{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1836,"total_is_capped":false,"direct_labels_cover":4,"predictions_cover":1836,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"80988dedfc78","filters":{"topic":"Gene expression and cancer classification"}},"results":[{"id":"W2165232124","doi":"10.1126/science.1136800","title":"Clustering by Passing Messages Between Data Points","year":2007,"lang":"en","type":"article","venue":"Science","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6876,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Affinity propagation; Cluster analysis; Computer science; Similarity (geometry); Data mining; Set (abstract data type); Data set; Data point; Cluster (spacecraft); Pattern recognition (psychology); Artificial intelligence; Fuzzy clustering; CURE data clustering algorithm; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.04208135963436652,"gpt":0.3467320399085356,"spread":0.3046506802741691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008116945,0.00005236278,0.00004059783,0.00003449474,0.0001487998,0.00004700734,0.0006140489,0.00003561459,0.000007785375],"category_scores_gemma":[0.00008004397,0.00004712572,0.000009128335,0.0001792348,0.0001675255,0.00001220343,0.0003520441,0.00003635537,0.000006167931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001174211,"about_ca_system_score_gemma":0.00006621773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003158056,"about_ca_topic_score_gemma":0.000005332481,"domain_scores_codex":[0.9991568,0.00001012169,0.00009703664,0.0003624644,0.0001801674,0.000193452],"domain_scores_gemma":[0.9992931,0.000005105926,0.00004455982,0.0005421077,0.00003408089,0.00008098457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003001394,0.000004362566,0.00388711,0.000001636215,0.000001134402,1.544672e-7,0.00001198121,9.164629e-7,0.9604666,0.00000298162,0.003913627,0.03170655],"study_design_scores_gemma":[0.000102391,0.0000199469,0.0311933,0.000008609874,0.00000253177,0.000001505109,0.00009000726,0.0001016222,0.8346209,0.00001895048,0.1337479,0.0000923135],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7640045,0.0007693896,0.2287889,0.0006932233,0.0003501843,0.0001004267,0.00002811701,0.00002278193,0.00524244],"genre_scores_gemma":[0.9972983,0.00003000437,0.001929245,0.0001681172,0.0001169159,9.453298e-7,0.00005754258,0.000004597616,0.0003943256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2332938,"threshold_uncertainty_score":0.1921731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045949302","doi":"10.1038/nprot.2009.97","title":"Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt","year":2009,"lang":"en","type":"article","venue":"Nature Protocols","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4605,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; Ontario Institute for Cancer Research; University of California, Santa Cruz","keywords":"Ensembl; Bioconductor; Computer science; Identifier; Computational biology; R package; Genomics; Data mining; Data integration; Genome; Data science; Biology; Gene; Genetics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02574701164941351,"gpt":0.3351561014281086,"spread":0.3094090897786951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002125365,0.00008679512,0.000066348,0.00002296514,0.0001049334,0.00003379438,0.0002817834,0.0001318804,0.000005921614],"category_scores_gemma":[0.00003778017,0.00004183931,0.00004647685,0.00008582064,0.00005327906,0.000004822954,0.00002107836,0.0001143444,0.000001016736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008752427,"about_ca_system_score_gemma":0.00005397313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000127127,"about_ca_topic_score_gemma":0.000008003552,"domain_scores_codex":[0.9994608,0.00003445338,0.000117974,0.000190963,0.00009835379,0.0000974721],"domain_scores_gemma":[0.9993019,0.00001373634,0.0001324376,0.0004502561,0.00008218323,0.0000194698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000142241,0.00001699158,0.00002863057,0.0000116663,0.00001672664,6.049315e-8,0.00004905394,0.000002366124,0.957191,0.0001899102,0.03549945,0.006851916],"study_design_scores_gemma":[0.0003546956,0.0001394375,0.003890833,0.00002373025,0.00000705416,0.000001707861,0.0001704743,0.00001809766,0.6786815,0.00007668651,0.3165774,0.00005838797],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4446024,0.003257461,0.1608687,0.02549486,0.0006141639,0.3627046,0.001236545,0.0000801381,0.001141129],"genre_scores_gemma":[0.9723658,0.00000789751,0.0007032587,0.0008651299,0.0001779941,0.02519609,0.0003729404,0.00001019753,0.000300709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5277634,"threshold_uncertainty_score":0.1706157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002900187","doi":"10.1371/journal.pone.0000718","title":"An “Electronic Fluorescent Pictograph” Browser for Exploring and Analyzing Large-Scale Biological Data Sets","year":2007,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2605,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Microarray databases; Computer science; Microarray analysis techniques; Arabidopsis; Big data; Scale (ratio); Data mining; Data science; Bioinformatics; Biology; Gene; Genetics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.1180948559540449,"gpt":0.3064109425362626,"spread":0.1883160865822177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003585752,0.0000967275,0.0001061096,0.00004701594,0.00009535009,0.00002180991,0.0002182527,0.00008133217,0.00000770634],"category_scores_gemma":[0.00003493823,0.00008665556,0.00002604781,0.00007898634,0.00002904949,0.00001027283,0.0001061671,0.00006723886,0.000001001562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009211468,"about_ca_system_score_gemma":0.00002077294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002061584,"about_ca_topic_score_gemma":0.00004782295,"domain_scores_codex":[0.9989901,0.00002574779,0.0001425577,0.0004408955,0.00008809547,0.0003125959],"domain_scores_gemma":[0.9992849,0.000009293041,0.00004687135,0.0005084675,0.00005021975,0.0001003144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001110674,0.0003749925,0.01681462,0.0000172769,0.0000536306,1.984148e-7,0.00003828617,6.933672e-7,0.9785595,0.00004094391,0.0001633856,0.003825386],"study_design_scores_gemma":[0.0007251908,0.0004710111,0.03706685,0.000032031,0.00005596942,0.000001173102,0.0002742959,0.0007509778,0.9492776,0.00007612078,0.01103972,0.0002290131],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836631,0.000956381,0.01496508,0.00009817688,0.00002673687,0.0002005986,0.00003781206,0.00002000244,0.0000320445],"genre_scores_gemma":[0.9933079,0.001195747,0.004385528,0.000116814,0.0001861996,0.00004356843,0.0007263782,0.00001428311,0.00002350701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02928188,"threshold_uncertainty_score":0.3533711,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987219048","doi":"10.1038/nmeth.2810","title":"Similarity network fusion for aggregating data types on a genomic scale","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2096,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; University of Toronto; SickKids Foundation","funders":"","keywords":"Complementarity (molecular biology); Computer science; Data type; Computational biology; Similarity (geometry); Data mining; Sensor fusion; Biological data; Bioinformatics; Artificial intelligence; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03629640495208623,"gpt":0.4015071126948916,"spread":0.3652107077428053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461017,0.0001021008,0.0001094207,0.00001948835,0.0001226367,0.00001960478,0.0003380751,0.0003371656,0.000009793023],"category_scores_gemma":[0.0006151896,0.00008622878,0.00004679987,0.00007165055,0.00002040189,0.000002389224,0.0001661689,0.0001939229,0.00000202549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009112514,"about_ca_system_score_gemma":0.00003832065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001299754,"about_ca_topic_score_gemma":0.00001030402,"domain_scores_codex":[0.9989242,0.0002947274,0.0001208672,0.0004255228,0.00007453234,0.0001601553],"domain_scores_gemma":[0.9989381,0.00008824364,0.00009277484,0.0007760149,0.00005597194,0.00004889306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001080053,0.00001919912,0.0002186595,0.00001535547,0.00001248269,3.467152e-8,0.000009916789,0.0001806505,0.694872,0.0003471917,0.02847094,0.2757456],"study_design_scores_gemma":[0.0003200259,0.000111529,0.001606982,0.00002300763,0.00001881401,0.000001095087,0.000009188792,0.006521226,0.1928847,0.001297192,0.797068,0.0001382203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04728657,0.00408188,0.9396948,0.00139874,0.001735509,0.0004956727,0.00005379592,0.00004210126,0.005210903],"genre_scores_gemma":[0.2887183,0.0001187172,0.7051285,0.00243825,0.002129901,0.00003517778,0.000635849,0.00003164197,0.0007637296],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7685971,"threshold_uncertainty_score":0.3516307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2778455075","doi":"10.21873/cgp.20063","title":"Applications of Support Vector Machine (SVM) Learning in Cancer Genomics","year":2018,"lang":"en","type":"review","venue":"Cancer Genomics & Proteomics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1539,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Research Institute in Oncology and Hematology; CancerCare Manitoba","funders":"CancerCare Manitoba Foundation","keywords":"Support vector machine; Artificial intelligence; Computer science; Genomics; Machine learning; Epigenomics; Feature (linguistics); Margin (machine learning); Computational biology; Genome; Biology; Gene; Gene expression; Genetics; DNA methylation","retraction":null,"screen_n_in":null,"score":{"opus":0.03065086917084864,"gpt":0.3392317558605671,"spread":0.3085808866897184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003491794,0.0005466961,0.001087807,0.0002567543,0.0001086731,0.00003747579,0.0007946911,0.0006955901,0.0001177898],"category_scores_gemma":[0.00003017689,0.0005529309,0.0003864616,0.0004004483,0.0001746449,0.000006535573,0.0003067384,0.0005227133,0.00002299925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006337933,"about_ca_system_score_gemma":0.00319887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001817546,"about_ca_topic_score_gemma":0.0003136238,"domain_scores_codex":[0.9971995,0.000138293,0.001058946,0.0009841481,0.0001655496,0.0004536133],"domain_scores_gemma":[0.9976234,0.00001526335,0.001123725,0.0008887344,0.0001984505,0.0001504382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00011782,0.0001516495,0.0002508195,0.005988648,0.0003335458,0.000001293089,0.0002067763,0.0002818132,0.0485879,0.000084207,0.002836427,0.9411591],"study_design_scores_gemma":[0.0003582211,0.0001081511,0.00001550692,0.0007127525,0.0002077324,0.00000607345,0.00002333091,0.00004861304,0.0101721,0.00002747923,0.9877795,0.0005405295],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000904541,0.9920949,0.003174247,0.0000538671,0.0004136763,0.002505696,0.0005419126,0.00002166472,0.0002894486],"genre_scores_gemma":[0.0003273824,0.989658,0.001499079,0.0000799601,0.001076635,0.004445519,0.0009999409,0.0001732269,0.001740264],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9849431,"threshold_uncertainty_score":0.9996922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153091158","doi":"10.1186/1471-2164-10-22","title":"BioMart – biological queries made easy","year":2009,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Occupational Cancer Research Centre; Ontario Institute for Cancer Research","funders":"European Commission; Government of Ontario; Ontario Institute for Cancer Research; Wellcome Trust","keywords":"Computer science; Ensembl; Interface (matter); Scalability; UniProt; User interface; Software; Bioconductor; Workflow; Resource (disambiguation); Graphical user interface; Scripting language; Biological data; Annotation; Process (computing); Biological database; Data integration; Data science; Data mining; Database; Bioinformatics; Genomics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.03037157327249606,"gpt":0.2664531492797902,"spread":0.2360815760072941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007034937,0.0001006042,0.00007905597,0.000025722,0.00006023221,0.00002080403,0.0001509684,0.0001353564,0.00002661972],"category_scores_gemma":[0.00002931551,0.00008693689,0.00006484958,0.00005269476,0.00004279096,0.00000159099,0.00003700184,0.00003712826,0.00003583761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001514366,"about_ca_system_score_gemma":0.00006820268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001628238,"about_ca_topic_score_gemma":0.000005242003,"domain_scores_codex":[0.9993688,0.00003340987,0.0001319134,0.0002603128,0.00004977635,0.0001557438],"domain_scores_gemma":[0.9995688,0.000003125458,0.00005023416,0.0002842534,0.00002820071,0.00006540216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006097228,0.00002981872,0.001964526,0.000001751155,0.000004078815,2.921981e-7,0.00001473664,0.00001620095,0.9891242,0.0004528792,0.004752594,0.003577964],"study_design_scores_gemma":[0.0002509553,0.0001768403,0.03530886,0.000002322385,0.000003624908,0.000007025604,0.00007631589,0.0000236047,0.5408819,0.0004283361,0.4226823,0.0001578809],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869034,0.0007741285,0.007326565,0.0003103714,0.0001692491,0.0001140119,0.000008752247,0.00002497091,0.004368564],"genre_scores_gemma":[0.9936124,0.0002559621,0.00343633,0.000720832,0.0002616374,0.00001028128,0.0000998896,0.000008038959,0.001594617],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4482423,"threshold_uncertainty_score":0.3545184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065912508","doi":"10.1073/pnas.97.18.9834","title":"Importance of replication in microarray gene expression studies: Statistical methods and evidence from repetitive cDNA hybridizations","year":2000,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":870,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Eye Institute; National Cancer Institute; National Heart, Lung, and Blood Institute","keywords":"DNA microarray; Pooling; Replication (statistics); Biology; Complementary DNA; Computational biology; Microarray; Gene expression; Gene; Microarray analysis techniques; Gene expression profiling; Genetics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06802896947410444,"gpt":0.4076459875944969,"spread":0.3396170181203925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051477,0.00005836353,0.0001079691,0.00005071923,0.0000600677,0.000005289353,0.0002489333,0.00004897843,0.00001267583],"category_scores_gemma":[0.001420292,0.00004223518,0.00002198296,0.0002725128,0.0004674796,0.00002550442,0.00006298151,0.0000513758,1.031357e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001393187,"about_ca_system_score_gemma":0.00003567966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005930785,"about_ca_topic_score_gemma":2.354139e-7,"domain_scores_codex":[0.998955,0.00002211688,0.0003151323,0.0003666203,0.0002776902,0.00006348337],"domain_scores_gemma":[0.9993336,0.00009498012,0.0003154613,0.00002753915,0.0002093945,0.00001904741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000276319,0.00001815057,0.01188445,0.00002048463,0.000005376199,1.338283e-9,0.0001460588,0.00003025192,0.9854377,0.0004109597,0.0003932388,0.001625727],"study_design_scores_gemma":[0.00008126539,0.00002624121,0.1251922,0.0001451852,0.000005040581,9.982947e-7,0.0001636258,0.0001410714,0.8685434,0.005548997,0.0001127669,0.00003914187],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966605,0.002023321,0.0002009638,0.0007182257,0.000007044298,0.0001253389,0.00002389006,0.000001801804,0.0002388996],"genre_scores_gemma":[0.9578028,0.001452441,0.04055245,0.00008683953,0.00002657267,0.00001919689,0.000001298529,0.000002424681,0.00005593754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1168942,"threshold_uncertainty_score":0.1722448,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2109488005","doi":"10.1093/nar/gkv350","title":"The BioMart community portal: an innovative alternative to large, centralized data repositories","year":2015,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":840,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"RIKEN; Office of Science; Centre National de la Recherche Scientifique; Fundación Sandra Ibarra de Solidaridad Frente al Cáncer; Universitat Pompeu Fabra; King Abdulaziz University; Ministry of Science, ICT and Future Planning; Ministry of Education, Culture, Sports, Science and Technology; National Human Genome Research Institute; Wellcome Trust; Agence Nationale de la Recherche; National Research Foundation; Breast Cancer Campaign; European Molecular Biology Laboratory; National Research Foundation of Korea; U.S. Department of Energy","keywords":"Toolbox; Interface (matter); World Wide Web; Service (business); Computer science; Data science; Ontology; User interface; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.1966316446498229,"gpt":0.4495173086639728,"spread":0.2528856640141499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003009449,0.0001047137,0.00009258102,0.00006725498,0.0006772167,0.0001582019,0.001499025,0.00009616913,0.00001166505],"category_scores_gemma":[0.00108934,0.00007572335,0.00001687231,0.0005880197,0.0002122437,0.00001932778,0.001271719,0.0003401948,0.00002529633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004075899,"about_ca_system_score_gemma":0.000292304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002209411,"about_ca_topic_score_gemma":0.0002286143,"domain_scores_codex":[0.9974891,0.001012398,0.0002035646,0.000355522,0.0005486947,0.0003907411],"domain_scores_gemma":[0.9965969,0.00003845049,0.00005984747,0.001954933,0.001105127,0.0002447966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008310892,0.0003240195,0.005721597,0.000008035486,0.00008804953,0.000006147775,0.003061963,0.000003962658,0.6484253,0.002038316,0.3309072,0.008584341],"study_design_scores_gemma":[0.0005704486,0.0004776862,0.006905928,0.00001102314,0.000002514117,0.000004648296,0.008071435,0.0001117224,0.1459349,0.0003207439,0.8374603,0.0001286172],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987138,0.0002629335,0.0009208671,0.001633539,0.0004259094,0.0004278355,0.0001110331,0.00002461568,0.009055252],"genre_scores_gemma":[0.9966911,0.00007498592,0.0003426479,0.0001853393,0.0003186024,0.00004858882,0.0006128523,0.00002153094,0.00170434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5065531,"threshold_uncertainty_score":0.5208672,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075037447","doi":"10.1016/j.lab.2005.10.005","title":"The peripheral blood transcriptome dynamically reflects system wide biology: a potential diagnostic tool","year":2006,"lang":"en","type":"article","venue":"Journal of Laboratory and Clinical Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":662,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Pyrogenesis (Canada)","funders":"","keywords":"Biology; Transcriptome; Gene expression; Gene; Gene expression profiling; Molecular biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.007677237538927482,"gpt":0.3004455930556619,"spread":0.2927683555167344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00098852,0.0001084274,0.0002384216,0.0000264581,0.0001200552,0.00001708247,0.0001636566,0.0001662868,0.000007182361],"category_scores_gemma":[0.0008485263,0.0000611127,0.00008929957,0.00009606682,0.0003079901,0.00000544976,0.00001785775,0.0002229287,5.499789e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001081291,"about_ca_system_score_gemma":0.0001316558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002511096,"about_ca_topic_score_gemma":0.000008214683,"domain_scores_codex":[0.9985039,0.000286531,0.0007506352,0.0001688229,0.0001473588,0.0001427677],"domain_scores_gemma":[0.9988825,0.0002087517,0.0003514909,0.0001740688,0.0002784066,0.0001047678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006489723,0.0001852811,0.02393849,0.00003946947,0.0001813855,0.00004631692,0.00002071744,0.00001073113,0.9616426,0.001154719,0.008291509,0.00383986],"study_design_scores_gemma":[0.02440901,0.01826196,0.4030378,0.001244789,0.001884754,0.0006488621,0.002144841,0.0003216993,0.03038742,0.001859131,0.514787,0.001012779],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869171,0.00692422,0.002113355,0.002780032,0.001011016,0.00008813058,0.000006502442,0.00000590433,0.0001537189],"genre_scores_gemma":[0.9957411,0.00184021,0.0001162718,0.0005419124,0.001640284,0.000004218132,0.000007473615,0.000009389342,0.00009912362],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9312551,"threshold_uncertainty_score":0.2492104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810986024","doi":"10.1016/j.inffus.2018.09.012","title":"Machine learning for integrating data in biology and medicine: Principles, practice, and opportunities","year":2018,"lang":"en","type":"article","venue":"Information Fusion","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":642,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"SickKids Foundation; Vector Institute; Princess Margaret Cancer Centre; University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Data science; Computer science; Systems biology; Identification (biology); Epigenome; Systems medicine; Field (mathematics); Implementation; Data integration; Big data; Grand Challenges; Bioinformatics; Data mining; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.064718829608819,"gpt":0.3548165048564162,"spread":0.2900976752475972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004453846,0.00005633412,0.00005686108,0.00007069419,0.00009483883,0.00001790336,0.00007218937,0.00006594018,0.000009179665],"category_scores_gemma":[0.0006734102,0.00004467635,0.000004002806,0.00003305444,0.00007433243,0.00004505575,0.0001509399,0.00004771382,7.54559e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005030548,"about_ca_system_score_gemma":0.00002841259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004043037,"about_ca_topic_score_gemma":0.00003734647,"domain_scores_codex":[0.9995562,0.00003759316,0.0001885225,0.0001078318,0.00004154373,0.00006826387],"domain_scores_gemma":[0.99957,0.00002560351,0.0001319227,0.00014755,0.00009630787,0.00002868224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004181752,0.00002227195,0.006595132,0.00009975478,0.00001627231,1.941657e-7,0.00221534,0.000009040659,0.2642967,0.01351268,0.004701138,0.7081134],"study_design_scores_gemma":[0.0005257334,0.0002471496,0.001259019,0.00002972701,0.000004467597,0.000007899849,0.001554775,0.01337156,0.002157978,0.00008486604,0.9806926,0.00006424297],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7449164,0.005923825,0.1775756,0.01661188,0.0008633762,0.001592338,0.0001374312,0.00008371461,0.05229542],"genre_scores_gemma":[0.9927129,0.002431772,0.002030481,0.0008602506,0.0001298663,0.00001806542,0.001653005,0.000004150089,0.0001595815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9759914,"threshold_uncertainty_score":0.1821849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2023906705","doi":"10.1038/nm.1908","title":"A stroma-related gene signature predicts resistance to neoadjuvant chemotherapy in breast cancer","year":2009,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":616,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Cancer Research; Erasmus+; Université de Lausanne; Erasmus Medisch Centrum","keywords":"Epirubicin; Breast cancer; Chemotherapy; Oncology; Gene signature; Cyclophosphamide; Stromal cell; Internal medicine; Estrogen receptor; Medicine; Stroma; Fluorouracil; Cancer; Cancer research; Biology; Gene; Gene expression; Immunohistochemistry; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.003775294202432117,"gpt":0.2668846344777426,"spread":0.2631093402753105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001577025,0.0001890264,0.0002062356,0.0001176032,0.00003813126,0.000006502633,0.0002336216,0.0004913853,0.0001087394],"category_scores_gemma":[0.00004373899,0.0001453289,0.00003876838,0.0004325957,0.00003886009,0.00000374649,0.00001768022,0.0004206889,0.000002541698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005319324,"about_ca_system_score_gemma":0.00008228067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008654611,"about_ca_topic_score_gemma":0.00005183264,"domain_scores_codex":[0.9987292,0.00004126895,0.0002431865,0.0004637225,0.0002704292,0.0002521341],"domain_scores_gemma":[0.9992715,0.000005037697,0.00008543594,0.0003753091,0.0001135954,0.0001491625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004272033,0.0000490042,0.000792633,0.00000741891,0.00001409254,0.000006596826,0.0001347601,0.00004173827,0.9159383,0.00006759205,0.07466457,0.007856126],"study_design_scores_gemma":[0.00506859,0.000451256,0.4298899,0.0005321663,0.00002463602,0.00002713729,0.000110615,0.0000457583,0.3429893,0.0003228708,0.2201249,0.0004128906],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8747061,0.02421046,0.0002609755,0.09695585,0.0006679292,0.0005412683,0.00005092313,0.00004456486,0.002561854],"genre_scores_gemma":[0.9848012,0.001120492,0.0002271996,0.01054987,0.0006072327,0.00002980909,0.0001073439,0.00001835637,0.002538521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.572949,"threshold_uncertainty_score":0.5926342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154437541","doi":"10.1038/ng1033","title":"From patterns to pathways: gene expression data analysis comes of age","year":2002,"lang":"en","type":"review","venue":"Nature Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":581,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Biology; DNA microarray; Gene expression profiling; Computational biology; Cluster analysis; Microarray analysis techniques; Profiling (computer programming); Microarray databases; Gene expression; Bioinformatics; Microarray; Gene chip analysis; Data science; Data mining; Gene; Genetics; Computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0686333173855451,"gpt":0.348058894037556,"spread":0.279425576652011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0001343673,0.000428594,0.001073556,0.0002745792,0.00004446575,0.00003427574,0.00161036,0.001308142,0.0001105566],"category_scores_gemma":[0.00006989002,0.0003550306,0.0004291797,0.0005686447,0.00003167493,0.000002464314,0.0008918969,0.0004016302,0.00001351321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002329624,"about_ca_system_score_gemma":0.0001013397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008967257,"about_ca_topic_score_gemma":0.0000247759,"domain_scores_codex":[0.9974201,0.0001744151,0.000630041,0.001150408,0.000380371,0.0002446888],"domain_scores_gemma":[0.9959074,0.00002432823,0.0004796089,0.003309079,0.0001080649,0.0001715215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002087673,0.0001850525,0.0003488481,0.001555759,0.001341207,0.00001019637,0.0000913055,0.00005885831,0.03327559,0.000001616695,0.04662742,0.9164833],"study_design_scores_gemma":[0.0001260058,0.00005296234,0.0002228354,0.0007169817,0.001659683,0.000001472101,0.0000203252,0.00001169086,0.01665372,0.000005527145,0.9801444,0.0003844265],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001253877,0.990408,0.003171003,0.00001269156,0.0004132988,0.0004181596,0.004210291,0.00001224052,0.0001004602],"genre_scores_gemma":[0.003366415,0.9704598,0.005502951,0.0001167066,0.0007783433,0.00004497049,0.01930461,0.00006232276,0.0003638702],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.933517,"threshold_uncertainty_score":0.9999884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065783627","doi":"10.1186/gb-2010-11-5-207","title":"The case for cloud computing in genome informatics","year":2010,"lang":"en","type":"article","venue":"Genome Biology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":529,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Cloud computing; Computer science; Informatics; Health informatics; Data science; Computational biology; Operating system; Biology; Health care; Engineering; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.01290986974402896,"gpt":0.2762403198329662,"spread":0.2633304500889372,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003470166,0.00008737207,0.00008310629,0.00003478652,0.0001655253,0.00001878288,0.0002006669,0.0001621855,0.00000664867],"category_scores_gemma":[0.00006908606,0.00006374392,0.00004404561,0.00006218987,0.00008820189,0.000001460628,0.00008855135,0.0001087944,0.000007210793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008854382,"about_ca_system_score_gemma":0.00005301218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007922056,"about_ca_topic_score_gemma":0.0001652399,"domain_scores_codex":[0.9993165,0.00003249962,0.0002486561,0.0001467655,0.00002061087,0.0002350417],"domain_scores_gemma":[0.9994691,0.00002970377,0.0001003508,0.0003037948,0.0000532447,0.00004383111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003459268,0.00001215713,0.0005435923,0.000007417024,0.00000964075,0.000001505447,0.0001322312,0.00003017557,0.9903778,0.001334561,0.0002468427,0.007269438],"study_design_scores_gemma":[0.0006369713,0.0001645317,0.003650414,0.000001291526,0.000004816398,0.0001670897,0.0005145589,0.0003995768,0.01198424,0.0004886014,0.9818133,0.0001746353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906495,0.0003882306,0.007222776,0.000240111,0.0006581371,0.0002606018,0.00002041086,0.00000805264,0.0005521972],"genre_scores_gemma":[0.99748,0.00007782993,0.001321036,0.0002618054,0.0005020907,0.00004083671,0.0001285628,0.000009240722,0.0001786088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9815664,"threshold_uncertainty_score":0.2599402,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143451223","doi":"10.1073/pnas.1408792111","title":"Automated identification of stratifying signatures in cellular subpopulations","year":2014,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":513,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Health Services and Policy Research","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Eye Institute; National Cancer Institute; National Heart, Lung, and Blood Institute; U.S. Public Health Service","keywords":"Identification (biology); Computational biology; Computer science; Biology; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.03100022259313767,"gpt":0.3167068147725308,"spread":0.2857065921793931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007318809,0.00004454247,0.00006624548,0.0001043892,0.00005379005,0.000007439543,0.0003153204,0.00007452044,0.000002900825],"category_scores_gemma":[0.0002929739,0.00003341403,0.0000345192,0.0003781873,0.0001973863,0.0000156942,0.00003833949,0.0000476998,1.259083e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006748317,"about_ca_system_score_gemma":0.00002010941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002961292,"about_ca_topic_score_gemma":1.766245e-7,"domain_scores_codex":[0.9991319,0.000009965731,0.0002904286,0.0001492617,0.0003601462,0.00005827921],"domain_scores_gemma":[0.9994082,0.00001299184,0.0003919272,0.00001060431,0.0001647992,0.00001147648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005085039,0.00001999952,0.005636557,0.00002355429,0.000002409163,1.317874e-10,0.0000326878,0.001344385,0.983641,0.008884452,0.0002835449,0.0001263424],"study_design_scores_gemma":[0.00007671551,0.00001558821,0.1480224,0.00002436068,0.000002494619,1.426997e-7,0.00006220603,0.00734917,0.8407489,0.003566936,0.0001002005,0.00003081488],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981171,0.00009602561,0.00002829882,0.0004016125,0.00001402032,0.00008815778,0.000004127232,0.000004660977,0.001246027],"genre_scores_gemma":[0.9994748,0.00001207939,0.0003719471,0.00003422839,0.00002686806,0.000006612123,8.639922e-7,0.000002050284,0.00007055843],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.142892,"threshold_uncertainty_score":0.1362585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4221069327","doi":"10.1093/genetics/iyab229","title":"Efficient ancestry and mutation simulation with msprime 1.0","year":2021,"lang":"en","type":"article","venue":"Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":508,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Directorate for Biological Sciences; National Institutes of Health; Canada Research Chairs; Deutsche Forschungsgemeinschaft; National Institute of General Medical Sciences; University of Edinburgh; Robertson Foundation; National Human Genome Research Institute; Villum Fonden","keywords":"Biology; Genetics; Mutation; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01714416052983847,"gpt":0.2799590324191464,"spread":0.2628148718893079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003121711,0.00006224874,0.00004367567,0.00001425715,0.00004636398,0.00001909539,0.00002954755,0.00005709511,0.000009683952],"category_scores_gemma":[0.00001371567,0.00005704035,0.00001188611,0.00007181955,0.00002864055,6.0834e-7,0.0000262941,0.00002725016,0.00000262911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005100291,"about_ca_system_score_gemma":0.00006363619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.860511e-7,"about_ca_topic_score_gemma":0.000006352113,"domain_scores_codex":[0.9995261,0.0000228871,0.00007622271,0.0002089679,0.00008531156,0.00008050355],"domain_scores_gemma":[0.9996457,0.000004285163,0.00003834847,0.0001727981,0.00009743653,0.00004144605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002987143,0.00003243284,0.0030728,0.0000120577,0.00001203018,0.000003108352,0.00005485818,0.1593512,0.8280767,0.00003325213,0.0002156265,0.009106065],"study_design_scores_gemma":[0.0006989872,0.0001561761,0.03860885,0.00001664977,0.00002238361,0.00003256587,0.0002373678,0.0260517,0.9027511,0.00004469396,0.03117826,0.0002011944],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726057,0.00134406,0.02536195,0.0001085746,0.00005136309,0.00005695098,0.000002845788,0.000006847403,0.0004617337],"genre_scores_gemma":[0.996131,0.0000884461,0.003158485,0.000129999,0.00008120375,0.000006803572,0.00005598152,0.000009157088,0.0003389419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1332995,"threshold_uncertainty_score":0.2326038,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059742736","doi":"10.1038/ng.2007.16","title":"A survey of genetic human cortical gene expression","year":2007,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":488,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kronos (Canada)","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Institute on Aging","keywords":"Biology; Genotyping; Transcriptome; Genetics; SNP genotyping; Gene expression; Computational biology; Gene; SNP array; DNA microarray; Gene expression profiling; Human genome; Genome; Genomics; Human brain; Human genetics; Genome-wide association study; Genotype; Single-nucleotide polymorphism; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.01685616516070646,"gpt":0.3108329340023596,"spread":0.2939767688416531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004624302,0.0001604299,0.0001554062,0.00007792495,0.00008311209,0.00001055431,0.0002855244,0.0005569694,0.00003223124],"category_scores_gemma":[0.0001344336,0.0001490679,0.00007013877,0.0002024714,0.0000928252,0.00000137878,0.0001132041,0.0002680804,0.000004107126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001305473,"about_ca_system_score_gemma":0.00007208288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008970082,"about_ca_topic_score_gemma":0.00007420729,"domain_scores_codex":[0.9985839,0.00009799451,0.0003816245,0.0003873314,0.0002855362,0.0002636634],"domain_scores_gemma":[0.9988106,0.0000200478,0.000158355,0.0005870639,0.0002877914,0.0001361162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007434653,0.0000696558,0.09062226,0.00001010502,0.00001254047,0.000001226321,0.00001720427,0.00002696696,0.9045364,0.000008281639,0.002865176,0.001755786],"study_design_scores_gemma":[0.0002307335,0.0001049431,0.4576571,0.000006311101,0.000007005533,0.000003218991,0.00001053004,0.000009267697,0.5364407,0.00001481911,0.005416795,0.00009867913],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830961,0.004674635,0.01106344,0.00001461162,0.0002920965,0.0001551704,0.00001839186,0.00001120765,0.0006744016],"genre_scores_gemma":[0.9929368,0.000220952,0.005891852,0.0001686681,0.0002381329,0.000005781218,0.0001941027,0.00002892618,0.0003147451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3680958,"threshold_uncertainty_score":0.6078811,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2567080747","doi":"10.1093/bib/bbw113","title":"A review on machine learning principles for multi-view biological data integration","year":2016,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":437,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; University of Windsor; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Council Canada; University of Windsor; University of Ottawa","keywords":"Computer science; Artificial intelligence; Machine learning; Deep learning; Tree (set theory); Data integration; Cluster analysis; Biological data; Similarity (geometry); Key (lock); Data mining; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.2476449868077063,"gpt":0.4070167608868869,"spread":0.1593717740791806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008296155,0.0003775332,0.0008125309,0.0001117295,0.0000776233,0.00003863775,0.0007543943,0.0004057105,0.00001476901],"category_scores_gemma":[0.001457429,0.0002327582,0.000212615,0.0001629292,0.00005471919,0.00001212962,0.0003524467,0.0002575975,0.00003815944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005113851,"about_ca_system_score_gemma":0.0001885573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003162227,"about_ca_topic_score_gemma":0.00000745025,"domain_scores_codex":[0.9979742,0.0001268164,0.001054733,0.000464453,0.0001218024,0.0002579505],"domain_scores_gemma":[0.9980924,0.00006507483,0.0007903501,0.0009161418,0.00007137783,0.00006470372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009208486,0.0000356861,0.000001131252,0.01400998,0.00002323621,1.678077e-7,0.000007735218,4.925391e-7,0.00001537608,0.0001384966,0.00780587,0.9779526],"study_design_scores_gemma":[0.0002809468,0.0001206324,0.000001064334,0.05410083,0.00005550876,0.00001069698,0.000003854244,0.0008929198,0.00002389853,0.000004492881,0.9442062,0.0002989803],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.389197e-7,0.9751614,0.02266774,0.0001531209,0.00011185,0.001338279,0.0002870271,0.00002254148,0.000257851],"genre_scores_gemma":[7.032559e-7,0.9796484,0.0109346,0.001320933,0.0001066462,0.0003341302,0.007213907,0.00003462119,0.0004060811],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9776536,"threshold_uncertainty_score":0.9491602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141222206","doi":"10.1073/pnas.0601180103","title":"Model-based analysis of tiling-arrays for ChIP-chip","year":2006,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":430,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Human Genome Research Institute","keywords":"Tiling array; Chip; Computer science; DNA microarray; Chromatin immunoprecipitation; Biology; Genetics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.04168431446088413,"gpt":0.318328516603344,"spread":0.2766442021424599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004696375,0.00005260315,0.0001011975,0.0001463713,0.00007055345,0.000005707947,0.0003560636,0.00006723583,0.000002640732],"category_scores_gemma":[0.0001178207,0.00003699149,0.0001313169,0.000535969,0.000252837,0.000007300202,0.00002919303,0.00002905141,3.965939e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006351264,"about_ca_system_score_gemma":0.00004381228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002263371,"about_ca_topic_score_gemma":2.031833e-7,"domain_scores_codex":[0.9991596,0.000002654801,0.0002198111,0.0001779297,0.0003675906,0.00007238499],"domain_scores_gemma":[0.999363,0.00001483273,0.0003368646,0.0000107023,0.0002613873,0.00001318031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002143024,0.00003042767,0.003271938,0.00002095567,0.0000217423,5.903594e-11,0.000008902985,0.0205073,0.9689354,0.006425239,0.0006702275,0.00008641073],"study_design_scores_gemma":[0.0001246957,0.00002750585,0.01741866,0.00001058908,0.00004865263,7.042375e-8,0.00002383294,0.07515317,0.9006478,0.006248962,0.0002551197,0.00004093825],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960865,0.000115023,0.0006780893,0.0007349031,0.000008827765,0.0001153916,0.00003536681,0.000002344648,0.002223517],"genre_scores_gemma":[0.9960493,0.000006815166,0.003614023,0.0001104686,0.00004203935,0.00001415274,0.000002704279,0.000002292352,0.0001582454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06828763,"threshold_uncertainty_score":0.1508469,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2172358623","doi":"10.1093/bioinformatics/btv693","title":"Genefu: an R/Bioconductor package for computation of gene expression-based signatures in breast cancer","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":410,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; Cancer Research Society; Canadian Institutes of Health Research; Instituto de Salud Carlos III; Banco Bilbao Vizcaya Argentaria; Fondation Brain Canada","keywords":"Bioconductor; Compendium; Subtyping; Computer science; R package; Breast cancer; Source code; Computational biology; Data mining; Bioinformatics; Cancer; Gene; Biology; Programming language; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03109304409576368,"gpt":0.3002827501170188,"spread":0.2691897060212551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001558309,0.000107761,0.000117595,0.00007902699,0.00002442485,0.00001468943,0.0001423493,0.000182608,0.000006923643],"category_scores_gemma":[0.00002945862,0.00009307463,0.00004327817,0.00009124016,0.00003488061,0.00001414686,0.00001936066,0.00005109623,8.628346e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002571054,"about_ca_system_score_gemma":0.0002365486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008336536,"about_ca_topic_score_gemma":0.000007978995,"domain_scores_codex":[0.999271,0.00002701296,0.0002952873,0.0001344076,0.0001389772,0.0001333186],"domain_scores_gemma":[0.9992787,0.000006888278,0.0001873101,0.0002278529,0.0002022887,0.00009695611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002169404,0.00009806028,0.002080118,0.0001039384,0.000007863956,1.172976e-7,0.0002086782,0.007475091,0.980761,0.00002771325,0.006252501,0.002768],"study_design_scores_gemma":[0.001386013,0.0001438013,0.003385637,0.00004335222,0.000008304053,8.906378e-7,0.0003641665,0.0260418,0.9663185,0.00004919209,0.002093667,0.0001646605],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9067128,0.0005773257,0.09103753,0.0002065128,0.0003470029,0.0005597638,0.0003396486,0.0000184462,0.0002009747],"genre_scores_gemma":[0.9769823,0.00002497287,0.02213881,0.000280815,0.0001101448,0.00007907332,0.0003429871,0.00001399068,0.0000268902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07026952,"threshold_uncertainty_score":0.3795473,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112491476","doi":"10.1093/bioinformatics/btp367","title":"<i>De novo</i> transcriptome assembly with ABySS","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":410,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"Genome British Columbia; Michael Smith Health Research BC; National Cancer Institute; Genome Canada","keywords":"Contig; Sequence assembly; Transcriptome; Genome; Computational biology; Java; Biology; De novo transcriptome assembly; Software; Computer science; Hybrid genome assembly; Source code; Shotgun sequencing; Reference genome; Perl; Genetics; Gene; Programming language; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.009809137250629119,"gpt":0.2413464444821044,"spread":0.2315373072314753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008221749,0.0001009066,0.00007508678,0.00003286066,0.00005228736,0.00004040577,0.000137057,0.00008603499,0.000009808737],"category_scores_gemma":[0.000008327382,0.00007901855,0.00003876605,0.00009264829,0.0000224046,0.000007514822,0.000007712173,0.00005189536,0.00001496428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001231678,"about_ca_system_score_gemma":0.00006871361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.826631e-7,"about_ca_topic_score_gemma":0.000001048587,"domain_scores_codex":[0.9994358,0.000009957727,0.0001592548,0.00009631336,0.0001195682,0.0001790934],"domain_scores_gemma":[0.9995604,0.000001801207,0.00006314139,0.0002550034,0.00004053687,0.00007910762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001323271,0.00007364222,0.0003245116,0.00002620607,0.00001900716,0.000001388251,0.0003624748,0.0001012088,0.955516,0.0006376433,0.01457695,0.02822868],"study_design_scores_gemma":[0.001642544,0.001037232,0.007781,0.00004461695,0.00003056975,0.00009293351,0.0004431247,0.001440564,0.4272533,0.0001087238,0.5596684,0.0004569664],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7296356,0.0004617217,0.1758008,0.001721551,0.0002105132,0.0004196342,0.00002332595,0.00009854194,0.09162831],"genre_scores_gemma":[0.9883066,0.00008871114,0.008279017,0.002241423,0.00008810328,0.000008521934,0.00005852093,0.000008194496,0.0009208595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5450915,"threshold_uncertainty_score":0.3222283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135598172","doi":"10.1101/gr.217802","title":"Control Genes and Variability: Absence of Ubiquitous Reference Transcripts in Diverse Mammalian Expression Studies","year":2002,"lang":"en","type":"article","venue":"Genome Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":378,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill Genome Centre; McGill University Health Centre","funders":"Takeda Oncology; Mitacs; Canadian Institutes of Health Research; Bristol-Myers Squibb","keywords":"Biology; Housekeeping gene; Gene; Microarray; Gene expression; Microarray analysis techniques; Genetics; Gene expression profiling; Computational biology; Reference genes; Phenotype; DNA microarray","retraction":null,"screen_n_in":null,"score":{"opus":0.1415979883306038,"gpt":0.3668231029196328,"spread":0.225225114589029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007623829,0.00008820318,0.0001470026,0.0001135835,0.00008076797,0.00001183064,0.0001848225,0.0001037633,0.00005512703],"category_scores_gemma":[0.0001278519,0.000076324,0.0000242985,0.0001705925,0.0002780138,0.000005533494,0.0001023438,0.0001277167,0.00000489398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002345885,"about_ca_system_score_gemma":0.0000288479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812519,"about_ca_topic_score_gemma":0.00002645822,"domain_scores_codex":[0.9986574,0.0002720558,0.0001983675,0.0003712478,0.0002509681,0.0002499603],"domain_scores_gemma":[0.9993096,0.00003653055,0.00004030774,0.0003385701,0.0002014815,0.00007350926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008102434,0.00005836738,0.003293221,0.00007230443,0.000009883771,0.000002294156,0.00037271,0.00001288038,0.9901646,0.0000689833,0.0003714962,0.005492213],"study_design_scores_gemma":[0.003041512,0.0008763015,0.06630449,0.0001469534,0.00001331044,0.0000101862,0.004406113,0.0002581466,0.8622676,0.0009665425,0.06126997,0.0004388725],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885306,0.009696269,0.0003959564,0.0003133986,0.00004677868,0.000290939,0.00002056767,0.000004683953,0.0007008194],"genre_scores_gemma":[0.9937988,0.005474958,0.000180762,0.00002209116,0.00005074546,0.00006022916,0.000006739951,0.000007747168,0.00039795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.127897,"threshold_uncertainty_score":0.3112403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040607104","doi":"10.1371/journal.pone.0013066","title":"Ontology-Based Meta-Analysis of Global Collections of High-Throughput Public Data","year":2010,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":373,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Nexen (Canada)","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Data science; Context (archaeology); Computer science; Data mining; Ontology; DNA microarray; Systems biology; Public domain; Computational biology; Biology; Genetics; Gene; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1786814345115131,"gpt":0.3160648088762007,"spread":0.1373833743646876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001449198,0.00007880633,0.0003712325,0.00007207752,0.00004393422,0.000008991306,0.0003604359,0.0001235523,0.0003802013],"category_scores_gemma":[0.0001549051,0.00006910773,0.0001786848,0.0006827741,0.00009455595,0.000003939276,0.00009562205,0.00005662478,0.000001516551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006307443,"about_ca_system_score_gemma":0.0001646721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000102786,"about_ca_topic_score_gemma":0.002177696,"domain_scores_codex":[0.9991346,0.00005415954,0.0002336443,0.0003037618,0.0001747288,0.00009909043],"domain_scores_gemma":[0.9983649,0.00001172671,0.0001884057,0.001159098,0.0002271449,0.00004868516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002837736,0.0009107951,0.002322328,0.00001443232,0.03132118,8.070892e-8,0.000003442327,0.0000223243,0.9621542,0.0005849907,0.002587262,0.00005062761],"study_design_scores_gemma":[0.0004675876,0.0001446448,0.006477021,0.000001802121,0.06766116,3.745712e-7,0.00002413258,0.001019708,0.9190786,0.0001320786,0.004842951,0.0001499638],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895511,0.0005416179,0.004371737,0.002077982,0.00007856402,0.0001996369,0.00124906,0.00001380038,0.001916484],"genre_scores_gemma":[0.9928878,0.00001866479,0.00569671,0.0001135006,0.00002914985,0.00002742502,0.0008105146,0.000005029672,0.0004112177],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04307559,"threshold_uncertainty_score":0.4162938,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0116415277658399,"gpt":0.3172743099225427,"spread":0.3056327821567029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001501975,0.0001543405,0.0001739096,0.0001746217,0.00006569173,0.00002541709,0.0002802066,0.0001437854,0.000006222986],"category_scores_gemma":[0.00003439376,0.0001371942,0.00002100922,0.000503482,0.00008884055,0.000003247243,0.0001097968,0.00009095197,0.000004637919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002288566,"about_ca_system_score_gemma":0.0000735633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002640857,"about_ca_topic_score_gemma":0.0002258291,"domain_scores_codex":[0.9986243,0.00006959488,0.0002785963,0.0007447324,0.00008569614,0.0001970546],"domain_scores_gemma":[0.998877,0.00001969473,0.00007685745,0.0008152878,0.00007838134,0.0001327619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001387084,0.0001500723,0.01118249,0.000004246129,0.00007268831,7.936789e-7,0.0000341223,0.002239775,0.8388838,0.05724917,0.0001849222,0.08985922],"study_design_scores_gemma":[0.002291093,0.003019528,0.6985397,0.00002295812,0.0009301742,0.00002335668,0.000284157,0.07314452,0.06044634,0.02418127,0.1354433,0.001673544],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1055784,0.0003197217,0.8927634,0.0004005783,0.00001226798,0.0005308639,0.0001294905,0.000009498585,0.0002557784],"genre_scores_gemma":[0.9446864,0.0001395787,0.05039243,0.0005118342,0.0000384506,0.0001712715,0.004029954,0.00001110464,0.00001894695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8423709,"threshold_uncertainty_score":0.5594615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030818161","doi":"10.1016/j.patcog.2010.12.015","title":"Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds","year":2010,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":347,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Actua; University of Waterloo","funders":"","keywords":"Principal component analysis; Dimensionality reduction; Pattern recognition (psychology); Visualization; Artificial intelligence; Mathematics; Generalization; Regression; Linear subspace; Linear discriminant analysis; Supervised learning; Regression analysis; Computer science; Machine learning; Statistics; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.02665332832183567,"gpt":0.2872518598011516,"spread":0.260598531479316,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000161797,0.0001296978,0.000108593,0.0001449266,0.0001157838,0.00005560956,0.00005612362,0.0001459769,0.00004967024],"category_scores_gemma":[0.00003017315,0.000113645,0.00003868043,0.0001408655,0.00004831353,0.0000092321,0.00003343001,0.00008491678,0.000008105985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005989457,"about_ca_system_score_gemma":0.00001252172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000137658,"about_ca_topic_score_gemma":0.0001394499,"domain_scores_codex":[0.9991034,0.00007646697,0.000172794,0.0003974898,0.0001362531,0.0001136102],"domain_scores_gemma":[0.999469,0.00001104113,0.0001150989,0.0002161612,0.00010134,0.00008736162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00006154053,0.00007392538,0.09757623,0.00002094662,0.0000517212,3.703211e-7,0.0001141912,0.000001354114,0.8544552,0.00003519574,0.000208228,0.04740113],"study_design_scores_gemma":[0.0007508991,0.0001638803,0.8013076,0.00003456383,0.0001465088,0.00000690563,0.00026604,0.003928589,0.1899954,0.00008552623,0.003040802,0.0002732924],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953225,0.0000797993,0.003770106,0.0002866881,0.0001266543,0.0001659801,0.00001874611,0.00002038221,0.0002091043],"genre_scores_gemma":[0.9979287,0.0003700764,0.0001177379,0.0002303708,0.0001354407,0.00005324617,0.001085486,0.00001400194,0.00006494929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7037314,"threshold_uncertainty_score":0.4634309,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022441134","doi":"10.1093/bioinformatics/btg182","title":"Class prediction and discovery using gene microarray andproteomics mass spectroscopy data: curses, caveats, cautions","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":332,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Curse of dimensionality; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Relevance (law); Data mining; Microarray analysis techniques; Identification (biology); Outlier; Machine learning; Biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02672686303689213,"gpt":0.270721456698394,"spread":0.2439945936615018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016134,0.0001427239,0.0001080956,0.00005231334,0.0001624988,0.00009888608,0.0001493769,0.0001380961,0.000004695149],"category_scores_gemma":[0.00003851781,0.00013321,0.00002862935,0.00009610545,0.00007403421,0.00004750143,0.00007251379,0.00008040398,0.000003133748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003383332,"about_ca_system_score_gemma":0.0001647615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005349584,"about_ca_topic_score_gemma":0.000005396958,"domain_scores_codex":[0.9991549,0.00003253181,0.0002742917,0.00022886,0.0001142922,0.0001951745],"domain_scores_gemma":[0.9991248,0.000003783961,0.0001351605,0.0006108661,0.00004454256,0.00008090024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001734975,0.00002247456,0.001806108,0.00002800284,0.0000245255,2.497175e-7,0.00004507237,0.0001073347,0.9937503,0.0003752942,0.003649843,0.0001734629],"study_design_scores_gemma":[0.0007975999,0.0001135847,0.001028959,0.00003228048,0.00006597338,0.0000646655,0.0004323355,0.01467741,0.8888269,0.000139671,0.09350351,0.0003170893],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4786457,0.001299118,0.5162196,0.0001173228,0.0006932209,0.0004699252,0.0005660174,0.00003167191,0.001957531],"genre_scores_gemma":[0.8009924,0.002766727,0.1923028,0.0003542175,0.0003685787,0.00002756982,0.002315417,0.00004316487,0.0008292151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3239168,"threshold_uncertainty_score":0.5432148,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756063524","doi":"10.1016/j.ejor.2017.08.040","title":"High dimensional data classification and feature selection using support vector machines","year":2017,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":320,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature selection; Support vector machine; Binary classification; Classifier (UML); Artificial intelligence; Data mining; Machine learning; Big data; Linear classifier; Data classification","retraction":null,"screen_n_in":null,"score":{"opus":0.1663939795343459,"gpt":0.419157855783111,"spread":0.2527638762487652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002118877,0.00007608934,0.00008035844,0.00009239162,0.0006471375,0.0002502403,0.0004975635,0.00003819708,0.00005597701],"category_scores_gemma":[0.0005936411,0.00006156945,0.00002394739,0.00004767651,0.0001258344,0.00004858857,0.0002839213,0.0002444861,0.000006851935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002279441,"about_ca_system_score_gemma":0.0003062806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006329946,"about_ca_topic_score_gemma":0.000006034796,"domain_scores_codex":[0.9985649,0.0004085336,0.0002061654,0.0002419038,0.0004543282,0.0001241998],"domain_scores_gemma":[0.9985773,0.00001319691,0.0001925779,0.0004170167,0.0006985162,0.00010142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001710931,0.00003837301,0.00370592,0.000005559924,0.00002688244,0.000007133406,0.00001739605,0.0001140185,0.9566143,0.0003325498,0.03332504,0.005641788],"study_design_scores_gemma":[0.001722779,0.0008025425,0.8261345,0.00007913789,0.00002739595,0.0004944432,0.00008266927,0.01261397,0.04031017,0.00008919367,0.11738,0.0002631941],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903306,0.0003496031,0.002287053,0.005501941,0.0003376169,0.0001180214,0.00003568859,0.000002731162,0.001036735],"genre_scores_gemma":[0.9932027,0.00009853783,0.00416811,0.00006916626,0.001053543,8.227538e-7,0.0001605559,0.00001617684,0.001230419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9163041,"threshold_uncertainty_score":0.4977324,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121651329","doi":"10.1038/emboj.2013.19","title":"A new genome‐driven integrated classification of breast cancer and its implications","year":2013,"lang":"en","type":"review","venue":"The EMBO Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":314,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Biology; Breast cancer; Computational biology; Cancer; Disease; Genomics; Genome; Precision medicine; Systems biology; Bioinformatics; Genetics; Gene; Internal medicine; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.05723941050077306,"gpt":0.3436795071666428,"spread":0.2864400966658697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001482943,0.000198262,0.0003590882,0.00008276897,0.0001247413,0.00005202549,0.0004033984,0.0001725208,0.0001568089],"category_scores_gemma":[0.00001886947,0.000117269,0.0001648415,0.0001778834,0.00004242605,0.000005810046,0.00007161617,0.0002781673,0.00001202397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004365499,"about_ca_system_score_gemma":0.0007061895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001118777,"about_ca_topic_score_gemma":0.000004926303,"domain_scores_codex":[0.9989585,0.0001347429,0.0004310798,0.0002251355,0.0001072291,0.0001432619],"domain_scores_gemma":[0.9986231,0.0000118852,0.0006621493,0.0003414602,0.0002315416,0.0001298378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008161829,0.00001785163,0.000009237677,0.0002892058,0.0001574753,1.025507e-7,0.00003370041,0.000002647004,0.04596225,0.0001741437,0.01132724,0.942018],"study_design_scores_gemma":[0.0001378924,0.00002678858,0.001108058,0.0006861843,0.0002532429,0.0003227069,0.00004335024,0.00001060186,0.0001511202,0.00005375858,0.9970556,0.0001506541],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005951329,0.997072,0.0008204489,0.0007018861,0.0001400654,0.0003660156,0.00009669291,0.000004540044,0.0002032432],"genre_scores_gemma":[0.001400728,0.9961154,0.0001158821,0.00003416215,0.0005138069,0.00009082801,0.0001014134,0.00002830189,0.001599507],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9857284,"threshold_uncertainty_score":0.4782089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965843937","doi":"10.1016/s0168-9525(02)02665-3","title":"Statistical issues with microarrays: processing and analysis","year":2002,"lang":"en","type":"review","venue":"Trends in Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":299,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"","keywords":"DNA microarray; Biology; Statistical analysis; Data science; Computational biology; Microarray; Expression (computer science); Bioinformatics; Computer science; Gene expression; Genetics; Gene; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04904404139976733,"gpt":0.3654559646476433,"spread":0.316411923247876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006838616,0.000278839,0.0006116737,0.0003835956,0.00003793294,0.00004829168,0.000157181,0.0002648102,0.0000836832],"category_scores_gemma":[0.000006813396,0.0002159171,0.00009125936,0.000700758,0.00009886243,0.000001275082,0.00005898943,0.0001357248,0.000003195293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001818761,"about_ca_system_score_gemma":0.00005237942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000347316,"about_ca_topic_score_gemma":0.00003844941,"domain_scores_codex":[0.9987078,0.00008700694,0.0003222346,0.0005523071,0.0001288726,0.0002017887],"domain_scores_gemma":[0.9993568,0.000006762261,0.0001611684,0.0003646764,0.00003352997,0.00007705214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005499875,0.0000338201,0.000254046,0.000666328,0.0001396809,0.000003051127,0.00002744264,0.000008650212,0.00004676889,0.000004437527,0.001558141,0.9972521],"study_design_scores_gemma":[0.0001514034,0.00009393045,0.0003654649,0.0003630388,0.001069293,0.00001126228,0.00001678757,0.00007161466,0.00004394001,0.000002906852,0.9975116,0.0002987116],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00008589745,0.9977868,0.001335262,0.00001798179,0.00002573682,0.00008687087,0.00005209028,0.000007022262,0.0006024051],"genre_scores_gemma":[0.0003659254,0.9903291,0.00509893,0.00001708571,0.00009455284,0.00004885922,0.0007225109,0.00003636013,0.003286611],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9969534,"threshold_uncertainty_score":0.8804842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050498681","doi":"10.1016/j.jmva.2006.11.002","title":"A test for the mean vector with fewer observations than the dimension","year":2006,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":278,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Independent and identically distributed random variables; Dimension (graph theory); Multivariate random variable; Scalar (mathematics); Statistics; Invariant (physics); Algorithm; Random variable; Combinatorics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01884784882125826,"gpt":0.2655927098441703,"spread":0.246744861022912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003083881,0.00008099941,0.0001205703,0.00005672638,0.0001908534,0.00003753858,0.0001884,0.00004383757,0.000007685617],"category_scores_gemma":[0.00008736634,0.00003551713,0.0002253655,0.0003288614,0.00003507067,0.000005421361,0.00001912783,0.00006614413,4.337271e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000128052,"about_ca_system_score_gemma":0.00005440414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009096544,"about_ca_topic_score_gemma":0.0003303094,"domain_scores_codex":[0.9993491,0.00004854875,0.0002338767,0.0001116278,0.0001626578,0.00009418298],"domain_scores_gemma":[0.9989092,0.0001060012,0.00034388,0.0002603746,0.0003540994,0.00002646995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001813912,0.0001273093,0.01709544,0.000002762365,0.0009035411,5.93554e-7,0.0001055911,0.01096063,0.9654827,0.0001701408,0.004432532,0.0005373857],"study_design_scores_gemma":[0.001546531,0.0004013773,0.7975907,0.00001995069,0.002925687,0.00001112389,0.0005854507,0.01088635,0.1072805,0.0001178414,0.07844045,0.0001940798],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8431386,0.0008397836,0.1479258,0.007566154,0.0001435406,0.0002618526,0.00001850479,0.000004827152,0.0001008528],"genre_scores_gemma":[0.9972886,0.00004633849,0.001376182,0.0001351643,0.0003041734,0.00001465218,0.00002327983,0.000008472508,0.0008031321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8582022,"threshold_uncertainty_score":0.146791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060749612","doi":"10.1038/ncomms1033","title":"Identification of high-quality cancer prognostic markers and metastasis network modules","year":2010,"lang":"en","type":"article","venue":"Nature Communications","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":263,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; National Research Council Canada; Biotechnology Research Institute","funders":"","keywords":"Breast cancer; Metastasis; Gene signature; Robustness (evolution); Gene; Cancer; Estrogen receptor; Microarray; Oncology; DNA microarray; Computational biology; Identification (biology); Bioinformatics; Medicine; Internal medicine; Biology; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01691715580896638,"gpt":0.3293116128362627,"spread":0.3123944570272963,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003490048,0.00008202822,0.0001025679,0.00002641197,0.0001383764,0.00001829906,0.0004185856,0.0002184204,0.00001191344],"category_scores_gemma":[0.0002198341,0.00007760061,0.00003960235,0.0001547112,0.0001669689,0.000005781544,0.0001738097,0.0002973476,8.738876e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005313751,"about_ca_system_score_gemma":0.00004721681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003829877,"about_ca_topic_score_gemma":0.0007054334,"domain_scores_codex":[0.9992323,0.000124058,0.0002534388,0.0001971516,0.00009856586,0.00009449985],"domain_scores_gemma":[0.9982722,0.00004409114,0.0002169964,0.001219905,0.000201181,0.00004561881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002527332,0.00005662774,0.01476209,0.00001310255,0.00004769154,1.498984e-8,0.00002092015,0.00002731573,0.958802,0.01067586,0.004253873,0.0113152],"study_design_scores_gemma":[0.0003182729,0.00002897711,0.7550761,0.0000180976,0.00007793115,0.00000201873,0.00007034185,0.0001957845,0.1795339,0.001092755,0.06339128,0.0001945614],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883223,0.007720544,0.0007947515,0.002184114,0.0003078305,0.0002509643,0.00009200972,0.00001517404,0.0003122786],"genre_scores_gemma":[0.9932534,0.002071424,0.004009376,0.0001201331,0.00007934834,0.0001082174,0.0002180237,0.00001053389,0.000129546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7792681,"threshold_uncertainty_score":0.3164461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150688669","doi":"10.1200/jco.2007.12.0352","title":"Three-Gene Prognostic Classifier for Early-Stage Non–Small-Cell Lung Cancer","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":261,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Oncology; Internal medicine; Concordance; Lung cancer; Microarray; Hazard ratio; TaqMan; Gene; Gene expression; Real-time polymerase chain reaction; Biology; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.09386054127647486,"gpt":0.4408110976917573,"spread":0.3469505564152824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002558634,0.0001435903,0.0004998349,0.00007300443,0.00006143702,0.00001383134,0.0003093331,0.0005642112,0.00004643822],"category_scores_gemma":[0.0007385784,0.0001122398,0.0004077303,0.00008937676,0.00009878676,0.0000064499,0.00006171369,0.0003729896,0.000003177674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005127238,"about_ca_system_score_gemma":0.00115647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001169199,"about_ca_topic_score_gemma":0.0001782635,"domain_scores_codex":[0.9977186,0.00008623155,0.00143509,0.0002779527,0.0001775232,0.0003046529],"domain_scores_gemma":[0.9972496,0.0003165345,0.001380398,0.0002346118,0.0005202805,0.000298579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004826047,0.001237286,0.3276848,0.00008753243,0.0003524975,0.00004509895,0.00006989689,0.0001127665,0.4970935,0.00006983581,0.04253277,0.125888],"study_design_scores_gemma":[0.006422848,0.005885876,0.3431743,0.00004684032,0.0002646421,0.00002015332,0.00009807933,0.0003205049,0.1121002,0.0001214196,0.5312649,0.0002802556],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8814226,0.00120373,0.1125662,0.0009194541,0.002006256,0.0003579154,0.000009867813,0.000004035161,0.001509926],"genre_scores_gemma":[0.9849852,0.0007138617,0.007989392,0.001199783,0.002875698,0.00003176034,0.00001019755,0.00002778569,0.00216627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4887321,"threshold_uncertainty_score":0.4577005,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005989052","doi":"10.1038/ng.282","title":"A transcriptome atlas of rice cell types uncovers cellular, functional and developmental hierarchies","year":2009,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":245,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Biology; Transcriptome; Laser capture microdissection; Cell type; Gene expression profiling; Gene; Genetics; Computational biology; Gene expression; Oryza sativa; Cell; Cell biology","retraction":null,"screen_n_in":null,"score":{"opus":0.006843994587758041,"gpt":0.2203817493830641,"spread":0.2135377547953061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004515679,0.0001018669,0.00008008313,0.00004725993,0.00004373429,0.000009492841,0.00008264692,0.0002109697,0.00001515227],"category_scores_gemma":[0.000009915441,0.00009454026,0.00003831527,0.00009251571,0.00004413456,0.000002148515,0.0000186332,0.0001203915,0.000002070812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008898744,"about_ca_system_score_gemma":0.00007896968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.330529e-7,"about_ca_topic_score_gemma":0.000001604177,"domain_scores_codex":[0.9993944,0.00001914846,0.0001228692,0.0002159724,0.0001400636,0.000107534],"domain_scores_gemma":[0.9997183,0.000004597629,0.00004830463,0.0001162189,0.00006047301,0.00005209933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007462143,0.00003919111,0.001104697,0.00001497161,0.00001170898,3.718852e-7,0.00006972081,0.00002673954,0.9923233,0.00003583724,0.004872141,0.001426667],"study_design_scores_gemma":[0.0003991818,0.0001431174,0.02275971,0.000005374111,0.00001381658,0.000003998792,0.00009002126,0.00001059825,0.8824366,0.00009661075,0.09392931,0.0001116259],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.98711,0.008668569,0.0007230313,0.0001484606,0.0001709807,0.00008097888,0.00001361949,0.000006115324,0.00307827],"genre_scores_gemma":[0.9949139,0.0006684312,0.002685511,0.000350581,0.0001027452,0.000002848454,0.00006549584,0.000007720412,0.001202789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1098867,"threshold_uncertainty_score":0.385524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080120324","doi":"10.3389/fmicb.2012.00019","title":"The genes and enzymes of phosphonate metabolism by bacteria, and their distribution in the marine environment","year":2012,"lang":"en","type":"article","venue":"Frontiers in Microbiology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":244,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Phosphonate; Catabolism; Bacteria; Biochemistry; Gene; Enzyme; Biology; Metabolic pathway; Metagenomics; Genome; Biosynthesis; Metabolism; Lyase; Chemistry; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.00324793747976693,"gpt":0.182292534817787,"spread":0.1790445973380201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002540495,0.00007627054,0.00009285793,0.00001259678,0.00003827735,0.000005509474,0.0000973788,0.00008308223,0.000003634499],"category_scores_gemma":[0.000009006381,0.00004304655,0.00001566156,0.00002795539,0.0001744545,0.000002858232,0.00008004107,0.00004902952,1.988966e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007652573,"about_ca_system_score_gemma":0.000006163654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001504768,"about_ca_topic_score_gemma":0.00000750357,"domain_scores_codex":[0.99946,0.0001321557,0.0001255524,0.000127201,0.00001362971,0.0001415048],"domain_scores_gemma":[0.9997705,0.0000108044,0.00005724261,0.0001406124,0.000005061115,0.00001577555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004760942,0.00002418625,0.02313694,0.000002856019,0.00001056308,2.797767e-8,0.0001239546,3.891483e-7,0.9530892,0.000057376,0.007720663,0.01578626],"study_design_scores_gemma":[0.0002494931,0.00002073761,0.05034553,0.000001596709,0.000003819435,0.000005020823,0.0004740832,0.000003881342,0.4640161,0.00006117225,0.4847665,0.00005201588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9478715,0.05048976,0.0008900886,0.0003360908,0.0002109288,0.0001178051,0.00006317472,8.750962e-7,0.00001975084],"genre_scores_gemma":[0.9873158,0.01199294,0.000186645,0.00008511309,0.00002917164,0.00002690127,0.0002771278,0.000003927756,0.00008237646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4890731,"threshold_uncertainty_score":0.1755387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992794281","doi":"10.1093/nar/gnh123","title":"Comprehensive comparison of six microarray technologies","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":243,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Canada","funders":"Health Canada","keywords":"Biology; Microarray; Gene chip analysis; Computational biology; DNA microarray; Microarray databases; Consistency (knowledge bases); Oligonucleotide; Microarray analysis techniques; Bioinformatics; Gene expression; Gene; Genetics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0679635767384071,"gpt":0.3859108987869891,"spread":0.3179473220485821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001671489,0.00008864133,0.0001363386,0.0001364966,0.000111045,0.00001653231,0.0003949624,0.0001947969,0.00002400072],"category_scores_gemma":[0.0001021022,0.00007951904,0.00005361223,0.0002963888,0.0003878121,0.000002925359,0.0002188099,0.000220248,0.00003913214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003201918,"about_ca_system_score_gemma":0.0001133948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001861919,"about_ca_topic_score_gemma":0.000006725164,"domain_scores_codex":[0.9988779,0.00006717798,0.0001923613,0.0002970437,0.0003087098,0.0002568397],"domain_scores_gemma":[0.9990481,0.00001315826,0.0000558991,0.0005053386,0.0003346861,0.00004285544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006521512,0.0001009289,0.002424473,0.00002495501,0.00001447144,5.054628e-7,0.0001185659,0.00005789865,0.9821214,0.0004182025,0.00551399,0.009139362],"study_design_scores_gemma":[0.0004207431,0.0002728114,0.003162836,0.000019839,0.00000182709,0.00000191532,0.0025919,0.000008814632,0.8614265,0.0003687622,0.1316473,0.00007666684],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934366,0.001830788,0.0008161957,0.0009494147,0.00006877272,0.000194544,0.000006702454,0.00003182801,0.002665094],"genre_scores_gemma":[0.9978312,0.0002652431,0.001463087,0.00002624645,0.00004278552,0.00002632496,0.00002503843,0.00001485367,0.0003052646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1261333,"threshold_uncertainty_score":0.3242693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2897133367","doi":"10.1093/bioinformatics/bty878","title":"BMDExpress 2: enhanced transcriptomic dose-response analysis workflow","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Canada","funders":"National Institute of Environmental Health Sciences; National Institutes of Health","keywords":"Workflow; Computer science; Software; Transcriptome; Software engineering; Data mining; Data science; Database; Operating system; Biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.0127195426686106,"gpt":0.2668319319701167,"spread":0.2541123893015061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002242649,0.0001434075,0.0001455129,0.0001511284,0.0001087406,0.00004589485,0.0002485839,0.0001429697,0.0001340848],"category_scores_gemma":[0.00005146385,0.0001277737,0.0001544415,0.0004269183,0.0001039137,0.000009499994,0.00004192216,0.00005231025,0.00009640239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001750604,"about_ca_system_score_gemma":0.00007618158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002228154,"about_ca_topic_score_gemma":0.00001412961,"domain_scores_codex":[0.9990706,0.00005415192,0.0003095627,0.0001832038,0.0001627092,0.0002197242],"domain_scores_gemma":[0.9991131,0.000009244523,0.0001205124,0.0005377756,0.0001183465,0.0001009689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007002221,0.00003514065,0.0001836549,0.00001188223,0.0001807349,1.507347e-7,0.0005861833,0.00007590882,0.978312,0.00002512407,0.006842582,0.01304646],"study_design_scores_gemma":[0.0006938564,0.0002448547,0.006666601,0.00001289923,0.0001420107,0.000001703891,0.0002091133,0.00384091,0.8834291,0.00003698003,0.104439,0.0002830936],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7500054,0.0001229453,0.2436288,0.0001585124,0.0003296876,0.0001854213,0.00002690385,0.00004127723,0.005501118],"genre_scores_gemma":[0.992379,0.00006213914,0.005286837,0.0004480881,0.0001885199,0.00002613656,0.00009485852,0.00001235597,0.001502101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2423736,"threshold_uncertainty_score":0.5210459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116146198","doi":"10.1161/01.cir.0000152105.79665.c6","title":"Using Peripheral Blood Mononuclear Cells to Determine a Gene Expression Profile of Acute Ischemic Stroke","year":2005,"lang":"en","type":"article","venue":"Circulation","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Medicine; Stroke (engine); Peripheral blood mononuclear cell; Cohort; Internal medicine; Pathology; Oncology; Immunology; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02077347495911201,"gpt":0.2664586511663781,"spread":0.2456851762072661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005484005,0.0001006083,0.00009627201,0.00005046439,0.00004900798,0.00001204846,0.00009791845,0.0001068013,0.0000626244],"category_scores_gemma":[0.000006984402,0.0001027775,0.00006162226,0.00007604453,0.0000165567,0.00000915594,0.00004837568,0.00003831592,0.000006533673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002144926,"about_ca_system_score_gemma":0.00003860694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002529763,"about_ca_topic_score_gemma":7.930503e-7,"domain_scores_codex":[0.9992599,0.00002612722,0.0001990814,0.0002655171,0.0001209414,0.0001283785],"domain_scores_gemma":[0.9994565,0.000001610395,0.0001125912,0.0002843098,0.00007728107,0.00006768206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005240837,0.00004562113,0.001041764,0.000008169383,0.00001929949,2.380156e-7,0.00008106919,0.003240643,0.9925298,0.000001078445,0.000604171,0.002375753],"study_design_scores_gemma":[0.0003968342,0.00004135781,0.002547526,0.00001619766,0.00003501756,0.000005440629,0.00001916529,0.004928069,0.9885062,0.000001211124,0.003386388,0.0001165942],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821834,0.00008765527,0.01693838,0.00003885731,0.00006256952,0.0002011421,0.00002146765,0.00001084036,0.000455695],"genre_scores_gemma":[0.9818729,0.00001678603,0.01739895,0.00009167888,0.000222179,0.00001767343,0.00006965414,0.00001999131,0.0002901664],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004023587,"threshold_uncertainty_score":0.4191146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168980979","doi":"10.1093/bioinformatics/btq498","title":"Model-based clustering of microarray expression data via latent Gaussian mixture models","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Bayesian information criterion; Cluster analysis; Covariance; Expectation–maximization algorithm; Computer science; Model selection; Gene chip analysis; Data mining; Gaussian; Statistical model; Bayesian probability; Artificial intelligence; Mathematics; Statistics; DNA microarray; Gene expression; Biology; Gene; Genetics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.03102465879333444,"gpt":0.266033582338828,"spread":0.2350089235454936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001517125,0.0001339526,0.0001173166,0.00005307891,0.00005739375,0.00002060832,0.0004979389,0.000205851,0.00001368661],"category_scores_gemma":[0.00001897257,0.0001106229,0.0000484694,0.00006197183,0.00005252165,0.00002051487,0.0002249605,0.0001208508,0.000003815399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005273337,"about_ca_system_score_gemma":0.0001023917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002577998,"about_ca_topic_score_gemma":0.00001367956,"domain_scores_codex":[0.999155,0.00001249969,0.0003293416,0.0001879044,0.000156835,0.0001584099],"domain_scores_gemma":[0.9985076,0.000003631675,0.0002000916,0.001128451,0.0000736997,0.00008659292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003755903,0.00003565833,0.00004171414,0.00007162154,0.000006419621,8.695088e-8,0.00008599438,0.01171126,0.9807997,0.00001886306,0.003915119,0.00327599],"study_design_scores_gemma":[0.0002527685,0.00002231182,0.00002913289,0.00002145014,0.000006920661,0.000001820268,0.00002123049,0.613032,0.3833612,0.00004562673,0.003105258,0.0001003372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05385277,0.00008337088,0.9435609,0.0001299105,0.0002712298,0.0001925958,0.0001008608,0.00001892604,0.001789422],"genre_scores_gemma":[0.8817456,0.0000289608,0.1171527,0.0001854776,0.00006646309,0.000008997255,0.0006619159,0.00001529466,0.000134644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8278928,"threshold_uncertainty_score":0.4511069,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978392040","doi":"10.1016/s0014-5793(03)01275-4","title":"Molecular classification of cancer types from microarray data using the combination of genetic algorithms and support vector machines","year":2003,"lang":"en","type":"article","venue":"FEBS Letters","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":218,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Genetics; National High-tech Research and Development Program","keywords":"Support vector machine; Multiclass classification; Class (philosophy); Algorithm; Computer science; Identification (biology); Artificial intelligence; Microarray analysis techniques; Feature (linguistics); Set (abstract data type); Machine learning; Pattern recognition (psychology); Data mining; Gene; Biology; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02616442849578652,"gpt":0.2889537724358807,"spread":0.2627893439400942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000877134,0.00007531892,0.00008250184,0.00002512532,0.00003151155,0.000008980483,0.0001739403,0.00004994532,0.00001856944],"category_scores_gemma":[0.00002593249,0.00005999758,0.00002175206,0.00006640382,0.00008303407,0.000004597214,0.00003314375,0.00003501383,2.848168e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007542651,"about_ca_system_score_gemma":0.00004361811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001310781,"about_ca_topic_score_gemma":0.0000179917,"domain_scores_codex":[0.9993623,0.00007759409,0.0001657619,0.000225536,0.00009672306,0.00007208037],"domain_scores_gemma":[0.9993281,0.000007712762,0.0001571162,0.000438407,0.00004847519,0.00002023795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000115363,0.00001827773,0.008337843,0.00001041178,0.0000349525,1.630414e-7,0.00004728256,0.00007950296,0.9888428,0.00002606741,0.0005093355,0.002081829],"study_design_scores_gemma":[0.000297321,0.00002496701,0.06460807,0.0000126989,0.00005363572,0.000001462762,0.00004904067,0.001175415,0.9292404,0.00002687165,0.004425034,0.00008505618],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873055,0.001623074,0.01011669,0.0005927022,0.0001327034,0.0001142328,0.00007530792,0.000002416246,0.00003733605],"genre_scores_gemma":[0.9975377,0.0001446367,0.001736902,0.0003209355,0.00003592324,0.000008241788,0.0001865367,0.00001071114,0.00001843159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05960238,"threshold_uncertainty_score":0.244663,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145517878","doi":"10.1186/1471-2164-6-126","title":"Fish and chips: Various methodologies demonstrate utility of a 16,006-gene salmonid microarray","year":2005,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":205,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vancouver General Hospital; Simon Fraser University; University of Victoria","funders":"Division of Ocean Sciences; Genome Canada; Fisheries and Oceans Canada; Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland; Genome British Columbia","keywords":"Biology; DNA microarray; Microarray; Transcriptome; Computational biology; Gene; Genetics; Microarray analysis techniques; Complementary DNA; Expressed sequence tag; Gene chip analysis; Gene expression profiling; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.04837674175422345,"gpt":0.294628585448131,"spread":0.2462518436939075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002938888,0.0001277523,0.0001558757,0.00003277748,0.00005400957,0.00001630854,0.0001562347,0.0001524887,0.00001830096],"category_scores_gemma":[0.00007142429,0.0001229063,0.00006561099,0.00005051285,0.0001136377,0.000003273323,0.00009462635,0.00006290182,0.000002288545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001629393,"about_ca_system_score_gemma":0.0001128841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001920998,"about_ca_topic_score_gemma":0.0002146512,"domain_scores_codex":[0.9990978,0.0001132479,0.000243758,0.000326704,0.00005727218,0.0001612112],"domain_scores_gemma":[0.9993683,0.00002046132,0.0001351925,0.0003617209,0.00005279101,0.00006159575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001238578,0.00003218755,0.002743576,0.00002041636,0.00001971705,1.062824e-7,0.00008894996,0.00004076505,0.9766794,0.00001181363,0.001668198,0.01857094],"study_design_scores_gemma":[0.0003668352,0.00006725374,0.01426864,0.0000040045,0.00001819917,0.00001115779,0.0001831421,0.00009262294,0.9423429,0.0001823416,0.04232778,0.0001351224],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746923,0.001424039,0.02256526,0.000187857,0.00008148096,0.0001425284,0.00004969714,0.00001141527,0.0008453602],"genre_scores_gemma":[0.9428275,0.0007071444,0.05570906,0.0002397994,0.000117427,0.00001360653,0.00005656124,0.00001361073,0.0003153105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04065958,"threshold_uncertainty_score":0.5011973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158012006","doi":"10.1109/tcbb.2005.17","title":"Attribute Clustering for Grouping, Selection, and Classification of Gene Expression Data","year":2005,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Pattern Discovery Technologies (Canada); University of Waterloo","funders":"Hong Kong Polytechnic University","keywords":"Cluster analysis; Tuple; Data mining; Selection (genetic algorithm); Computer science; Dimension (graph theory); Preprocessor; Expression (computer science); Data pre-processing; Feature selection; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04644094477285871,"gpt":0.3179398821988953,"spread":0.2714989374260366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001798654,0.000114067,0.0001148449,0.00009416818,0.0001900702,0.00001578421,0.0001552586,0.0001534934,0.000005181738],"category_scores_gemma":[0.0000322269,0.0001035869,0.00002911981,0.00007769634,0.00008015646,0.00002624472,0.00001502013,0.00006697048,0.000001403587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001079652,"about_ca_system_score_gemma":0.00004742749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001305151,"about_ca_topic_score_gemma":0.0000131856,"domain_scores_codex":[0.9992346,0.00003020971,0.0003189165,0.0002362152,0.00006719708,0.0001129001],"domain_scores_gemma":[0.9993457,0.00006960911,0.0001570425,0.0002511842,0.000125485,0.00005096442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003917217,0.0001891805,0.001120024,0.0001603329,0.0001136922,3.449707e-8,0.0002712981,0.02776298,0.8021449,0.0002127008,0.001587393,0.1660457],"study_design_scores_gemma":[0.002515468,0.0008388699,0.00738157,0.00007560835,0.00008383216,0.00005471209,0.000291622,0.65176,0.3149825,0.001006928,0.02053387,0.0004750717],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06601627,0.0001249288,0.9328046,0.0004388819,0.0001117967,0.0002158091,0.0002478316,0.00001419637,0.00002568646],"genre_scores_gemma":[0.8119479,0.0002040643,0.1868857,0.00015879,0.00008654338,0.00002840132,0.0006401439,0.000007301419,0.00004118341],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7459316,"threshold_uncertainty_score":0.422415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140427893","doi":"10.1158/1078-0432.ccr-04-0429","title":"Hierarchical Clustering Analysis of Tissue Microarray Immunostaining Data Identifies Prognostically Significant Groups of Breast Carcinoma","year":2004,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":203,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vancouver General Hospital; University of British Columbia; BC Cancer Agency","funders":"National Cancer Institute","keywords":"Breast cancer; Oncology; Tissue microarray; Clinical significance; Hierarchical clustering; Survival analysis; Internal medicine; Lymph node; Pathology; Medicine; Cancer; Biology; Cluster analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1505223680735656,"gpt":0.4697113693201739,"spread":0.3191890012466083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002338987,0.0001335418,0.0004204499,0.0002642406,0.00009598899,0.00003287648,0.001040078,0.0002104235,0.00008439867],"category_scores_gemma":[0.0008235996,0.0001193636,0.0001589668,0.0008857914,0.000798967,0.00001084844,0.0009173243,0.0003807673,0.000003017428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003705643,"about_ca_system_score_gemma":0.0006635551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00044341,"about_ca_topic_score_gemma":0.0002349507,"domain_scores_codex":[0.9970336,0.0004072758,0.0008772801,0.0007583489,0.0005522066,0.0003712995],"domain_scores_gemma":[0.9974934,0.0001930215,0.0002091194,0.001353219,0.0005808754,0.0001703213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0006894474,0.0002762708,0.02487235,0.00008106291,0.0004919289,0.000004222962,0.000114845,0.0002810342,0.9584917,0.0001075826,0.0004244559,0.01416515],"study_design_scores_gemma":[0.002108502,0.001011369,0.5458828,0.0001830263,0.0004887388,0.00000614022,0.0009556858,0.0008757832,0.4440128,0.0002576249,0.003830778,0.0003867706],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927018,0.001013918,0.004601098,0.0007255623,0.000154878,0.0003200993,0.0002890895,0.000007187664,0.0001863639],"genre_scores_gemma":[0.9977306,0.0006683826,0.0007526666,0.00003238532,0.0002148025,0.00004782337,0.0004013416,0.00002093065,0.0001311154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5210105,"threshold_uncertainty_score":0.4867506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999720425","doi":"10.1016/j.ajhg.2007.12.015","title":"Evaluation of Genetic Variation Contributing to Differences in Gene Expression between Populations","year":2008,"lang":"en","type":"article","venue":"The American Journal of Human Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":203,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; McGill University","keywords":"Biology; Genetics; International HapMap Project; Gene; Genetic variation; Expression quantitative trait loci; Gene expression; Population; Single-nucleotide polymorphism; Quantitative trait locus; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.08148144139945811,"gpt":0.3443999260844321,"spread":0.262918484684974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001033743,0.00009317527,0.0002120103,0.0001329048,0.0001273229,0.000007924795,0.0002598954,0.00003440428,0.000008548609],"category_scores_gemma":[0.0001399419,0.00007029067,0.00006199603,0.0002266744,0.0001003188,0.000003726374,0.00006082225,0.00008155376,6.913014e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003843974,"about_ca_system_score_gemma":0.0001439045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001649709,"about_ca_topic_score_gemma":0.00000838043,"domain_scores_codex":[0.998252,0.0004232226,0.000529972,0.0001318125,0.0005094518,0.0001535889],"domain_scores_gemma":[0.9983859,0.00001987647,0.0007447154,0.0002552463,0.0005320252,0.00006220441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003032192,0.00003207749,0.2225545,0.000001283973,0.00001776192,2.976109e-7,0.0004099377,0.002126077,0.768942,0.000003141996,0.00006790427,0.005814725],"study_design_scores_gemma":[0.0003766541,0.0004908047,0.8266511,0.00002124488,0.00005530039,0.000009480514,0.0001740928,0.0001201313,0.1717854,0.0002166716,0.0000282191,0.00007085033],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894454,0.0004424785,0.009745659,0.0001064289,0.00006654216,0.0001589423,0.000005114433,0.000001520923,0.00002789252],"genre_scores_gemma":[0.9968362,0.00010687,0.002736933,0.00004151003,0.0002402745,0.000007666074,0.000008335023,0.00001025372,0.00001196748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6040967,"threshold_uncertainty_score":0.286637,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034978601","doi":"10.1016/s0002-9440(10)64434-3","title":"Software Tools for High-Throughput Analysis and Archiving of Immunohistochemistry Staining Data Obtained with Tissue Microarrays","year":2002,"lang":"en","type":"article","venue":"American Journal Of Pathology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":203,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vancouver General Hospital","funders":"National Cancer Institute; National Institutes of Health","keywords":"Tissue microarray; Immunohistochemistry; DNA microarray; Pathology; Staining; Software; Throughput; Computational biology; Computer science; Biology; Bioinformatics; Medicine; Gene expression; Genetics; Operating system; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.0204996876350654,"gpt":0.2851276990646679,"spread":0.2646280114296026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002125667,0.000102998,0.0003210121,0.00009490912,0.0000463642,0.00001291156,0.0002865437,0.00004284326,0.00001284152],"category_scores_gemma":[0.0002106912,0.00008613906,0.00004905985,0.0001767458,0.0002830857,0.0000108298,0.00008395681,0.00008024914,1.219138e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007801386,"about_ca_system_score_gemma":0.00004954977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005558004,"about_ca_topic_score_gemma":0.000002325431,"domain_scores_codex":[0.9991513,0.00006737528,0.0003105262,0.0002457574,0.00008313905,0.0001419047],"domain_scores_gemma":[0.998661,0.0000585259,0.0006340957,0.0004354498,0.0001553792,0.00005558624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001552165,0.00003393904,0.001922685,0.00001459036,0.000215495,0.00000871111,0.0001727044,0.00005418128,0.9162527,0.000006332601,0.00026804,0.08089535],"study_design_scores_gemma":[0.002830682,0.005804907,0.01877676,0.00009492854,0.001231323,0.0009400197,0.004164109,0.0002381442,0.9546597,0.00008948163,0.01059565,0.0005743134],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7500974,0.0007567629,0.2488455,0.0001354202,0.00002445414,0.00005280379,0.00005228585,0.000002243256,0.00003313067],"genre_scores_gemma":[0.9366177,0.0002576219,0.06279857,0.0000780185,0.00007639844,0.000004837582,0.00009142406,0.0000120185,0.00006342391],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1865203,"threshold_uncertainty_score":0.3512649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158146385","doi":"10.1186/1751-0473-8-10","title":"The non-negative matrix factorization toolbox for biological data mining","year":2013,"lang":"en","type":"article","venue":"Source Code for Biology and Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Toolbox; Computer science; Matrix decomposition; Data mining; Non-negative matrix factorization; Data science; Factorization; Matrix (chemical analysis); Algorithm; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.05379666123036762,"gpt":0.3628653503258378,"spread":0.3090686890954701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002712736,0.00009953511,0.0001179923,0.00001874875,0.0002590826,0.000009644943,0.0002181554,0.0001665718,0.00001030643],"category_scores_gemma":[0.0006754777,0.00005498031,0.00002266931,0.00003770245,0.0002529992,0.00000380609,0.00007087961,0.00003915918,0.000001170946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004068266,"about_ca_system_score_gemma":0.00002485772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007714247,"about_ca_topic_score_gemma":0.00001205883,"domain_scores_codex":[0.9992736,0.00003737412,0.0001639914,0.0003232346,0.0000283659,0.0001734361],"domain_scores_gemma":[0.999282,0.0001675659,0.00009693676,0.0002973145,0.0001015653,0.0000545969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002421058,0.00001635394,0.003374697,0.00001757134,0.00005779845,2.295838e-8,0.0002103542,0.000003785886,0.8855258,0.0006878711,0.05871626,0.05114739],"study_design_scores_gemma":[0.001725986,0.001189465,0.003924547,0.00002129581,0.00003166255,0.000002782294,0.001922587,0.002116414,0.02252915,0.001799622,0.9645686,0.0001678503],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4021796,0.003010541,0.5840101,0.007870808,0.000722883,0.001637331,0.0002495618,0.00002506706,0.0002941001],"genre_scores_gemma":[0.992844,0.0006195863,0.001624718,0.0004843253,0.0006757528,0.0002938109,0.001699785,0.00001082971,0.001747168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9058524,"threshold_uncertainty_score":0.2242032,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149954962","doi":"10.1186/1471-2105-7-228","title":"A stable gene selection in microarray data analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene selection; Selection (genetic algorithm); Microarray analysis techniques; DNA microarray; Support vector machine; Computer science; Gene; Data mining; Significance analysis of microarrays; Microarray; Sample (material); Computational biology; Biology; Artificial intelligence; Genetics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02232773026539993,"gpt":0.2640294807481557,"spread":0.2417017504827558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001926141,0.00008789197,0.0001008117,0.0001543785,0.00004194013,0.00003584372,0.0002316793,0.00009625354,0.00002245797],"category_scores_gemma":[0.00001981122,0.00008275922,0.00004197379,0.0005328075,0.00001846202,0.00001256509,0.00008988152,0.00004562709,0.00001341755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002043673,"about_ca_system_score_gemma":0.00008718816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008793709,"about_ca_topic_score_gemma":0.0009769851,"domain_scores_codex":[0.999253,0.00002286988,0.000285208,0.0001825471,0.0001011933,0.0001552144],"domain_scores_gemma":[0.9993722,0.000003738002,0.0001072821,0.0004492078,0.00003887327,0.00002874159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008675913,0.0001789413,0.1282457,0.00007781985,0.0001175736,3.209275e-7,0.0000824724,0.02248474,0.805485,0.0001405166,0.04056619,0.002533964],"study_design_scores_gemma":[0.001223799,0.00007928676,0.1152406,0.00001300717,0.0001906735,0.000008668841,0.0002888941,0.469686,0.2787883,0.0001012521,0.1338769,0.0005027478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2237392,0.0004452696,0.7699481,0.00005883782,0.00009340797,0.0002384751,0.00009645036,0.00002794024,0.005352417],"genre_scores_gemma":[0.8086453,0.0001239797,0.1844859,0.0001869585,0.0002009784,0.00002572018,0.004087811,0.00001668662,0.002226582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5854621,"threshold_uncertainty_score":0.3374823,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169996531","doi":"10.1186/s12865-015-0113-0","title":"Immune cell subsets and their gene expression profiles from human PBMC isolated by Vacutainer Cell Preparation Tube (CPT™) and standard density gradient","year":2015,"lang":"en","type":"article","venue":"BMC Immunology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Sciences Centre; Memorial University of Newfoundland","funders":"Canadian Institutes of Health Research","keywords":"Vacutainer; Biology; Immune system; Gene expression; Peripheral blood mononuclear cell; Gene; Molecular biology; Cell; Immunology; Virology; Chemistry; Genetics; In vitro","retraction":null,"screen_n_in":null,"score":{"opus":0.01213817788316295,"gpt":0.2369250570543734,"spread":0.2247868791712104,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001581553,0.0002173652,0.0002172001,0.00004473743,0.0001519057,0.00003585378,0.0001346752,0.00028726,0.00001545425],"category_scores_gemma":[0.00002043967,0.0001799833,0.00004051665,0.00005075438,0.0001221952,0.00001174417,0.0001911606,0.0001104275,0.000004344893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002654956,"about_ca_system_score_gemma":0.00007481774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007040774,"about_ca_topic_score_gemma":0.00002651546,"domain_scores_codex":[0.9986918,0.0002113504,0.0002733442,0.0005168889,0.00008465223,0.0002219604],"domain_scores_gemma":[0.9991671,0.00001228896,0.0001739563,0.0004282144,0.0001269435,0.00009150013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006445893,0.00007019255,0.003063497,0.00001017674,0.00001774391,5.024315e-7,0.0003872341,0.000004245904,0.9913079,0.000004826726,0.004267363,0.0002217377],"study_design_scores_gemma":[0.001571381,0.0005315645,0.004902631,0.00001003355,0.00001816431,0.000007953388,0.0004911948,0.00008621282,0.9839326,0.0001403541,0.008093243,0.0002146857],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981205,0.01274792,0.005274529,0.0000495957,0.0001661303,0.0002927039,0.000068767,0.0000263944,0.0001689087],"genre_scores_gemma":[0.9970049,0.0004960531,0.0007359014,0.00004298531,0.00005905042,0.00004876589,0.000982004,0.00002355778,0.0006067426],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01579989,"threshold_uncertainty_score":0.7339504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110350344","doi":"10.1093/nar/gkt338","title":"INMEX—a web-based tool for integrative meta-analysis of expression data","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"KEGG; Visualization; Data visualization; Microarray databases; Annotation; Data mining; Computer science; Data integration; Identifier; Web application; Biology; Biological data; Gene expression profiling; Information retrieval; Bioinformatics; Gene ontology; World Wide Web; Gene; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.1720002399639334,"gpt":0.4150088590377898,"spread":0.2430086190738564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009791275,0.0001274386,0.0003530535,0.0002932671,0.0001108214,0.00004542964,0.000846025,0.0001582788,0.001078491],"category_scores_gemma":[0.0004690338,0.00008800381,0.0003202926,0.0006146921,0.0001577029,0.0000139436,0.0003404391,0.0001383431,0.00002007327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001736403,"about_ca_system_score_gemma":0.0001901891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003242509,"about_ca_topic_score_gemma":0.00001545125,"domain_scores_codex":[0.9981495,0.0002946548,0.0002842185,0.0005650255,0.0004458534,0.0002607242],"domain_scores_gemma":[0.9974802,0.0001029996,0.0001009788,0.001521594,0.0007124115,0.00008180178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007841251,0.00007847368,0.0003429333,0.0000155247,0.003599116,7.388996e-8,0.00003055849,0.00003679869,0.9265854,0.0000511027,0.06745347,0.001728166],"study_design_scores_gemma":[0.0005809743,0.0002585154,0.001735679,0.000006081439,0.003732627,1.356057e-7,0.0003670783,0.01030705,0.8994153,0.0001178354,0.08330894,0.0001698102],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9357179,0.002571997,0.05061065,0.003106943,0.0001264916,0.002679729,0.001138712,0.00003844906,0.004009087],"genre_scores_gemma":[0.9912606,0.00005031186,0.005157228,0.0001196897,0.00005153571,0.0004622681,0.0009823678,0.00001952179,0.001896432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05554271,"threshold_uncertainty_score":0.9998347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141954357","doi":"10.1007/s11222-016-9636-3","title":"On optimal multiple changepoint algorithms for large data","year":2016,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":191,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Division of Mathematical Sciences; Engineering and Physical Sciences Research Council; Isaac Newton Institute for Mathematical Sciences","keywords":"Dynamic programming; Pruning; Computer science; Algorithm; Quadratic growth; Segmentation; Market segmentation; Mathematical optimization; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04544760114604016,"gpt":0.3237773195000501,"spread":0.27832971835401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001388846,0.00007041523,0.0000610708,0.00001586817,0.00009818561,0.00001759203,0.0001137731,0.00003704236,0.000005581911],"category_scores_gemma":[0.0001403949,0.00005081514,0.00001063447,0.0000167682,0.00001621201,0.000001590249,0.000150696,0.00001956936,0.000001892921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004228289,"about_ca_system_score_gemma":0.00001871785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001629053,"about_ca_topic_score_gemma":0.000004477645,"domain_scores_codex":[0.9993981,0.00001444008,0.00009859628,0.0002886051,0.00005536576,0.0001448554],"domain_scores_gemma":[0.9995376,0.00005446091,0.00005397384,0.000264266,0.0000441619,0.00004557211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001816216,0.0001212204,0.0005841603,0.00004895483,0.000053157,0.000002325389,0.00009511984,0.00003107695,0.2447132,0.01866117,0.09096047,0.6445475],"study_design_scores_gemma":[0.007339788,0.001499548,0.006112367,0.0002026307,0.00004931964,0.00001780377,0.000344491,0.3251132,0.08645383,0.003315699,0.5686367,0.0009146925],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02673674,0.0001198638,0.9716559,0.000157186,0.0001578981,0.000111663,0.0009998144,0.000007010257,0.0000539096],"genre_scores_gemma":[0.949622,0.00006247389,0.0491537,0.0001937503,0.0002445943,0.000007602302,0.0004295645,0.00001262982,0.0002737312],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9228852,"threshold_uncertainty_score":0.2072181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3026693286","doi":"10.1038/s41598-020-64803-w","title":"Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services; National Institutes of Health; National Multiple Sclerosis Society; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health","keywords":"Parsing; Segmentation; Computer science; Artificial intelligence; Dice; Pattern recognition (psychology); Image segmentation; Measure (data warehouse); Natural language processing; Data mining; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04844342174854471,"gpt":0.3328887037370361,"spread":0.2844452819884913,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003485601,0.00009718971,0.0001037206,0.00008326957,0.0002122687,0.000120739,0.00008280016,0.00004700056,0.0002931499],"category_scores_gemma":[0.00004135619,0.00007892029,0.00007631668,0.0007745083,0.00006809139,0.000006944968,0.00005169066,0.00004520088,0.00002453947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000110101,"about_ca_system_score_gemma":0.0001047838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000371876,"about_ca_topic_score_gemma":0.00001485691,"domain_scores_codex":[0.9985107,0.00005685373,0.0002630132,0.0006936833,0.0003344996,0.0001412791],"domain_scores_gemma":[0.9989663,0.000002854544,0.0002290538,0.000536385,0.0001523437,0.0001130088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003007381,0.00001890492,0.03877496,0.000008409419,0.00006610654,0.00000741901,0.000171106,0.002577783,0.9244017,0.000001263955,0.0333159,0.0006263875],"study_design_scores_gemma":[0.0006468043,0.0003142115,0.09649348,0.00003213113,0.0006473147,0.0000613431,0.0009244072,0.004130832,0.7979304,0.00008887685,0.09815381,0.000576416],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851031,0.0000844688,0.01012864,0.002136857,0.0004275987,0.0001806545,0.000003549414,0.00002262479,0.001912542],"genre_scores_gemma":[0.9902979,0.000002256328,0.003285185,0.0005604223,0.00007176292,0.00002946064,0.0004645904,0.00001115551,0.005277294],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1264713,"threshold_uncertainty_score":0.3218276,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064237923","doi":"10.1006/geno.2001.6675","title":"Characterization of Variability in Large-Scale Gene Expression Data: Implications for Study Design","year":2002,"lang":"en","type":"article","venue":"Genomics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":185,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill Genome Centre; McGill University Health Centre","funders":"","keywords":"Replicate; Biology; Gene expression; Computational biology; Gene expression profiling; Gene; DNA microarray; Genetics; RNA; Biological system; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05720001007938594,"gpt":0.292345021835385,"spread":0.2351450117559991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005882562,0.00007293001,0.00009745316,0.00003459491,0.00004772153,0.00000855154,0.0002518995,0.00007477206,0.00001186117],"category_scores_gemma":[0.0000668416,0.00007398949,0.00002170513,0.00007901827,0.00001366109,0.000006710648,0.0001103339,0.00002932401,0.000001206493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001852826,"about_ca_system_score_gemma":0.000029444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001146066,"about_ca_topic_score_gemma":0.000006604345,"domain_scores_codex":[0.9991373,0.000120251,0.0002398243,0.0003485428,0.00004017677,0.0001138854],"domain_scores_gemma":[0.9989974,0.00001588702,0.0001140649,0.0007805625,0.00006174496,0.00003033689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003847852,0.0003801089,0.007629335,0.000006820794,0.000005223227,1.761821e-8,0.0001937461,0.00006694646,0.9892974,0.000007104944,0.0003050476,0.002069733],"study_design_scores_gemma":[0.0009764712,0.000135656,0.0743387,0.000004650649,0.00001572855,7.047669e-7,0.0001528353,0.003937896,0.9101885,0.0000924374,0.01001616,0.0001402551],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5925347,0.00003715794,0.4065115,0.00007655085,0.00005381718,0.0005662935,0.0001895875,0.000003984661,0.00002647973],"genre_scores_gemma":[0.9909368,0.0001216513,0.007752791,0.00004109497,0.00008133643,0.0001528911,0.0008073904,0.00001264908,0.00009341301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3987587,"threshold_uncertainty_score":0.3017204,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}