{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":20,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":20,"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":"5d90b1ae8224","filters":{"venue":"International Journal of Data Mining and Bioinformatics"}},"results":[{"id":"W2072197604","doi":"10.1504/ijdmb.2011.038578","title":"SVM-RFE based feature selection for tandem mass spectrum quality assessment","year":2011,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"University of Saskatchewan; Université Laval","keywords":"Computer science; Tandem; Support vector machine; Pattern recognition (psychology); Artificial intelligence; Feature selection; Quality (philosophy); Quality assessment; Feature (linguistics); Mass spectrum; Machine learning; Evaluation methods; Chemistry; Reliability engineering; Mass spectrometry; Physics; Engineering","authors":[{"name":"Jiarui Ding","is_ca":true},{"name":"Jinhong Shi","is_ca":true},{"name":"Fang‐Xiang Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0812831393055651,"gpt":0.3529058030219979,"spread":0.2716226637164327,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007253456,0.0000974187,0.0001542721,0.00009141329,0.00005736616,0.00005127297,0.0003510174,0.00006647562,0.00001011474],"category_scores_gemma":[0.0001661365,0.00007676728,0.00005733596,0.00004088636,0.0000328264,0.00003680436,0.0001108577,0.00007596795,2.16269e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001761432,"about_ca_system_score_gemma":0.00009903478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004023371,"about_ca_topic_score_gemma":0.0000177328,"domain_scores_codex":[0.9991979,0.00002056,0.000367551,0.0001009463,0.0002012425,0.0001118219],"domain_scores_gemma":[0.99911,0.00003203865,0.0004337212,0.0001410535,0.0002341897,0.00004903725],"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":[0.003107989,0.00105845,0.3380772,0.0004501734,0.007185435,0.00002079038,0.001730603,0.00004866692,0.1643095,0.00408393,0.1302097,0.3497176],"study_design_scores_gemma":[0.0209761,0.009141347,0.1674556,0.0005578416,0.001109608,0.001004698,0.009604724,0.1403148,0.1802876,0.002671981,0.464292,0.002583705],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3173778,0.0006268294,0.674973,0.001899644,0.001474083,0.0002233056,0.0007142317,0.00001125085,0.002699848],"genre_scores_gemma":[0.4393672,0.0003786061,0.5592926,0.0002488109,0.0003549115,0.00000169312,0.0002618161,0.000006870112,0.00008746512],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3471338,"threshold_uncertainty_score":0.3130479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063036182","doi":"10.1504/ijdmb.2006.009920","title":"Bi-level clustering of mixed categorical and numerical biomedical data","year":2006,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Data type; Computer science; Data mining; Artificial intelligence; Machine learning","authors":[{"name":"Bill Andreopoulos","is_ca":true},{"name":"Aijun An","is_ca":true},{"name":"Xiaogang Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1019047829298678,"gpt":0.3569539844642329,"spread":0.2550492015343652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007990333,0.00009886799,0.0002038957,0.000250333,0.00004286364,0.0001832398,0.002725622,0.0000500737,0.000001976235],"category_scores_gemma":[0.000304641,0.00007742592,0.00001708958,0.0001657146,0.000132072,0.0020468,0.00386073,0.0001616509,9.288214e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002564522,"about_ca_system_score_gemma":0.0001074682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003297573,"about_ca_topic_score_gemma":0.000003830962,"domain_scores_codex":[0.9981415,0.00002794362,0.0007155047,0.0001589,0.0007922238,0.000163922],"domain_scores_gemma":[0.9984868,0.0002742905,0.0003933182,0.0005062743,0.000228262,0.0001110286],"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":[0.0000333745,0.00009267765,0.0006406522,0.00005318322,0.00009095223,0.00009073778,0.0003120343,0.00005487994,0.000208397,0.0002145683,0.002941543,0.995267],"study_design_scores_gemma":[0.00062458,0.0001197354,0.001481823,0.00008508408,0.000009285175,0.001515184,0.0001565801,0.99239,0.00007030753,0.0001338228,0.003316827,0.00009680893],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005758441,0.0001587197,0.9925163,0.0008636056,0.0003889063,0.00002823906,0.0002008397,0.00001029409,0.00007464011],"genre_scores_gemma":[0.1756194,0.0001022919,0.8239229,0.00002802152,0.0001860232,2.040133e-7,0.0001165953,0.000004668612,0.00001983355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9951702,"threshold_uncertainty_score":0.5064929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067203347","doi":"10.1504/ijdmb.2008.016753","title":"Gene Regulatory Network modelling: a state-space approach","year":2008,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Dalian University of Technology","keywords":"Principal component analysis; Gene regulatory network; Probabilistic logic; State variable; Computer science; Bayesian network; State (computer science); State space; Control (management); Bayesian information criterion; Expression (computer science); Statistical model; State-space representation; Data mining; Gene; Mathematics; Artificial intelligence; Gene expression; Biology; Statistics; Genetics; Algorithm; Physics","authors":[{"name":"Fang‐Xiang Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0413704728274463,"gpt":0.2592375920972098,"spread":0.2178671192697635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004974115,0.0001240036,0.000176062,0.00008674233,0.00007703376,0.00004248806,0.0006353718,0.00007328115,0.00000252541],"category_scores_gemma":[0.0000337456,0.0001059174,0.00006854015,0.00007648629,0.00009327954,0.00004825361,0.0003333453,0.00008366367,9.553498e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001302251,"about_ca_system_score_gemma":0.0001143215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001972922,"about_ca_topic_score_gemma":0.000001319498,"domain_scores_codex":[0.9988051,0.00002795765,0.0005048635,0.0001305451,0.0003738757,0.0001576655],"domain_scores_gemma":[0.9988075,0.00001615535,0.0004508567,0.0003521694,0.0002708837,0.0001023675],"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":[0.001022563,0.0004356024,0.03955233,0.00009095464,0.005371032,0.000173713,0.003559057,0.4999116,0.006461634,0.00005804198,0.1893711,0.2539923],"study_design_scores_gemma":[0.001456238,0.0002784942,0.001559512,0.00008847141,0.0001516866,0.003407024,0.0005056871,0.9657974,0.003465528,0.00004563837,0.02279244,0.0004519281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7629157,0.001722408,0.2345861,0.00008933654,0.0002372799,0.00004023766,0.00004760909,0.00000513754,0.0003562032],"genre_scores_gemma":[0.5803987,0.001830571,0.4165266,0.0001088656,0.0006442234,4.288468e-7,0.0003123908,0.00001086635,0.0001672525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4658858,"threshold_uncertainty_score":0.4319184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4252436249","doi":"10.1504/ijdmb.2018.094776","title":"Integration of k-means clustering algorithm with network analysis for drug-target interactions network prediction","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Cluster analysis; Bayes' theorem; Naive Bayes classifier; Computer science; Artificial intelligence; Drug discovery; Machine learning; Interaction network; In silico; Support vector machine; Classifier (UML); Computational biology; Pattern recognition (psychology); Data mining; Bioinformatics; Biology; Bayesian probability","authors":[{"name":"Sara Aghakhani","is_ca":true},{"name":"Ala Qabaja","is_ca":true},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04307975514025782,"gpt":0.3345422988701792,"spread":0.2914625437299214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001291389,0.0001101532,0.0002279466,0.0003178727,0.00009968389,0.0002069254,0.0008929725,0.00002718098,0.000004562432],"category_scores_gemma":[0.0001247571,0.00008606382,0.00007259654,0.0004979818,0.00007127987,0.002481361,0.0003322814,0.00009549067,3.690026e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004121867,"about_ca_system_score_gemma":0.000110346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007269544,"about_ca_topic_score_gemma":0.00005713151,"domain_scores_codex":[0.9984872,0.00005364774,0.00075598,0.0001312849,0.0004350533,0.0001368206],"domain_scores_gemma":[0.9973328,0.0005214156,0.0008828424,0.0002581826,0.0009458504,0.00005895523],"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":[0.0001779069,0.00007204224,0.003072849,0.00002497295,0.002042684,0.000003418478,0.003483441,0.1845315,0.00001736276,0.0007087283,0.005237208,0.8006278],"study_design_scores_gemma":[0.0003792451,0.0002013971,0.002036325,0.0001910268,0.0001415827,0.0001015902,0.0003378668,0.99442,0.00004313439,0.0004920519,0.001573425,0.00008233459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00398559,0.00003858528,0.9941746,0.0003190012,0.001052,0.00007561491,0.0001752359,0.00001374098,0.0001656408],"genre_scores_gemma":[0.05203418,0.00002421599,0.9467968,0.00008906472,0.0008420667,0.000001630035,0.0001891342,0.000004904317,0.00001794712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8098885,"threshold_uncertainty_score":0.3509581,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1975341743","doi":"10.1504/ijdmb.2010.035898","title":"Using Gene Ontology to enhance effectiveness of similarity measures for microarray data","year":2010,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Redundancy (engineering); Gene ontology; Computer science; Semantic similarity; Data mining; Feature selection; Similarity (geometry); Gene selection; Microarray analysis techniques; Artificial intelligence; Pattern recognition (psychology); Gene; Gene expression; Biology; Genetics","authors":[{"name":"Zheng Chen","is_ca":true},{"name":"Jian Tang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08225493591224538,"gpt":0.400972716185559,"spread":0.3187177802733136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009433402,0.00006746373,0.0001224298,0.0000755644,0.00002850235,0.00002826679,0.0008581082,0.00007153614,0.000001685861],"category_scores_gemma":[0.0005312133,0.00005622169,0.00002261604,0.00003165196,0.00004401616,0.00004243381,0.0003364496,0.00006105265,1.218812e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005796529,"about_ca_system_score_gemma":0.0001279086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004639323,"about_ca_topic_score_gemma":0.00002239467,"domain_scores_codex":[0.9992855,0.00002701163,0.0003414715,0.0001204088,0.0001531289,0.00007252433],"domain_scores_gemma":[0.99877,0.00005214543,0.0003238904,0.0004043559,0.0003980463,0.00005155183],"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":[0.0002709596,0.00002925351,0.0009541618,0.00003266445,0.00008471137,3.561696e-7,0.00007029805,0.000008988123,0.9349967,0.000006482236,0.001163368,0.06238208],"study_design_scores_gemma":[0.000797971,0.0002507297,0.001835458,0.0001491256,0.00005872175,0.000181429,0.0002348462,0.006988453,0.957881,0.00003495308,0.03143234,0.0001549472],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7165506,0.0001446617,0.281812,0.0001505946,0.0006494477,0.000083824,0.0005669753,0.000001288623,0.00004061244],"genre_scores_gemma":[0.6870803,0.00007288565,0.3121783,0.00008436623,0.0001860996,8.453645e-7,0.0003874568,0.000004356429,0.000005461984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06222713,"threshold_uncertainty_score":0.2292654,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018695726","doi":"10.1504/ijdmb.2011.040384","title":"Image segmentation of biofilm structures using optimal multi-level thresholding","year":2011,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Bacterial biofilms and quorum sensing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"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":"Universidad de Atacama; Ontario Innovation Trust","keywords":"Thresholding; Segmentation; Artificial intelligence; Image segmentation; Computer science; Cluster analysis; Pattern recognition (psychology); Rand index; Process (computing); Set (abstract data type); Computer vision; Image (mathematics)","authors":[{"name":"Darío Rojas","is_ca":false},{"name":"Luis Rueda","is_ca":true},{"name":"Alioune Ngom","is_ca":true},{"name":"Homero Hurrutia","is_ca":false},{"name":"Gerardo Cárcamo‐Oyarce","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1163285617521467,"gpt":0.3320784984421196,"spread":0.2157499366899729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002453756,0.00008700167,0.0001160043,0.00008994644,0.0000317314,0.00004375345,0.0003023724,0.00006163682,0.000009669019],"category_scores_gemma":[0.00007256589,0.00007067641,0.00003520365,0.00002851638,0.00007149568,0.00008865041,0.0002324813,0.00004872864,1.814383e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006971165,"about_ca_system_score_gemma":0.0000524215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001399245,"about_ca_topic_score_gemma":0.000002944092,"domain_scores_codex":[0.9992204,0.00001317778,0.0004506706,0.00007450541,0.0001543602,0.00008689593],"domain_scores_gemma":[0.9990791,0.000008666778,0.0005109578,0.0001333905,0.0002263236,0.00004154582],"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":[0.0001536889,0.00003071557,0.001472197,0.00002090844,0.0001762984,0.00000576473,0.000688863,0.000006453432,0.9432079,0.000006758048,0.0001767301,0.05405369],"study_design_scores_gemma":[0.002445623,0.0005274843,0.007414463,0.0002736409,0.0001415814,0.001161525,0.005307749,0.04877076,0.9331096,0.000008027404,0.0004819492,0.0003576207],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.97786,0.00009868729,0.02133465,0.00001509744,0.000350511,0.00003020203,0.0002532245,0.000001606136,0.00005602041],"genre_scores_gemma":[0.4086001,0.00009286519,0.5910506,0.00003185808,0.0001048769,4.028738e-8,0.0001124803,0.000004370383,0.000002880547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5697159,"threshold_uncertainty_score":0.2882101,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146392361","doi":"10.1504/ijdmb.2013.056616","title":"A robust hidden semi-Markov model with application to aCGH data processing","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"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; BC Cancer Agency; University of British Columbia Hospital","funders":"University of British Columbia","keywords":"Outlier; Hidden Markov model; Markov model; Computer science; Benchmark (surveying); Glioblastoma; Comparative genomic hybridization; Markov chain; Reliability (semiconductor); Data-driven; Data mining; Artificial intelligence; Machine learning; Biology; Power (physics)","authors":[{"name":"Jiarui Ding","is_ca":true},{"name":"Sohrab P. Shah","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04764101485050556,"gpt":0.3031798806265017,"spread":0.2555388657759962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002372889,0.00008385089,0.00008415034,0.0000817625,0.00004036184,0.0001474586,0.0009912713,0.00004770251,0.000004389954],"category_scores_gemma":[0.00006885183,0.00006104424,0.00001011239,0.00005895927,0.0000271204,0.0001471677,0.0004706017,0.00005654032,0.000002520223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000108103,"about_ca_system_score_gemma":0.0001360161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004126513,"about_ca_topic_score_gemma":0.000006107916,"domain_scores_codex":[0.9991704,0.000008694701,0.0003204594,0.0001466869,0.0002676909,0.00008612331],"domain_scores_gemma":[0.9988013,0.000007801164,0.0003146956,0.0004442027,0.000344635,0.00008735229],"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":[0.00009658203,0.00003866629,0.0007378631,0.00002454976,0.00007071928,6.664728e-7,0.0003068675,0.0004011824,0.02227538,0.000003213346,0.04432654,0.9317178],"study_design_scores_gemma":[0.0008548965,0.0001858004,0.0007685813,0.0002244492,0.00004347274,0.0002124653,0.001595862,0.9725981,0.002622346,0.00001769037,0.02064411,0.0002322282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1298782,0.0002371306,0.8663247,0.002293146,0.0001060728,0.0001738436,0.0001976763,0.000007603165,0.0007816175],"genre_scores_gemma":[0.5478618,0.0001584091,0.4501775,0.0005433836,0.0002147182,0.000005256913,0.0009014518,0.000009074987,0.0001284526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9721969,"threshold_uncertainty_score":0.2489312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891379954","doi":"10.1504/ijdmb.2018.10016075","title":"Integration of k-means clustering algorithm with network analysis for drug-target interactions network prediction","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Drug; Algorithm; Network analysis; k-means clustering; Data mining; Artificial intelligence; Biology; Pharmacology; Physics","authors":[{"name":"Sara Aghakhani","is_ca":true},{"name":"Ala Qabaja","is_ca":true},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04307975514025782,"gpt":0.3345422988701792,"spread":0.2914625437299214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001291389,0.0001101532,0.0002279466,0.0003178727,0.00009968389,0.0002069254,0.0008929725,0.00002718098,0.000004562432],"category_scores_gemma":[0.0001247571,0.00008606382,0.00007259654,0.0004979818,0.00007127987,0.002481361,0.0003322814,0.00009549067,3.690026e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004121867,"about_ca_system_score_gemma":0.000110346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007269544,"about_ca_topic_score_gemma":0.00005713151,"domain_scores_codex":[0.9984872,0.00005364774,0.00075598,0.0001312849,0.0004350533,0.0001368206],"domain_scores_gemma":[0.9973328,0.0005214156,0.0008828424,0.0002581826,0.0009458504,0.00005895523],"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":[0.0001779069,0.00007204224,0.003072849,0.00002497295,0.002042684,0.000003418478,0.003483441,0.1845315,0.00001736276,0.0007087283,0.005237208,0.8006278],"study_design_scores_gemma":[0.0003792451,0.0002013971,0.002036325,0.0001910268,0.0001415827,0.0001015902,0.0003378668,0.99442,0.00004313439,0.0004920519,0.001573425,0.00008233459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00398559,0.00003858528,0.9941746,0.0003190012,0.001052,0.00007561491,0.0001752359,0.00001374098,0.0001656408],"genre_scores_gemma":[0.05203418,0.00002421599,0.9467968,0.00008906472,0.0008420667,0.000001630035,0.0001891342,0.000004904317,0.00001794712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8098885,"threshold_uncertainty_score":0.3509581,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119632600","doi":"10.1504/ijdmb.2011.040388","title":"Combining multiple perspective as intelligent agents into robust approach for biomarker detection in gene expression data","year":2011,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Perspective (graphical); Gene; Gene expression; Biomarker; Computer science; Computational biology; Expression (computer science); microRNA; Data mining; Biology; Artificial intelligence; Genetics","authors":[{"name":"Mohammed Alshalalfa","is_ca":true},{"name":"Ghada Naji","is_ca":false},{"name":"Ala Qabaja","is_ca":true},{"name":"Reda Alhajj","is_ca":true},{"name":"Jon Rokne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1596503619878044,"gpt":0.336622064281259,"spread":0.1769717022934547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007373284,0.00009501711,0.0001193483,0.0002397783,0.0000918507,0.0001140539,0.001996252,0.00004685287,0.000002486829],"category_scores_gemma":[0.0002427733,0.00007970985,0.00002484058,0.0001328535,0.00004170412,0.002441065,0.00109424,0.00009946938,0.000001171098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006593099,"about_ca_system_score_gemma":0.00007228009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006687723,"about_ca_topic_score_gemma":0.00001058,"domain_scores_codex":[0.9988776,0.00002233087,0.0005149733,0.0001921391,0.0002823678,0.0001106189],"domain_scores_gemma":[0.9986597,0.0001141848,0.0004076963,0.0004553579,0.0002967787,0.00006625487],"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":[0.0002728147,0.001020854,0.003266001,0.00006115615,0.0003501326,0.00002128678,0.03292635,0.0003411169,0.00168387,0.001265967,0.002378504,0.956412],"study_design_scores_gemma":[0.0006177345,0.00008561528,0.0009251338,0.00006886211,0.00001053867,0.0001797372,0.004625457,0.9911951,0.001414982,0.0004066427,0.00036748,0.0001027617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01386599,0.000115191,0.9852022,0.0001273747,0.0002622577,0.0001171046,0.00008431279,0.00001126225,0.000214309],"genre_scores_gemma":[0.3008516,0.00009299121,0.6987962,0.00004209977,0.00005225166,0.000002550085,0.0001534139,0.000003543129,0.000005406898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.990854,"threshold_uncertainty_score":0.3709566,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150689251","doi":"10.1504/ijdmb.2013.054696","title":"A clustering approach for estimating parameters of a profile hidden Markov model","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"University of Waterloo; University of Tehran; Iran National Science Foundation","keywords":"Hidden Markov model; Cluster analysis; Pattern recognition (psychology); Computer science; Markov chain Monte Carlo; Markov chain; Artificial intelligence; Markov model; Bayesian probability; Mathematics; Algorithm; Machine learning","authors":[{"name":"Rosa Aghdam","is_ca":false},{"name":"Hamid Pezeshk","is_ca":false},{"name":"Seyed Amir Malekpour","is_ca":true},{"name":"Soudabeh Shemehsavar","is_ca":false},{"name":"Changiz Eslahchi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06555281677021664,"gpt":0.3188018336758385,"spread":0.2532490169056219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007542415,0.0000844429,0.0001773733,0.0001359067,0.00003122294,0.0001913401,0.001190304,0.00003784728,0.000001075126],"category_scores_gemma":[0.0002021747,0.00006352737,0.00004266548,0.00005228075,0.00003024509,0.001806585,0.0004524578,0.00007280089,2.056093e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001254837,"about_ca_system_score_gemma":0.00006743253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004042022,"about_ca_topic_score_gemma":1.929702e-7,"domain_scores_codex":[0.9989329,0.00001676771,0.0005808762,0.00009021727,0.0002677173,0.0001115338],"domain_scores_gemma":[0.9986558,0.0001518702,0.0005783045,0.000231074,0.000322244,0.00006073885],"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":[0.000008674156,0.00001843044,0.00001975792,0.00006409115,0.0000564154,5.107701e-7,0.001101156,0.00006509409,0.00006322383,0.00003634271,0.001090254,0.997476],"study_design_scores_gemma":[0.0003518705,0.00006417711,0.000009927744,0.0001166192,0.00001262305,0.0001306572,0.0001595827,0.9986648,0.00008132104,0.0003333163,0.000003847425,0.00007127033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002885956,0.00003225511,0.9961635,0.0002213527,0.0001807659,0.0001148441,0.00004752254,0.000007126941,0.0003466474],"genre_scores_gemma":[0.01058219,0.00001126255,0.9891937,0.0001098802,0.00005490531,0.000003852793,0.00002055429,0.000004312176,0.00001933739],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9985997,"threshold_uncertainty_score":0.2590571,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4230716249","doi":"10.1504/ijdmb.2020.112850","title":"MHCherryPan: a novel pan-specific model for binding affinity prediction of class I HLA-peptide","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Human leukocyte antigen; Benchmark (surveying); Computational biology; Allele; Immune system; Artificial immune system; Biology; Computer science; Class (philosophy); Peptide; Artificial intelligence; Antigen; Immunology; Gene; Genetics; Biochemistry; Geography","authors":[{"name":"Xuezhi Xie","is_ca":true},{"name":"Yuanyuan Han","is_ca":true},{"name":"Kaizhong Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1157585872825637,"gpt":0.2929261544225714,"spread":0.1771675671400076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003476207,0.0001059897,0.0001708144,0.00006773903,0.00003736304,0.00006374464,0.0005320844,0.0000780562,0.000001463004],"category_scores_gemma":[0.0001744869,0.00008806781,0.00006797957,0.00004600304,0.00003395343,0.0001031174,0.000273407,0.00007981592,3.885685e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009408412,"about_ca_system_score_gemma":0.00008433775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.44719e-7,"about_ca_topic_score_gemma":7.319253e-7,"domain_scores_codex":[0.9988704,0.000005670975,0.0007204241,0.00008451405,0.0002170487,0.0001019709],"domain_scores_gemma":[0.998815,0.00003087988,0.0006294281,0.0001645257,0.000298525,0.00006161743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003147477,0.0006188831,0.004118044,0.0009554221,0.002920612,0.000003713658,0.01353642,0.004135551,0.4879043,0.0005052672,0.07974154,0.4024128],"study_design_scores_gemma":[0.002084413,0.0005376021,0.0002514114,0.0001141815,0.00005519513,0.0001031552,0.003319034,0.9705908,0.008187351,0.000008976749,0.01460493,0.0001430022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5689059,0.0002874327,0.4276636,0.0005902587,0.0002371442,0.0001230487,0.001960133,0.000005283428,0.000227139],"genre_scores_gemma":[0.6987544,0.0006939322,0.299195,0.0001867103,0.000300107,0.000001454704,0.0008355454,0.00001052383,0.00002231578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9664552,"threshold_uncertainty_score":0.3591301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045369746","doi":"10.1504/ijdmb.2013.056090","title":"Integrating machine learning techniques into robust data enrichment approach and its application to gene expression data","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Machine learning; Sample (material); Data mining; Process (computing); Artificial intelligence; Domain (mathematical analysis); Expression (computer science); Representation (politics); Independence (probability theory); Domain knowledge; Probabilistic logic","authors":[{"name":"Utku Erdoğdu","is_ca":false},{"name":"Mehmet Tan","is_ca":false},{"name":"Reda Alhajj","is_ca":true},{"name":"Faruk Polat","is_ca":false},{"name":"Jon Rokne","is_ca":true},{"name":"Douglas J. Demetrick","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04640594359035279,"gpt":0.3157167867357922,"spread":0.2693108431454394,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006432956,0.0001136712,0.0001167522,0.000114475,0.00007761027,0.0001531331,0.001503527,0.00006941001,0.000004373984],"category_scores_gemma":[0.0002943494,0.00008701869,0.000009915369,0.00005851041,0.0000227817,0.0002129429,0.002350872,0.0001180532,0.000001392941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001276458,"about_ca_system_score_gemma":0.00004923917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000176168,"about_ca_topic_score_gemma":0.000004465182,"domain_scores_codex":[0.9988905,0.00003428392,0.0004567022,0.0002559269,0.0002701011,0.00009247029],"domain_scores_gemma":[0.9985707,0.00002008702,0.0004025273,0.0006751015,0.0002327523,0.00009881473],"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":[0.00004578566,0.00005191613,0.001278104,0.00003700625,0.00006516683,5.058013e-7,0.0004115077,0.00002241262,0.435733,0.000007437917,0.008930247,0.553417],"study_design_scores_gemma":[0.0009963666,0.0003986021,0.0007559874,0.0003825851,0.00007127389,0.0003418943,0.003974955,0.7304515,0.1355034,0.00002334956,0.1265984,0.0005016237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09435966,0.001952407,0.9009864,0.001268845,0.0002129081,0.0003815856,0.0004059974,0.00002088203,0.0004113344],"genre_scores_gemma":[0.3173203,0.001306843,0.6747535,0.0002371957,0.0002907839,0.000007792487,0.006026357,0.00001046831,0.00004677277],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7304291,"threshold_uncertainty_score":0.3548519,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2946233355","doi":"10.1504/ijdmb.2019.099714","title":"Effective induction of gene regulatory networks using a novel recommendation method","year":2019,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Computer science; Data mining; Inference; Set (abstract data type); Receiver operating characteristic; Gene regulatory network; Data set; In silico; Precision and recall; Measure (data warehouse); Collaborative filtering; Machine learning; Artificial intelligence; Gene; Recommender system; Biology; Genetics","authors":[{"name":"Makbule Gülçin Özsoy","is_ca":false},{"name":"Faruk Polat","is_ca":false},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02846873594889496,"gpt":0.3166203865312484,"spread":0.2881516505823534,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008579244,0.00008652148,0.0001652106,0.000134002,0.00002148468,0.00002604345,0.0002876139,0.00008798116,0.000008809964],"category_scores_gemma":[0.00006497533,0.00007626042,0.00005607616,0.00007597454,0.00002790984,0.00006313335,0.0001800838,0.00006892771,2.609461e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000214617,"about_ca_system_score_gemma":0.00005039018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003693568,"about_ca_topic_score_gemma":0.000001754621,"domain_scores_codex":[0.9991135,0.00004126073,0.0004774108,0.00009971457,0.0001900771,0.00007805401],"domain_scores_gemma":[0.9986532,0.00003561185,0.0007470602,0.0002078836,0.0003176913,0.00003853651],"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":[0.0002633313,0.00008176952,0.007243915,0.00003487353,0.00132708,8.622097e-7,0.0002900941,0.01294227,0.2691423,0.00001132739,0.0006061386,0.708056],"study_design_scores_gemma":[0.001768387,0.0004048743,0.005710371,0.0002060749,0.0002577341,0.0007011971,0.001018224,0.9406303,0.04654967,0.000009522332,0.002495082,0.0002485348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6224362,0.000139636,0.376903,0.00003198357,0.000355221,0.0000512203,0.00003505193,0.000001252991,0.0000464383],"genre_scores_gemma":[0.6140057,0.00009005385,0.3852705,0.00004399825,0.0002968514,2.614238e-7,0.0002751443,0.000006604562,0.00001089053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9276881,"threshold_uncertainty_score":0.310981,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3063921741","doi":"10.1504/ijdmb.2020.10031424","title":"Identification of protein hot regions by combing structure-based classification, energy-based clustering and sequence-based conservation in evolution","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Combing; Cluster analysis; Computer science; Sequence (biology); Identification (biology); Data mining; Hot spot (computer programming); Pattern recognition (psychology); Biological system; Artificial intelligence; Materials science; Biology; Genetics","authors":[{"name":"Nansheng Chen","is_ca":true},{"name":"Xiaolong Zhang","is_ca":false},{"name":"Haomin Gan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03435348076170269,"gpt":0.2755679535106321,"spread":0.2412144727489294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002318686,0.00008990947,0.0001176694,0.0001028412,0.00003269055,0.00005294588,0.00028079,0.00008304633,8.580833e-7],"category_scores_gemma":[0.0002277237,0.00008425197,0.00002065595,0.00008587065,0.00008447725,0.0000635904,0.00005948709,0.00006922462,3.468524e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002392518,"about_ca_system_score_gemma":0.0001897402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001620327,"about_ca_topic_score_gemma":0.00003097333,"domain_scores_codex":[0.9989785,0.00003573866,0.0005866921,0.0001136887,0.0002147413,0.00007064075],"domain_scores_gemma":[0.9988484,0.00002620434,0.0006780842,0.0001468072,0.0002510931,0.00004942916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006193497,0.00005186885,0.01104988,0.0002046417,0.00007837066,0.000003129971,0.0001986448,0.001500657,0.9588283,0.000244784,0.0005944725,0.02662592],"study_design_scores_gemma":[0.001377673,0.0001933531,0.001483552,0.0001804352,0.00002100767,0.00001497682,0.0002271019,0.9506624,0.04521989,0.0000762175,0.0004210403,0.0001223053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4800052,0.0001537034,0.5178738,0.001468801,0.00005383435,0.00008029372,0.0003551494,0.000003312103,0.000005952072],"genre_scores_gemma":[0.9584793,0.00002210301,0.04000654,0.0004236114,0.00004127007,0.000001643002,0.001018319,0.000005600106,0.00000165552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9491618,"threshold_uncertainty_score":0.3435696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103153231","doi":"10.1504/ijdmb.2012.048172","title":"Re-ranking with context for high-performance biomedical information retrieval","year":2012,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"U.S. National Library of Medicine","keywords":"Ranking (information retrieval); Context (archaeology); Information retrieval; Computer science; Data science; Biology; Paleontology","authors":[{"name":"Xiaoshi Yin","is_ca":false},{"name":"Jimmy Xiangji Huang","is_ca":true},{"name":"Zhoujun Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0339923099069285,"gpt":0.3003697377014244,"spread":0.266377427794496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000792942,0.00009918382,0.0001384654,0.0001071333,0.00005594558,0.00006475423,0.0004415015,0.0001075662,0.00000429814],"category_scores_gemma":[0.0004590888,0.00006754205,0.00002231591,0.00005254399,0.0001378182,0.0001701264,0.0001679019,0.00008230592,0.000001326485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001212136,"about_ca_system_score_gemma":0.00008248851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001904862,"about_ca_topic_score_gemma":0.000002042668,"domain_scores_codex":[0.9989483,0.00001221632,0.0004706652,0.00005815885,0.0003390478,0.0001716084],"domain_scores_gemma":[0.9990005,0.00007192674,0.0004069193,0.0001565059,0.0002643329,0.00009982345],"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":[0.0009271656,0.00005718766,0.006610164,0.00007069624,0.0002792031,0.000001232621,0.001025949,0.000002155952,0.0004743246,0.00002196973,0.009476258,0.9810537],"study_design_scores_gemma":[0.01395707,0.007573354,0.01596327,0.00133514,0.0003638236,0.001973749,0.02291483,0.01818413,0.0187395,0.00002835708,0.8978383,0.001128479],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9130077,0.0004008418,0.08447476,0.0008211721,0.000849323,0.00008537841,0.0002320401,0.000009064119,0.0001196846],"genre_scores_gemma":[0.8212212,0.0002036435,0.1770969,0.0004047182,0.0005052267,8.428207e-7,0.000549767,0.000004732362,0.0000129286],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9799252,"threshold_uncertainty_score":0.2754285,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130013930","doi":"10.1504/ijdmb.2013.056080","title":"Subtree selection in kernels for graph classification","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Cheminformatics; Feature selection; Computer science; In silico; Graph; Selection (genetic algorithm); Feature (linguistics); Data mining; Artificial intelligence; Machine learning; Pattern recognition (psychology); Theoretical computer science; Bioinformatics; Biology","authors":[{"name":"Mehmet Tan","is_ca":false},{"name":"Faruk Polat","is_ca":false},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09114874666879506,"gpt":0.3597068872948939,"spread":0.2685581406260988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008232552,0.00006716311,0.0001031946,0.000327876,0.00002829345,0.0003021426,0.0009674492,0.00003164751,0.000003247028],"category_scores_gemma":[0.0002898887,0.00005718474,0.00002779063,0.0001600957,0.00002127265,0.003465637,0.0001961366,0.00007153854,0.000002111263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003876911,"about_ca_system_score_gemma":0.0000942029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001385986,"about_ca_topic_score_gemma":0.000009894524,"domain_scores_codex":[0.9989549,0.00003140628,0.0005273196,0.00009169111,0.0003033922,0.00009128355],"domain_scores_gemma":[0.9986569,0.0003942467,0.0003895602,0.0001175944,0.000398744,0.00004295375],"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":[0.00001498947,0.00004507419,0.004023468,0.00001564283,0.00004602899,0.000001135527,0.0007542758,0.0003724971,0.0001631538,0.001947171,0.002385179,0.9902314],"study_design_scores_gemma":[0.0004493912,0.0000602044,0.02195236,0.00005530291,0.000004428715,0.0001081721,0.0002471541,0.9724442,0.00006150126,0.003953014,0.0005957107,0.00006855183],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09274721,0.00003498441,0.9052516,0.001378123,0.0003343417,0.00008770508,0.00001889869,0.000008724436,0.0001384441],"genre_scores_gemma":[0.3169099,0.00003672927,0.682803,0.0001264993,0.00008403161,0.000002716273,0.00002608273,0.000002496115,0.000008553197],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9901628,"threshold_uncertainty_score":0.2913568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3137172717","doi":"10.1504/ijdmb.2020.10036329","title":"A network enhancement-based method for clustering of single cell RNA-seq data","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Cluster analysis; Computer science; Similarity (geometry); Data mining; Node (physics); Noise (video); Artificial intelligence; Pattern recognition (psychology); Physics","authors":[{"name":"Hong Dong Li","is_ca":false},{"name":"Fang‐Xiang Wu","is_ca":true},{"name":"Xiaoqing Peng","is_ca":false},{"name":"Yunpei Xu","is_ca":false},{"name":"Rongyuan Li","is_ca":false},{"name":"Xiaoshu Zhu","is_ca":false},{"name":"Lilu Guo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09629500041666537,"gpt":0.3209526518611276,"spread":0.2246576514444623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004484213,0.00009128354,0.0001595944,0.00003168837,0.00002774788,0.00005060249,0.0009108718,0.00005473853,0.000004296882],"category_scores_gemma":[0.0001619381,0.00007975949,0.00003853092,0.00003618876,0.0000299737,0.00004734597,0.0003347502,0.00005263113,2.050836e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005453826,"about_ca_system_score_gemma":0.00008790326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003806792,"about_ca_topic_score_gemma":0.000006353621,"domain_scores_codex":[0.9990453,0.00001803805,0.0005295588,0.0001172584,0.0001842476,0.0001056497],"domain_scores_gemma":[0.9989876,0.00006413407,0.000450041,0.0002456931,0.0001869058,0.00006559311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001744085,0.0002650174,0.0009202693,0.0004821302,0.0005296996,0.000006846115,0.0008047593,0.002001959,0.6058518,0.000006128034,0.02838049,0.3590069],"study_design_scores_gemma":[0.002660903,0.001249959,0.00001511373,0.0002033166,0.0001229895,0.00003193244,0.000476423,0.8538492,0.1048926,0.000008227862,0.03627821,0.0002110775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02077669,0.0003199745,0.9772298,0.000535988,0.0003316815,0.00006548462,0.0005958356,0.000002344051,0.0001421474],"genre_scores_gemma":[0.1435731,0.000110783,0.8536635,0.0009236261,0.0005240917,4.75917e-7,0.0011829,0.00000951936,0.00001203467],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8518472,"threshold_uncertainty_score":0.3252498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3214325870","doi":"10.1504/ijdmb.2020.113690","title":"A network enhancement-based method for clustering of single cell RNA-seq data","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Cluster analysis; Computer science; Similarity (geometry); Data mining; Node (physics); Noise (video); Artificial intelligence; Pattern recognition (psychology)","authors":[{"name":"Xiaoshu Zhu","is_ca":false},{"name":"Lilu Guo","is_ca":false},{"name":"Rongyuan Li","is_ca":false},{"name":"Yunpei Xu","is_ca":false},{"name":"Fang‐Xiang Wu","is_ca":true},{"name":"Xiaoqing Peng","is_ca":false},{"name":"Hong Dong Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09629500041666537,"gpt":0.3209526518611276,"spread":0.2246576514444623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004484213,0.00009128354,0.0001595944,0.00003168837,0.00002774788,0.00005060249,0.0009108718,0.00005473853,0.000004296882],"category_scores_gemma":[0.0001619381,0.00007975949,0.00003853092,0.00003618876,0.0000299737,0.00004734597,0.0003347502,0.00005263113,2.050836e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005453826,"about_ca_system_score_gemma":0.00008790326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003806792,"about_ca_topic_score_gemma":0.000006353621,"domain_scores_codex":[0.9990453,0.00001803805,0.0005295588,0.0001172584,0.0001842476,0.0001056497],"domain_scores_gemma":[0.9989876,0.00006413407,0.000450041,0.0002456931,0.0001869058,0.00006559311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001744085,0.0002650174,0.0009202693,0.0004821302,0.0005296996,0.000006846115,0.0008047593,0.002001959,0.6058518,0.000006128034,0.02838049,0.3590069],"study_design_scores_gemma":[0.002660903,0.001249959,0.00001511373,0.0002033166,0.0001229895,0.00003193244,0.000476423,0.8538492,0.1048926,0.000008227862,0.03627821,0.0002110775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02077669,0.0003199745,0.9772298,0.000535988,0.0003316815,0.00006548462,0.0005958356,0.000002344051,0.0001421474],"genre_scores_gemma":[0.1435731,0.000110783,0.8536635,0.0009236261,0.0005240917,4.75917e-7,0.0011829,0.00000951936,0.00001203467],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8518472,"threshold_uncertainty_score":0.3252498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3107387809","doi":"10.1504/ijdmb.2020.10033716","title":"MHCherryPan: a novel pan-specific model for binding affinity prediction of class I HLA-peptide","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Human leukocyte antigen; Benchmark (surveying); Computational biology; Allele; Immune system; Artificial immune system; Peptide; Computer science; Biology; Class (philosophy); Artificial intelligence; Antigen; Immunology; Gene; Genetics; Biochemistry; Geography","authors":[{"name":"Kaizhong Zhang","is_ca":true},{"name":"Yuanyuan Han","is_ca":true},{"name":"Xuezhi Xie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1157585872825637,"gpt":0.2929261544225714,"spread":0.1771675671400076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003476207,0.0001059897,0.0001708144,0.00006773903,0.00003736304,0.00006374464,0.0005320844,0.0000780562,0.000001463004],"category_scores_gemma":[0.0001744869,0.00008806781,0.00006797957,0.00004600304,0.00003395343,0.0001031174,0.000273407,0.00007981592,3.885685e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009408412,"about_ca_system_score_gemma":0.00008433775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.44719e-7,"about_ca_topic_score_gemma":7.319253e-7,"domain_scores_codex":[0.9988704,0.000005670975,0.0007204241,0.00008451405,0.0002170487,0.0001019709],"domain_scores_gemma":[0.998815,0.00003087988,0.0006294281,0.0001645257,0.000298525,0.00006161743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003147477,0.0006188831,0.004118044,0.0009554221,0.002920612,0.000003713658,0.01353642,0.004135551,0.4879043,0.0005052672,0.07974154,0.4024128],"study_design_scores_gemma":[0.002084413,0.0005376021,0.0002514114,0.0001141815,0.00005519513,0.0001031552,0.003319034,0.9705908,0.008187351,0.000008976749,0.01460493,0.0001430022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5689059,0.0002874327,0.4276636,0.0005902587,0.0002371442,0.0001230487,0.001960133,0.000005283428,0.000227139],"genre_scores_gemma":[0.6987544,0.0006939322,0.299195,0.0001867103,0.000300107,0.000001454704,0.0008355454,0.00001052383,0.00002231578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9664552,"threshold_uncertainty_score":0.3591301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4233884501","doi":"10.1504/ijdmb.2020.109503","title":"Identification of protein hot regions by combining structure-based classification, energy-based clustering and sequence-based conservation in evolution","year":2020,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Sequence (biology); Computer science; Identification (biology); Energy conservation; Data mining; Energy (signal processing); Pattern recognition (psychology); Artificial intelligence; Biological system; Algorithm; Mathematics; Statistics; Biology","authors":[{"name":"Jing Hu","is_ca":true},{"name":"Haomin Gan","is_ca":false},{"name":"Nansheng Chen","is_ca":true},{"name":"Xiaolong Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0338256636374612,"gpt":0.276483070015979,"spread":0.2426574063785178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002448791,0.00009366263,0.000123817,0.0001070536,0.00003366682,0.00005366961,0.000289892,0.00008662946,9.428106e-7],"category_scores_gemma":[0.0002461259,0.00008796852,0.00002106173,0.00008977208,0.00008932973,0.00006500236,0.00006213231,0.0000732582,3.744728e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002318556,"about_ca_system_score_gemma":0.0002025958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000151137,"about_ca_topic_score_gemma":0.00002873328,"domain_scores_codex":[0.9989393,0.00003755877,0.0006094277,0.0001185127,0.0002216893,0.00007350722],"domain_scores_gemma":[0.9987971,0.00002863224,0.0007142378,0.0001503373,0.0002578814,0.00005184026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007323047,0.00005630344,0.01187854,0.0002107375,0.00008961819,0.000003613546,0.0002520698,0.001695811,0.9562538,0.0002809136,0.0006986716,0.02784757],"study_design_scores_gemma":[0.001473776,0.0002223151,0.001423726,0.0001878389,0.00002195888,0.00001573126,0.0002715325,0.9562758,0.03944264,0.00007298899,0.0004636608,0.0001280118],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4792041,0.0001618532,0.5186263,0.001479471,0.00005821608,0.00008255887,0.0003765732,0.000003669791,0.000007238965],"genre_scores_gemma":[0.9545542,0.00002166054,0.04385667,0.0004393874,0.00004230827,0.000001773845,0.001076342,0.000005918739,0.000001741271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.95458,"threshold_uncertainty_score":0.3587252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}