{"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","author_layer_release":"2026-06-26"},"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)","authors":[{"name":"Brendan J. Frey","is_ca":true},{"name":"Delbert Dueck","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005035858,0.001458078,0.001260995,0.003353351,0.001479555,0.002690773,0.002259393,0.002049085,0.00247825],"category_scores_gemma":[0.02317958,0.001053983,0.001054468,0.00307627,0.00140011,0.003645592,0.00298671,0.002388845,0.001623856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001336946,"about_ca_system_score_gemma":0.00134617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00231423,"about_ca_topic_score_gemma":0.001882395,"domain_scores_codex":[0.9952201,0.001374974,0.0004360293,0.001134229,0.001619732,0.0002148472],"domain_scores_gemma":[0.9878143,0.0058983,0.001065849,0.002594813,0.00236474,0.0002619813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009630579,0.0003277462,0.008793039,0.0008793217,0.0005308539,0.0003016817,0.002039601,0.1505029,0.05134729,0.05666303,0.008019519,0.719632],"study_design_scores_gemma":[0.0001737229,0.0005064922,0.004429281,0.000119435,0.0002474711,0.0003361338,0.0005664507,0.7822812,0.06541619,0.1177885,0.02797342,0.00016184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03119938,0.0002665187,0.9644821,0.0005661648,0.0001303404,0.0003555188,0.0002742414,0.001644868,0.00108082],"genre_scores_gemma":[0.2214265,0.0002813763,0.7730503,0.0002508067,0.0001647515,0.000745456,0.000951713,0.0002415799,0.002887499],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005035858,"threshold_uncertainty_score":0.02663249,"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","authors":[{"name":"Steffen Durinck","is_ca":false},{"name":"Paul T. Spellman","is_ca":false},{"name":"Ewan Birney","is_ca":false},{"name":"Wolfgang Huber","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008947399,0.004157401,0.00537162,0.009213435,0.003085177,0.003739532,0.006524035,0.002050383,0.1214247],"category_scores_gemma":[0.02718917,0.0026524,0.003323582,0.01293424,0.0009504007,0.003557617,0.005474584,0.005173627,0.0931298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382134,"about_ca_system_score_gemma":0.005601751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004248708,"about_ca_topic_score_gemma":0.006270681,"domain_scores_codex":[0.9950402,0.001145054,0.0008008096,0.001712563,0.0008235711,0.0004778008],"domain_scores_gemma":[0.9887242,0.004269199,0.001231606,0.003546164,0.001429938,0.0007989003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001590918,0.000170842,0.003685394,0.005334612,0.0008272965,0.0003961251,0.0008698832,0.00150907,0.01228212,0.02127714,0.9004349,0.05162169],"study_design_scores_gemma":[0.0007275362,0.0001657456,0.009437721,0.0008963386,0.0008008403,0.0007177947,0.0002774774,0.009003683,0.02538405,0.05470356,0.897594,0.0002912342],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.002773369,0.0006416228,0.2201265,0.0005292886,0.0007480278,0.0005552851,0.5567527,0.2106906,0.007182495],"genre_scores_gemma":[0.01301477,0.0004974372,0.3494246,0.0005116481,0.0001485539,0.00453899,0.5686747,0.05729251,0.005896795],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1214247,"threshold_uncertainty_score":0.4062062,"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","authors":[{"name":"Ben Vinegar","is_ca":true},{"name":"Hardeep K. Nahal-Bose","is_ca":true},{"name":"Ron Ammar","is_ca":true},{"name":"Greg Wilson","is_ca":true},{"name":"Nicholas J. Provart","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003740286,0.001852925,0.0008361927,0.004203639,0.0007883774,0.001812422,0.002564465,0.001697292,0.04528598],"category_scores_gemma":[0.008324001,0.0007679752,0.001262021,0.002706606,0.0006166136,0.002852932,0.001734161,0.002045939,0.01361362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009160431,"about_ca_system_score_gemma":0.002199568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003118776,"about_ca_topic_score_gemma":0.004315354,"domain_scores_codex":[0.9988882,0.0003226422,0.0001736025,0.0001344876,0.0004054486,0.00007566041],"domain_scores_gemma":[0.9944833,0.003235642,0.0002981235,0.000719673,0.0008776132,0.0003855901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009696357,0.0003704385,0.004449151,0.002431551,0.0001885752,0.001551946,0.000725346,0.004746461,0.0598526,0.03156073,0.6543798,0.2387739],"study_design_scores_gemma":[0.0004927026,0.0002504157,0.00856139,0.0009636324,0.0002142942,0.003962161,0.0004343017,0.09327495,0.07452174,0.05644584,0.7605188,0.000359849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004832503,0.0007224565,0.6726219,0.001429603,0.0003049852,0.0004797504,0.07193506,0.2340343,0.01363954],"genre_scores_gemma":[0.02687812,0.001347638,0.8658597,0.0008215493,0.0001150469,0.001786502,0.0856859,0.01175267,0.005752791],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04528598,"threshold_uncertainty_score":0.1514966,"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","authors":[{"name":"Bo Wang","is_ca":true},{"name":"Aziz M. Mezlini","is_ca":true},{"name":"Feyyaz Demir","is_ca":true},{"name":"Marc Fiume","is_ca":true},{"name":"Zhuowen Tu","is_ca":false},{"name":"Michael Brudno","is_ca":true},{"name":"Benjamin Haibe‐Kains","is_ca":true},{"name":"Anna Goldenberg","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002449431,0.0007757712,0.001390514,0.006513283,0.00078647,0.002215095,0.001300522,0.001135624,0.003464813],"category_scores_gemma":[0.01207268,0.0004859234,0.001772867,0.008232263,0.0005865227,0.004395023,0.003721216,0.001142587,0.001374399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009855184,"about_ca_system_score_gemma":0.0008353135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002274157,"about_ca_topic_score_gemma":0.003060606,"domain_scores_codex":[0.9971777,0.000445165,0.0003079633,0.0005641842,0.001317724,0.0001872202],"domain_scores_gemma":[0.9945374,0.001613571,0.0004468412,0.002007065,0.001152723,0.0002423679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001048163,0.0004509995,0.01841497,0.0005731809,0.0006500741,0.0007070553,0.000687518,0.05985802,0.06121989,0.06959478,0.01678772,0.7700077],"study_design_scores_gemma":[0.00004708474,0.0001987832,0.008553925,0.00007163492,0.0002232717,0.0006163612,0.0003455823,0.7778926,0.03815929,0.1559381,0.01786664,0.00008670786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02298035,0.0002563788,0.9688681,0.000214748,0.00007605876,0.0001585446,0.002173622,0.003862124,0.001410041],"genre_scores_gemma":[0.3309782,0.0003918554,0.6561834,0.0001757314,0.0001233142,0.000353494,0.008776956,0.0004369983,0.002580034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006513283,"threshold_uncertainty_score":0.012954,"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","authors":[{"name":"Shujun Huang","is_ca":true},{"name":"Nianguang Cai","is_ca":true},{"name":"P. Pacheco","is_ca":true},{"name":"Shavira Narrandes","is_ca":true},{"name":"Yang Wang","is_ca":true},{"name":"Wayne Wenzhong Xu","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011379,0.0007083343,0.001006748,0.002323401,0.0002429371,0.001019673,0.0007150696,0.001062857,0.001572904],"category_scores_gemma":[0.001737288,0.0002631099,0.0006532746,0.002579296,0.0005930459,0.001289698,0.0006402376,0.002025155,0.00111719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006476117,"about_ca_system_score_gemma":0.000883963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009150085,"about_ca_topic_score_gemma":0.0008332653,"domain_scores_codex":[0.9996222,0.00009424062,0.00004689953,0.00008349272,0.0001266091,0.00002653842],"domain_scores_gemma":[0.999119,0.0005247632,0.00005593848,0.00002627919,0.0002366571,0.00003736989],"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":[0.00003967128,0.00005923271,0.0006145706,0.004694944,0.00009476723,0.0001988407,0.0000644238,0.002146245,0.001192016,0.01239089,0.01292192,0.9655825],"study_design_scores_gemma":[0.0000194306,0.0001995023,0.002021699,0.003114244,0.0001641268,0.002244487,0.0001115811,0.005293967,0.003009063,0.02445457,0.9592699,0.00009740546],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0006269533,0.9851899,0.009869482,0.001152021,0.0006158769,0.00001448919,0.00004663062,0.00005010805,0.002434608],"genre_scores_gemma":[0.008742123,0.9817742,0.006735251,0.0004979217,0.0007379896,0.00002367506,0.0001129032,0.00001214761,0.0013639],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002323401,"threshold_uncertainty_score":0.006017864,"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","authors":[{"name":"Damian Smedley","is_ca":true},{"name":"Syed Haider","is_ca":false},{"name":"Benoît Ballester","is_ca":false},{"name":"Richard Holland","is_ca":false},{"name":"Darin London","is_ca":false},{"name":"Guðmundur Á. Þórisson","is_ca":false},{"name":"Arek Kasprzyk","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008323005,0.004203587,0.002680877,0.00399801,0.002132411,0.008354325,0.005839194,0.004205468,0.06989714],"category_scores_gemma":[0.02453628,0.002359906,0.003288682,0.005175422,0.002313423,0.009933572,0.00910904,0.004840482,0.09118365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001819972,"about_ca_system_score_gemma":0.002662895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001966839,"about_ca_topic_score_gemma":0.001513529,"domain_scores_codex":[0.992412,0.002105935,0.0012208,0.001608397,0.002205352,0.0004474894],"domain_scores_gemma":[0.9860799,0.006951982,0.0008370027,0.003637326,0.001517882,0.0009759649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001690047,0.0001221251,0.001560802,0.002701125,0.0002606517,0.0010685,0.0007672319,0.002561375,0.01229188,0.04700093,0.8366041,0.09337123],"study_design_scores_gemma":[0.0002121663,0.00007417145,0.000836498,0.0003539499,0.00006508576,0.0009243166,0.00009895964,0.0108246,0.01398059,0.04798282,0.9244707,0.0001762315],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002536125,0.003367457,0.2745215,0.003556204,0.00111885,0.0004205471,0.06341171,0.6174641,0.03360353],"genre_scores_gemma":[0.04986408,0.005723617,0.4432904,0.008261197,0.001433552,0.003022213,0.2437472,0.2144827,0.03017501],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.06989714,"threshold_uncertainty_score":0.2338293,"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","authors":[{"name":"Mei‐Ling Ting Lee","is_ca":true},{"name":"Frank C. Kuo","is_ca":true},{"name":"G. À. Whitmore","is_ca":true},{"name":"Jeffrey Sklar","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4349477,0.003455167,0.00767958,0.00668438,0.00361805,0.005906691,0.00815415,0.007822663,0.00130479],"category_scores_gemma":[0.7389513,0.003240919,0.005782176,0.009079381,0.01700516,0.009168137,0.004844711,0.01130573,0.0006279034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003486496,"about_ca_system_score_gemma":0.005988366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00206909,"about_ca_topic_score_gemma":0.002127894,"domain_scores_codex":[0.293879,0.5750791,0.03790332,0.0277697,0.06385333,0.001515585],"domain_scores_gemma":[0.1246591,0.7431009,0.02909886,0.08312883,0.01878448,0.001227709],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01147204,0.002333049,0.1576514,0.01689988,0.01673145,0.008846704,0.01178285,0.0517628,0.07846197,0.1335981,0.009553994,0.5009056],"study_design_scores_gemma":[0.002905451,0.01483223,0.1109782,0.004863516,0.007139218,0.006467278,0.002192194,0.3529337,0.07239334,0.3712752,0.05100595,0.003013717],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01937476,0.00272972,0.9704898,0.001327081,0.001222521,0.002803979,0.0002185212,0.0009064244,0.00092725],"genre_scores_gemma":[0.2338192,0.001323285,0.7486837,0.001165286,0.001031761,0.01197855,0.0004091876,0.0009609704,0.0006279493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5650523,"threshold_uncertainty_score":0.6968101,"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","authors":[{"name":"Damian Smedley","is_ca":false},{"name":"Syed Haider","is_ca":false},{"name":"Steffen Durinck","is_ca":false},{"name":"Luca Pandini","is_ca":false},{"name":"Paolo Provero","is_ca":false},{"name":"James E. Allen","is_ca":false},{"name":"Olivier Arnaiz","is_ca":false},{"name":"Mohammad Awedh","is_ca":false},{"name":"Richard Baldock","is_ca":false},{"name":"Giulia Barbiera","is_ca":false},{"name":"Philippe Bardou","is_ca":false},{"name":"Tim Beck","is_ca":false},{"name":"Andrew Blake","is_ca":false},{"name":"Merideth Bonierbale","is_ca":false},{"name":"Anthony J. Brookes","is_ca":false},{"name":"Gabriele Bucci","is_ca":false},{"name":"Iwan Buetti","is_ca":false},{"name":"Sarah Burge","is_ca":false},{"name":"Cédric Cabau","is_ca":false},{"name":"Joseph W. Carlson","is_ca":false},{"name":"Claude Chelala","is_ca":false},{"name":"Charalambos Chrysostomou","is_ca":false},{"name":"Davide Cittaro","is_ca":false},{"name":"Olivier Collin","is_ca":false},{"name":"Raul Cordova","is_ca":false},{"name":"Rosalind Cutts","is_ca":false},{"name":"Erik Dassi","is_ca":false},{"name":"Alex Di Genova","is_ca":false},{"name":"Anis Djari","is_ca":false},{"name":"Anthony Esposito","is_ca":false},{"name":"Heather Estrella","is_ca":false},{"name":"Eduardo Eyras","is_ca":false},{"name":"Julio Fernandez-Banet","is_ca":false},{"name":"Simon Forbes","is_ca":false},{"name":"Robert C. Free","is_ca":false},{"name":"Takatomo Fujisawa","is_ca":false},{"name":"Emanuela Gadaleta","is_ca":false},{"name":"José Manuel García-Manteiga","is_ca":false},{"name":"David Goodstein","is_ca":false},{"name":"Kristian Gray","is_ca":false},{"name":"José Afonso Guerra‐Assunção","is_ca":false},{"name":"Bernard Haggarty","is_ca":false},{"name":"Dong-Jin Han","is_ca":false},{"name":"Byung Woo Han","is_ca":false},{"name":"Todd Harris","is_ca":true},{"name":"Jayson Harshbarger","is_ca":false},{"name":"Robert Hastings","is_ca":false},{"name":"Richard D. Hayes","is_ca":false},{"name":"Claire Hoede","is_ca":false},{"name":"Shen Hu","is_ca":false},{"name":"Zhi-Liang Hu","is_ca":false},{"name":"Lucie N. Hutchins","is_ca":false},{"name":"Zhengyan Kan","is_ca":false},{"name":"Hideya Kawaji","is_ca":false},{"name":"Aminah Keliet","is_ca":false},{"name":"Arnaud Kerhornou","is_ca":false},{"name":"Sung‐Hoon Kim","is_ca":false},{"name":"Rhoda Kinsella","is_ca":false},{"name":"Christophe Klopp","is_ca":false},{"name":"Lei Kong","is_ca":false},{"name":"Daniel Lawson","is_ca":false},{"name":"Dejan Lazarević","is_ca":false},{"name":"Ji‐Hyun Lee","is_ca":false},{"name":"Thomas Letellier","is_ca":false},{"name":"Chuan-Yun Li","is_ca":false},{"name":"Píetro Lió","is_ca":false},{"name":"Chu-Jun Liu","is_ca":false},{"name":"Jie Luo","is_ca":false},{"name":"Alejandro Maass","is_ca":false},{"name":"Jérôme Mariette","is_ca":false},{"name":"Thomas Maurel","is_ca":false},{"name":"Stefania Merella","is_ca":false},{"name":"Azza M. Mohamed","is_ca":false},{"name":"François Moreews","is_ca":false},{"name":"Ibounyamine Nabihoudine","is_ca":false},{"name":"Nelson Ndegwa","is_ca":false},{"name":"Céline Noirot","is_ca":false},{"name":"Cristian Perez-Llamas","is_ca":false},{"name":"Michael Primig","is_ca":false},{"name":"Alessandro Quattrone","is_ca":false},{"name":"Hadi Quesneville","is_ca":false},{"name":"Davide Rambaldi","is_ca":false},{"name":"James M. Reecy","is_ca":false},{"name":"Michela Riba","is_ca":false},{"name":"Steven Rosanoff","is_ca":false},{"name":"Amna A. Saddiq","is_ca":false},{"name":"Elisa Salas","is_ca":false},{"name":"Olivier Sallou","is_ca":false},{"name":"Rebecca Shepherd","is_ca":false},{"name":"Reinhard Simon","is_ca":false},{"name":"Linda Sperling","is_ca":false},{"name":"William Spooner","is_ca":false},{"name":"D. Staines","is_ca":false},{"name":"Delphine Steinbach","is_ca":false},{"name":"Kevin Stone","is_ca":false},{"name":"Elia Stupka","is_ca":false},{"name":"Jon W. Teague","is_ca":false},{"name":"Abu Z M Dayem Ullah","is_ca":false},{"name":"Jun Wang","is_ca":false},{"name":"Doreen Ware","is_ca":false},{"name":"Marie Wong","is_ca":false},{"name":"Ken Youens‐Clark","is_ca":false},{"name":"Amonida Zadissa","is_ca":false},{"name":"Shi-Jian Zhang","is_ca":false},{"name":"Arek Kasprzyk","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0173261,0.001959295,0.002839289,0.009330045,0.002822006,0.01286495,0.00866252,0.003003729,0.03725407],"category_scores_gemma":[0.03646284,0.001928239,0.002005849,0.01948509,0.001552123,0.01821295,0.01713958,0.004555895,0.04040598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001453566,"about_ca_system_score_gemma":0.007425811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004965257,"about_ca_topic_score_gemma":0.004534824,"domain_scores_codex":[0.9872468,0.00365375,0.001541581,0.001820644,0.004942543,0.0007946898],"domain_scores_gemma":[0.9616485,0.007154288,0.002093642,0.01784992,0.006006085,0.005247594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001687025,0.0004613174,0.003777958,0.001333441,0.0004463449,0.0007166076,0.0008451571,0.001825052,0.005656762,0.05571806,0.6905413,0.236991],"study_design_scores_gemma":[0.0003749843,0.00009829274,0.001614054,0.0003650422,0.0001405239,0.0006247125,0.0002721551,0.01004869,0.004162586,0.04907368,0.9330423,0.0001830119],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.006078068,0.003861251,0.6137356,0.007786418,0.001632219,0.0008023738,0.04072383,0.2849956,0.04038465],"genre_scores_gemma":[0.05131324,0.004849305,0.6383384,0.004538457,0.001998353,0.001672978,0.2087451,0.05527917,0.03326492],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03725407,"threshold_uncertainty_score":0.1246273,"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","authors":[{"name":"Choong‐Chin Liew","is_ca":true},{"name":"Jun Ma","is_ca":false},{"name":"Hong-Chang Tang","is_ca":false},{"name":"Run Zheng","is_ca":false},{"name":"Adam A. Dempsey","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004484904,0.0002680156,0.0004720197,0.0007000043,0.0001896798,0.001027475,0.0001977601,0.00041763,0.001500278],"category_scores_gemma":[0.000901659,0.0001659647,0.0001618554,0.0007138447,0.0002526572,0.0004689653,0.0002408733,0.0006080038,0.0004508119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002082783,"about_ca_system_score_gemma":0.0001747293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001961976,"about_ca_topic_score_gemma":0.0002942392,"domain_scores_codex":[0.9997247,0.00009135015,0.00001326173,0.00009890333,0.00004177905,0.00003004197],"domain_scores_gemma":[0.9995068,0.0002450524,0.00009136579,0.00005137704,0.00004627447,0.0000591354],"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":[0.001961677,0.0001835848,0.3874565,0.0002389666,0.00019123,0.0004874421,0.0002574511,0.001289161,0.5066593,0.001053776,0.00249066,0.09773016],"study_design_scores_gemma":[0.00004316403,0.0008470275,0.8985569,0.00004370596,0.0003056143,0.002284648,0.0003684207,0.01230333,0.07395879,0.004539553,0.006699568,0.00004927396],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9577581,0.00343775,0.02795596,0.0008422396,0.0001822667,0.00005927529,0.003665988,0.0004066201,0.005691766],"genre_scores_gemma":[0.9890149,0.001007962,0.007015088,0.0004224356,0.0001893161,0.00007879189,0.001193308,0.00005314285,0.001025015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001500278,"threshold_uncertainty_score":0.00501895,"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","authors":[{"name":"Marinka Žitnik","is_ca":false},{"name":"Francis Nguyen","is_ca":true},{"name":"Bo Wang","is_ca":false},{"name":"Jure Leskovec","is_ca":false},{"name":"Anna Goldenberg","is_ca":true},{"name":"Michael M. Hoffman","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03127309,0.00134769,0.002347266,0.00513162,0.0009899833,0.009751108,0.003384365,0.004306385,0.001781828],"category_scores_gemma":[0.03434939,0.0009447473,0.001229078,0.00613843,0.009644618,0.01742116,0.005195647,0.007396892,0.001042406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002539437,"about_ca_system_score_gemma":0.003154663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00129588,"about_ca_topic_score_gemma":0.001029659,"domain_scores_codex":[0.9894714,0.006427625,0.0006352743,0.00082157,0.002443916,0.0002001635],"domain_scores_gemma":[0.9547186,0.03762462,0.0008905623,0.004033224,0.001986875,0.0007460734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001018205,0.0001673407,0.00364319,0.001188037,0.0001601855,0.0001509831,0.0006626052,0.008136914,0.0008359053,0.6536917,0.007190786,0.3240706],"study_design_scores_gemma":[0.00001917198,0.00004532659,0.0004068391,0.0006652429,0.00002170455,0.0002001594,0.0002201283,0.03760991,0.0007595002,0.9400825,0.0199247,0.00004491886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005751457,0.08371989,0.8479134,0.05249601,0.0004534345,0.0001827478,0.0001719013,0.000554799,0.008756286],"genre_scores_gemma":[0.161372,0.05955782,0.7695403,0.003309715,0.00293123,0.0004423459,0.0002488675,0.0001605105,0.002437292],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.03127309,"threshold_uncertainty_score":0.1653899,"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","authors":[{"name":"Pierre Farmer","is_ca":false},{"name":"Hervé Bonnefoi","is_ca":false},{"name":"Pascale Anderle","is_ca":false},{"name":"David Cameron","is_ca":false},{"name":"P. Wirapati","is_ca":false},{"name":"Véronique Becette","is_ca":false},{"name":"Sylvie André","is_ca":false},{"name":"Martine Piccart","is_ca":false},{"name":"Mario Campone","is_ca":false},{"name":"Étienne Brain","is_ca":false},{"name":"Gaëtan MacGrogan","is_ca":false},{"name":"Thierry Petit","is_ca":false},{"name":"Jacek Jassem","is_ca":false},{"name":"Frédéric Bibeau","is_ca":false},{"name":"Emmanuel Blot","is_ca":false},{"name":"Jan Bogaerts","is_ca":false},{"name":"Michel Aguet","is_ca":false},{"name":"Jonas Bergh","is_ca":false},{"name":"Richard Iggo","is_ca":false},{"name":"Mauro Delorenzi","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002112358,0.0001181992,0.0001647697,0.0005920166,0.0001556616,0.0003154651,0.0001130356,0.0002248983,0.001069022],"category_scores_gemma":[0.0006445819,0.00007068893,0.0001153829,0.000470183,0.0002301593,0.0001162237,0.0001383798,0.0001991309,0.0001836241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001644016,"about_ca_system_score_gemma":0.000151717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003851758,"about_ca_topic_score_gemma":0.0007089286,"domain_scores_codex":[0.9999037,0.00002579766,0.00001186859,0.00001655493,0.00002152127,0.00002049802],"domain_scores_gemma":[0.9995636,0.0001324997,0.0001622048,0.00001965912,0.00004769931,0.00007433454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001319512,0.00006676596,0.9115232,0.00003349081,0.00004773751,0.0002390755,0.00005858305,0.0003095515,0.07477884,0.00008856294,0.000244397,0.01129037],"study_design_scores_gemma":[0.00002078151,0.0002725193,0.9896351,0.000005887607,0.00005560902,0.001174501,0.0001051564,0.001601908,0.006385476,0.0001531634,0.0005856175,0.000004299782],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990916,0.0001915825,0.0001020555,0.00005415228,0.000005276133,0.000003351809,0.00009847,0.000003139815,0.0004503675],"genre_scores_gemma":[0.9993099,0.00009747356,0.0001590275,0.00002601659,0.0000107453,0.000004786158,0.0001912773,0.000001890688,0.0001987939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001069022,"threshold_uncertainty_score":0.003576219,"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","authors":[{"name":"Donna K. Slonim","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006010381,0.001418416,0.004133211,0.004022303,0.0006413599,0.005688698,0.003092102,0.002894391,0.002888953],"category_scores_gemma":[0.01065181,0.0008921972,0.000827846,0.006424491,0.007124946,0.0108088,0.001978747,0.008434493,0.003024864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001682759,"about_ca_system_score_gemma":0.002227857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002594963,"about_ca_topic_score_gemma":0.003195823,"domain_scores_codex":[0.998266,0.0004474348,0.0002022118,0.000342378,0.0006856739,0.00005629014],"domain_scores_gemma":[0.9870024,0.009421355,0.0003330858,0.0007768061,0.002054806,0.0004115585],"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":[0.00008230729,0.00005589265,0.0008493721,0.004978473,0.0001654337,0.0001995107,0.0002534247,0.0009572822,0.001792714,0.04036582,0.06719047,0.8831093],"study_design_scores_gemma":[0.00003136655,0.00005206545,0.001154962,0.002325683,0.00009080013,0.001522784,0.0003542138,0.001097927,0.001048878,0.1943251,0.7979014,0.0000947392],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003518759,0.9502451,0.0314977,0.01360053,0.002045306,0.00001709814,0.000175577,0.0002669999,0.001799862],"genre_scores_gemma":[0.003422858,0.9592471,0.02531197,0.007184801,0.002832153,0.00004125177,0.0002361734,0.0001026622,0.001621049],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006010381,"threshold_uncertainty_score":0.03178632,"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","authors":[{"name":"Lincoln Stein","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02311461,0.0005410797,0.001174436,0.0020493,0.005303796,0.01497169,0.003981825,0.01074166,0.01229415],"category_scores_gemma":[0.03909092,0.0006699944,0.001064832,0.004435637,0.01175232,0.03824323,0.007200234,0.0153981,0.003195456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004673094,"about_ca_system_score_gemma":0.005941601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007952897,"about_ca_topic_score_gemma":0.004667745,"domain_scores_codex":[0.9909369,0.003693923,0.0003418182,0.001064555,0.002635822,0.001326906],"domain_scores_gemma":[0.9482606,0.0309243,0.001342434,0.009494069,0.005412992,0.004565638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001366687,0.00007174304,0.001677541,0.0001832316,0.00003172346,0.0003076472,0.000390877,0.002388111,0.0005890664,0.8868197,0.07310665,0.03429714],"study_design_scores_gemma":[0.00003915857,0.00002303241,0.0006797586,0.0003063708,0.00001960129,0.0003080748,0.0008706903,0.01290628,0.0005593096,0.8167999,0.1674528,0.00003500691],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01580635,0.01719812,0.09682921,0.7749495,0.005649718,0.0001304171,0.0007002436,0.0007902689,0.08794624],"genre_scores_gemma":[0.6907755,0.02733253,0.155008,0.07943379,0.02043341,0.0004733459,0.0008993168,0.0009731216,0.02467086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02311461,"threshold_uncertainty_score":0.1222432,"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","authors":[{"name":"Robert V. Bruggner","is_ca":false},{"name":"Bernd Bodenmiller","is_ca":false},{"name":"David L. Dill","is_ca":false},{"name":"Robert Tibshirani","is_ca":true},{"name":"Garry P. Nolan","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034763,0.0005085347,0.0009751382,0.003597856,0.0004340397,0.001347789,0.0005530825,0.000581003,0.0009146794],"category_scores_gemma":[0.002437439,0.0002099151,0.0005876569,0.001629777,0.0002999016,0.0006743906,0.0009694282,0.0006469477,0.0007279016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004912679,"about_ca_system_score_gemma":0.0007756862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001340202,"about_ca_topic_score_gemma":0.002801493,"domain_scores_codex":[0.9994662,0.00009510759,0.00004920236,0.0001969245,0.0001244095,0.00006810093],"domain_scores_gemma":[0.9986872,0.0004906231,0.0002348662,0.0002564822,0.0002491702,0.00008158886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000922653,0.0003126238,0.2015096,0.0005154581,0.0001950294,0.0002849186,0.0006403598,0.02270394,0.3266263,0.004531394,0.005887252,0.4358706],"study_design_scores_gemma":[0.0001201706,0.0005017291,0.3163239,0.0001368366,0.0002258998,0.0008926469,0.0008869369,0.4806337,0.1509554,0.02613673,0.02303642,0.0001496402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6562241,0.002315352,0.3246344,0.0005508725,0.00005525232,0.0004478412,0.008471603,0.00466627,0.002634363],"genre_scores_gemma":[0.7560167,0.0006773377,0.230809,0.0001746365,0.00004323205,0.0003417496,0.01029395,0.0001486921,0.001494698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003597856,"threshold_uncertainty_score":0.005472422,"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","authors":[{"name":"Franz Baumdicker","is_ca":false},{"name":"Gertjan Bisschop","is_ca":false},{"name":"Daniel Goldstein","is_ca":false},{"name":"Graham Gower","is_ca":false},{"name":"Aaron P. Ragsdale","is_ca":false},{"name":"Georgia Tsambos","is_ca":false},{"name":"Sha Zhu","is_ca":false},{"name":"Bjarki Eldon","is_ca":false},{"name":"E. Castedo Ellerman","is_ca":false},{"name":"Jared Galloway","is_ca":false},{"name":"Ariella Gladstein","is_ca":false},{"name":"Gregor Gorjanc","is_ca":false},{"name":"Bing Guo","is_ca":false},{"name":"Ben Jeffery","is_ca":false},{"name":"Warren W Kretzschumar","is_ca":false},{"name":"Konrad Lohse","is_ca":false},{"name":"Michael Matschiner","is_ca":false},{"name":"Dominic Nelson","is_ca":true},{"name":"Nathaniel S. Pope","is_ca":false},{"name":"Consuelo D. Quinto-Cortés","is_ca":false},{"name":"Murillo F. Rodrigues","is_ca":false},{"name":"Kumar Saunack","is_ca":false},{"name":"Thibaut Sellinger","is_ca":false},{"name":"Kevin Thornton","is_ca":false},{"name":"Hugo van Kemenade","is_ca":false},{"name":"Anthony Wilder Wohns","is_ca":false},{"name":"Yan Wong","is_ca":false},{"name":"Simon Gravel","is_ca":true},{"name":"Andrew D. Kern","is_ca":false},{"name":"Jere Koskela","is_ca":false},{"name":"Peter L. Ralph","is_ca":false},{"name":"Jerome Kelleher","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002429232,0.0009195878,0.001337348,0.0007829439,0.0007081152,0.001526398,0.003106702,0.001428348,0.0122909],"category_scores_gemma":[0.01074773,0.0008884671,0.001337651,0.0008223907,0.0006021988,0.00172845,0.001988869,0.002543583,0.005234234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007303098,"about_ca_system_score_gemma":0.001817557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003267732,"about_ca_topic_score_gemma":0.00398209,"domain_scores_codex":[0.9993008,0.0002199121,0.0000602091,0.0001401504,0.0002102971,0.00006863725],"domain_scores_gemma":[0.9969549,0.001973973,0.0001473356,0.0004082979,0.0003521591,0.0001633465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008062709,0.0004829339,0.01876354,0.001438814,0.0007823053,0.0008880686,0.001343829,0.5535005,0.02650434,0.09483499,0.09919343,0.201461],"study_design_scores_gemma":[0.0001053225,0.00004877047,0.0007358758,0.00004511039,0.00004308192,0.0001649612,0.00004429465,0.9440296,0.007110149,0.02275035,0.02486876,0.00005371566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.03335071,0.0003255064,0.8738125,0.000409049,0.0001821378,0.0001552619,0.003339358,0.07958379,0.008841652],"genre_scores_gemma":[0.2100045,0.0005483849,0.7533024,0.0004800752,0.00008651788,0.0008884017,0.008836273,0.01991059,0.005942849],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.0122909,"threshold_uncertainty_score":0.04111713,"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","authors":[{"name":"Amanda Myers","is_ca":false},{"name":"J. Raphael Gibbs","is_ca":false},{"name":"Jennifer Webster","is_ca":false},{"name":"Kristen Rohrer","is_ca":false},{"name":"Alice Zhao","is_ca":false},{"name":"Lauren Marlowe","is_ca":false},{"name":"Mona Kaleem","is_ca":false},{"name":"Doris G. Leung","is_ca":false},{"name":"Leslie Bryden","is_ca":false},{"name":"Priti Nath","is_ca":false},{"name":"Victoria Zismann","is_ca":false},{"name":"Keta Joshipura","is_ca":false},{"name":"Matthew J. Huentelman","is_ca":false},{"name":"Diane Hu‐Lince","is_ca":false},{"name":"Keith D. Coon","is_ca":false},{"name":"David W. Craig","is_ca":false},{"name":"John V. Pearson","is_ca":false},{"name":"Peter Holmans","is_ca":false},{"name":"Christopher B. Heward","is_ca":true},{"name":"Eric M. Reiman","is_ca":false},{"name":"Dietrich Stephan","is_ca":false},{"name":"John Hardy","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002349473,0.0001409505,0.0001760106,0.001894899,0.0002950063,0.0003290043,0.0001489207,0.0001099015,0.002637925],"category_scores_gemma":[0.0006117465,0.0000812401,0.0001262795,0.002452229,0.000250369,0.000138566,0.0001916684,0.0001711471,0.0004909961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003991705,"about_ca_system_score_gemma":0.000462384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006231436,"about_ca_topic_score_gemma":0.008107323,"domain_scores_codex":[0.9998847,0.0000223596,0.000007940213,0.00003241881,0.00003056408,0.00002196656],"domain_scores_gemma":[0.999525,0.0002008862,0.00003877258,0.00004291644,0.0001369482,0.00005568034],"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":[0.0009883393,0.00006160002,0.2337043,0.0005307709,0.0002398309,0.00141761,0.0008188035,0.001391858,0.5193648,0.005532443,0.005063944,0.2308858],"study_design_scores_gemma":[0.00001363012,0.0001515815,0.8659795,0.00004201407,0.0001297947,0.005214566,0.0006318458,0.001109571,0.08074635,0.002405368,0.04355111,0.00002463646],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.964806,0.0124292,0.005895845,0.0003617906,0.00001908164,0.00001131774,0.004612567,0.0001254458,0.01173874],"genre_scores_gemma":[0.9830918,0.008121258,0.001740716,0.000108932,0.00001833855,0.00001631469,0.003341979,0.00004869794,0.003512052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006231436,"threshold_uncertainty_score":0.01239032,"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","authors":[{"name":"Yifeng Li","is_ca":true},{"name":"Fang‐Xiang Wu","is_ca":true},{"name":"Alioune Ngom","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001755391,0.001205211,0.00160946,0.003036452,0.0003143819,0.001497919,0.001654158,0.00160858,0.003504473],"category_scores_gemma":[0.003026502,0.0006728172,0.001173533,0.004548166,0.001133465,0.003052262,0.0009957065,0.002933593,0.003541386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009469083,"about_ca_system_score_gemma":0.001409454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001162111,"about_ca_topic_score_gemma":0.001145344,"domain_scores_codex":[0.9992808,0.0001591336,0.0001011978,0.0001383333,0.0002852343,0.00003538899],"domain_scores_gemma":[0.998437,0.001103606,0.00008810744,0.00006957573,0.0002618944,0.00003992226],"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":[0.00003541073,0.00005534774,0.0002462541,0.008834427,0.0001404752,0.0001890952,0.00008827092,0.002412868,0.001290989,0.03190311,0.04501422,0.9097894],"study_design_scores_gemma":[0.00001217978,0.00006426274,0.0006540307,0.003481847,0.00008710684,0.001033988,0.00004521915,0.00223165,0.0008342256,0.0364751,0.9550099,0.00007056065],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001975355,0.9623724,0.03100615,0.001641479,0.0009236461,0.00003373885,0.000125735,0.000139467,0.003559817],"genre_scores_gemma":[0.002270653,0.9696438,0.02384474,0.001095578,0.001122081,0.00008206241,0.0002206999,0.0000431067,0.001677248],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.003504473,"threshold_uncertainty_score":0.0117237,"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","authors":[{"name":"W. Evan Johnson","is_ca":false},{"name":"Wei Li","is_ca":false},{"name":"Clifford A. Meyer","is_ca":false},{"name":"Raphaël Gottardo","is_ca":true},{"name":"Jason S. Carroll","is_ca":false},{"name":"Myles Brown","is_ca":false},{"name":"X. Shirley Liu","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002478498,0.001833381,0.001658411,0.00108839,0.0007102418,0.001463635,0.002397935,0.001107801,0.004864337],"category_scores_gemma":[0.007969342,0.0009208311,0.002663247,0.001127135,0.0007842529,0.001333228,0.001361353,0.002519404,0.002013015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014643,"about_ca_system_score_gemma":0.001503876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001773157,"about_ca_topic_score_gemma":0.00230148,"domain_scores_codex":[0.9983162,0.0005776744,0.00009298709,0.0003426605,0.0005694135,0.000101061],"domain_scores_gemma":[0.9969297,0.0018669,0.0002202364,0.0005767906,0.0003257683,0.0000806324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001680812,0.0000987633,0.002303934,0.0003533893,0.0002847642,0.0001596039,0.0001291031,0.7694616,0.02615916,0.06247795,0.007070494,0.1313332],"study_design_scores_gemma":[0.000008280527,0.0000169439,0.0001240856,0.000005016946,0.00001055243,0.00002503774,0.000005333014,0.9722606,0.00317681,0.02221182,0.002143666,0.0000117495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006802308,0.00002411872,0.9977258,0.00002142612,0.00001027348,0.00001616021,0.00007782992,0.001322537,0.0001217343],"genre_scores_gemma":[0.03991513,0.0001103479,0.9571252,0.00009905653,0.00003480217,0.0005815555,0.0009040902,0.0007942836,0.0004354759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004864337,"threshold_uncertainty_score":0.01627284,"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","authors":[{"name":"Deena M.A. Gendoo","is_ca":true},{"name":"Natchar Ratanasirigulchai","is_ca":true},{"name":"Markus Schröder","is_ca":false},{"name":"Laia Paré","is_ca":false},{"name":"Joel S. Parker","is_ca":false},{"name":"Aleix Prat","is_ca":false},{"name":"Benjamin Haibe‐Kains","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004921597,0.003409109,0.003888082,0.004686331,0.001197075,0.003068876,0.006291312,0.001723204,0.07262591],"category_scores_gemma":[0.01833904,0.001621294,0.002861573,0.006439942,0.0009837315,0.002171446,0.003517039,0.003388315,0.08145295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001361496,"about_ca_system_score_gemma":0.005068794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007072493,"about_ca_topic_score_gemma":0.007580501,"domain_scores_codex":[0.9968036,0.0009417438,0.0002890245,0.0008847995,0.0008084525,0.000272284],"domain_scores_gemma":[0.9933709,0.003148016,0.0005630314,0.001084406,0.001488089,0.0003455235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007485022,0.00005990236,0.003964307,0.004000402,0.001056487,0.0002747306,0.0003192693,0.006423289,0.003486944,0.009514165,0.8967363,0.07341562],"study_design_scores_gemma":[0.000613947,0.0001920396,0.01163744,0.001083643,0.0009098543,0.0008947784,0.0001627456,0.09261557,0.01148938,0.05323693,0.8268584,0.0003052361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004503896,0.004724947,0.3292332,0.002177115,0.001099189,0.0005680693,0.2724838,0.3721277,0.01308201],"genre_scores_gemma":[0.04705314,0.003301325,0.501153,0.002353496,0.000393478,0.006189192,0.3027973,0.1187409,0.01801822],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.07262591,"threshold_uncertainty_score":0.2429578,"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","authors":[{"name":"İnanç Birol","is_ca":true},{"name":"Shaun D. Jackman","is_ca":true},{"name":"Cydney Nielsen","is_ca":true},{"name":"Jenny Q. Qian","is_ca":true},{"name":"Richard Varhol","is_ca":true},{"name":"Greg Stazyk","is_ca":true},{"name":"Ryan D. Morin","is_ca":true},{"name":"Yongjun Zhao","is_ca":true},{"name":"Martin Hirst","is_ca":true},{"name":"Jacqueline E. Schein","is_ca":true},{"name":"Doug Horsman","is_ca":true},{"name":"Joseph M. Connors","is_ca":true},{"name":"Randy D. Gascoyne","is_ca":true},{"name":"Marco A. Marra","is_ca":true},{"name":"Steven J.M. Jones","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001255243,0.00135697,0.001077289,0.001365208,0.001240932,0.001417599,0.001341532,0.000473187,0.01085775],"category_scores_gemma":[0.002508519,0.0007159594,0.0009406978,0.001998946,0.0003408731,0.0009607808,0.001017283,0.001632274,0.01074004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006508848,"about_ca_system_score_gemma":0.001148939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002905208,"about_ca_topic_score_gemma":0.002795181,"domain_scores_codex":[0.9993291,0.00009023656,0.00007970218,0.0002475982,0.00018667,0.00006675911],"domain_scores_gemma":[0.9990481,0.0002372529,0.0001380167,0.0002157884,0.0002767429,0.00008413003],"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":[0.001874581,0.0003061548,0.009438693,0.00243257,0.0002616401,0.0007770505,0.001042124,0.01291445,0.6658593,0.007731067,0.1010009,0.1963614],"study_design_scores_gemma":[0.0002451697,0.0003221306,0.01809814,0.0002120205,0.0001896128,0.001120157,0.000238528,0.118048,0.6131237,0.0142615,0.2339628,0.0001782109],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.07456221,0.000832986,0.7816455,0.0007854522,0.0004173405,0.0006638335,0.05449798,0.07887584,0.007718813],"genre_scores_gemma":[0.05934261,0.0006425941,0.8372577,0.0002591162,0.0001018689,0.001048399,0.08777719,0.008014159,0.00555637],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01085775,"threshold_uncertainty_score":0.03632283,"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","authors":[{"name":"Peter Lee","is_ca":true},{"name":"Robert Sladek","is_ca":true},{"name":"Celia M.T. Greenwood","is_ca":true},{"name":"Thomas J. Hudson","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02380622,0.0006310717,0.001696352,0.001834204,0.001092135,0.001958852,0.001153928,0.001222154,0.0006920024],"category_scores_gemma":[0.03770883,0.0005776891,0.0009289573,0.003050759,0.002253551,0.000951643,0.001715197,0.001247526,0.000304265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038148,"about_ca_system_score_gemma":0.0006398506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00128093,"about_ca_topic_score_gemma":0.00237841,"domain_scores_codex":[0.960275,0.01548407,0.004528401,0.01002723,0.008753347,0.0009320364],"domain_scores_gemma":[0.9458801,0.03591,0.004062558,0.01097014,0.002860928,0.0003164009],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002187577,0.0004769887,0.1099304,0.00237982,0.001033165,0.0008894425,0.001529365,0.01323112,0.7243724,0.01314969,0.001906513,0.1289135],"study_design_scores_gemma":[0.0001945393,0.001318094,0.3612675,0.0003995203,0.001237115,0.003264381,0.0004939688,0.04117524,0.5145925,0.03702204,0.03879118,0.0002438593],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.269903,0.00704263,0.7132151,0.0004322059,0.0003193753,0.0005821137,0.002654317,0.0009867412,0.004864617],"genre_scores_gemma":[0.8355682,0.001497077,0.1490644,0.001051821,0.0001766932,0.002079796,0.007948711,0.001080498,0.001532806],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9761938,"threshold_uncertainty_score":0.1259009,"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","authors":[{"name":"Ilya Kupershmidt","is_ca":true},{"name":"Qiaojuan Jane Su","is_ca":false},{"name":"Anoop Grewal","is_ca":false},{"name":"Suman Sundaresh","is_ca":false},{"name":"Inbal Halperin","is_ca":false},{"name":"James Flynn","is_ca":false},{"name":"Mamatha Shekar","is_ca":false},{"name":"Helen H. Wang","is_ca":false},{"name":"Jenny Park","is_ca":false},{"name":"Wenwu Cui","is_ca":false},{"name":"Gregory D. Wall","is_ca":false},{"name":"Robert G. Wisotzkey","is_ca":false},{"name":"Satnam Alag","is_ca":false},{"name":"Saeid Akhtari","is_ca":false},{"name":"Mostafa Ronaghi","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02351213,0.001955897,0.002308386,0.02051604,0.001500237,0.005135358,0.003509715,0.00115168,0.0008109752],"category_scores_gemma":[0.04944529,0.0006896841,0.007811781,0.01304246,0.001282936,0.004216441,0.003943593,0.002185459,0.0002651322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002632783,"about_ca_system_score_gemma":0.004680252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007701384,"about_ca_topic_score_gemma":0.0142377,"domain_scores_codex":[0.9845489,0.005357273,0.001707636,0.003881692,0.003998921,0.0005056381],"domain_scores_gemma":[0.9459103,0.03248569,0.005504566,0.01157556,0.003653841,0.0008700991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.001690774,0.001203704,0.3399364,0.006872135,0.04045177,0.002734608,0.002087035,0.1912581,0.03818341,0.03870242,0.01192577,0.3249539],"study_design_scores_gemma":[0.00026771,0.0007515337,0.1082031,0.0008539051,0.01301865,0.00167536,0.00234902,0.58475,0.02719946,0.2326028,0.02796158,0.0003668106],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1553531,0.005988989,0.7905957,0.002630933,0.000218307,0.000670652,0.03460585,0.007790038,0.002146494],"genre_scores_gemma":[0.4906619,0.001942686,0.4501458,0.0006111754,0.0001862972,0.000923908,0.05453757,0.0005473109,0.0004434441],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02351213,"threshold_uncertainty_score":0.1243455,"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","authors":[{"name":"Elena Parkhomenko","is_ca":true},{"name":"David Tritchler","is_ca":true},{"name":"Joseph Beyene","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006129766,0.001123187,0.001736009,0.002825363,0.0008944802,0.001730793,0.001154435,0.0009241579,0.001822803],"category_scores_gemma":[0.0269892,0.0007544024,0.001721168,0.005786106,0.001394288,0.001367244,0.002554005,0.001689794,0.0008017233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000698657,"about_ca_system_score_gemma":0.002797199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007458253,"about_ca_topic_score_gemma":0.007655779,"domain_scores_codex":[0.9951421,0.003032197,0.0001889262,0.0005377608,0.0009024663,0.0001965766],"domain_scores_gemma":[0.986686,0.008915103,0.0006846015,0.001316154,0.002135587,0.0002625903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001779413,0.0001243162,0.005293696,0.0001879431,0.0002644072,0.0002916987,0.0003264921,0.5758081,0.003831551,0.06773324,0.005126552,0.340834],"study_design_scores_gemma":[0.00001228338,0.00001799154,0.00043413,0.000008736448,0.00001344768,0.00004670759,0.00001935429,0.9743692,0.0005878257,0.02317324,0.001299743,0.00001736589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004331824,0.0001278346,0.9946413,0.0001258227,0.00001497676,0.00003180453,0.00007714395,0.0003463601,0.0003028161],"genre_scores_gemma":[0.1231001,0.0004928758,0.8739049,0.0001495512,0.0001171051,0.0003754335,0.0008005368,0.0002240315,0.0008354917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007458253,"threshold_uncertainty_score":0.03241771,"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","authors":[{"name":"Elnaz Barshan","is_ca":false},{"name":"Ali Ghodsi","is_ca":true},{"name":"Zohreh Azimifar","is_ca":false},{"name":"Mansoor Zolghadri Jahromi","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001899904,0.001400192,0.001053173,0.001906708,0.0004636008,0.001922154,0.0007541551,0.0005913971,0.003311431],"category_scores_gemma":[0.004970188,0.0005220108,0.001004647,0.002192129,0.0008697556,0.001577898,0.001279236,0.001321804,0.001207071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000361374,"about_ca_system_score_gemma":0.0008808551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001715322,"about_ca_topic_score_gemma":0.001675406,"domain_scores_codex":[0.9989662,0.0004936097,0.0000783223,0.0001610154,0.000259207,0.00004160047],"domain_scores_gemma":[0.9976614,0.001198191,0.0001631014,0.0004078697,0.0004623963,0.0001071586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002949991,0.000134983,0.001392991,0.0005746951,0.0001253054,0.00009710668,0.0004600863,0.0484261,0.03458398,0.02961078,0.01438787,0.8699111],"study_design_scores_gemma":[0.00003384996,0.00005962489,0.001903358,0.00004639386,0.00003635403,0.0001598937,0.0001385021,0.9145367,0.01239898,0.0641064,0.006528976,0.00005093095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008842282,0.0004741297,0.9877827,0.0002431703,0.00004451741,0.00004739757,0.0001974579,0.001872356,0.0004959728],"genre_scores_gemma":[0.1192095,0.0008567736,0.8769147,0.00005018189,0.00008789381,0.0002418938,0.0005555234,0.0005338579,0.001549665],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003311431,"threshold_uncertainty_score":0.01107782,"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","authors":[{"name":"Ray Somorjai","is_ca":true},{"name":"B. Dolenko","is_ca":true},{"name":"Richard Baumgartner","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1796042,0.001531537,0.002446074,0.00530771,0.004426388,0.006545733,0.007214189,0.003686488,0.002363728],"category_scores_gemma":[0.4895865,0.0009583092,0.001863114,0.005488106,0.009792486,0.00741513,0.004712669,0.010185,0.002040396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002325916,"about_ca_system_score_gemma":0.004105507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01178083,"about_ca_topic_score_gemma":0.02010186,"domain_scores_codex":[0.8853942,0.0689757,0.01307398,0.005416232,0.02624118,0.0008988306],"domain_scores_gemma":[0.4902711,0.3845799,0.02004348,0.06128975,0.0419264,0.00188933],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008763171,0.0002476487,0.03888613,0.003307163,0.001225909,0.001900594,0.008468962,0.01004438,0.004863781,0.1162334,0.3819064,0.4320394],"study_design_scores_gemma":[0.0003369114,0.0003437484,0.02906239,0.004865755,0.0005395048,0.004405912,0.004230811,0.07430884,0.01426827,0.675099,0.1919379,0.000601083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04042498,0.009708071,0.59969,0.3181714,0.01056303,0.001319844,0.003461407,0.005013795,0.01164755],"genre_scores_gemma":[0.2642408,0.004080911,0.6048182,0.1046801,0.009547694,0.003185086,0.001212038,0.001223517,0.007011552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8203958,"threshold_uncertainty_score":0.9498491,"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","authors":[{"name":"Bissan Ghaddar","is_ca":true},{"name":"Joe Naoum‐Sawaya","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002055928,0.0009878018,0.00197059,0.001588276,0.0006079655,0.001694996,0.001017577,0.0008694271,0.001545851],"category_scores_gemma":[0.006068901,0.000378515,0.001351564,0.002215904,0.0004106692,0.000996097,0.001000061,0.00155312,0.0008774838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000385556,"about_ca_system_score_gemma":0.0008474047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001984419,"about_ca_topic_score_gemma":0.001214832,"domain_scores_codex":[0.9983757,0.000409257,0.0002392928,0.0003257564,0.0004719881,0.0001779189],"domain_scores_gemma":[0.9976291,0.001463502,0.0001318974,0.0002164189,0.0004922058,0.00006692272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004845104,0.0003820201,0.003168726,0.0001858675,0.0001489553,0.0002319706,0.0001217206,0.06664678,0.01312678,0.001792119,0.004220436,0.90949],"study_design_scores_gemma":[0.00002789967,0.0001355412,0.00172061,0.00001470188,0.00003634662,0.0001038553,0.00006211396,0.9876072,0.005692884,0.003630239,0.0009483383,0.00002022718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05966457,0.0006229279,0.935925,0.0003282488,0.00013573,0.0001865414,0.0004026274,0.002148289,0.0005860858],"genre_scores_gemma":[0.5725841,0.0004020119,0.4228747,0.0001069926,0.0001843228,0.0005388892,0.001549163,0.00009620753,0.001663637],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002055928,"threshold_uncertainty_score":0.0108729,"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","authors":[{"name":"Sarah‐Jane Dawson","is_ca":false},{"name":"Oscar M. Rueda","is_ca":false},{"name":"Samuel Aparício","is_ca":true},{"name":"Carlos Caldas","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00117604,0.0007465119,0.001655953,0.00149177,0.0002590155,0.001356508,0.001372357,0.001447706,0.001202942],"category_scores_gemma":[0.0009420768,0.0003425868,0.0004109968,0.00221569,0.001608253,0.001484149,0.00090242,0.002130511,0.001085243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001746021,"about_ca_system_score_gemma":0.001333702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002136979,"about_ca_topic_score_gemma":0.00237353,"domain_scores_codex":[0.999676,0.00005316189,0.00003190141,0.0001078036,0.00008635992,0.00004469855],"domain_scores_gemma":[0.9995828,0.0001389546,0.00005410177,0.00002283848,0.0001634827,0.00003781489],"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":[0.0001342573,0.00004232109,0.000994383,0.0045356,0.00008184316,0.0001900745,0.00007932737,0.0007310616,0.0102605,0.02243705,0.03095901,0.9295546],"study_design_scores_gemma":[0.00002874994,0.00009279099,0.003790413,0.001837284,0.000227924,0.001963538,0.0001728798,0.00074361,0.00404207,0.01903271,0.968002,0.00006616312],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0006972851,0.9925523,0.002484452,0.002312691,0.0006219748,0.000005806965,0.0001140833,0.00003205769,0.001179334],"genre_scores_gemma":[0.007262012,0.9857522,0.003047491,0.001596622,0.0007724202,0.00001764567,0.0002368738,0.00001421004,0.001300613],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002136979,"threshold_uncertainty_score":0.01266837,"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","authors":[{"name":"Robert Nadon","is_ca":true},{"name":"Jennifer Shoemaker","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03460711,0.001991109,0.004164866,0.003377392,0.0007898386,0.004733632,0.0044493,0.003874196,0.003747992],"category_scores_gemma":[0.08222173,0.001572244,0.001628997,0.007182678,0.006152782,0.003548921,0.00158312,0.007990764,0.00390149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001611143,"about_ca_system_score_gemma":0.00297502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001669884,"about_ca_topic_score_gemma":0.002367252,"domain_scores_codex":[0.9789481,0.01291269,0.001238221,0.001375668,0.00534502,0.0001804232],"domain_scores_gemma":[0.9002407,0.08400416,0.001372891,0.005687815,0.008197159,0.0004973049],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009865617,0.00006924918,0.001456027,0.00311739,0.0004259393,0.0001962199,0.0002601312,0.004116818,0.002504175,0.04137567,0.07939912,0.8669806],"study_design_scores_gemma":[0.0001250202,0.0002551096,0.005101219,0.001494798,0.0004250055,0.002851023,0.0003057692,0.03987799,0.006997807,0.4780718,0.4642305,0.0002639771],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.0006446977,0.2089226,0.7673303,0.01497683,0.004616223,0.0001403848,0.0003267957,0.001216396,0.001825695],"genre_scores_gemma":[0.01263538,0.2438374,0.7064035,0.009573835,0.02016502,0.001093309,0.0007330251,0.0009228374,0.004635681],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9653929,"threshold_uncertainty_score":0.1830221,"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","authors":[{"name":"Muni S. Srivastava","is_ca":true},{"name":"Meng Du","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03574391,0.001366082,0.003504697,0.003232925,0.002165986,0.003073761,0.003235799,0.004729051,0.01136274],"category_scores_gemma":[0.1380267,0.0005641946,0.003253642,0.002831228,0.003673357,0.004970198,0.002579623,0.003832114,0.001171118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007342212,"about_ca_system_score_gemma":0.002686095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006046054,"about_ca_topic_score_gemma":0.0006663532,"domain_scores_codex":[0.9567832,0.02394001,0.003832676,0.007957975,0.006184656,0.001301543],"domain_scores_gemma":[0.7295249,0.2458214,0.004628799,0.01296607,0.005079719,0.001979145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01491113,0.002468724,0.2841518,0.001509186,0.009833069,0.001768452,0.0008295272,0.01595213,0.04722956,0.03676672,0.01243882,0.5721408],"study_design_scores_gemma":[0.005810649,0.02502103,0.2640092,0.0004754179,0.004215779,0.007822909,0.003019087,0.5065554,0.04294698,0.1232059,0.01625786,0.000659755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.394996,0.0007026477,0.5931966,0.002808966,0.000918748,0.000557731,0.001912754,0.001589091,0.00331755],"genre_scores_gemma":[0.8320915,0.0001255958,0.1596567,0.001239676,0.0006880136,0.0008844398,0.002514066,0.0002585376,0.002541446],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03574391,"threshold_uncertainty_score":0.1890341,"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","authors":[{"name":"Jie Li","is_ca":true},{"name":"Anne E.G. Lenferink","is_ca":true},{"name":"Yinghai Deng","is_ca":true},{"name":"Catherine Collins","is_ca":true},{"name":"Qinghua Cui","is_ca":true},{"name":"Enrico O. Purisima","is_ca":true},{"name":"Maureen D. O'Connor‐McCourt","is_ca":true},{"name":"Edwin Wang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006703135,0.0005331303,0.0005636355,0.001782296,0.0003523387,0.0005877877,0.0004241465,0.0003288541,0.001110393],"category_scores_gemma":[0.002344003,0.0002043921,0.0003168982,0.001137321,0.0001905059,0.0007445106,0.0005231989,0.0003108303,0.0002871228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005469731,"about_ca_system_score_gemma":0.0005629371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001501565,"about_ca_topic_score_gemma":0.002986175,"domain_scores_codex":[0.999711,0.00007527754,0.00001396567,0.00006872281,0.00009070157,0.00004039193],"domain_scores_gemma":[0.9992445,0.0002830923,0.0001323048,0.00006853076,0.0002058942,0.00006580747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001023034,0.0004468849,0.2110882,0.0005654563,0.0004537739,0.0006329825,0.000307557,0.1260971,0.2227866,0.009340842,0.004077786,0.4231799],"study_design_scores_gemma":[0.00006438399,0.0003210616,0.1354056,0.00003983972,0.0002436767,0.0004310048,0.00010779,0.8035936,0.04168586,0.01364,0.004421843,0.00004536369],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8053871,0.0007665604,0.1893352,0.0003250977,0.00001591663,0.0001577533,0.001376268,0.0006337651,0.002002361],"genre_scores_gemma":[0.9249107,0.0002539143,0.07047238,0.00003853946,0.00002141257,0.0001033361,0.003288863,0.00005285957,0.0008580766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001782296,"threshold_uncertainty_score":0.003968596,"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","authors":[{"name":"Suzanne K. Lau","is_ca":true},{"name":"Paul C. Boutros","is_ca":true},{"name":"Melania Pintilie","is_ca":true},{"name":"Fiona Blackhall","is_ca":true},{"name":"Chang‐Qi Zhu","is_ca":true},{"name":"Dan Strumpf","is_ca":true},{"name":"Michael R. Johnston","is_ca":true},{"name":"Gail Darling","is_ca":true},{"name":"Shaf Keshavjee","is_ca":true},{"name":"Thomas K. Waddell","is_ca":true},{"name":"Geoffrey Liu","is_ca":true},{"name":"Davina Lau","is_ca":true},{"name":"Linda Z. Penn","is_ca":true},{"name":"Frances A. Shepherd","is_ca":true},{"name":"Igor Jurišica","is_ca":true},{"name":"Sandy D. Der","is_ca":true},{"name":"Ming‐Sound Tsao","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001318675,0.0003632561,0.0005339111,0.001362827,0.0003468119,0.0005330794,0.000407558,0.0004671243,0.001076885],"category_scores_gemma":[0.003662494,0.00005716082,0.0004528232,0.0005786976,0.0002515381,0.0002927947,0.0002419649,0.0005330883,0.000478632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008321302,"about_ca_system_score_gemma":0.0008579408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001032581,"about_ca_topic_score_gemma":0.001179302,"domain_scores_codex":[0.9995807,0.00009106927,0.00004073938,0.00006167923,0.0001659036,0.00006000581],"domain_scores_gemma":[0.9982725,0.0006930302,0.0003015907,0.00008775468,0.0004856886,0.0001594322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00169565,0.0004453588,0.8528906,0.0001358254,0.0002137107,0.0002401185,0.00008173065,0.007848115,0.02112182,0.000479977,0.004452423,0.1103947],"study_design_scores_gemma":[0.0003879092,0.001768698,0.6606187,0.0001006261,0.0006721413,0.001979808,0.0002505017,0.2857617,0.03773182,0.004701342,0.005929031,0.00009773193],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760533,0.0007754042,0.01961188,0.0007149621,0.00007927283,0.0001232358,0.00142261,0.000208775,0.001010675],"genre_scores_gemma":[0.9800138,0.0000987054,0.01740021,0.0000645002,0.00004339123,0.00008290256,0.00195017,0.00001070222,0.0003356628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001362827,"threshold_uncertainty_score":0.006973922,"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","authors":[{"name":"Yuling Jiao","is_ca":true},{"name":"S. Lori Tausta","is_ca":false},{"name":"Neeru Gandotra","is_ca":false},{"name":"Ning Sun","is_ca":false},{"name":"Tie Liu","is_ca":true},{"name":"Nicole K. Clay","is_ca":true},{"name":"Teresa Ceserani","is_ca":true},{"name":"Meiqin Chen","is_ca":true},{"name":"Ligeng Ma","is_ca":true},{"name":"Matthew Holford","is_ca":false},{"name":"Huiyong Zhang","is_ca":true},{"name":"Hongyu Zhao","is_ca":false},{"name":"Xing‐Wang Deng","is_ca":false},{"name":"Timothy Nelson","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001317336,0.0002399571,0.0003419197,0.0008945428,0.0003203215,0.0004726253,0.0001630876,0.0001551486,0.0009618835],"category_scores_gemma":[0.0001265105,0.0001915454,0.0003302088,0.001250084,0.0001835765,0.0002710528,0.000281594,0.0003358147,0.0005468248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003621249,"about_ca_system_score_gemma":0.0005152055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003154367,"about_ca_topic_score_gemma":0.006966183,"domain_scores_codex":[0.9999137,0.000005144039,0.000004143645,0.00003878659,0.00001648729,0.00002175438],"domain_scores_gemma":[0.9998472,0.00002737034,0.00002789753,0.00002693855,0.0000349396,0.0000356274],"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":[0.0001150448,0.000008703801,0.007716228,0.00005908349,0.00002192192,0.00006039803,0.00008202289,0.0003512948,0.9804674,0.0004331527,0.0005342783,0.01015037],"study_design_scores_gemma":[0.00003157617,0.0002135358,0.7413722,0.00002722379,0.0002530988,0.0013709,0.0003776588,0.009427143,0.2115654,0.002927924,0.03237877,0.00005456581],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9346369,0.001531569,0.03048099,0.0001913362,0.00003262114,0.00003773315,0.02631851,0.001149583,0.005620729],"genre_scores_gemma":[0.9131114,0.002082829,0.04134137,0.000191507,0.00003322382,0.00009461698,0.03584157,0.0003880809,0.006915491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003154367,"threshold_uncertainty_score":0.006272018,"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","authors":[{"name":"Juan Francisco Villarreal-Chiu","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008268965,0.0004476857,0.0002775738,0.0009213981,0.0001984637,0.0007000723,0.0001610265,0.0003529206,0.0008767137],"category_scores_gemma":[0.0003218339,0.0001735183,0.0003385083,0.001859578,0.0002118248,0.0003427813,0.0002521115,0.0002409305,0.0008255419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003148498,"about_ca_system_score_gemma":0.0005175755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002684157,"about_ca_topic_score_gemma":0.001443732,"domain_scores_codex":[0.9997743,0.00001945888,0.00001719197,0.00007504948,0.00007807573,0.00003601058],"domain_scores_gemma":[0.9998708,0.00002567077,0.00003978181,0.000008257024,0.00003141117,0.00002402222],"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":[0.0004464099,0.00008186905,0.05425466,0.002813305,0.00008722457,0.0005241156,0.0005001966,0.001611511,0.7218859,0.001607418,0.001435151,0.2147522],"study_design_scores_gemma":[0.00002615181,0.0005098379,0.6561087,0.0005554126,0.0002926548,0.005222146,0.001631673,0.002231097,0.1650815,0.002202514,0.1660432,0.00009508725],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8070771,0.147596,0.009020237,0.0007918784,0.0001239276,0.0001117464,0.01977085,0.0002969533,0.01521138],"genre_scores_gemma":[0.8459513,0.108615,0.02047583,0.0002539557,0.00008070498,0.0001478065,0.01445117,0.0000590764,0.009965155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002684157,"threshold_uncertainty_score":0.005337119,"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","authors":[{"name":"Carole L. Yauk","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00777395,0.001073093,0.002049606,0.003624918,0.0008285803,0.002075478,0.001143053,0.001214407,0.001459638],"category_scores_gemma":[0.008549118,0.0006550995,0.001612067,0.00344811,0.0003849836,0.001172677,0.001324989,0.000915049,0.001127583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009405252,"about_ca_system_score_gemma":0.001108882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005437788,"about_ca_topic_score_gemma":0.00101163,"domain_scores_codex":[0.9876873,0.00278205,0.001363379,0.001667895,0.005832778,0.0006666383],"domain_scores_gemma":[0.9935027,0.002105107,0.0005839968,0.0007647732,0.002794996,0.0002485357],"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":[0.0008957656,0.0001281195,0.007552582,0.00141363,0.0003679104,0.000104132,0.0001508289,0.001768469,0.9025549,0.001216354,0.001173011,0.08267431],"study_design_scores_gemma":[0.0000545699,0.002007077,0.06373174,0.0002453023,0.001242313,0.001234521,0.0002547748,0.007104397,0.876691,0.001951518,0.04530711,0.0001756479],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5553579,0.03001405,0.3798947,0.001356512,0.0008026595,0.001741474,0.01519377,0.003803695,0.01183515],"genre_scores_gemma":[0.3338298,0.01636631,0.6141155,0.0007763578,0.0001872229,0.002677351,0.02605338,0.0005574726,0.00543663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00777395,"threshold_uncertainty_score":0.04111308,"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","authors":[{"name":"Jason Phillips","is_ca":false},{"name":"Daniel Svoboda","is_ca":false},{"name":"Arpit Tandon","is_ca":false},{"name":"Shyam A. Patel","is_ca":false},{"name":"Alex Sedykh","is_ca":false},{"name":"Deepak Mav","is_ca":false},{"name":"Byron Kuo","is_ca":true},{"name":"Carole L. Yauk","is_ca":true},{"name":"Longlong Yang","is_ca":false},{"name":"Russell S. Thomas","is_ca":false},{"name":"Jeff Gift","is_ca":false},{"name":"Jerry Davis","is_ca":false},{"name":"Louis Olszyk","is_ca":false},{"name":"B. Alex Merrick","is_ca":false},{"name":"Richard S. Paules","is_ca":false},{"name":"Fred Parham","is_ca":false},{"name":"Trey Saddler","is_ca":false},{"name":"Ruchir Shah","is_ca":false},{"name":"Scott S. Auerbach","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005281206,0.002286209,0.001885364,0.002368759,0.001063291,0.00318936,0.003294622,0.001411364,0.06499657],"category_scores_gemma":[0.006553502,0.002293989,0.002740934,0.001638665,0.0007377716,0.001493698,0.003065707,0.003329894,0.05087113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0012149,"about_ca_system_score_gemma":0.003298285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00316945,"about_ca_topic_score_gemma":0.004763609,"domain_scores_codex":[0.9971654,0.0003870598,0.00030926,0.0008114321,0.001112213,0.000214657],"domain_scores_gemma":[0.9967468,0.001525474,0.0002463097,0.0005473868,0.0007746271,0.0001593994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001776839,0.000222739,0.005765626,0.003781361,0.0004421232,0.0008627956,0.0008289178,0.008913109,0.08538679,0.008693162,0.7721235,0.111203],"study_design_scores_gemma":[0.0006022804,0.0002458098,0.009848394,0.0005684613,0.0002190414,0.0007115974,0.0002124306,0.04551249,0.1324403,0.02106044,0.7880208,0.0005579279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.005462926,0.0005293731,0.3830606,0.0008409783,0.00050457,0.000854728,0.2070585,0.3919918,0.009696511],"genre_scores_gemma":[0.02592133,0.0008321633,0.5117707,0.003307418,0.0002152739,0.00673829,0.3180996,0.1121983,0.020917],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.06499657,"threshold_uncertainty_score":0.2174352,"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","authors":[{"name":"David F. Moore","is_ca":true},{"name":"Hong Li","is_ca":true},{"name":"Neal Jeffries","is_ca":true},{"name":"Violet Wright","is_ca":true},{"name":"Ronald A. Cooper","is_ca":true},{"name":"Abdel Elkahloun","is_ca":true},{"name":"Monique P. Gelderman","is_ca":true},{"name":"Enrique Zudaire","is_ca":true},{"name":"Gregg Blevins","is_ca":true},{"name":"Hua Yu","is_ca":true},{"name":"Ehud Goldin","is_ca":true},{"name":"Alison E. Baird","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003406749,0.0002375211,0.000265847,0.0005395648,0.000188861,0.0003945322,0.0001091568,0.0002529539,0.0009318512],"category_scores_gemma":[0.0005735513,0.00008316919,0.0001230728,0.0004553226,0.0001907957,0.0001183232,0.0001693978,0.0002322663,0.0004087353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001349082,"about_ca_system_score_gemma":0.0001297969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002313253,"about_ca_topic_score_gemma":0.0004156326,"domain_scores_codex":[0.9996458,0.00007483438,0.00002627322,0.0001444517,0.00007736067,0.00003130066],"domain_scores_gemma":[0.9998042,0.00006881139,0.00003724866,0.00002283223,0.00004481168,0.00002211647],"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":[0.002036448,0.0002669725,0.2347881,0.0002015507,0.0001300724,0.0003374431,0.0003207998,0.0003719428,0.7230736,0.00009126603,0.0004430192,0.03793883],"study_design_scores_gemma":[0.0001268551,0.003321409,0.7148279,0.00006803853,0.0002943227,0.002692002,0.0004163824,0.002453476,0.2709498,0.0004795382,0.004335517,0.00003486212],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913697,0.001371319,0.005241424,0.00006712216,0.00003295691,0.00008443731,0.0007952219,0.00003511207,0.001002605],"genre_scores_gemma":[0.9887577,0.0008258656,0.007602048,0.0001744649,0.00005618832,0.0002690974,0.001510057,0.000009790679,0.0007947334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0009318512,"threshold_uncertainty_score":0.003117383,"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","authors":[{"name":"Paul D. McNicholas","is_ca":true},{"name":"Thomas Brendan Murphy","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005221775,0.001340169,0.001908002,0.00218399,0.0006772004,0.001582358,0.002320992,0.001499818,0.001395689],"category_scores_gemma":[0.01220773,0.0008048644,0.001947457,0.003973768,0.001198261,0.001996074,0.00149755,0.00198666,0.00163961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001337463,"about_ca_system_score_gemma":0.001464452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005352209,"about_ca_topic_score_gemma":0.003876729,"domain_scores_codex":[0.9963771,0.001559985,0.0001713608,0.0007931546,0.0009599967,0.000138492],"domain_scores_gemma":[0.9958866,0.002558795,0.0003943622,0.0005001835,0.0005895766,0.00007043288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001931857,0.0001012006,0.004048637,0.0005312556,0.0002667212,0.0001194597,0.0003842173,0.7398279,0.008474026,0.03887624,0.004249649,0.2029274],"study_design_scores_gemma":[0.0000131272,0.0000249608,0.001072658,0.00002928738,0.00003455353,0.00007854966,0.00001997219,0.967033,0.001678005,0.02824108,0.001738738,0.00003593684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003588445,0.0003341764,0.9950705,0.0001264549,0.00001254663,0.00003738274,0.0001327413,0.0004642743,0.0002335218],"genre_scores_gemma":[0.1836413,0.00170011,0.8088726,0.0002001927,0.0001436001,0.0005765536,0.002671791,0.0002992567,0.001894606],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005352209,"threshold_uncertainty_score":0.02761567,"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","authors":[{"name":"Sihua Peng","is_ca":false},{"name":"Qianghua Xu","is_ca":false},{"name":"Xuefeng B. Ling","is_ca":false},{"name":"Xiaoning Peng","is_ca":false},{"name":"Wei Du","is_ca":false},{"name":"Liangbiao Chen","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00168254,0.0007680352,0.0008981143,0.001307602,0.000241044,0.0008642734,0.0004807502,0.0005572283,0.0004906642],"category_scores_gemma":[0.003470237,0.0001887204,0.000669561,0.001072307,0.0003391008,0.0008136705,0.0002904598,0.0007533862,0.0004630192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002950308,"about_ca_system_score_gemma":0.0003880406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007734442,"about_ca_topic_score_gemma":0.001365345,"domain_scores_codex":[0.9992142,0.0003027768,0.00006548601,0.000143613,0.000218842,0.0000550874],"domain_scores_gemma":[0.9987599,0.0007291646,0.0001338612,0.0001806588,0.0001681564,0.00002833216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003119635,0.0002284597,0.01802808,0.0002347196,0.0002834358,0.0001224431,0.0000811893,0.09067847,0.1206522,0.002363997,0.001207813,0.7658072],"study_design_scores_gemma":[0.00003535641,0.0005268273,0.01751843,0.00003802965,0.0001356034,0.0003336375,0.00008652781,0.8763282,0.09179222,0.009997517,0.003123466,0.00008422342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2395388,0.0011569,0.7556635,0.0004170299,0.0000843087,0.0001333819,0.0003989477,0.001536972,0.00106999],"genre_scores_gemma":[0.4715691,0.0006747377,0.525642,0.0001034459,0.00005768511,0.0001641362,0.0008623708,0.00005638992,0.0008702193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00168254,"threshold_uncertainty_score":0.008898199,"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","authors":[{"name":"Kristian R. von Schalburg","is_ca":true},{"name":"Matthew L. Rise","is_ca":false},{"name":"Glenn A. Cooper","is_ca":true},{"name":"Gordon D. Brown","is_ca":true},{"name":"A. R. Gibbs","is_ca":true},{"name":"Colleen C. Nelson","is_ca":true},{"name":"William S. Davidson","is_ca":true},{"name":"Ben F. Koop","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001614368,0.00064566,0.0005047707,0.0005546649,0.0004136861,0.0008462455,0.0006652235,0.0008361958,0.003709895],"category_scores_gemma":[0.0008957952,0.0004779028,0.0006276575,0.0004984715,0.0005204066,0.0005652148,0.0007919309,0.0008339293,0.00282072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004925656,"about_ca_system_score_gemma":0.0004267669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006084435,"about_ca_topic_score_gemma":0.001492466,"domain_scores_codex":[0.9987148,0.0001911292,0.0001079497,0.0003765502,0.0004929926,0.0001164971],"domain_scores_gemma":[0.9994648,0.0001840893,0.00005979515,0.0001083683,0.0001372209,0.00004565108],"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":[0.00006989157,0.00001552272,0.0006051736,0.0001386346,0.00001816521,0.00002108399,0.00002536273,0.0002080576,0.9918413,0.0002867634,0.0003831406,0.006386932],"study_design_scores_gemma":[0.0000164658,0.0002484404,0.00668785,0.00002535339,0.00004259391,0.000333256,0.00003689741,0.002023126,0.9694679,0.0003716087,0.02070559,0.00004095366],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3463992,0.007457731,0.6104927,0.002088397,0.0005761946,0.000786522,0.00766363,0.005286493,0.01924908],"genre_scores_gemma":[0.3011157,0.005100872,0.6565078,0.002002866,0.000131739,0.00209737,0.01089034,0.0006903589,0.02146299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003709895,"threshold_uncertainty_score":0.01241082,"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","authors":[{"name":"Wai-Ho Au","is_ca":false},{"name":"Keith C. C. Chan","is_ca":false},{"name":"Alexander Wong","is_ca":true},{"name":"Yang Wang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004971422,0.00112001,0.001732437,0.004780129,0.001624621,0.001981142,0.001770587,0.001037808,0.001361583],"category_scores_gemma":[0.01010078,0.0005443972,0.002351645,0.006520364,0.001071852,0.001832373,0.001215397,0.002162342,0.00122128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001176773,"about_ca_system_score_gemma":0.001841439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002702489,"about_ca_topic_score_gemma":0.002398763,"domain_scores_codex":[0.994375,0.001752954,0.0004326528,0.0009608879,0.002275331,0.0002032141],"domain_scores_gemma":[0.9961064,0.001786604,0.0004120473,0.0007395246,0.0008275327,0.0001277876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002494027,0.0002696989,0.009273515,0.0008616008,0.000508021,0.0002518096,0.001002765,0.1034146,0.02538577,0.05058292,0.008381963,0.7998179],"study_design_scores_gemma":[0.00005750147,0.0002796327,0.006720603,0.0001780622,0.0002416183,0.0007962384,0.0003873379,0.8140094,0.03855082,0.08488781,0.05366154,0.0002294196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00471435,0.0006459797,0.9927246,0.0001120895,0.00005839611,0.0001253704,0.0002118832,0.0008011503,0.0006062459],"genre_scores_gemma":[0.0587114,0.0007654176,0.9384183,0.00008379762,0.00009350164,0.0003055089,0.0008688668,0.0001447773,0.0006084169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004971422,"threshold_uncertainty_score":0.02629167,"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","authors":[{"name":"Nikita Makretsov","is_ca":true},{"name":"David G. Huntsman","is_ca":true},{"name":"Torsten O. Nielsen","is_ca":true},{"name":"Erika Yorida","is_ca":true},{"name":"Michael L. Peacock","is_ca":true},{"name":"Maggie C.U. Cheang","is_ca":true},{"name":"Sandra E. Dunn","is_ca":true},{"name":"Malcolm Hayes","is_ca":false},{"name":"Matt van de Rijn","is_ca":false},{"name":"Chris Bajdik","is_ca":true},{"name":"C. Blake Gilks","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007166755,0.0003364128,0.0005737656,0.001476351,0.000385106,0.0006998673,0.0002806797,0.0002418818,0.0003725698],"category_scores_gemma":[0.002979703,0.0001352726,0.0005153096,0.001002498,0.0002544733,0.0002094401,0.0002896216,0.000306314,0.0003268272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004942074,"about_ca_system_score_gemma":0.0004544562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002152312,"about_ca_topic_score_gemma":0.002579666,"domain_scores_codex":[0.9991548,0.0002829028,0.00006565251,0.000179668,0.0002037502,0.0001131531],"domain_scores_gemma":[0.998808,0.0004257276,0.0002594768,0.0001578162,0.0002784996,0.00007051149],"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":[0.001389092,0.0004503855,0.3643474,0.0005589117,0.0008131234,0.0006063514,0.00166612,0.02402021,0.4242222,0.001060725,0.003462397,0.1774032],"study_design_scores_gemma":[0.00006683372,0.0005885494,0.849282,0.00007022882,0.0002927898,0.0009221659,0.0007999712,0.0840965,0.05494191,0.003384863,0.005444332,0.0001098868],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9591456,0.0008315104,0.03795448,0.0001307575,0.0000202242,0.0001522605,0.0006894232,0.0002511592,0.0008245978],"genre_scores_gemma":[0.9637622,0.0003083415,0.0331575,0.00003671701,0.00001649611,0.0001919629,0.002086374,0.00002669928,0.0004135807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002152312,"threshold_uncertainty_score":0.004279613,"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","authors":[{"name":"Wei Zhang","is_ca":false},{"name":"Shiwei Duan","is_ca":false},{"name":"Emily O. Kistner","is_ca":false},{"name":"Wasim K. Bleibel","is_ca":false},{"name":"R. Stephanie Huang","is_ca":false},{"name":"Tyson A. Clark","is_ca":false},{"name":"Tina X. Chen","is_ca":false},{"name":"Anthony Schweitzer","is_ca":false},{"name":"John E. Blume","is_ca":false},{"name":"Nancy J. Cox","is_ca":false},{"name":"M. Eileen Dolan","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001632165,0.0004892951,0.0005798864,0.002234631,0.0007034853,0.0007168674,0.0006077402,0.0005965411,0.002382943],"category_scores_gemma":[0.002564492,0.0002606147,0.0009977026,0.001453197,0.0008101368,0.0002066318,0.0004716262,0.0007685419,0.0002176303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003954066,"about_ca_system_score_gemma":0.0002895473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003156236,"about_ca_topic_score_gemma":0.003081933,"domain_scores_codex":[0.9981679,0.0007445624,0.0001052937,0.0005402716,0.0002299466,0.0002120853],"domain_scores_gemma":[0.9979141,0.00134911,0.0001950224,0.0001731716,0.0001768867,0.000191739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003973852,0.0003444719,0.5901515,0.00007985655,0.001602633,0.001355391,0.001370725,0.00126615,0.3778686,0.001498067,0.0001476879,0.02034105],"study_design_scores_gemma":[0.0000479511,0.0003767709,0.98748,0.000008117029,0.000359588,0.0006823263,0.0003825946,0.001997663,0.00772376,0.0004770411,0.0004428588,0.00002133213],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984799,0.00006927456,0.000904192,0.00001745043,0.000005225083,0.000007788141,0.000107277,0.000005286473,0.0004036553],"genre_scores_gemma":[0.9990222,0.00003366021,0.0005068664,0.00001468866,0.000005294653,0.000009266477,0.0001507703,0.00001213121,0.0002450504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003156236,"threshold_uncertainty_score":0.008631825,"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","authors":[{"name":"Chih Long Liu","is_ca":false},{"name":"Wijan Prapong","is_ca":false},{"name":"Yasodha Natkunam","is_ca":false},{"name":"Ash A. Alizadeh","is_ca":false},{"name":"Kelli Montgomery","is_ca":false},{"name":"C. Blake Gilks","is_ca":true},{"name":"Matt van de Rijn","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006342094,0.004824639,0.003619658,0.007073953,0.001832278,0.003514209,0.005723665,0.001779143,0.05830963],"category_scores_gemma":[0.01037801,0.003959264,0.002471893,0.005294906,0.0009636966,0.003062287,0.002534206,0.005151283,0.03144373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001776736,"about_ca_system_score_gemma":0.002623063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005061917,"about_ca_topic_score_gemma":0.005718166,"domain_scores_codex":[0.9971092,0.000335796,0.0006706152,0.0004729537,0.001102178,0.0003091468],"domain_scores_gemma":[0.9910999,0.004092663,0.0009356834,0.00158066,0.00177856,0.0005124758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00296084,0.0007061624,0.004425656,0.004225877,0.001193726,0.001236731,0.001419111,0.007101023,0.1031331,0.009659467,0.6014942,0.2624442],"study_design_scores_gemma":[0.002118598,0.0005202669,0.02122041,0.001123004,0.001063977,0.003215974,0.0004332119,0.1556541,0.2857112,0.04384872,0.4838907,0.001199753],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002968269,0.0003374421,0.4258036,0.0001795534,0.0003016003,0.001047395,0.03291082,0.5337044,0.002747006],"genre_scores_gemma":[0.02696841,0.001096405,0.7203502,0.0009389936,0.0002647501,0.01202112,0.1086547,0.1166514,0.01305408],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.05830963,"threshold_uncertainty_score":0.1950651,"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","authors":[{"name":"Yifeng Li","is_ca":true},{"name":"Alioune Ngom","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003480221,0.002407854,0.001341306,0.002517509,0.0005972263,0.001986553,0.002413835,0.001128573,0.04554033],"category_scores_gemma":[0.01349254,0.001087412,0.001797,0.002240151,0.0008397211,0.001722042,0.002546395,0.003075329,0.04211643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005390697,"about_ca_system_score_gemma":0.002638821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001616162,"about_ca_topic_score_gemma":0.00240288,"domain_scores_codex":[0.9983197,0.0005037411,0.0002144882,0.0002892965,0.0005904818,0.00008222288],"domain_scores_gemma":[0.9937423,0.003424133,0.0005046256,0.0008680324,0.001229266,0.000231579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002961564,0.0001585649,0.001359753,0.003016825,0.0003200483,0.0007333871,0.0004734317,0.04300165,0.01911071,0.06448986,0.3374327,0.5296068],"study_design_scores_gemma":[0.0002641946,0.0001137884,0.002381207,0.0006232244,0.00008119496,0.001528621,0.0001017383,0.3500966,0.01291506,0.2243195,0.4073864,0.0001885283],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0003408753,0.0004845917,0.9725868,0.0002573823,0.00008933412,0.0001007547,0.004408925,0.01961325,0.002118029],"genre_scores_gemma":[0.006380267,0.0007750741,0.9771947,0.0002608754,0.00008908325,0.001164002,0.007696939,0.003530022,0.002909071],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04554033,"threshold_uncertainty_score":0.1523476,"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","authors":[{"name":"Kun Yang","is_ca":false},{"name":"Zhipeng Cai","is_ca":true},{"name":"Jianzhong Li","is_ca":false},{"name":"Guohui Lin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007050524,0.0009185729,0.001282332,0.002014989,0.0008004248,0.0008120408,0.001276723,0.0009581276,0.001187556],"category_scores_gemma":[0.009047967,0.0003965794,0.001229334,0.003709777,0.001360564,0.0007279796,0.0009667414,0.0008242402,0.001010387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007373635,"about_ca_system_score_gemma":0.001146383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006772691,"about_ca_topic_score_gemma":0.0007189894,"domain_scores_codex":[0.9940743,0.002616057,0.0003015479,0.001240212,0.001555556,0.000212234],"domain_scores_gemma":[0.9950408,0.002971614,0.000386931,0.0005785874,0.0009124081,0.0001096878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001437601,0.000243322,0.01702281,0.0009097118,0.0004948355,0.0005546516,0.0002988377,0.09596805,0.1226732,0.01143412,0.006468324,0.7424945],"study_design_scores_gemma":[0.0001472651,0.0008179385,0.01504679,0.00007108572,0.0002223978,0.0007213898,0.00009187322,0.8793719,0.06886196,0.02238142,0.01218695,0.0000789865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02532264,0.0009359634,0.9716108,0.0002282032,0.00007869198,0.0001431011,0.0003470904,0.00106826,0.0002651264],"genre_scores_gemma":[0.301036,0.0009847891,0.6928438,0.0003096264,0.0002801498,0.001027477,0.001781314,0.0002863547,0.001450556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007050524,"threshold_uncertainty_score":0.03728724,"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","authors":[{"name":"Christopher Corkum","is_ca":true},{"name":"Danielle P. Ings","is_ca":true},{"name":"Christopher J. Burgess","is_ca":false},{"name":"Sylwia Karwowska","is_ca":false},{"name":"Werner Kroll","is_ca":false},{"name":"Tomasz I. Michalak","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001960929,0.0001993243,0.0002775225,0.0004240577,0.0002000999,0.0004133875,0.0001503356,0.0002394116,0.001474141],"category_scores_gemma":[0.0003292958,0.00008363765,0.0002251244,0.0006206843,0.0001774089,0.0001202403,0.0001449744,0.0003480061,0.0007054879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001067381,"about_ca_system_score_gemma":0.0001752897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003408824,"about_ca_topic_score_gemma":0.0004922232,"domain_scores_codex":[0.999656,0.00004219693,0.00002867538,0.0001118997,0.0001143852,0.00004681393],"domain_scores_gemma":[0.9998863,0.00003893848,0.00001979009,0.000009232263,0.00003525005,0.00001051716],"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":[0.0005279515,0.00005958864,0.004802325,0.0001360533,0.0000264515,0.00006030784,0.0001283267,0.0001093075,0.9841687,0.00004992544,0.0001742072,0.00975684],"study_design_scores_gemma":[0.00006537259,0.001750488,0.1778982,0.0000787055,0.0002730847,0.001222981,0.0003365316,0.002126527,0.802658,0.0002171717,0.01333702,0.00003598348],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962898,0.00755076,0.01941425,0.0001420389,0.00009185862,0.0002713369,0.005978934,0.0001389176,0.00351404],"genre_scores_gemma":[0.9225459,0.006500426,0.04280187,0.0003640302,0.0001763812,0.001444852,0.02117537,0.0001051296,0.004886055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001474141,"threshold_uncertainty_score":0.004931509,"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","authors":[{"name":"Jianguo Xia","is_ca":true},{"name":"Christopher D. Fjell","is_ca":true},{"name":"Matthew L. Mayer","is_ca":true},{"name":"Olga M. Pena","is_ca":true},{"name":"David S. Wishart","is_ca":true},{"name":"Robert E. W. Hancock","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01097565,0.004172609,0.002901833,0.007010763,0.0008197536,0.002908955,0.004120144,0.001101703,0.02483222],"category_scores_gemma":[0.0106036,0.002191002,0.005098534,0.004507049,0.0005515842,0.0024512,0.004797379,0.002846351,0.007743374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074472,"about_ca_system_score_gemma":0.002297354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001934668,"about_ca_topic_score_gemma":0.002827988,"domain_scores_codex":[0.9966264,0.001041104,0.0004632946,0.0007889945,0.0009268557,0.0001533735],"domain_scores_gemma":[0.9933028,0.00459,0.0005568552,0.0009485697,0.000371228,0.000230526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004615903,0.0008951609,0.03069217,0.01428004,0.0229599,0.003646163,0.002254445,0.03097276,0.06556855,0.03214585,0.3975228,0.3944463],"study_design_scores_gemma":[0.001877547,0.0006893011,0.03808679,0.002015514,0.005520371,0.002369482,0.0005021544,0.1701554,0.0726617,0.08243765,0.6228675,0.0008166261],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.005623373,0.001454332,0.55358,0.0004691436,0.0002906395,0.0005424745,0.1202494,0.313773,0.004017615],"genre_scores_gemma":[0.03905055,0.00149624,0.7250602,0.0009078099,0.0002241202,0.004322872,0.1874506,0.03787426,0.003613366],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02483222,"threshold_uncertainty_score":0.08307207,"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","authors":[{"name":"Robert Maidstone","is_ca":false},{"name":"Toby Dylan Hocking","is_ca":true},{"name":"Guillem Rigaill","is_ca":false},{"name":"Paul Fearnhead","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009203659,0.002337479,0.003033969,0.004692438,0.001381096,0.002660994,0.00396439,0.003139174,0.004831675],"category_scores_gemma":[0.03079165,0.002166398,0.002790583,0.005821527,0.003223544,0.004506097,0.003890964,0.005253536,0.002182596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002235466,"about_ca_system_score_gemma":0.002805644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006955462,"about_ca_topic_score_gemma":0.006366158,"domain_scores_codex":[0.9958539,0.001509535,0.000347328,0.00106671,0.001020686,0.0002018128],"domain_scores_gemma":[0.9776362,0.01879253,0.0009643934,0.00108939,0.001244624,0.0002728009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002463757,0.0001325114,0.001465514,0.0002991156,0.0001684042,0.000148084,0.0002634808,0.6348819,0.003167384,0.06236197,0.003537368,0.2933279],"study_design_scores_gemma":[0.00003280175,0.00004263147,0.0002267705,0.00002770394,0.0000132906,0.00004525537,0.00001933224,0.9380102,0.0008671844,0.05901086,0.001685741,0.00001822878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001878675,0.0003538414,0.9965045,0.0001706397,0.0000242267,0.0000568515,0.00005053035,0.0006486106,0.0003120767],"genre_scores_gemma":[0.03370195,0.0004077399,0.9624128,0.0002204962,0.0001229259,0.0004614242,0.000552758,0.0005433451,0.001576604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009203659,"threshold_uncertainty_score":0.04867417,"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","authors":[{"name":"Aaron Carass","is_ca":false},{"name":"Snehashis Roy","is_ca":false},{"name":"Adrian Gherman","is_ca":false},{"name":"Jacob C. Reinhold","is_ca":false},{"name":"Andrew Jesson","is_ca":true},{"name":"Tal Arbel","is_ca":true},{"name":"Oskar Maier","is_ca":false},{"name":"Heinz Handels","is_ca":false},{"name":"Mohsen Ghafoorian","is_ca":false},{"name":"Bram Platel","is_ca":false},{"name":"Ariel Birenbaum","is_ca":false},{"name":"Hayit Greenspan","is_ca":false},{"name":"Dzung L. Pham","is_ca":false},{"name":"Ciprian M. Crainiceanu","is_ca":false},{"name":"Peter A. Calabresi","is_ca":false},{"name":"Jerry L. Prince","is_ca":false},{"name":"William R. Gray Roncal","is_ca":false},{"name":"Russell T. Shinohara","is_ca":false},{"name":"İpek Oğuz","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008634335,0.001311547,0.001275472,0.007597923,0.0005265413,0.002821392,0.0009090257,0.001720127,0.001111024],"category_scores_gemma":[0.02124584,0.0005472591,0.001241242,0.002491065,0.001058956,0.001665069,0.001335999,0.00113085,0.0006304678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001087975,"about_ca_system_score_gemma":0.001343798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00415916,"about_ca_topic_score_gemma":0.005670623,"domain_scores_codex":[0.9969174,0.0007588541,0.0004991219,0.0005989611,0.001021784,0.0002039159],"domain_scores_gemma":[0.988378,0.005256942,0.001423065,0.001569432,0.003121497,0.0002510815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001714516,0.0002351186,0.02343848,0.0008926272,0.0009053115,0.0008160039,0.001541504,0.2873195,0.1889337,0.009399195,0.004369323,0.4804347],"study_design_scores_gemma":[0.0000308695,0.0002795347,0.01836276,0.00007090644,0.0001681522,0.0006101967,0.0002210582,0.897724,0.0714782,0.007264265,0.003664273,0.0001258246],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1637472,0.001017832,0.8302755,0.0003362536,0.00006959634,0.0003335679,0.0007547565,0.002203696,0.00126149],"genre_scores_gemma":[0.3421334,0.0004644974,0.654564,0.00009659925,0.00005839032,0.0001328431,0.001443416,0.0004209668,0.0006858774],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008634335,"threshold_uncertainty_score":0.04566324,"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","authors":[{"name":"Jaroslav Novák","is_ca":true},{"name":"Robert Sladek","is_ca":true},{"name":"Thomas J. Hudson","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09474655,0.000533773,0.001875509,0.002183267,0.001368577,0.004666371,0.002641656,0.001334298,0.0005259935],"category_scores_gemma":[0.2117444,0.000594039,0.00119175,0.003241919,0.002479979,0.002838829,0.002038849,0.002157492,0.0002261644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001208447,"about_ca_system_score_gemma":0.002330244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001526921,"about_ca_topic_score_gemma":0.002827654,"domain_scores_codex":[0.9476784,0.03416808,0.004757902,0.006423651,0.00627292,0.0006990437],"domain_scores_gemma":[0.6122392,0.3306726,0.0165729,0.0292493,0.00935393,0.001912054],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002045669,0.0008191993,0.6789475,0.001475834,0.002713494,0.0007825379,0.001969442,0.02279021,0.08391351,0.01552144,0.003162269,0.1858589],"study_design_scores_gemma":[0.0003262401,0.001208304,0.6394028,0.0002379935,0.001246787,0.002463975,0.001573378,0.1482961,0.03633833,0.1567436,0.01190204,0.0002604531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3200042,0.00136044,0.6714929,0.00192224,0.0001646205,0.0007239111,0.001865881,0.0008118848,0.001653906],"genre_scores_gemma":[0.860971,0.0002768513,0.133163,0.000796083,0.0001531796,0.001244611,0.002879011,0.0002976505,0.0002186564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9052535,"threshold_uncertainty_score":0.5010737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}