology); Computer science; Artificial intelligence","score_opus":0.022958027026440155,"score_gpt":0.3317837427468998,"score_spread":0.30882571572045964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505409898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8823707,0.0034024715,0.113347165,0.00007769722,0.0000067680694,0.00014958486,0.00044366953,0.000015180041,0.00018672731],"genre_scores_gemma":[0.8794085,0.00014962538,0.11892222,0.00003256215,0.000010126664,0.000030493413,0.0014317278,0.000013177832,0.0000016122423],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998665,0.000028276143,0.00041580116,0.0005450315,0.00006648702,0.00027944692],"domain_scores_gemma":[0.9988299,0.0006666301,0.00008241516,0.00030966772,0.000027037111,0.00008433127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016195496,0.00016849785,0.0002719142,0.00014029877,0.00006220077,0.000031596097,0.00017189956,0.00016342172,0.00002404699],"category_scores_gemma":[0.00029011167,0.00016734048,0.000008829047,0.0003453238,0.00032114398,0.000017232895,0.00016610247,0.00020480625,5.6324296e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008718252,0.00017577004,0.56992805,0.00006191195,0.000016366728,0.000025406785,0.00006850585,0.000016598227,0.41794965,0.003798056,0.000002340684,0.007948632],"study_design_scores_gemma":[0.0038539474,0.00016045097,0.70456207,0.00015612993,0.00024612638,0.000019165072,0.0010805563,0.07098879,0.12903354,0.08864147,0.0002133883,0.0010443523],"about_ca_topic_score_codex":0.003651056,"about_ca_topic_score_gemma":0.0015316185,"teacher_disagreement_score":0.2889161,"about_ca_system_score_codex":0.000027414035,"about_ca_system_score_gemma":0.000023219374,"threshold_uncertainty_score":0.6823947},"labels":[],"label_agreement":null},{"id":"W2563004743","doi":"10.1515/sagmb-2015-0096","title":"Statistical models and computational algorithms for discovering relationships in microbiome data","year":2016,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Microbiome; Human microbiome; Multinomial distribution; Computer science; Human Microbiome Project; Human health; Dirichlet distribution; Computational biology; Data science; Biology; Bioinformatics; Statistics; Mathematics","score_opus":0.05676287330995345,"score_gpt":0.3576809279288802,"score_spread":0.30091805461892673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563004743","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013963865,0.00038861728,0.99617046,0.00058890437,0.000018870805,0.00038798555,0.0010058242,0.000009972012,0.000032970012],"genre_scores_gemma":[0.2510066,0.000082357314,0.74857926,0.000059412785,0.0000074981976,0.00008761383,0.00016811957,0.0000061015858,0.0000030497422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998819,0.00011104142,0.00026172202,0.0005553656,0.000046333073,0.00020655988],"domain_scores_gemma":[0.9986857,0.00083137356,0.000035821773,0.00033794143,0.000031726122,0.00007741268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003526062,0.00010514058,0.00015348889,0.0000936872,0.000060603656,0.000033679207,0.0002837836,0.00008329635,0.0000010028206],"category_scores_gemma":[0.000074042524,0.00008249025,0.000007462055,0.00011829307,0.00019171798,0.000060179416,0.00031424177,0.00007832313,5.3810595e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027492474,0.000026362353,0.0004065837,0.000008871682,0.0000043487353,0.0000012325861,0.000028559416,0.000052001553,0.0016827994,0.89380866,0.000014219501,0.103963636],"study_design_scores_gemma":[0.00033232744,0.00003188368,0.0027462975,0.000006688565,0.0000045395605,0.0000056459526,0.0000029879618,0.23670302,0.000056452896,0.7594993,0.0005081121,0.00010275721],"about_ca_topic_score_codex":0.000011406249,"about_ca_topic_score_gemma":0.000021255933,"teacher_disagreement_score":0.24961022,"about_ca_system_score_codex":0.000016208984,"about_ca_system_score_gemma":0.000044713343,"threshold_uncertainty_score":0.3363855},"labels":[],"label_agreement":null},{"id":"W2586945381","doi":"10.1515/sagmb-2016-0035","title":"Polyunphased: an extension to polytomous outcomes of the Unphased package for family-based genetic association analysis","year":2017,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre intégré universitaire de santé et de services sociaux de la Capitale-Nationale; Institut Universitaire en Santé Mentale de Québec","funders":"Canadian Institutes of Health Research","keywords":"Polytomous Rasch model; Genetic association; Population; Logistic regression; Conditional dependence; Statistics; Computer science; Econometrics; Data mining; Mathematics; Biology; Genetics; Medicine; Genotype; Single-nucleotide polymorphism","score_opus":0.014199936806380912,"score_gpt":0.3469983778209622,"score_spread":0.3327984410145813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586945381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5265518,0.00012471141,0.47170308,0.00044332666,0.000037275946,0.0004927095,0.0006144627,0.0000029035198,0.000029747362],"genre_scores_gemma":[0.9249879,0.000034354056,0.073516235,0.0006992656,0.000028432823,0.0002520303,0.00043997096,0.000017643737,0.000024141478],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99844414,0.00017052231,0.0004280911,0.0005378617,0.000098183344,0.00032118813],"domain_scores_gemma":[0.99820656,0.00014377924,0.00032127826,0.0010214258,0.0001889513,0.00011803169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003774075,0.00017971845,0.0003684614,0.000112848655,0.00026404223,0.000027148355,0.00041385865,0.0002556062,0.0000031429695],"category_scores_gemma":[0.0007310784,0.00014586434,0.0001304476,0.00014909095,0.00018505217,0.0000016907136,0.00014467334,0.000071717055,7.290724e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003329682,0.00018176403,0.6443353,0.000009609452,0.00020367056,3.281582e-7,0.00001733429,0.000638494,0.34513223,0.0030909409,0.00007103412,0.0062859864],"study_design_scores_gemma":[0.00069287437,0.00033224685,0.97540194,0.0000023030025,0.00027869834,3.4854713e-7,0.000026848058,0.0019936792,0.014626463,0.0047015375,0.0017446864,0.00019840215],"about_ca_topic_score_codex":0.00014343859,"about_ca_topic_score_gemma":0.00037241133,"teacher_disagreement_score":0.39843613,"about_ca_system_score_codex":0.000029479797,"about_ca_system_score_gemma":0.00008703494,"threshold_uncertainty_score":0.5948175},"labels":[],"label_agreement":null},{"id":"W2738214912","doi":"10.1515/sagmb-2016-0066","title":"Comparing the performance of linear and nonlinear principal components in the context of high-dimensional genomic data integration","year":2017,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Impact; McMaster University; Population Health Research Institute","funders":"Canadian Institutes of Health Research","keywords":"Context (archaeology); Principal component analysis; Nonlinear system; Computer science; Mathematics; Data mining; Statistics; Econometrics; Biology; Physics","score_opus":0.04208724528262083,"score_gpt":0.3307104930972203,"score_spread":0.28862324781459947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738214912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776415,0.00048438035,0.021256289,0.00019049358,0.00001849832,0.00026614353,0.000114179325,6.7068277e-7,0.000027796243],"genre_scores_gemma":[0.9925312,0.0004001482,0.00641746,0.000070643015,0.000017933953,0.000038886126,0.00051695365,0.0000047743156,0.000002008575],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99931175,0.00007232941,0.0002356968,0.00023645227,0.000056839217,0.00008693374],"domain_scores_gemma":[0.9991458,0.00003551801,0.00013031434,0.00062581507,0.000042623127,0.000019928364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024114779,0.00007455216,0.00012021569,0.000027012404,0.000094003386,0.0000096221365,0.0003898049,0.00006375444,9.939192e-7],"category_scores_gemma":[0.00004534909,0.0000491554,0.000009065635,0.000030777075,0.00041463875,0.0000021996498,0.00030026608,0.00007916151,2.1476728e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008634175,0.00010643069,0.06994534,0.000025972553,0.000016857324,2.6925795e-7,0.000090724156,0.00008919449,0.8936633,0.021708867,0.000017855518,0.01424888],"study_design_scores_gemma":[0.0011215601,0.00033454588,0.834747,0.000028272309,0.000032763353,0.000007345913,0.00023188259,0.05860702,0.09935614,0.001447798,0.0039101564,0.0001754964],"about_ca_topic_score_codex":0.00009816693,"about_ca_topic_score_gemma":0.00012274468,"teacher_disagreement_score":0.7943071,"about_ca_system_score_codex":0.000003381669,"about_ca_system_score_gemma":0.000028859497,"threshold_uncertainty_score":0.2004499},"labels":[],"label_agreement":null},{"id":"W2765927438","doi":"10.1515/sagmb-2016-0062","title":"A smoothed EM-algorithm for DNA methylation profiles from sequencing-based methods in cell lines or for a single cell type","year":2017,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University; Jewish General Hospital; Université Laval","funders":"","keywords":"DNA methylation; CpG site; Biology; Computational biology; Methylation; Illumina Methylation Assay; DNA sequencing; Differentially methylated regions; DNA; Algorithm; Genetics; Computer science; Gene; Gene expression","score_opus":0.035912019318060456,"score_gpt":0.38405813375488007,"score_spread":0.34814611443681964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765927438","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13273214,0.0013655734,0.86390543,0.00005693334,0.000062403764,0.0011758093,0.0006202594,0.000005530531,0.00007592023],"genre_scores_gemma":[0.36882973,0.00014002349,0.6290244,0.000059703765,0.00006435654,0.0005826,0.001248371,0.000027419805,0.000023416173],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99860317,0.000116905394,0.00037378917,0.00058084325,0.000053514363,0.00027179095],"domain_scores_gemma":[0.99882954,0.00027925931,0.00018535242,0.00046436515,0.00016543067,0.00007604182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036282657,0.00019572825,0.00025075264,0.00008168852,0.00014010168,0.000057177855,0.00023132876,0.0002842771,0.000005177342],"category_scores_gemma":[0.0003157897,0.00017953641,0.00004861144,0.00007016308,0.00014726014,0.0000026254297,0.00008457242,0.00007097839,5.127996e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076050695,0.00011355825,0.00062537333,0.00003827603,0.000010345731,5.841062e-7,0.00002394415,0.000097762975,0.93300754,0.0007597003,0.000006718926,0.06524016],"study_design_scores_gemma":[0.0013039138,0.00072139443,0.001096565,0.00000786145,0.000041179297,2.3440772e-7,0.000043754233,0.020944262,0.9440135,0.025790652,0.005774518,0.00026219882],"about_ca_topic_score_codex":0.00004541816,"about_ca_topic_score_gemma":0.00018270353,"teacher_disagreement_score":0.23609757,"about_ca_system_score_codex":0.000025685433,"about_ca_system_score_gemma":0.00015387994,"threshold_uncertainty_score":0.7321282},"labels":[],"label_agreement":null},{"id":"W2790219140","doi":"10.1515/sagmb-2017-0038","title":"Ensemble survival tree models to reveal pairwise interactions of variables with time-to-events outcomes in low-dimensional setting","year":2018,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institute of Allergy and Infectious Diseases; National Cancer Institute; Russian Science Foundation; National Institute of General Medical Sciences; McGill University","keywords":"Pairwise comparison; Estimator; Statistics; Econometrics; Event (particle physics); Survival analysis; Computer science; Mathematics","score_opus":0.0340043625606339,"score_gpt":0.36531668971846626,"score_spread":0.3313123271578324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790219140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14005442,0.000007222045,0.8582673,0.00017888808,0.00001709266,0.000454883,0.00023793116,0.000007532589,0.00077473023],"genre_scores_gemma":[0.37882048,0.0000011512876,0.62088764,0.00010036202,0.000008676769,0.000119438446,0.00001820072,0.0000109333405,0.000033150587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877626,0.00014966114,0.000398867,0.0003367046,0.00010100758,0.00023749951],"domain_scores_gemma":[0.9981497,0.0012917776,0.000062939514,0.00023722606,0.00013552682,0.00012281803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029236826,0.00013859612,0.0003181358,0.00012709796,0.00004052189,0.00000666101,0.000116846706,0.000063957865,0.000048619135],"category_scores_gemma":[0.00041803607,0.00011345684,0.000015562484,0.00023069035,0.00013747238,0.000008656779,0.00012215307,0.00009961803,0.00001058017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081051236,0.00040808276,0.004725036,0.000052964795,0.0000398359,0.0000035895341,0.0001894435,0.00023158304,0.029013835,0.94254255,0.00010062463,0.022611413],"study_design_scores_gemma":[0.00041749666,0.00047988555,0.00908798,0.000070736874,0.000030536787,0.000003138644,0.000041486855,0.013557125,0.0026628978,0.97325486,0.0001677367,0.00022612186],"about_ca_topic_score_codex":0.000046829977,"about_ca_topic_score_gemma":0.00011618475,"teacher_disagreement_score":0.23876604,"about_ca_system_score_codex":0.000022400287,"about_ca_system_score_gemma":0.00004721376,"threshold_uncertainty_score":0.46266356},"labels":[],"label_agreement":null},{"id":"W2950331006","doi":"10.1515/sagmb-2016-0077","title":"Multivariate association between single-nucleotide polymorphisms in Alzgene linkage regions and structural changes in the brain: discovery, refinement and validation","year":2017,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"National Institute on Aging","keywords":"Multivariate statistics; Single-nucleotide polymorphism; Linkage (software); Multivariate analysis; Computational biology; Association (psychology); Biology; Genetic association; Genetics; Computer science; Psychology; Genotype; Machine learning; Gene","score_opus":0.021259273517171755,"score_gpt":0.3167864999722645,"score_spread":0.2955272264550927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950331006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.964677,0.00066601456,0.027541034,0.00635198,0.000030570707,0.00047041153,0.00017318095,0.0000026281525,0.00008722895],"genre_scores_gemma":[0.99237055,0.0007120345,0.0058310265,0.00039041528,0.00006876706,0.00013636025,0.0004562695,0.000011536921,0.000023052437],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986421,0.00026025833,0.00030665207,0.00044545997,0.00006497063,0.00028056663],"domain_scores_gemma":[0.9991704,0.00022052048,0.00019130863,0.00033535846,0.00003239072,0.00005001805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005398118,0.00015487189,0.00022141624,0.00007625413,0.0001755758,0.00006681683,0.00017069539,0.00022695166,0.000001351533],"category_scores_gemma":[0.00041581623,0.00013178829,0.000016775763,0.0000618768,0.00021602506,0.000004839908,0.00019807543,0.00013777248,3.2322487e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011989821,0.00004750435,0.8958146,0.000011703136,0.00003591288,0.0000022289437,0.00016213079,0.000019364268,0.08218013,0.011442221,0.000045066827,0.0102271475],"study_design_scores_gemma":[0.00063321256,0.00018233928,0.97547275,0.00000826844,0.000026987986,0.000003094766,0.00008489166,0.0002634562,0.0016186518,0.019410346,0.0021245456,0.00017143085],"about_ca_topic_score_codex":0.000373081,"about_ca_topic_score_gemma":0.0014583197,"teacher_disagreement_score":0.080561474,"about_ca_system_score_codex":0.000031405572,"about_ca_system_score_gemma":0.00002182293,"threshold_uncertainty_score":0.537417},"labels":[],"label_agreement":null},{"id":"W3009238540","doi":"10.1515/sagmb-2018-0026","title":"Identification of supervised and sparse functional genomic pathways","year":2020,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Identification (biology); Computational biology; Computer science; Artificial intelligence; Machine learning; Biology","score_opus":0.012856851338160271,"score_gpt":0.2431907907528628,"score_spread":0.2303339394147025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009238540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37442178,0.0012404708,0.62365186,0.00014908487,0.00001534205,0.0002389965,0.00017569453,0.0000031959692,0.00010357751],"genre_scores_gemma":[0.98795515,0.000509985,0.010688948,0.00032483737,0.000040908253,0.00005077969,0.0004149569,0.000010980976,0.0000034550455],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991628,0.00003226378,0.000339198,0.0002850344,0.000041703224,0.00013903224],"domain_scores_gemma":[0.99960065,0.000021681302,0.000075078206,0.0001617889,0.000043931774,0.000096894146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009676769,0.00010835901,0.00014040619,0.000030142604,0.000037183116,0.000010801182,0.000085924294,0.0001227236,0.000007146492],"category_scores_gemma":[0.000027262737,0.00010858317,0.000020874984,0.000070556474,0.00021606035,0.0000012764892,0.00012586749,0.00006824842,0.0000019707054],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028921448,0.000029469915,0.0029302626,0.000036157682,0.000022307488,3.9873683e-7,0.000053262662,0.00010175637,0.8882019,0.095909186,0.000057269757,0.0126290945],"study_design_scores_gemma":[0.0064693484,0.0027114723,0.15771057,0.000029939016,0.0003036229,0.000062588,0.00083322555,0.1122546,0.29461506,0.3821805,0.04060816,0.0022209217],"about_ca_topic_score_codex":0.0000032164887,"about_ca_topic_score_gemma":0.00000393019,"teacher_disagreement_score":0.6135334,"about_ca_system_score_codex":0.0000037910422,"about_ca_system_score_gemma":0.000033824577,"threshold_uncertainty_score":0.44278932},"labels":[],"label_agreement":null},{"id":"W3082808948","doi":"10.1515/sagmb-2019-0058","title":"Spectral dynamic causal modelling of resting-state fMRI: an exploratory study relating effective brain connectivity in the default mode network to genetics","year":2020,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"Canadian Statistical Sciences Institute; National Institute on Aging; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Defense","keywords":"Default mode network; Imaging genetics; Neuroimaging; Functional magnetic resonance imaging; Context (archaeology); Resting state fMRI; Single-nucleotide polymorphism; Alzheimer's Disease Neuroimaging Initiative; Psychology; Neuroscience; Genetics; Biology; Cognition; Genotype","score_opus":0.03760839718825871,"score_gpt":0.3276621817974205,"score_spread":0.2900537846091618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082808948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53511757,0.00006923182,0.4631224,0.0006254239,0.00001454071,0.0009533699,0.00006296737,0.0000102599615,0.000024269428],"genre_scores_gemma":[0.9841447,0.000019465397,0.013950758,0.0013745179,0.000025444506,0.00045373052,0.000011510887,0.000019409103,4.977562e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758554,0.0008934823,0.00035087386,0.0007130732,0.00014544983,0.00031161224],"domain_scores_gemma":[0.9945794,0.004927857,0.00008288465,0.00026785175,0.000050824223,0.00009119141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004681126,0.0001796344,0.0002730903,0.00006982973,0.00014355416,0.00001915296,0.00022079395,0.00006137695,8.396787e-7],"category_scores_gemma":[0.0018514955,0.00016053024,0.000020824495,0.00054993015,0.0002326723,0.000019521895,0.000181511,0.0002894515,0.0000013799025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014474784,0.00046810677,0.01997,0.000034574354,0.00002355014,0.000031765965,0.00687565,0.7919644,0.12645262,0.048756998,0.000024605006,0.005252971],"study_design_scores_gemma":[0.00086083147,0.0025024854,0.026849631,0.000014879785,0.000035445337,0.0000067622627,0.0014415649,0.8325204,0.0050033946,0.1302255,0.00012350299,0.00041557787],"about_ca_topic_score_codex":0.000058874793,"about_ca_topic_score_gemma":0.0008383714,"teacher_disagreement_score":0.44917163,"about_ca_system_score_codex":0.00003641523,"about_ca_system_score_gemma":0.00004093103,"threshold_uncertainty_score":0.6546233},"labels":[],"label_agreement":null},{"id":"W3098349241","doi":"10.1515/1544-6115.1765","title":"Empirical Bayes Interval Estimates that are Conditionally Equal to Unadjusted Confidence Intervals or to Default Prior Credibility Intervals","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Credible interval; Confidence interval; Statistics; Mathematics; CDF-based nonparametric confidence interval; Confidence distribution; Posterior probability; Point estimation; Coverage probability; Bayes' theorem; Prior probability; Frequentist inference; Binomial proportion confidence interval; Bayesian probability; Econometrics; Bayesian inference; Poisson distribution; Negative binomial distribution","score_opus":0.14014334099700204,"score_gpt":0.47542304051199746,"score_spread":0.3352796995149954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098349241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14077972,0.00012121182,0.8565217,0.0005401742,0.00007316028,0.00088023214,0.00094468944,0.000033690692,0.0001054108],"genre_scores_gemma":[0.5333568,0.00000836161,0.4653481,0.0008204206,0.000027287308,0.00036762707,0.000047263726,0.00001642744,0.000007743505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99772143,0.00031142632,0.00066312024,0.00058451487,0.00017831245,0.00054121617],"domain_scores_gemma":[0.9948657,0.0039035324,0.000120480196,0.0004224978,0.00019006329,0.000497723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006763588,0.00028106463,0.0005363931,0.00012839842,0.000084292034,0.000048095855,0.000316172,0.00017705771,0.0003071731],"category_scores_gemma":[0.0053564236,0.00022267456,0.000046727248,0.00023231888,0.0003445583,0.000024221648,0.0003942062,0.0002168219,0.00003491952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012677639,0.00045533298,0.034201436,0.00016428619,0.00005729197,0.000008544795,0.0004906484,0.000006002193,0.006248086,0.9386486,0.00090883387,0.0186842],"study_design_scores_gemma":[0.0004073257,0.0006649289,0.11874886,0.00012257168,0.000089629895,0.000025229514,0.00034115414,0.0013125045,0.0064876927,0.86892426,0.00237043,0.00050540816],"about_ca_topic_score_codex":0.00002912219,"about_ca_topic_score_gemma":0.00008267131,"teacher_disagreement_score":0.39257708,"about_ca_system_score_codex":0.000060774793,"about_ca_system_score_gemma":0.00006131086,"threshold_uncertainty_score":0.90804046},"labels":[],"label_agreement":null},{"id":"W4385969104","doi":"10.1515/sagmb-2023-0017","title":"CAT PETR: a graphical user interface for differential analysis of phosphorylation and expression data","year":2023,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Advanced Biosensing Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kinexus Bioinformatics Corporation (Canada); University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Visualization; Computer science; Graphical user interface; Data mining; Data visualization; User interface; Operating system","score_opus":0.01634073589515513,"score_gpt":0.36196739715944914,"score_spread":0.34562666126429403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385969104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3315249,0.0001834495,0.6671849,0.00006257853,0.000007159092,0.00029538284,0.000722938,0.000009323217,0.000009383172],"genre_scores_gemma":[0.9068884,0.0006764268,0.088149,0.000023258304,0.0000128904685,0.00013960867,0.0040872516,0.00001166852,0.000011445073],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990793,0.0000295102,0.00022857984,0.00047297747,0.00004197548,0.00014769052],"domain_scores_gemma":[0.99931544,0.00007028481,0.00006365997,0.00044674618,0.000052942618,0.000050930368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000097309974,0.00010571791,0.00017710705,0.00012755589,0.00005386314,0.000008562727,0.0001510414,0.00013027726,0.0000016781773],"category_scores_gemma":[0.000052700725,0.000098349716,0.000028521446,0.0002983786,0.00022173113,0.0000012868517,0.0002975709,0.000040797935,1.9050745e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002969374,0.000049514623,0.002815166,0.000017539287,0.00007424619,1.7054127e-7,0.000011110445,0.00004672233,0.958438,0.03123256,0.00011447627,0.007170842],"study_design_scores_gemma":[0.0016278053,0.00085203274,0.08131858,0.000032086067,0.0010994918,0.0000062091435,0.00018810677,0.09767864,0.67390054,0.083288245,0.059021927,0.0009863335],"about_ca_topic_score_codex":0.000009834338,"about_ca_topic_score_gemma":0.000036719943,"teacher_disagreement_score":0.5790359,"about_ca_system_score_codex":0.000003437598,"about_ca_system_score_gemma":0.000014450941,"threshold_uncertainty_score":0.4010585},"labels":[],"label_agreement":null},{"id":"W7129040716","doi":"10.1515/sagmb-2025-0043","title":"Perfect collinearity not created equal: measuring and visualizing the severity of multi-collinearity of modern omics data","year":2025,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; St. Joseph’s Healthcare Hamilton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Collinearity; Redundancy (engineering); Statistical model; Linkage disequilibrium; Linkage (software); Selection (genetic algorithm); Contrast (vision); Multicollinearity; Disequilibrium","score_opus":0.03285082144057044,"score_gpt":0.3393574296199837,"score_spread":0.3065066081794133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7129040716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24315952,0.0020047447,0.7537174,0.000056636534,0.00001726718,0.0003806688,0.00060584425,0.000002734539,0.000055165063],"genre_scores_gemma":[0.95956975,0.0008535522,0.038932294,0.00011289483,0.0000115207185,0.000031277683,0.000474331,0.000008561826,0.000005838209],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989173,0.000113337956,0.000413562,0.00033151874,0.000053719144,0.00017055332],"domain_scores_gemma":[0.9990808,0.00011877483,0.000108882,0.0005480803,0.00009955029,0.000043928918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005026871,0.00012801346,0.00023765775,0.00004385208,0.00008767743,0.000012823576,0.00028290975,0.00018042253,7.799575e-7],"category_scores_gemma":[0.0001346966,0.00011059335,0.000023329829,0.0001254532,0.00046321878,0.0000018658379,0.000556917,0.00014541861,9.4210684e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025525875,0.00049223786,0.031139385,0.00049070717,0.0003590792,0.0000012046372,0.00022826958,0.0009528901,0.6891458,0.13931851,0.00006565459,0.137551],"study_design_scores_gemma":[0.002868981,0.00045213508,0.038671337,0.00006447227,0.00030290088,0.000016346896,0.00023192729,0.71232426,0.17808656,0.06056005,0.0057431837,0.0006778349],"about_ca_topic_score_codex":0.0000790505,"about_ca_topic_score_gemma":0.000104848325,"teacher_disagreement_score":0.7164102,"about_ca_system_score_codex":0.000006787416,"about_ca_system_score_gemma":0.000083022125,"threshold_uncertainty_score":0.45098656},"labels":[],"label_agreement":null}]}