{"meta":{"query_hash":"5d90b1ae8224","filters":{"venue":"International Journal of Data Mining and Bioinformatics"},"cohort_total":20,"direct_labels_cover":1,"predictions_cover":20,"exported":20,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/5d90b1ae8224","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Journal+of+Data+Mining+and+Bioinformatics"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08225493591224538,"score_gpt":0.40097271618555896,"score_spread":0.3187177802733136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975341743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7165506,0.0001446617,0.28181204,0.00015059463,0.0006494477,0.000083824,0.00056697533,0.0000012886229,0.000040612438],"genre_scores_gemma":[0.68708026,0.000072885654,0.31217825,0.000084366235,0.0001860996,8.4536447e-7,0.00038745676,0.000004356429,0.000005461984],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928546,0.000027011629,0.00034147146,0.00012040876,0.00015312892,0.00007252433],"domain_scores_gemma":[0.99877,0.000052145428,0.00032389042,0.00040435587,0.0003980463,0.000051551833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094334024,0.000067463734,0.00012242979,0.0000755644,0.000028502353,0.000028266793,0.00085810816,0.00007153614,0.0000016858612],"category_scores_gemma":[0.0005312133,0.00005622169,0.000022616035,0.00003165196,0.000044016164,0.00004243381,0.00033644956,0.00006105265,1.2188117e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027095957,0.00002925351,0.0009541618,0.000032664448,0.00008471137,3.561696e-7,0.000070298054,0.000008988123,0.93499666,0.0000064822357,0.0011633682,0.06238208],"study_design_scores_gemma":[0.00079797104,0.0002507297,0.0018354579,0.00014912555,0.00005872175,0.00018142902,0.0002348462,0.0069884527,0.95788103,0.00003495308,0.031432338,0.00015494722],"about_ca_topic_score_codex":0.0000046393234,"about_ca_topic_score_gemma":0.000022394674,"teacher_disagreement_score":0.062227134,"about_ca_system_score_codex":0.0000057965285,"about_ca_system_score_gemma":0.00012790858,"threshold_uncertainty_score":0.22926539},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.11632856175214673,"score_gpt":0.3320784984421196,"score_spread":0.2157499366899729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018695726","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97786003,0.00009868729,0.021334646,0.000015097444,0.000350511,0.000030202033,0.00025322445,0.000001606136,0.000056020413],"genre_scores_gemma":[0.40860006,0.000092865186,0.59105057,0.000031858082,0.00010487686,4.0287382e-8,0.00011248025,0.0000043703826,0.0000028805468],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992204,0.000013177783,0.00045067057,0.00007450541,0.0001543602,0.00008689593],"domain_scores_gemma":[0.9990791,0.000008666778,0.0005109578,0.00013339048,0.0002263236,0.00004154582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002453756,0.00008700167,0.00011600433,0.00008994644,0.000031731397,0.00004375345,0.0003023724,0.00006163682,0.000009669019],"category_scores_gemma":[0.00007256589,0.00007067641,0.000035203655,0.000028516377,0.000071495684,0.000088650406,0.0002324813,0.00004872864,1.8143827e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015368893,0.00003071557,0.0014721968,0.00002090844,0.0001762984,0.0000057647303,0.00068886305,0.0000064534315,0.9432079,0.0000067580477,0.00017673014,0.054053687],"study_design_scores_gemma":[0.0024456233,0.00052748434,0.0074144625,0.00027364088,0.00014158142,0.0011615247,0.0053077494,0.048770756,0.9331096,0.000008027404,0.00048194925,0.00035762065],"about_ca_topic_score_codex":0.000013992449,"about_ca_topic_score_gemma":0.0000029440916,"teacher_disagreement_score":0.5697159,"about_ca_system_score_codex":0.000006971165,"about_ca_system_score_gemma":0.000052421503,"threshold_uncertainty_score":0.28821006},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04640594359035279,"score_gpt":0.3157167867357922,"score_spread":0.2693108431454394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045369746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09435966,0.0019524071,0.9009864,0.0012688449,0.0002129081,0.00038158565,0.00040599745,0.000020882026,0.00041133445],"genre_scores_gemma":[0.31732026,0.0013068431,0.67475355,0.00023719574,0.00029078388,0.000007792487,0.006026357,0.0000104683095,0.000046772766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988905,0.00003428392,0.00045670223,0.00025592692,0.0002701011,0.00009247029],"domain_scores_gemma":[0.99857074,0.00002008702,0.00040252725,0.00067510153,0.00023275227,0.00009881473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064329564,0.000113671165,0.00011675223,0.000114475,0.00007761027,0.0001531331,0.0015035269,0.00006941001,0.0000043739838],"category_scores_gemma":[0.00029434942,0.00008701869,0.000009915369,0.00005851041,0.000022781698,0.00021294295,0.0023508724,0.000118053154,0.0000013929414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045785662,0.000051916133,0.0012781045,0.00003700625,0.00006516683,5.058013e-7,0.00041150773,0.000022412618,0.43573296,0.0000074379172,0.008930247,0.55341697],"study_design_scores_gemma":[0.0009963666,0.00039860207,0.0007559874,0.0003825851,0.00007127389,0.00034189434,0.003974955,0.7304515,0.13550343,0.000023349558,0.12659842,0.0005016237],"about_ca_topic_score_codex":0.000017616803,"about_ca_topic_score_gemma":0.0000044651824,"teacher_disagreement_score":0.7304291,"about_ca_system_score_codex":0.000012764578,"about_ca_system_score_gemma":0.000049239166,"threshold_uncertainty_score":0.35485193},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Data type; Computer science; Data mining; Artificial intelligence; Machine learning","score_opus":0.10190478292986778,"score_gpt":0.35695398446423293,"score_spread":0.25504920153436517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063036182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057584406,0.00015871972,0.99251634,0.0008636056,0.00038890625,0.000028239065,0.00020083971,0.000010294088,0.000074640106],"genre_scores_gemma":[0.17561944,0.000102291895,0.82392293,0.000028021517,0.00018602323,2.0401328e-7,0.00011659532,0.000004668612,0.000019833555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981415,0.000027943624,0.0007155047,0.00015890003,0.0007922238,0.00016392196],"domain_scores_gemma":[0.9984868,0.0002742905,0.0003933182,0.0005062743,0.000228262,0.00011102865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007990333,0.00009886799,0.00020389566,0.00025033302,0.000042863645,0.00018323978,0.002725622,0.000050073697,0.0000019762347],"category_scores_gemma":[0.000304641,0.000077425924,0.000017089578,0.00016571456,0.00013207197,0.0020467998,0.0038607297,0.00016165087,9.288214e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033374505,0.00009267765,0.0006406522,0.000053183216,0.00009095223,0.000090737776,0.0003120343,0.000054879943,0.00020839696,0.00021456828,0.0029415425,0.995267],"study_design_scores_gemma":[0.00062458,0.00011973539,0.0014818226,0.00008508408,0.000009285175,0.0015151843,0.00015658012,0.99239,0.000070307535,0.00013382283,0.003316827,0.00009680893],"about_ca_topic_score_codex":0.000032975728,"about_ca_topic_score_gemma":0.000003830962,"teacher_disagreement_score":0.9951702,"about_ca_system_score_codex":0.000025645224,"about_ca_system_score_gemma":0.000107468186,"threshold_uncertainty_score":0.5064929},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.041370472827446304,"score_gpt":0.2592375920972098,"score_spread":0.21786711926976352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067203347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76291573,0.0017224081,0.23458607,0.00008933654,0.00023727992,0.00004023766,0.000047609094,0.0000051375396,0.00035620324],"genre_scores_gemma":[0.58039874,0.0018305707,0.41652665,0.00010886557,0.0006442234,4.2884685e-7,0.00031239082,0.000010866353,0.00016725245],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988051,0.000027957647,0.0005048635,0.00013054512,0.00037387572,0.0001576655],"domain_scores_gemma":[0.99880755,0.000016155349,0.00045085666,0.00035216942,0.00027088367,0.00010236747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049741147,0.0001240036,0.000176062,0.00008674233,0.000077033765,0.00004248806,0.0006353718,0.00007328115,0.0000025254103],"category_scores_gemma":[0.0000337456,0.00010591735,0.000068540154,0.000076486285,0.000093279545,0.00004825361,0.00033334535,0.00008366367,9.553498e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010225625,0.00043560236,0.039552327,0.00009095464,0.0053710323,0.00017371296,0.003559057,0.49991158,0.0064616343,0.000058041984,0.18937114,0.25399235],"study_design_scores_gemma":[0.0014562381,0.00027849423,0.0015595116,0.00008847141,0.00015168665,0.0034070238,0.0005056871,0.96579736,0.0034655281,0.00004563837,0.02279244,0.00045192806],"about_ca_topic_score_codex":0.000001972922,"about_ca_topic_score_gemma":0.0000013194981,"teacher_disagreement_score":0.4658858,"about_ca_system_score_codex":0.000013022514,"about_ca_system_score_gemma":0.00011432149,"threshold_uncertainty_score":0.43191844},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0812831393055651,"score_gpt":0.35290580302199787,"score_spread":0.27162266371643273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072197604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31737784,0.0006268294,0.67497295,0.001899644,0.0014740829,0.00022330559,0.00071423175,0.000011250853,0.0026998483],"genre_scores_gemma":[0.4393672,0.00037860606,0.5592926,0.0002488109,0.00035491155,0.0000016931205,0.00026181605,0.0000068701124,0.000087465116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991979,0.00002056,0.00036755097,0.000100946345,0.0002012425,0.00011182188],"domain_scores_gemma":[0.99911,0.00003203865,0.0004337212,0.00014105353,0.00023418969,0.00004903725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007253456,0.0000974187,0.00015427213,0.00009141329,0.000057366156,0.00005127297,0.00035101743,0.000066475615,0.000010114739],"category_scores_gemma":[0.00016613647,0.00007676728,0.00005733596,0.000040886363,0.0000328264,0.00003680436,0.00011085773,0.000075967946,2.1626903e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031079892,0.0010584499,0.33807722,0.00045017336,0.007185435,0.000020790383,0.001730603,0.00004866692,0.16430952,0.00408393,0.13020968,0.34971756],"study_design_scores_gemma":[0.020976098,0.009141347,0.16745561,0.00055784156,0.0011096076,0.001004698,0.009604724,0.14031483,0.18028755,0.0026719805,0.464292,0.0025837047],"about_ca_topic_score_codex":0.0000040233713,"about_ca_topic_score_gemma":0.000017732797,"teacher_disagreement_score":0.34713385,"about_ca_system_score_codex":0.000017614324,"about_ca_system_score_gemma":0.00009903478,"threshold_uncertainty_score":0.3130479},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.033992309906928496,"score_gpt":0.30036973770142444,"score_spread":0.26637742779449597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103153231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91300774,0.00040084176,0.084474765,0.00082117214,0.000849323,0.000085378415,0.00023204013,0.000009064119,0.000119684555],"genre_scores_gemma":[0.82122123,0.00020364349,0.1770969,0.00040471822,0.0005052267,8.428207e-7,0.00054976705,0.0000047323624,0.000012928596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989483,0.000012216324,0.00047066517,0.000058158854,0.00033904778,0.0001716084],"domain_scores_gemma":[0.9990005,0.00007192674,0.0004069193,0.00015650589,0.0002643329,0.000099823454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000792942,0.000099183824,0.00013846537,0.000107133346,0.000055945577,0.000064754226,0.00044150147,0.00010756617,0.0000042981396],"category_scores_gemma":[0.00045908877,0.00006754205,0.000022315906,0.000052543994,0.00013781819,0.00017012644,0.00016790192,0.000082305916,0.0000013264848],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092716556,0.000057187663,0.0066101644,0.00007069624,0.00027920306,0.0000012326213,0.0010259493,0.0000021559524,0.00047432462,0.000021969732,0.009476258,0.9810537],"study_design_scores_gemma":[0.013957073,0.0075733536,0.015963268,0.00133514,0.0003638236,0.0019737494,0.022914834,0.018184135,0.018739503,0.000028357079,0.8978383,0.0011284794],"about_ca_topic_score_codex":0.0000019048621,"about_ca_topic_score_gemma":0.0000020426685,"teacher_disagreement_score":0.9799252,"about_ca_system_score_codex":0.000012121358,"about_ca_system_score_gemma":0.000082488514,"threshold_uncertainty_score":0.2754285},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.15965036198780436,"score_gpt":0.336622064281259,"score_spread":0.17697170229345466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119632600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013865992,0.00011519095,0.9852022,0.00012737472,0.0002622577,0.000117104566,0.000084312785,0.0000112622465,0.00021430904],"genre_scores_gemma":[0.30085155,0.00009299121,0.6987962,0.000042099775,0.000052251664,0.0000025500854,0.00015341386,0.000003543129,0.0000054068983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988776,0.000022330867,0.0005149733,0.00019213911,0.00028236778,0.00011061893],"domain_scores_gemma":[0.99865973,0.00011418483,0.00040769627,0.0004553579,0.00029677866,0.00006625487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073732843,0.00009501711,0.000119348304,0.00023977831,0.0000918507,0.00011405392,0.001996252,0.000046852867,0.0000024868289],"category_scores_gemma":[0.00024277327,0.000079709855,0.00002484058,0.00013285353,0.000041704123,0.0024410652,0.00109424,0.000099469384,0.0000011710979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027281474,0.0010208536,0.0032660007,0.00006115615,0.00035013256,0.000021286784,0.032926347,0.0003411169,0.0016838696,0.0012659674,0.0023785036,0.95641196],"study_design_scores_gemma":[0.0006177345,0.00008561528,0.00092513376,0.00006886211,0.000010538669,0.00017973724,0.0046254573,0.9911951,0.0014149821,0.00040664268,0.00036747998,0.000102761725],"about_ca_topic_score_codex":0.00006687723,"about_ca_topic_score_gemma":0.000010580004,"teacher_disagreement_score":0.99085397,"about_ca_system_score_codex":0.00006593099,"about_ca_system_score_gemma":0.00007228009,"threshold_uncertainty_score":0.3709566},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09114874666879506,"score_gpt":0.3597068872948939,"score_spread":0.26855814062609884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130013930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09274721,0.000034984412,0.90525156,0.0013781227,0.00033434172,0.000087705084,0.000018898692,0.000008724436,0.00013844407],"genre_scores_gemma":[0.3169099,0.00003672927,0.682803,0.00012649926,0.000084031606,0.0000027162732,0.000026082733,0.0000024961153,0.000008553197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989549,0.000031406278,0.00052731956,0.00009169111,0.0003033922,0.00009128355],"domain_scores_gemma":[0.9986569,0.00039424674,0.0003895602,0.00011759443,0.00039874398,0.00004295375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008232552,0.00006716311,0.00010319462,0.00032787595,0.00002829345,0.00030214258,0.0009674492,0.00003164751,0.000003247028],"category_scores_gemma":[0.00028988867,0.000057184745,0.000027790633,0.00016009575,0.000021272648,0.003465637,0.00019613659,0.00007153854,0.000002111263],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014989473,0.00004507419,0.0040234677,0.000015642825,0.00004602899,0.000001135527,0.0007542758,0.00037249713,0.00016315377,0.0019471713,0.0023851788,0.9902314],"study_design_scores_gemma":[0.0004493912,0.0000602044,0.021952363,0.00005530291,0.0000044287153,0.000108172106,0.0002471541,0.97244424,0.00006150126,0.0039530136,0.0005957107,0.00006855183],"about_ca_topic_score_codex":0.000013859859,"about_ca_topic_score_gemma":0.000009894524,"teacher_disagreement_score":0.99016285,"about_ca_system_score_codex":0.000038769107,"about_ca_system_score_gemma":0.0000942029,"threshold_uncertainty_score":0.2913568},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.04764101485050556,"score_gpt":0.3031798806265017,"score_spread":0.25553886577599616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146392361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12987818,0.00023713063,0.8663247,0.0022931457,0.000106072795,0.00017384364,0.00019767629,0.000007603165,0.0007816175],"genre_scores_gemma":[0.5478618,0.00015840914,0.45017746,0.0005433836,0.00021471818,0.000005256913,0.0009014518,0.000009074987,0.00012845258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917036,0.000008694701,0.0003204594,0.00014668686,0.00026769095,0.000086123306],"domain_scores_gemma":[0.9988013,0.000007801164,0.00031469564,0.00044420268,0.000344635,0.000087352295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023728888,0.00008385089,0.00008415034,0.000081762504,0.00004036184,0.00014745862,0.0009912713,0.000047702506,0.0000043899545],"category_scores_gemma":[0.000068851834,0.000061044244,0.000010112394,0.000058959267,0.000027120403,0.00014716767,0.00047060175,0.000056540324,0.0000025202235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009658203,0.000038666287,0.00073786307,0.000024549765,0.00007071928,6.664728e-7,0.00030686753,0.00040118242,0.022275375,0.0000032133455,0.044326536,0.93171775],"study_design_scores_gemma":[0.0008548965,0.00018580038,0.00076858135,0.00022444916,0.000043472744,0.00021246534,0.0015958622,0.9725981,0.0026223464,0.000017690374,0.020644106,0.00023222815],"about_ca_topic_score_codex":0.0000041265134,"about_ca_topic_score_gemma":0.0000061079163,"teacher_disagreement_score":0.97219694,"about_ca_system_score_codex":0.000010810299,"about_ca_system_score_gemma":0.0001360161,"threshold_uncertainty_score":0.2489312},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06555281677021664,"score_gpt":0.31880183367583853,"score_spread":0.2532490169056219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150689251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028859559,0.000032255106,0.99616355,0.00022135275,0.00018076593,0.00011484412,0.000047522542,0.0000071269415,0.00034664737],"genre_scores_gemma":[0.010582195,0.000011262551,0.9891937,0.000109880224,0.000054905307,0.0000038527933,0.00002055429,0.000004312176,0.000019337385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989329,0.000016767712,0.0005808762,0.00009021727,0.00026771726,0.00011153379],"domain_scores_gemma":[0.9986558,0.00015187025,0.00057830446,0.00023107402,0.00032224398,0.000060738854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075424154,0.0000844429,0.00017737325,0.00013590674,0.000031222942,0.00019134014,0.0011903042,0.000037847276,0.000001075126],"category_scores_gemma":[0.00020217469,0.00006352737,0.00004266548,0.00005228075,0.000030245094,0.0018065847,0.00045245784,0.00007280089,2.0560933e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008674156,0.000018430443,0.000019757925,0.00006409115,0.0000564154,5.107701e-7,0.0011011559,0.00006509409,0.00006322383,0.000036342706,0.001090254,0.99747604],"study_design_scores_gemma":[0.0003518705,0.00006417711,0.000009927744,0.00011661915,0.000012623047,0.0001306572,0.00015958275,0.9986648,0.00008132104,0.0003333163,0.0000038474245,0.000071270326],"about_ca_topic_score_codex":0.0000040420223,"about_ca_topic_score_gemma":1.9297023e-7,"teacher_disagreement_score":0.9985997,"about_ca_system_score_codex":0.000012548374,"about_ca_system_score_gemma":0.000067432535,"threshold_uncertainty_score":0.25905707},"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":"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.043079755140257824,"score_gpt":0.3345422988701792,"score_spread":0.2914625437299214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891379954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00398559,0.00003858528,0.9941746,0.00031900124,0.0010520001,0.00007561491,0.00017523592,0.00001374098,0.00016564078],"genre_scores_gemma":[0.052034177,0.00002421599,0.94679683,0.00008906472,0.00084206666,0.0000016300346,0.00018913415,0.0000049043174,0.000017947123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848723,0.00005364774,0.00075598,0.0001312849,0.00043505328,0.00013682056],"domain_scores_gemma":[0.99733275,0.0005214156,0.0008828424,0.00025818258,0.0009458504,0.00005895523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012913895,0.00011015316,0.00022794661,0.00031787268,0.000099683886,0.00020692537,0.0008929725,0.00002718098,0.000004562432],"category_scores_gemma":[0.00012475712,0.000086063825,0.000072596544,0.00049798185,0.00007127987,0.0024813607,0.00033228143,0.00009549067,3.6900263e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017790691,0.00007204224,0.0030728488,0.000024972951,0.0020426842,0.0000034184784,0.0034834407,0.18453154,0.000017362756,0.0007087283,0.005237208,0.8006278],"study_design_scores_gemma":[0.00037924512,0.00020139707,0.002036325,0.00019102676,0.00014158268,0.00010159018,0.00033786678,0.99442,0.000043134387,0.0004920519,0.0015734247,0.00008233459],"about_ca_topic_score_codex":0.000007269544,"about_ca_topic_score_gemma":0.000057131507,"teacher_disagreement_score":0.8098885,"about_ca_system_score_codex":0.000041218675,"about_ca_system_score_gemma":0.000110345994,"threshold_uncertainty_score":0.3509581},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.028468735948894958,"score_gpt":0.31662038653124835,"score_spread":0.28815165058235337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946233355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6224362,0.00013963596,0.376903,0.000031983574,0.00035522095,0.0000512203,0.000035051933,0.0000012529908,0.000046438297],"genre_scores_gemma":[0.6140057,0.00009005385,0.3852705,0.000043998247,0.00029685145,2.6142382e-7,0.00027514427,0.0000066045623,0.000010890534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991135,0.000041260733,0.00047741082,0.00009971457,0.00019007707,0.00007805401],"domain_scores_gemma":[0.99865323,0.00003561185,0.0007470602,0.00020788358,0.00031769133,0.000038536513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008579244,0.000086521475,0.00016521056,0.00013400204,0.000021484682,0.00002604345,0.0002876139,0.00008798116,0.000008809964],"category_scores_gemma":[0.000064975335,0.00007626042,0.000056076162,0.00007597454,0.000027909844,0.00006313335,0.00018008378,0.00006892771,2.6094605e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026333125,0.00008176952,0.007243915,0.000034873534,0.0013270802,8.622097e-7,0.00029009406,0.012942271,0.2691423,0.000011327391,0.0006061386,0.70805603],"study_design_scores_gemma":[0.001768387,0.0004048743,0.005710371,0.00020607485,0.0002577341,0.0007011971,0.0010182237,0.9406303,0.046549667,0.000009522332,0.0024950823,0.00024853478],"about_ca_topic_score_codex":0.0000036935685,"about_ca_topic_score_gemma":0.0000017546212,"teacher_disagreement_score":0.92768806,"about_ca_system_score_codex":0.0000214617,"about_ca_system_score_gemma":0.000050390183,"threshold_uncertainty_score":0.31098098},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.034353480761702686,"score_gpt":0.2755679535106321,"score_spread":0.24121447274892943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3063921741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48000517,0.00015370341,0.51787376,0.0014688012,0.000053834352,0.00008029372,0.0003551494,0.0000033121034,0.000005952072],"genre_scores_gemma":[0.9584793,0.000022103013,0.04000654,0.00042361137,0.000041270072,0.0000016430016,0.0010183188,0.0000056001063,0.00000165552],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989785,0.000035738663,0.0005866921,0.00011368871,0.00021474133,0.00007064075],"domain_scores_gemma":[0.9988484,0.000026204338,0.00067808415,0.00014680722,0.0002510931,0.000049429163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023186863,0.000089909474,0.000117669355,0.00010284117,0.000032690554,0.000052945885,0.00028079003,0.00008304633,8.580833e-7],"category_scores_gemma":[0.00022772369,0.00008425197,0.000020655945,0.00008587065,0.00008447725,0.0000635904,0.000059487094,0.00006922462,3.4685243e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006193497,0.000051868847,0.011049883,0.00020464168,0.00007837066,0.0000031299708,0.0001986448,0.0015006574,0.9588283,0.000244784,0.0005944725,0.026625924],"study_design_scores_gemma":[0.0013776727,0.0001933531,0.0014835524,0.00018043524,0.000021007672,0.000014976821,0.0002271019,0.95066243,0.04521989,0.000076217504,0.00042104034,0.00012230531],"about_ca_topic_score_codex":0.000016203274,"about_ca_topic_score_gemma":0.000030973333,"teacher_disagreement_score":0.94916177,"about_ca_system_score_codex":0.000023925184,"about_ca_system_score_gemma":0.0001897402,"threshold_uncertainty_score":0.34356958},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11575858728256372,"score_gpt":0.29292615442257136,"score_spread":0.17716756714000764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107387809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56890595,0.00028743272,0.42766362,0.0005902587,0.00023714417,0.00012304865,0.001960133,0.0000052834284,0.00022713895],"genre_scores_gemma":[0.6987544,0.00069393223,0.29919502,0.00018671033,0.00030010703,0.0000014547038,0.0008355454,0.000010523825,0.000022315782],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988704,0.000005670975,0.0007204241,0.000084514046,0.00021704871,0.000101970916],"domain_scores_gemma":[0.998815,0.000030879877,0.00062942813,0.00016452574,0.00029852497,0.00006161743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034762075,0.00010598974,0.00017081435,0.000067739034,0.00003736304,0.00006374464,0.0005320844,0.0000780562,0.0000014630039],"category_scores_gemma":[0.0001744869,0.000088067805,0.00006797957,0.000046003042,0.000033953434,0.000103117374,0.00027340703,0.00007981592,3.885685e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031474773,0.00061888306,0.004118044,0.00095542206,0.0029206118,0.0000037136583,0.01353642,0.0041355514,0.4879043,0.0005052672,0.07974154,0.40241277],"study_design_scores_gemma":[0.0020844126,0.0005376021,0.00025141137,0.00011418152,0.00005519513,0.00010315522,0.0033190337,0.9705908,0.008187351,0.000008976749,0.014604932,0.00014300221],"about_ca_topic_score_codex":6.4471897e-7,"about_ca_topic_score_gemma":7.319253e-7,"teacher_disagreement_score":0.9664552,"about_ca_system_score_codex":0.000009408412,"about_ca_system_score_gemma":0.00008433775,"threshold_uncertainty_score":0.35913008},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09629500041666537,"score_gpt":0.32095265186112765,"score_spread":0.22465765144446226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137172717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020776693,0.00031997447,0.97722983,0.00053598796,0.00033168148,0.000065484615,0.0005958356,0.0000023440514,0.0001421474],"genre_scores_gemma":[0.14357308,0.000110783,0.8536635,0.0009236261,0.0005240917,4.7591698e-7,0.0011829002,0.00000951936,0.000012034666],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904525,0.000018038048,0.0005295588,0.00011725841,0.00018424759,0.00010564973],"domain_scores_gemma":[0.9989876,0.00006413407,0.00045004103,0.0002456931,0.00018690576,0.000065593114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044842125,0.00009128354,0.00015959436,0.000031688374,0.000027747881,0.00005060249,0.0009108718,0.000054738528,0.0000042968823],"category_scores_gemma":[0.00016193812,0.00007975949,0.000038530925,0.00003618876,0.000029973697,0.000047345973,0.00033475016,0.00005263113,2.0508364e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017440845,0.00026501744,0.00092026935,0.00048213018,0.00052969955,0.000006846115,0.0008047593,0.0020019594,0.60585177,0.000006128034,0.028380493,0.35900685],"study_design_scores_gemma":[0.0026609034,0.0012499591,0.000015113731,0.0002033166,0.0001229895,0.00003193244,0.000476423,0.85384923,0.10489265,0.000008227862,0.036278207,0.00021107745],"about_ca_topic_score_codex":0.000003806792,"about_ca_topic_score_gemma":0.000006353621,"teacher_disagreement_score":0.85184723,"about_ca_system_score_codex":0.0000054538264,"about_ca_system_score_gemma":0.00008790326,"threshold_uncertainty_score":0.32524976},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.09629500041666537,"score_gpt":0.32095265186112765,"score_spread":0.22465765144446226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214325870","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020776693,0.00031997447,0.97722983,0.00053598796,0.00033168148,0.000065484615,0.0005958356,0.0000023440514,0.0001421474],"genre_scores_gemma":[0.14357308,0.000110783,0.8536635,0.0009236261,0.0005240917,4.7591698e-7,0.0011829002,0.00000951936,0.000012034666],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904525,0.000018038048,0.0005295588,0.00011725841,0.00018424759,0.00010564973],"domain_scores_gemma":[0.9989876,0.00006413407,0.00045004103,0.0002456931,0.00018690576,0.000065593114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044842125,0.00009128354,0.00015959436,0.000031688374,0.000027747881,0.00005060249,0.0009108718,0.000054738528,0.0000042968823],"category_scores_gemma":[0.00016193812,0.00007975949,0.000038530925,0.00003618876,0.000029973697,0.000047345973,0.00033475016,0.00005263113,2.0508364e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017440845,0.00026501744,0.00092026935,0.00048213018,0.00052969955,0.000006846115,0.0008047593,0.0020019594,0.60585177,0.000006128034,0.028380493,0.35900685],"study_design_scores_gemma":[0.0026609034,0.0012499591,0.000015113731,0.0002033166,0.0001229895,0.00003193244,0.000476423,0.85384923,0.10489265,0.000008227862,0.036278207,0.00021107745],"about_ca_topic_score_codex":0.000003806792,"about_ca_topic_score_gemma":0.000006353621,"teacher_disagreement_score":0.85184723,"about_ca_system_score_codex":0.0000054538264,"about_ca_system_score_gemma":0.00008790326,"threshold_uncertainty_score":0.32524976},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11575858728256372,"score_gpt":0.29292615442257136,"score_spread":0.17716756714000764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230716249","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56890595,0.00028743272,0.42766362,0.0005902587,0.00023714417,0.00012304865,0.001960133,0.0000052834284,0.00022713895],"genre_scores_gemma":[0.6987544,0.00069393223,0.29919502,0.00018671033,0.00030010703,0.0000014547038,0.0008355454,0.000010523825,0.000022315782],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988704,0.000005670975,0.0007204241,0.000084514046,0.00021704871,0.000101970916],"domain_scores_gemma":[0.998815,0.000030879877,0.00062942813,0.00016452574,0.00029852497,0.00006161743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034762075,0.00010598974,0.00017081435,0.000067739034,0.00003736304,0.00006374464,0.0005320844,0.0000780562,0.0000014630039],"category_scores_gemma":[0.0001744869,0.000088067805,0.00006797957,0.000046003042,0.000033953434,0.000103117374,0.00027340703,0.00007981592,3.885685e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031474773,0.00061888306,0.004118044,0.00095542206,0.0029206118,0.0000037136583,0.01353642,0.0041355514,0.4879043,0.0005052672,0.07974154,0.40241277],"study_design_scores_gemma":[0.0020844126,0.0005376021,0.00025141137,0.00011418152,0.00005519513,0.00010315522,0.0033190337,0.9705908,0.008187351,0.000008976749,0.014604932,0.00014300221],"about_ca_topic_score_codex":6.4471897e-7,"about_ca_topic_score_gemma":7.319253e-7,"teacher_disagreement_score":0.9664552,"about_ca_system_score_codex":0.000009408412,"about_ca_system_score_gemma":0.00008433775,"threshold_uncertainty_score":0.35913008},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0338256636374612,"score_gpt":0.276483070015979,"score_spread":0.2426574063785178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233884501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47920412,0.0001618532,0.5186263,0.001479471,0.000058216083,0.00008255887,0.00037657318,0.0000036697909,0.000007238965],"genre_scores_gemma":[0.9545542,0.000021660537,0.043856665,0.0004393874,0.00004230827,0.0000017738448,0.0010763418,0.000005918739,0.0000017412711],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989393,0.00003755877,0.00060942775,0.00011851275,0.00022168932,0.000073507224],"domain_scores_gemma":[0.99879706,0.000028632245,0.0007142378,0.00015033732,0.0002578814,0.000051840256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002448791,0.00009366263,0.00012381704,0.000107053645,0.000033666824,0.000053669606,0.000289892,0.000086629465,9.4281063e-7],"category_scores_gemma":[0.0002461259,0.00008796852,0.000021061725,0.00008977208,0.00008932973,0.00006500236,0.000062132305,0.0000732582,3.7447276e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007323047,0.000056303445,0.011878538,0.00021073752,0.00008961819,0.0000036135461,0.0002520698,0.0016958109,0.9562538,0.00028091358,0.0006986716,0.02784757],"study_design_scores_gemma":[0.0014737763,0.00022231507,0.0014237261,0.00018783887,0.000021958882,0.000015731255,0.0002715325,0.9562758,0.039442636,0.000072988994,0.00046366078,0.00012801182],"about_ca_topic_score_codex":0.000015113701,"about_ca_topic_score_gemma":0.000028733275,"teacher_disagreement_score":0.95458,"about_ca_system_score_codex":0.000023185563,"about_ca_system_score_gemma":0.00020259584,"threshold_uncertainty_score":0.35872522},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.043079755140257824,"score_gpt":0.3345422988701792,"score_spread":0.2914625437299214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252436249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00398559,0.00003858528,0.9941746,0.00031900124,0.0010520001,0.00007561491,0.00017523592,0.00001374098,0.00016564078],"genre_scores_gemma":[0.052034177,0.00002421599,0.94679683,0.00008906472,0.00084206666,0.0000016300346,0.00018913415,0.0000049043174,0.000017947123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848723,0.00005364774,0.00075598,0.0001312849,0.00043505328,0.00013682056],"domain_scores_gemma":[0.99733275,0.0005214156,0.0008828424,0.00025818258,0.0009458504,0.00005895523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012913895,0.00011015316,0.00022794661,0.00031787268,0.000099683886,0.00020692537,0.0008929725,0.00002718098,0.000004562432],"category_scores_gemma":[0.00012475712,0.000086063825,0.000072596544,0.00049798185,0.00007127987,0.0024813607,0.00033228143,0.00009549067,3.6900263e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017790691,0.00007204224,0.0030728488,0.000024972951,0.0020426842,0.0000034184784,0.0034834407,0.18453154,0.000017362756,0.0007087283,0.005237208,0.8006278],"study_design_scores_gemma":[0.00037924512,0.00020139707,0.002036325,0.00019102676,0.00014158268,0.00010159018,0.00033786678,0.99442,0.000043134387,0.0004920519,0.0015734247,0.00008233459],"about_ca_topic_score_codex":0.000007269544,"about_ca_topic_score_gemma":0.000057131507,"teacher_disagreement_score":0.8098885,"about_ca_system_score_codex":0.000041218675,"about_ca_system_score_gemma":0.000110345994,"threshold_uncertainty_score":0.3509581},"labels":[],"label_agreement":null}]}