{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":48,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":48,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"c7cf3172b93e","filters":{"venue":"BioData Mining"}},"results":[{"id":"W2771169143","doi":"10.1186/s13040-017-0155-3","title":"Ten quick tips for machine learning in computational biology","year":2017,"lang":"en","type":"review","venue":"BioData Mining","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":915,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of California, Irvine; University of Toronto","keywords":"Computer science; Informatics; Context (archaeology); Data science; Artificial intelligence; Machine learning; Biology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1424812159179113,"gpt":0.4167059229229167,"spread":0.2742247070050055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009179356,0.0003375644,0.0008237524,0.0002284152,0.0001886253,0.00009141845,0.0008888399,0.0006316953,0.0000188233],"category_scores_gemma":[0.001535642,0.0002760885,0.0002502033,0.00007949196,0.0002446866,0.000005769113,0.0006040239,0.0003094054,0.00003985384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003301943,"about_ca_system_score_gemma":0.000547216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002680299,"about_ca_topic_score_gemma":0.00005673579,"domain_scores_codex":[0.9979508,0.0001221261,0.0006868754,0.0005405715,0.0001722747,0.0005273508],"domain_scores_gemma":[0.9986847,0.0001558366,0.0004041327,0.0005169205,0.00009062795,0.0001477575],"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":[0.00001683414,0.00002987155,0.0001770518,0.00253243,0.00009047185,0.000002407506,0.00001914958,0.000001825112,0.00001674073,0.00001920388,0.002394302,0.9946997],"study_design_scores_gemma":[0.0004362948,0.0003121877,0.00001616118,0.0009650246,0.00005307427,0.0000213423,0.00002333123,0.0006337372,0.000008047216,0.00002559802,0.9971819,0.0003233306],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003616129,0.9951862,0.002285841,0.0000839155,0.0002779021,0.0006352193,0.0010352,0.00001323952,0.0004463413],"genre_scores_gemma":[0.0001085521,0.9671943,0.009108716,0.00005345495,0.0004734231,0.00009475398,0.02191419,0.0000421894,0.001010468],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9947876,"threshold_uncertainty_score":0.9999691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3126232929","doi":"10.1186/s13040-021-00244-z","title":"The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":893,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Krembil Foundation","funders":"Deutsche Forschungsgemeinschaft","keywords":"Confusion matrix; Correlation; False positive paradox; Computer science; Confusion; False positives and false negatives; Classifier (UML); Statistics; Artificial intelligence; Metric (unit); Correlation coefficient; Machine learning; Data mining; Mathematics; Psychology; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.02927417731283126,"gpt":0.3307727570661502,"spread":0.3014985797533189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001762428,0.0001970354,0.0002002522,0.0001260251,0.0003517381,0.0005833707,0.000739908,0.00009551262,0.00003247773],"category_scores_gemma":[0.0006715515,0.0001489541,0.00002999572,0.0006928727,0.0001055955,0.001234671,0.000704595,0.000183002,0.00002834772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001623063,"about_ca_system_score_gemma":0.0003414543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007134146,"about_ca_topic_score_gemma":0.00011563,"domain_scores_codex":[0.9977421,0.0001492541,0.0005368413,0.0005956199,0.0006270448,0.0003491307],"domain_scores_gemma":[0.9976253,0.0003633969,0.0003491719,0.001276071,0.0003178012,0.00006828783],"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":[0.0002876632,0.0003627121,0.1041116,0.0002320732,0.00007303976,0.00005586188,0.01516407,0.0007974996,0.02464442,0.03576079,0.09862348,0.7198868],"study_design_scores_gemma":[0.001067561,0.00003157498,0.05069922,0.0002263046,0.00001611916,0.00003875652,0.001250027,0.8883365,0.007416944,0.0003809202,0.05020287,0.0003331762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5127193,0.002180492,0.4586311,0.01517173,0.002717055,0.003033906,0.0003182659,0.0008298899,0.004398221],"genre_scores_gemma":[0.9420449,0.0007553545,0.0531632,0.001355942,0.00007308814,0.0002808835,0.00098885,0.00003450177,0.001303316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.887539,"threshold_uncertainty_score":0.607417,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321214126","doi":"10.1186/s13040-023-00322-4","title":"The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":513,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Receiver operating characteristic; Matthews correlation coefficient; Binary classification; Statistics; Confusion matrix; False positive rate; Artificial intelligence; Correlation; Mathematics; Binary number; Sensitivity (control systems); Metric (unit); Classifier (UML); Computer science; Pattern recognition (psychology); Machine learning; Support vector machine; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.1099873591318314,"gpt":0.3627967148767833,"spread":0.2528093557449519,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004527626,0.0001897326,0.0001500108,0.0002021247,0.002025972,0.001443565,0.002546804,0.0001023849,0.000004457973],"category_scores_gemma":[0.00176413,0.0001014715,0.00007332858,0.002370559,0.0001822049,0.0008307789,0.0005902674,0.0002358752,0.00008865461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001672805,"about_ca_system_score_gemma":0.0002291622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001151915,"about_ca_topic_score_gemma":0.000005820631,"domain_scores_codex":[0.9975507,0.0002870343,0.0004909845,0.0006005724,0.0006539651,0.0004167016],"domain_scores_gemma":[0.9942104,0.002775441,0.0004784605,0.002267737,0.0002188182,0.00004914254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009181811,0.00006502582,0.001617078,0.00003878062,0.00006402737,0.00000426817,0.002719463,0.0005908711,0.009261704,0.157185,0.4464743,0.3818877],"study_design_scores_gemma":[0.0002458281,0.000102889,0.01393474,0.00005681081,0.00002881783,0.0000147217,0.002323982,0.6029679,0.003380282,0.001024668,0.375668,0.0002514689],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003982812,0.0002232328,0.9644635,0.02789442,0.0008631662,0.001040715,0.0001058182,0.0008031839,0.0006231703],"genre_scores_gemma":[0.9387665,0.0003413442,0.05482959,0.001547972,0.0002815714,0.0009967815,0.0007729403,0.00006939482,0.002393937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9347836,"threshold_uncertainty_score":0.999593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171815584","doi":"10.1186/1756-0381-7-22","title":"Applications of the MapReduce programming framework to clinical big data analysis: current landscape and future trends","year":2014,"lang":"en","type":"review","venue":"BioData Mining","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":147,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Computer science; Big data; Scalability; Programming paradigm; Data-intensive computing; Distributed computing; Data processing; Node (physics); Distributed File System; Grid computing; Grid; Database; Data mining; Operating system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.5193724130788084,"gpt":0.6095661319612116,"spread":0.09019371888240313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003090408,0.0003914495,0.001985457,0.0004666673,0.0007214493,0.00003635354,0.002442347,0.0008568054,0.00008808188],"category_scores_gemma":[0.0011631,0.0002549591,0.0003395232,0.00316106,0.0001466716,0.00007051732,0.002442243,0.001921242,0.00008166684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005036618,"about_ca_system_score_gemma":0.000713143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009804327,"about_ca_topic_score_gemma":0.0006583137,"domain_scores_codex":[0.9936592,0.001631277,0.002553487,0.001212557,0.000366047,0.0005774499],"domain_scores_gemma":[0.9908563,0.002586156,0.001615813,0.00443811,0.0001799027,0.0003236547],"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":[0.000003603549,0.00003748704,0.0123736,0.006829333,0.0002122759,1.903684e-7,0.0005127334,6.334742e-8,2.823552e-9,0.0002037501,0.003952099,0.9758748],"study_design_scores_gemma":[0.00002192185,0.00002526938,0.0002790058,0.009436141,0.002326132,7.593265e-7,0.001597635,0.00005883389,1.605101e-8,0.00001478438,0.9860072,0.0002322844],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001833857,0.9875675,0.004133681,0.0007431405,0.003201017,0.001960353,0.002228681,0.00006137962,0.00008585974],"genre_scores_gemma":[0.00007047948,0.980335,0.007361438,0.0001415855,0.00876006,0.0008298667,0.002353413,0.00005435283,0.00009382927],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9820551,"threshold_uncertainty_score":0.9999903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413362561","doi":"10.1186/s13040-025-00465-6","title":"A simple guide to the use of Student’s t-test, Mann-Whitney U test, Chi-squared test, and Kruskal-Wallis test in biostatistics","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Ministero dell'Università e della Ricerca; Dipartimenti di Eccellenza","keywords":"Test (biology); Biostatistics; Null hypothesis; Univariate; Kruskal–Wallis one-way analysis of variance; Mann–Whitney U test; Statistical hypothesis testing; Computer science; Chi-square test; Statistics; Simple (philosophy); Machine learning; Artificial intelligence; Data mining; Mathematics; Multivariate statistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04371332968964679,"gpt":0.3430738913752828,"spread":0.299360561685636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005626553,0.0002490723,0.0002824162,0.0002010967,0.0001214227,0.0001491649,0.0006753318,0.0001850248,0.0000190253],"category_scores_gemma":[0.009590433,0.0001941262,0.00004987441,0.000451301,0.0002882505,0.00001373884,0.00104773,0.0001528531,0.00001071281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002815538,"about_ca_system_score_gemma":0.0002353008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002168343,"about_ca_topic_score_gemma":0.0008144376,"domain_scores_codex":[0.9979381,0.00004790775,0.0006971731,0.0004459259,0.0003637924,0.0005070939],"domain_scores_gemma":[0.9977043,0.0009969148,0.0001328241,0.0007781153,0.0001921835,0.0001956781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005201416,0.000593884,0.6500624,0.0002612414,0.00007554805,0.00001899586,0.0005517808,0.0000168901,0.09366671,0.0000286952,0.2222238,0.03244793],"study_design_scores_gemma":[0.001864187,0.001940397,0.3553789,0.0003175776,0.00007811316,0.00001403092,0.001865053,0.004300404,0.03355342,0.00004009902,0.60004,0.0006078715],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975262,0.001594988,0.006422746,0.003825834,0.0003350625,0.001948819,0.008629618,0.0000468775,0.001934022],"genre_scores_gemma":[0.9632183,0.001524349,0.02807721,0.002248092,0.0002119539,0.00006460139,0.001258767,0.0000404731,0.003356192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3778161,"threshold_uncertainty_score":0.9987522,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3136786679","doi":"10.1186/s13040-021-00251-0","title":"Indels in SARS-CoV-2 occur at template-switching hotspots","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"National Science Foundation of Sri Lanka; Stanford Bio-X; National Science Foundation","keywords":"Indel; Genetics; Biology; RNA; Computational biology; Homologous recombination; RNA polymerase; Recombination; Evolutionary biology; Gene; Single-nucleotide polymorphism; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.121934235703093,"gpt":0.3875826429091648,"spread":0.2656484072060718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005881471,0.0002336666,0.0004281366,0.000335921,0.0001299057,0.00008756403,0.0002798181,0.0002032894,0.00003733936],"category_scores_gemma":[0.0006607117,0.0002251014,0.00009417207,0.0008038072,0.0000542124,0.000254126,0.0005544227,0.0004251776,0.0003258644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002396129,"about_ca_system_score_gemma":0.0004819572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003396104,"about_ca_topic_score_gemma":0.000555017,"domain_scores_codex":[0.997633,0.0000885444,0.0004368836,0.0006724215,0.0005310462,0.0006381528],"domain_scores_gemma":[0.9987676,0.0002147418,0.00008056161,0.0007849624,0.0001011139,0.00005108747],"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":[0.0001995583,0.0001104359,0.2749416,0.0001134398,0.0000476434,0.002157266,0.0008988772,1.542323e-7,0.7078355,0.00002290926,0.003057898,0.01061468],"study_design_scores_gemma":[0.00286296,0.0001212814,0.04115409,0.000560822,0.00004013232,0.0004042046,0.0009585819,0.0007303421,0.785057,0.0000347399,0.1676893,0.0003865857],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934157,0.0009689867,0.00009761504,0.0004627011,0.0002078519,0.0002106216,0.00003657556,0.00008058277,0.004519425],"genre_scores_gemma":[0.9728529,0.00001224397,0.001274195,0.02545524,0.0001946823,0.00002309971,0.00005234976,0.00004273136,0.00009254414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2337875,"threshold_uncertainty_score":0.9179369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2273538503","doi":"10.1186/s13040-016-0082-8","title":"Network-based analysis of genetic variants associated with hippocampal volume in Alzheimer’s disease: a study of ADNI cohorts","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; Servier; Eisai; Pfizer; Biogen; BioClinica; Medpace; F. Hoffmann-La Roche; Synarc; University of Southern California; Novartis Pharmaceuticals Corporation; Dartmouth College; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Gordon and Betty Moore Foundation; Foundation for the National Institutes of Health; Alzheimer's Association; National Science Foundation","keywords":"Hippocampal formation; Disease; Volume (thermodynamics); Genetic variants; Alzheimer's disease; Neuroscience; Computer science; Medicine; Data science; Computational biology; Biology; Internal medicine; Genetics; Genotype; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02897990539535016,"gpt":0.2713402144407311,"spread":0.2423603090453809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005515988,0.0001495033,0.0004633805,0.0001450955,0.00003481639,0.000004386938,0.0002136325,0.0001150916,0.00003841625],"category_scores_gemma":[0.0004090106,0.0001118562,0.0000736482,0.0005533658,0.00007982076,0.000003382904,0.00009039056,0.00003291947,7.636692e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001632068,"about_ca_system_score_gemma":0.0001336634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001240094,"about_ca_topic_score_gemma":0.0009912568,"domain_scores_codex":[0.9983377,0.0003030643,0.0005033942,0.0004085799,0.0001523856,0.0002948292],"domain_scores_gemma":[0.9987598,0.0001020997,0.0004242068,0.000521498,0.000112242,0.00008015046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001212242,0.0003093752,0.9912654,0.000002207196,0.001282145,0.000005206212,0.00005015694,0.00372702,0.001338462,8.813338e-7,0.0004011757,0.001496761],"study_design_scores_gemma":[0.001145145,0.0005354465,0.9946813,0.0000383992,0.001231937,2.086773e-7,0.00008290075,0.00202258,0.00006045047,0.000005670055,0.00004838772,0.0001475609],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970605,0.0004857629,0.001860672,0.00005917398,0.00003880171,0.0002313673,0.0002381695,0.000004919671,0.00002063636],"genre_scores_gemma":[0.9981344,0.00001824048,0.00135705,0.00004800843,0.00003146596,0.00003014967,0.0003389554,0.00001403134,0.00002764446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00341593,"threshold_uncertainty_score":0.4561364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111827030","doi":"10.1186/1756-0381-7-7","title":"Semi-supervised consensus clustering for gene expression data analysis","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Cluster analysis; Computer science; Data mining; Consensus clustering; Computational biology; Expression (computer science); Artificial intelligence; Biology; Correlation clustering; CURE data clustering algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1087011612012788,"gpt":0.350048260191916,"spread":0.2413470989906372,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001074892,0.0001865265,0.0003042344,0.0002818987,0.0002755565,0.0002835256,0.003219828,0.00007660229,0.000009857924],"category_scores_gemma":[0.0006304999,0.0001784796,0.00006704203,0.0007648593,0.00005473943,0.0005521654,0.003958372,0.0001070373,0.00001482132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003882491,"about_ca_system_score_gemma":0.00004917199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002465786,"about_ca_topic_score_gemma":0.00001797364,"domain_scores_codex":[0.9975791,0.0001104999,0.0003273331,0.001083809,0.0003712849,0.0005279975],"domain_scores_gemma":[0.9956253,0.0006040205,0.0001127965,0.003383631,0.0001008125,0.0001734198],"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":[0.0001242456,0.0001384017,0.002223409,0.0002391892,0.0006212818,0.00004875237,0.001585195,0.01723127,0.237254,0.0002338319,0.006686448,0.733614],"study_design_scores_gemma":[0.0004974369,0.00004901356,0.0001921712,0.00003076276,0.00003938052,0.000009660277,0.00006302111,0.9821523,0.009976949,0.00003405219,0.006723162,0.0002320497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009160727,0.00009615543,0.9895481,0.0002990807,0.0002124157,0.0001926708,0.0001928705,0.0001903047,0.0001076338],"genre_scores_gemma":[0.1002515,0.000008777801,0.8988735,0.0001024943,0.0001694507,0.00002626522,0.000393356,0.00001943593,0.0001551698],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9649211,"threshold_uncertainty_score":0.7278187,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161488150","doi":"10.1186/1756-0381-5-8","title":"A comparison and evaluation of five biclustering algorithms by quantifying goodness of biclusters for gene expression data","year":2012,"lang":"en","type":"article","venue":"BioData Mining","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University","keywords":"Biclustering; Ranking (information retrieval); Computer science; Data mining; Gene ontology; Correlation; Algorithm; Expression (computer science); Cluster analysis; Artificial intelligence; Pattern recognition (psychology); Mathematics; Gene; Gene expression; Biology; Correlation clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.264235945200037,"gpt":0.4307928668063278,"spread":0.1665569216062908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000836422,0.00009516445,0.0001503139,0.00004699529,0.00005333243,0.00001091745,0.000232475,0.0000863854,0.000004157487],"category_scores_gemma":[0.000123285,0.00008934622,0.00002060238,0.00006443893,0.00004478934,0.00002682007,0.0003191044,0.00002413783,1.661105e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008202066,"about_ca_system_score_gemma":0.00003724252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001281101,"about_ca_topic_score_gemma":0.000002389513,"domain_scores_codex":[0.9990333,0.00007178386,0.0002778207,0.0002873331,0.0001848004,0.0001449146],"domain_scores_gemma":[0.9990252,0.00002321767,0.0002688466,0.0005244761,0.0001043707,0.00005393753],"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":[0.00006154382,0.0000491225,0.008278358,0.00006325463,0.00001862091,6.815372e-9,0.0003171729,0.00002155566,0.9716069,0.000001015627,0.003106461,0.016476],"study_design_scores_gemma":[0.0008091119,0.00006487116,0.002056366,0.0000773194,0.00005968614,0.000001412712,0.001990351,0.02154644,0.9695394,7.799332e-7,0.003739737,0.0001145489],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9643252,0.004466833,0.03031077,0.0000224571,0.0001949673,0.0002575746,0.0003959804,0.000004119159,0.00002202492],"genre_scores_gemma":[0.9816087,0.00008516629,0.01605055,0.00001308165,0.00008735937,0.00002883075,0.002096337,0.00001228595,0.00001763394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02152488,"threshold_uncertainty_score":0.3643433,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2202714662","doi":"10.1186/s13040-015-0077-x","title":"Characterizing gene-gene interactions in a statistical epistasis network of twelve candidate genes for obesity","year":2015,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"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":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Epistasis; SNP; Missing heritability problem; Single-nucleotide polymorphism; Genetics; Gene; Genome-wide association study; Biology; Candidate gene; Pairwise comparison; Computational biology; Statistics; Genotype; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05905887234879215,"gpt":0.3274183350026971,"spread":0.2683594626539049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005952005,0.0001166309,0.000241204,0.00003506705,0.00005774744,0.00001111764,0.0001463816,0.00008818838,0.000008474427],"category_scores_gemma":[0.0005252609,0.0001200615,0.00004848481,0.00008623498,0.00005057487,0.000005764859,0.00012888,0.00004857384,0.000002681929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003456397,"about_ca_system_score_gemma":0.0001314755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002157753,"about_ca_topic_score_gemma":0.000486647,"domain_scores_codex":[0.9988764,0.0001027555,0.0003691097,0.0002961786,0.00005901082,0.0002965636],"domain_scores_gemma":[0.9992782,0.0000847191,0.0001802684,0.0002616287,0.0001037909,0.00009131681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002973617,0.0001725129,0.6614468,0.00003811972,0.0002019444,0.000005777489,0.0003680948,0.0005192878,0.3078722,0.000170289,0.01471987,0.01418773],"study_design_scores_gemma":[0.00334101,0.0009404897,0.7237233,0.0000917791,0.0001954231,0.0000621027,0.001454101,0.005521557,0.1195145,0.0006267246,0.1435188,0.001010229],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9683664,0.0004976006,0.02951682,0.0001914801,0.0002601407,0.0001695392,0.0009081705,0.00000546923,0.00008437403],"genre_scores_gemma":[0.9239696,0.0001112725,0.07297545,0.0001371018,0.0002937157,0.00004508571,0.002384851,0.00001365467,0.00006921602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1883577,"threshold_uncertainty_score":0.4895964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2528021625","doi":"10.1186/s13040-017-0129-5","title":"Variant Set Enrichment: an R package to identify disease-associated functional genomic regions","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Ontario Institute for Cancer Research; University of Toronto; Princess Margaret Cancer Centre","funders":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health; Prostate Cancer Canada; Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Computational biology; Disease; Set (abstract data type); Genome; R package; Human genome; Computer science; Biology; Genetics; Gene; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.05028613776478923,"gpt":0.3121266194218884,"spread":0.2618404816570991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001635781,0.0001580715,0.0001142665,0.00004403819,0.0006131394,0.000258054,0.0005121229,0.0000825309,0.00005203029],"category_scores_gemma":[0.0002443164,0.0001599778,0.000082007,0.00002958017,0.00005396561,0.00001593428,0.0004401143,0.00004326829,0.00006035819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002456577,"about_ca_system_score_gemma":0.0001323388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004115216,"about_ca_topic_score_gemma":0.00007308572,"domain_scores_codex":[0.9988866,0.00003978664,0.0001651996,0.0005094143,0.0001178798,0.0002811002],"domain_scores_gemma":[0.9983409,0.000007023969,0.0001344814,0.001103518,0.0000593586,0.0003547138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0005127924,0.000557189,0.09996618,0.00003315358,0.0004852827,0.0003903622,0.0003080857,0.00007561444,0.78363,0.0007592381,0.1104134,0.002868678],"study_design_scores_gemma":[0.0006449974,0.000144402,0.9551973,0.00002633648,0.00009620297,0.00001689805,0.000185677,0.00007355188,0.001384488,0.0001164647,0.04169673,0.0004169175],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961224,0.000262652,0.0006533072,0.000359256,0.0004150873,0.0001510797,0.001694254,0.00001727752,0.000324675],"genre_scores_gemma":[0.9934433,0.00005694859,0.000329553,0.0004419348,0.0003518689,0.00002413854,0.004634201,0.00002566913,0.0006923586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8552312,"threshold_uncertainty_score":0.6523705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3128825412","doi":"10.1186/s13040-021-00235-0","title":"Data analytics and clinical feature ranking of medical records of patients with sepsis","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Krembil Foundation","funders":"University of Toronto","keywords":"Sepsis; Medical record; Septic shock; Medicine; Context (archaeology); Ranking (information retrieval); Electronic medical record; Machine learning; Binary classification; Computer science; Logistic regression; SOFA score; Artificial intelligence; Intensive care medicine; Data mining; Emergency medicine; Internal medicine; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.2182863075406786,"gpt":0.4170764311393291,"spread":0.1987901235986505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004206733,0.00009859974,0.0004385634,0.00004677206,0.00002213673,0.000009260788,0.0001604161,0.0001266117,0.0001636163],"category_scores_gemma":[0.0009935577,0.00006868263,0.00004090194,0.0001937242,0.0001076762,0.00006861632,0.000325594,0.0001176885,7.487097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001016451,"about_ca_system_score_gemma":0.0001862703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002709612,"about_ca_topic_score_gemma":0.00009029516,"domain_scores_codex":[0.998611,0.00004841631,0.0003584902,0.0003429938,0.0005242733,0.0001148233],"domain_scores_gemma":[0.9984432,0.0003529509,0.0001653561,0.0007696185,0.000138616,0.0001302433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009488151,0.0006131957,0.9565057,0.00007678131,0.0004291371,0.0000486165,0.00004787763,3.793018e-8,0.000002752848,0.000009242114,0.00601961,0.03615219],"study_design_scores_gemma":[0.003594867,0.0004758882,0.9871297,0.0008044874,0.0007790867,0.00001024747,0.0002996325,0.0003507899,0.0001979901,0.000001297284,0.006279586,0.000076366],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967834,0.0009448522,0.00004079502,0.001330638,0.00009577035,0.00009496078,0.0005632169,0.000006908987,0.0001394006],"genre_scores_gemma":[0.9805368,0.001036878,0.01552847,0.0003123064,0.00007804661,0.000001519526,0.002459916,0.00001362704,0.00003245137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03607582,"threshold_uncertainty_score":0.2800796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2368906419","doi":"10.1186/s13040-016-0098-0","title":"Machine learning algorithms for mode-of-action classification in toxicity assessment","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"MacEwan University; University of Calgary; Alberta Health; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Action (physics); Mode (computer interface); Machine learning; Artificial intelligence; Mode of action; Algorithm; Chemistry; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.08482953243657332,"gpt":0.3714903720574589,"spread":0.2866608396208856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001939269,0.00007786582,0.00008630115,0.00006224531,0.00004311485,0.000008671505,0.0001100492,0.0000879584,0.00001284682],"category_scores_gemma":[0.00008603922,0.00006096068,0.00003399295,0.00007134599,0.00002515024,0.000009848298,0.00004102308,0.00003311305,0.000001022783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003188599,"about_ca_system_score_gemma":0.00005573585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000997814,"about_ca_topic_score_gemma":0.00001847695,"domain_scores_codex":[0.9992779,0.00004659194,0.0002015511,0.000274943,0.00008135638,0.000117594],"domain_scores_gemma":[0.9995379,0.0000190751,0.0001415713,0.0002205132,0.00005059589,0.00003030297],"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":[0.00004520913,0.00003094857,0.009402194,0.00001027424,0.0000059028,4.998762e-8,0.0000180644,0.00001061183,0.8775288,0.00008457217,0.0002919388,0.1125714],"study_design_scores_gemma":[0.001068981,0.0002304136,0.02401192,0.00005769706,0.000008593912,0.000001424417,0.0002654099,0.01055315,0.8944213,0.00003987935,0.06917287,0.0001683956],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7219605,0.0001736889,0.276395,0.0004426615,0.0002135005,0.0002469754,0.0001038786,0.00001531479,0.0004485161],"genre_scores_gemma":[0.9904549,0.0002305458,0.008397649,0.00002443835,0.0000861273,0.00007102003,0.0003313754,0.00001082046,0.0003931295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2684944,"threshold_uncertainty_score":0.2485904,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2587099845","doi":"10.1186/s13040-017-0123-y","title":"Semantics-based plausible reasoning to extend the knowledge coverage of medical knowledge bases for improved clinical decision support","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Model-based reasoning; Semantics (computer science); Semantic Web; Data science; Artificial intelligence; Information retrieval; Knowledge representation and reasoning","retraction":null,"screen_n_in":null,"score":{"opus":0.076125745526062,"gpt":0.4277109479327042,"spread":0.3515852024066422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002621737,0.000214158,0.0003851912,0.00005421508,0.0004391892,0.0000974355,0.001449908,0.0004326135,0.00006001593],"category_scores_gemma":[0.01165102,0.000149883,0.0001937753,0.000066523,0.0004830825,0.000008058413,0.0008788945,0.0001580767,0.00001369818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001033093,"about_ca_system_score_gemma":0.0005870427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002308773,"about_ca_topic_score_gemma":0.0002851382,"domain_scores_codex":[0.9981056,0.00009368276,0.00058929,0.0005933867,0.0002248962,0.0003931258],"domain_scores_gemma":[0.9974645,0.0006909219,0.0002933583,0.001130287,0.0001623192,0.0002585555],"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":[0.000834221,0.0004249631,0.01275208,0.0001122108,0.0001297595,0.00000771902,0.0001514434,0.000001773642,0.01246945,0.0001456762,0.09258411,0.8803866],"study_design_scores_gemma":[0.003185473,0.001987,0.01571281,0.0005119773,0.0000994549,0.00001747221,0.0002492731,0.007726649,0.02324253,0.00003043341,0.9468006,0.0004362777],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8281624,0.001747478,0.160899,0.003835395,0.002157803,0.0008225049,0.0006623878,0.00006133982,0.001651753],"genre_scores_gemma":[0.9513898,0.0002201402,0.04595153,0.0006410342,0.0008734776,0.00005659929,0.0002701099,0.00003869489,0.000558543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8799503,"threshold_uncertainty_score":0.9966742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2232773008","doi":"10.1186/s13040-015-0078-9","title":"Iteratively refining breast cancer intrinsic subtypes in the METABRIC dataset","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"BC Cancer Agency; Australian Research Council; Cancer Research UK","keywords":"Discriminative model; Computer science; Machine learning; Artificial intelligence; Set (abstract data type); Breast cancer; Class (philosophy); Data mining; Pattern recognition (psychology); Cancer; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04386414633269161,"gpt":0.2884951767383135,"spread":0.2446310304056219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006578565,0.0001289336,0.0001283753,0.0001348607,0.0001153032,0.0001850618,0.001228204,0.00004039767,0.00005116298],"category_scores_gemma":[0.00006078825,0.00007262917,0.00002017415,0.0006225513,0.00005333847,0.001302769,0.0003569616,0.00009763119,0.00007410496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009965905,"about_ca_system_score_gemma":0.0000844985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003516575,"about_ca_topic_score_gemma":0.00039945,"domain_scores_codex":[0.9986773,0.0001500181,0.000212127,0.0004497655,0.0002399975,0.0002707498],"domain_scores_gemma":[0.9988001,0.0002515865,0.0001155054,0.0007666735,0.00003135241,0.00003480083],"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":[0.00002388513,0.00002327562,0.01179665,0.000008783866,0.00002282951,0.00002672143,0.001358188,0.000002534051,0.002261038,0.001549138,0.01981375,0.9631132],"study_design_scores_gemma":[0.002147567,0.0002068578,0.3935787,0.0006967668,0.00005203018,0.0004697305,0.0005928747,0.002609158,0.007025558,0.0003932452,0.5910686,0.001158843],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5046088,0.005460222,0.3870594,0.07345656,0.006464271,0.001001881,0.01887175,0.0008159541,0.002261138],"genre_scores_gemma":[0.9847666,0.0001262025,0.01327662,0.00124729,0.0002996771,0.00008172485,0.00009313774,0.00001312391,0.00009564235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9619544,"threshold_uncertainty_score":0.2961732,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390605262","doi":"10.1186/s13040-023-00352-y","title":"Machine learning approaches to identify systemic lupus erythematosus in anti-nuclear antibody-positive patients using genomic data and electronic health records","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Academia Sinica; Taichung Veterans General Hospital; National Science and Technology Council","keywords":"Logistic regression; Single-nucleotide polymorphism; Medicine; Random forest; Titer; Gradient boosting; Artificial intelligence; Medical record; Machine learning; Systemic lupus erythematosus; Internal medicine; Cohort; Support vector machine; Oncology; Immunology; Antibody; Computer science; Disease; Biology; Genetics; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.1125995094971304,"gpt":0.3603028582297049,"spread":0.2477033487325745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002258288,0.0003620259,0.0008233445,0.0008497837,0.0002145279,0.0002851315,0.0005343058,0.0001475136,0.00002094755],"category_scores_gemma":[0.0003283024,0.0003353977,0.00005450282,0.0008442577,0.00007641534,0.0004504002,0.001290458,0.0006598197,0.00007698884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008521454,"about_ca_system_score_gemma":0.0005314467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007665101,"about_ca_topic_score_gemma":0.00007932384,"domain_scores_codex":[0.9959561,0.0003627137,0.0008181758,0.00130882,0.0005394103,0.001014754],"domain_scores_gemma":[0.998225,0.0002147206,0.0001694045,0.00102202,0.00004895051,0.0003199463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002221946,0.0001259353,0.9690961,0.004561451,0.0002636971,0.0002267977,0.007720669,0.00002217139,0.008346267,0.0001593837,0.0004435295,0.008811775],"study_design_scores_gemma":[0.0114499,0.003064541,0.05727405,0.06219552,0.0005981222,0.1154272,0.034626,0.696498,0.0002800564,0.00004052632,0.01582676,0.002719244],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819611,0.01484204,0.0005322692,0.0002718339,0.0004244143,0.00134687,0.0003184515,0.0001531227,0.000149949],"genre_scores_gemma":[0.9951003,0.001042087,0.001859787,0.00007213729,0.0001626547,0.0000130523,0.001428167,0.0001401748,0.0001815955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9118221,"threshold_uncertainty_score":0.9999098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4323050290","doi":"10.1186/s13040-023-00325-1","title":"Signature literature review reveals AHCY, DPYSL3, and NME1 as the most recurrent prognostic genes for neuroblastoma","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Neuroblastoma Research and Treatments","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Neuroblastoma; Gene; Bioinformatics; Oncology; Biology; Computational biology; Medicine; Internal medicine; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.04151356111928294,"gpt":0.3423840202260795,"spread":0.3008704591067966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003429684,0.0002334807,0.0003156793,0.000119982,0.0002170386,0.0001030621,0.0001929578,0.00008195115,0.00001981944],"category_scores_gemma":[0.00146654,0.0001411927,0.00008128423,0.0007749032,0.00007666973,0.0001216248,0.0002091537,0.000258571,0.00006965642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001750437,"about_ca_system_score_gemma":0.00008464901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001420096,"about_ca_topic_score_gemma":0.000003048777,"domain_scores_codex":[0.9983619,0.00009991376,0.000251825,0.0005019063,0.0003320587,0.0004523641],"domain_scores_gemma":[0.9985467,0.0005147771,0.00008711711,0.0005012208,0.0001318591,0.0002182801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009829717,0.0003263713,0.006192939,0.01222518,0.0004364389,0.002645029,0.0006539954,3.924572e-7,0.02304524,0.0001513466,0.4958451,0.457495],"study_design_scores_gemma":[0.005787549,0.009276769,0.05279427,0.05724127,0.001400738,0.003378787,0.0003752952,0.0008851404,0.00697872,0.0002889637,0.8605402,0.001052361],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7083659,0.2568818,0.00001084564,0.02603633,0.000502131,0.006267874,0.001176911,0.0003757634,0.0003824503],"genre_scores_gemma":[0.5168814,0.4319795,0.004380993,0.01967026,0.001995874,0.002985461,0.007927476,0.0004002336,0.0137788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4564427,"threshold_uncertainty_score":0.5757672,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2069849680","doi":"10.1186/1756-0381-6-8","title":"Prediction of Drosophila melanogaster gene function using Support Vector Machines","year":2013,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto; University of Washington","keywords":"Drosophila melanogaster; Gene; Genome; Biology; Computational biology; Support vector machine; Gene prediction; Genome project; Microarray analysis techniques; Melanogaster; Gene Annotation; Genetics; Annotation; Function (biology); Computer science; Artificial intelligence; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02614048323694971,"gpt":0.224926785095025,"spread":0.1987863018580753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001109467,0.0001074954,0.0001070426,0.00003623704,0.00005259928,0.00002527915,0.0001102968,0.0001202054,0.0001123394],"category_scores_gemma":[0.00001140548,0.00009790954,0.00004615754,0.00005050535,0.00003880021,0.00001493937,0.0001111901,0.00004188047,0.00001591339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006063194,"about_ca_system_score_gemma":0.00002968583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002617856,"about_ca_topic_score_gemma":0.000003004718,"domain_scores_codex":[0.999324,0.0000142291,0.0002586418,0.0001674257,0.00007848915,0.0001572435],"domain_scores_gemma":[0.9994865,0.000004081912,0.0001283983,0.0002775352,0.00005436354,0.00004913264],"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":[0.0000326911,0.00002171348,0.006812282,0.00002645971,0.00007383496,3.491966e-7,0.00006792496,0.00005835849,0.9788399,0.00002195308,0.005761096,0.008283396],"study_design_scores_gemma":[0.005861073,0.004372421,0.2146823,0.0002584681,0.0007520072,0.0003839103,0.001167051,0.1537419,0.5126716,0.0006328018,0.1034162,0.002060208],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9887379,0.0002286179,0.009700145,0.0000294747,0.0004185984,0.0001482492,0.0001587703,0.000009886924,0.000568367],"genre_scores_gemma":[0.9930558,0.00002477929,0.005237799,0.0001267106,0.0004137555,0.000007060402,0.0009489257,0.00001418928,0.0001710176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4661683,"threshold_uncertainty_score":0.3992635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2222833576","doi":"10.1186/s13040-015-0062-4","title":"Functional dyadicity and heterophilicity of gene-gene interactions in statistical epistasis networks","year":2015,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"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":"National Institute of Allergy and Infectious Diseases; U.S. National Library of Medicine; National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Epistasis; Context (archaeology); Computational biology; Biology; Genetic association; Gene; Gene interaction; Gene ontology; Genetics; Computer science; Genotype; Single-nucleotide polymorphism; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.04534004385984268,"gpt":0.2740099323237019,"spread":0.2286698884638592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002514328,0.00009828845,0.0001341709,0.00004088408,0.00003350321,0.00001721909,0.00008495055,0.00007370537,0.00001048877],"category_scores_gemma":[0.00006658953,0.00009698726,0.00002214693,0.00006264519,0.00009915008,0.000008205081,0.000128967,0.00008352226,0.000001699419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001557984,"about_ca_system_score_gemma":0.00004469246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007665505,"about_ca_topic_score_gemma":0.0001520249,"domain_scores_codex":[0.9992716,0.00003397475,0.0002709529,0.0001876317,0.00007451219,0.0001612947],"domain_scores_gemma":[0.999541,0.00002520308,0.00008391117,0.0002011472,0.00004470428,0.0001039648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003301064,0.001084896,0.3741522,0.0002466036,0.0009038185,0.00006484165,0.002095484,0.02020334,0.2597431,0.002675282,0.1261795,0.2093499],"study_design_scores_gemma":[0.01306244,0.002928176,0.4550058,0.0003084221,0.0003289448,0.0008790327,0.003799555,0.3356251,0.1014146,0.001661732,0.08171199,0.003274205],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8859716,0.0005469391,0.1125762,0.00006200327,0.0002218276,0.00008350639,0.0002483056,0.000004547419,0.0002851194],"genre_scores_gemma":[0.9878322,0.0000578871,0.01098473,0.0001186561,0.0001598375,0.000005541767,0.0007998287,0.00000767144,0.00003367863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3154218,"threshold_uncertainty_score":0.3955026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3101574558","doi":"10.1186/s13040-016-0108-2","title":"ProtNN: fast and accurate protein 3D-structure classification in structural and topological space","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Space (punctuation); Topology (electrical circuits); Topological space; Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics; Pure mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01616966876460837,"gpt":0.2731470377325991,"spread":0.2569773689679907,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001172141,0.0001245401,0.0001000082,0.00003477929,0.00005704685,0.00004156224,0.0001124741,0.0001486267,0.00001937073],"category_scores_gemma":[0.0002719962,0.0000802654,0.000009272518,0.00004583746,0.0001344331,0.00001631007,0.0001857671,0.00007860058,0.000001408195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008499168,"about_ca_system_score_gemma":0.00002020405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008002297,"about_ca_topic_score_gemma":0.00003265201,"domain_scores_codex":[0.999288,0.00004803406,0.0001671993,0.0002581444,0.00006680194,0.0001718143],"domain_scores_gemma":[0.9996044,0.00001331827,0.00009546259,0.0002171801,0.00001948793,0.00005014577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00008421532,0.000005244339,0.1043859,0.00005200848,0.00001151879,0.000002305399,0.0002165936,0.000001586414,0.841424,0.0008054814,0.0001113125,0.05289991],"study_design_scores_gemma":[0.00375592,0.001015038,0.8217405,0.0003310917,0.00002713416,0.0002822589,0.001311498,0.009850509,0.1322805,0.0004466098,0.02770505,0.001253868],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.997902,0.000107199,0.0007609064,0.0006712601,0.00003083632,0.0002565612,0.00005433185,0.00001132972,0.0002056224],"genre_scores_gemma":[0.9849529,0.0000301332,0.01462277,0.00005407087,0.00006699149,0.0000133608,0.00007895111,0.00000791714,0.0001728997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7173547,"threshold_uncertainty_score":0.3273128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406160197","doi":"10.1186/s13040-024-00412-x","title":"The Venus score for the assessment of the quality and trustworthiness of biomedical datasets","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","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 Toronto","funders":"HORIZON EUROPE European Research Council; Ministero dell'Università e della Ricerca; HORIZON EUROPE Framework Programme; Dipartimenti di Eccellenza; European Commission; Alexander von Humboldt-Stiftung","keywords":"Computer science; Quality (philosophy); Informatics; Usability; Data science; Data quality; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3350027862965513,"gpt":0.5494247029763654,"spread":0.214421916679814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001191684,0.00004611109,0.0001147635,0.00002010565,0.0002203221,0.00001032641,0.000181477,0.00004011493,0.000004436397],"category_scores_gemma":[0.001115358,0.00002072986,0.00002908295,0.0001756361,0.0002993085,0.00002573567,0.00008645692,0.00007845483,1.326111e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001573843,"about_ca_system_score_gemma":0.0003254679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003931977,"about_ca_topic_score_gemma":0.00009772377,"domain_scores_codex":[0.9992637,0.00005383006,0.0003370503,0.0001059812,0.000143546,0.00009590737],"domain_scores_gemma":[0.9979889,0.001313363,0.0001375344,0.0004579192,0.00007850109,0.00002381322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001458802,0.0001275535,0.2834719,0.0006322511,0.0001035494,3.415571e-7,0.001290315,0.00000117467,0.001400459,0.00555711,0.02157002,0.6856995],"study_design_scores_gemma":[0.0001999757,0.0001729923,0.8663014,0.0007483834,0.0002326292,0.000005107978,0.01100365,0.003057357,0.007029041,0.0008682584,0.1102996,0.00008162911],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9646404,0.001511877,0.001897226,0.02948074,0.001184713,0.0006843893,0.0005241935,0.000006000145,0.00007047819],"genre_scores_gemma":[0.9988261,0.000126402,0.0004429555,0.0003079801,0.00009192425,0.00002856732,0.0001390496,0.000002623609,0.00003436738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6856179,"threshold_uncertainty_score":0.1694561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2736939530","doi":"10.1186/s13040-017-0145-5","title":"Discovery and replication of SNP-SNP interactions for quantitative lipid traits in over 60,000 individuals","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"U.S. National Library of Medicine; National Center for Advancing Translational Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; National Eye Institute; National Institute on Aging; Medical Research Council; British Heart Foundation; European Hematology Association; National Institute of General Medical Sciences; National Institute for Health and Care Research; Broad Institute; Harvard University; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Replication (statistics); SNP; Single-nucleotide polymorphism; Computational biology; Biology; Pairwise comparison; Genetics; Bioinformatics; Gene; Computer science; Artificial intelligence; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.09098401409320957,"gpt":0.3887127870929476,"spread":0.297728772999738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004305095,0.00007577794,0.0001487103,0.00004339496,0.000113237,0.00003285304,0.0001578385,0.00008599434,0.000003510452],"category_scores_gemma":[0.001528838,0.00007428561,0.00003435898,0.00002270463,0.00007718681,0.00002115623,0.0001186733,0.00003602601,4.793459e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007536504,"about_ca_system_score_gemma":0.00002946717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008279683,"about_ca_topic_score_gemma":0.0002666748,"domain_scores_codex":[0.9992515,0.00004160552,0.0002364452,0.0003086317,0.00003463763,0.0001271493],"domain_scores_gemma":[0.9991397,0.00009363434,0.0002969953,0.000408537,0.00003888293,0.00002219647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008410083,0.00009573015,0.6449084,0.00003659819,0.0001174139,3.07295e-7,0.0006145274,0.00001602158,0.3298247,0.0008022752,0.006484946,0.01701503],"study_design_scores_gemma":[0.0004681236,0.0001525955,0.9811971,0.00002914357,0.00001914066,0.000001704723,0.0003960382,0.0002244114,0.006818116,0.0001115663,0.01048044,0.0001016478],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961272,0.0001708653,0.002286015,0.0003953803,0.00008598913,0.0001582234,0.0005322578,0.000002032125,0.0002420235],"genre_scores_gemma":[0.9882939,0.0001178954,0.01080349,0.00006614529,0.00007230226,0.00004235776,0.0003713094,0.000007515524,0.0002251199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3362887,"threshold_uncertainty_score":0.3029279,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3141242658","doi":"10.1186/s13040-021-00249-8","title":"Prescreening and treatment of aortic dissection through an analysis of infinite-dimension data","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Aortic Disease and Treatment Approaches","field":"Medicine","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 Prince Edward Island; University of Waterloo","funders":"Shanghai Jiao Tong University; Shanghai Municipal Health Bureau; National Natural Science Foundation of China; School of Medicine, Shanghai Jiao Tong University; Comanche Nation","keywords":"Aortic dissection; Medicine; Cardiology; Blood pressure; Internal medicine; Mortality rate; Disease; Incidence (geometry); Medical diagnosis; Psychological intervention; Dissection (medical); Intensive care medicine; Emergency medicine; Surgery; Radiology; Aorta","retraction":null,"screen_n_in":null,"score":{"opus":0.1588053887997506,"gpt":0.3612328588707938,"spread":0.2024274700710433,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005965737,0.00010378,0.0003678098,0.00009641574,0.00003635504,0.000009590522,0.00004842656,0.00003978886,0.00005295083],"category_scores_gemma":[0.00006328208,0.00008202111,0.00005391537,0.0003892255,0.00005298021,0.0002851362,0.00008869472,0.00001680911,4.218005e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001483877,"about_ca_system_score_gemma":0.00005700874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002428885,"about_ca_topic_score_gemma":0.00007747343,"domain_scores_codex":[0.9991245,0.00003295682,0.0002621805,0.0003383108,0.0001418919,0.0001002039],"domain_scores_gemma":[0.9988964,0.00006690596,0.0001176038,0.0008052035,0.00004504428,0.00006882924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002700265,0.001232915,0.9322039,0.00006961172,0.003618697,0.00006822185,0.001875481,0.00001202601,0.008309008,0.00007726751,0.00001633026,0.05224647],"study_design_scores_gemma":[0.00246124,0.001305765,0.8843763,0.0001870009,0.02415264,0.00002438146,0.007248265,0.0477975,0.03192182,0.0000101886,0.0003218451,0.000193001],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978841,0.001150641,0.0003120851,0.00004182628,0.0000143949,0.000102431,0.0002323428,0.00001548435,0.0002467048],"genre_scores_gemma":[0.9836547,0.0002897943,0.01037284,0.00001023695,0.00002118538,0.000004232559,0.005592525,0.000007970896,0.000046492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05205347,"threshold_uncertainty_score":0.3344724,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321598956","doi":"10.1186/s13040-023-00326-0","title":"Ten simple rules for providing bioinformatics support within a hospital","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetics, Bioinformatics, and Biomedical Research","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":"University of Toronto","funders":"","keywords":"Simple (philosophy); Computer science; Data science; Data mining; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0376802126752831,"gpt":0.3102693955737785,"spread":0.2725891828984954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008073096,0.0001990217,0.0001908437,0.0001491925,0.000201036,0.0001278615,0.0005028555,0.0002045964,0.00001915671],"category_scores_gemma":[0.001097658,0.0001706573,0.000105939,0.0002045674,0.0001637339,0.00001953596,0.000499639,0.00008416125,0.000156045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001600757,"about_ca_system_score_gemma":0.0002404938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007629602,"about_ca_topic_score_gemma":0.00001128991,"domain_scores_codex":[0.9982327,0.00001675081,0.0004982576,0.0002969105,0.0003303783,0.0006249817],"domain_scores_gemma":[0.9989906,0.00005151645,0.0001489908,0.0004633374,0.0001283537,0.0002172144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002509207,0.000210528,0.01050121,0.001318065,0.0003746056,0.00002014887,0.004193138,0.00002744308,0.08994853,0.000224804,0.7294794,0.1634512],"study_design_scores_gemma":[0.002893376,0.004059665,0.002863642,0.0001174787,0.00008092825,0.00002840915,0.01372451,0.0395967,0.1491915,0.0003131047,0.7857583,0.001372468],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9855239,0.000100009,0.008086264,0.0009474446,0.0007729179,0.001156717,0.001753765,0.000152713,0.001506205],"genre_scores_gemma":[0.8393696,0.0006625907,0.1238251,0.001036701,0.001563558,0.0003183042,0.02858669,0.0001304282,0.004507067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1620787,"threshold_uncertainty_score":0.6959202,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101279094","doi":"10.1186/1756-0381-7-17","title":"Computational genetics analysis of grey matter density in Alzheimer’s disease","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Olfactory and Sensory Function Studies","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; National Cancer Institute; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Synarc; University of Southern California; Medpace; Novartis Pharmaceuticals Corporation; Dartmouth College; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Grey matter; Disease; Computer science; Data science; Computational biology; Biology; Medicine; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1900964567775927,"gpt":0.3033707888264548,"spread":0.1132743320488621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001053963,0.00007102155,0.000159889,0.0001887407,0.00006855484,0.00001596713,0.00009682115,0.00001791791,0.0001155285],"category_scores_gemma":[0.0001854663,0.00006701174,0.00004862301,0.0003909331,0.00008311064,0.00007816552,0.00007326807,0.00003635843,0.00004343892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005537752,"about_ca_system_score_gemma":0.000009899181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005554937,"about_ca_topic_score_gemma":0.00001316223,"domain_scores_codex":[0.9992141,0.0001022008,0.0001851128,0.0002425252,0.0001519674,0.0001041348],"domain_scores_gemma":[0.9994219,0.0002429763,0.00007531259,0.0001844925,0.00002802604,0.00004730205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003495546,0.00004264815,0.9916033,0.000004953437,0.00006132537,0.000004023291,0.0002725215,0.004324617,0.002256022,0.0001104461,0.0004500671,0.000835147],"study_design_scores_gemma":[0.0001351928,0.00001172069,0.9618882,0.000004788857,0.0002419593,4.50203e-7,0.00006160583,0.03460365,0.002048352,0.00003483369,0.0008805301,0.00008869949],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998397,0.00004042765,0.0009697186,0.0001187781,0.0001004105,0.00003717456,0.00008438841,0.00001128047,0.0002408475],"genre_scores_gemma":[0.9988786,0.000003553542,0.0004481949,0.0005907781,0.0000181972,0.000001358373,0.00002805279,0.000003720855,0.00002752603],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03027903,"threshold_uncertainty_score":0.2732659,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215710945","doi":"10.1186/s13040-021-00281-8","title":"Development of glaucoma predictive model and risk factors assessment based on supervised models","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Glaucoma; Machine learning; Artificial intelligence; Data science; Risk analysis (engineering); Medicine; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.05509305354175464,"gpt":0.3059507429795755,"spread":0.2508576894378208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002241643,0.0001307687,0.0002851545,0.0001058381,0.00008384713,0.00002025927,0.00005709231,0.00004216516,0.00002004749],"category_scores_gemma":[0.00007944686,0.0001066768,0.000055785,0.0001531413,0.00003762454,0.00008061558,0.00006185797,0.0001093946,6.245388e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004613966,"about_ca_system_score_gemma":0.0003288353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002534889,"about_ca_topic_score_gemma":0.000004203298,"domain_scores_codex":[0.9989323,0.00004102903,0.0002796404,0.0003086488,0.0002929787,0.0001454047],"domain_scores_gemma":[0.9993305,0.00007702618,0.00009425575,0.0002910867,0.0001014825,0.0001056345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001691212,0.0004803118,0.956747,0.0001852186,0.0005263974,0.00004524691,0.003376534,0.003847864,0.01712128,0.00004675638,0.0002308783,0.0172234],"study_design_scores_gemma":[0.0006819917,0.00006384934,0.06900541,0.0002207633,0.0002439978,0.000001869751,0.00164253,0.9195775,0.008401199,0.00001028882,0.00005201012,0.00009859442],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.943854,0.00007228615,0.05480021,0.00009467551,0.00001613474,0.00006182921,0.00009760877,0.0000231473,0.0009801554],"genre_scores_gemma":[0.8287465,0.00003458258,0.17079,0.00005406063,0.00001021206,0.000004406925,0.0002778971,0.00001040817,0.0000719888],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9157296,"threshold_uncertainty_score":0.4350152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155858762","doi":"10.1186/1756-0381-4-22","title":"Detection of putative new mutacins by bioinformatic analysis using available web tools","year":2011,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomics and Phylogenetic Studies","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":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bacteriocin; Computational biology; Context (archaeology); Identification (biology); Genome; Biology; Drug discovery; Whole genome sequencing; Computer science; Genetics; Gene; Bioinformatics; Bacteria","retraction":null,"screen_n_in":null,"score":{"opus":0.06311613741850325,"gpt":0.2527864325412549,"spread":0.1896702951227516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001121918,0.0001146727,0.0001784811,0.00008313139,0.00006322459,0.00001589701,0.0001342907,0.0000692193,0.00003554948],"category_scores_gemma":[0.00004953511,0.0001100417,0.00008282666,0.0002325223,0.00004806929,0.000004129515,0.0001215259,0.00002628893,0.000007485236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008352761,"about_ca_system_score_gemma":0.00006040375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001895533,"about_ca_topic_score_gemma":0.00003725627,"domain_scores_codex":[0.999316,0.00001921839,0.0002418177,0.0001979676,0.00006527873,0.0001597647],"domain_scores_gemma":[0.9994671,0.000009636507,0.0001625852,0.0002611069,0.00004742246,0.00005213575],"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":[0.00002370086,0.00001553125,0.003761746,0.000009567765,0.0004839544,2.832639e-7,0.000556665,0.00001797557,0.9912604,0.000001493715,0.0003508082,0.003517885],"study_design_scores_gemma":[0.0003109817,0.0002119594,0.002326088,0.00000645805,0.000380678,0.000003552577,0.001009211,0.002018586,0.988932,0.0000061434,0.00459745,0.0001969431],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907374,0.001033355,0.006712398,0.000002858626,0.0000626828,0.00008053322,0.0002697907,0.000002909309,0.001098013],"genre_scores_gemma":[0.9875294,0.0001290387,0.01194359,0.00002826223,0.0000327879,0.000002552425,0.0001478929,0.00000851129,0.0001779969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005231192,"threshold_uncertainty_score":0.4487368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136227372","doi":"10.1186/s13040-015-0056-2","title":"The role of visualization and 3-D printing in biological data mining","year":2015,"lang":"en","type":"article","venue":"BioData Mining","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Synarc; University of Southern California; Medpace; Novartis Pharmaceuticals Corporation; Dartmouth College; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Visualization; Data science; Computer science; Biological network; Biological data; Data mining; Endophenotype; Data visualization; Artificial intelligence; Machine learning; Bioinformatics; Biology; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.1481506632125918,"gpt":0.3576323327334887,"spread":0.2094816695208969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001065403,0.00006030624,0.00008951568,0.00006060499,0.00006241952,0.000156872,0.0009800876,0.00003215062,9.549539e-7],"category_scores_gemma":[0.0008314543,0.00004291663,0.000005482324,0.0003384922,0.00005735435,0.0005165736,0.001480504,0.00003022034,0.00000229139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006276935,"about_ca_system_score_gemma":0.00004674626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001520991,"about_ca_topic_score_gemma":0.00001702603,"domain_scores_codex":[0.9991651,0.00007305424,0.0002373741,0.0002603424,0.0001337954,0.0001303179],"domain_scores_gemma":[0.9990768,0.0001328003,0.0001147383,0.0005856568,0.00004200575,0.00004802493],"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":[0.00001292408,0.00009979546,0.3952276,0.0000179798,0.0000228037,0.000006726914,0.005399566,0.00001371757,0.001209028,0.1674277,0.002005783,0.4285564],"study_design_scores_gemma":[0.0002800441,0.00004452606,0.00377444,0.00005031479,0.000003375384,0.000005890909,0.00362853,0.9367109,0.0006496031,0.0002664347,0.05445931,0.0001266357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6608222,0.00327951,0.3322251,0.0004706022,0.0003638229,0.0002570251,0.0001007241,0.0001669022,0.00231413],"genre_scores_gemma":[0.9709592,0.0001257557,0.02859424,0.00007345355,0.00003278731,0.000001327054,0.0001901075,0.000004423838,0.00001864554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9366972,"threshold_uncertainty_score":0.1845342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414531239","doi":"10.1186/s13040-025-00480-7","title":"Temporal phenotyping and prognostic stratification of patients with sepsis through longitudinal clustering","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Multivariate statistics; Sepsis; Covariate; Silhouette; Disease; Biobank; Multivariate analysis; Metric (unit)","retraction":null,"screen_n_in":null,"score":{"opus":0.0254430725212012,"gpt":0.2456228539031261,"spread":0.2201797813819249,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001100653,0.00008822769,0.000138612,0.00006347091,0.0001253877,0.0001379251,0.0002367233,0.00002404271,0.000003887033],"category_scores_gemma":[0.00004045014,0.00007306303,0.00001692778,0.0003830269,0.00004589854,0.0006688213,0.000227363,0.00003871878,4.827842e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001040109,"about_ca_system_score_gemma":0.00002905085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004689225,"about_ca_topic_score_gemma":0.00004105736,"domain_scores_codex":[0.9992345,0.00001684634,0.000217428,0.0002860051,0.0001151898,0.0001300261],"domain_scores_gemma":[0.9994291,0.00004920639,0.0001465367,0.0002798814,0.00007534611,0.00001989799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001631249,0.00004286765,0.9275342,0.00008854676,0.00005975863,7.901327e-7,0.0007361158,0.00007366961,0.00007035709,0.002887392,0.00004283788,0.06844714],"study_design_scores_gemma":[0.0006124824,0.0002001972,0.7951111,0.0005204712,0.00009119558,0.000001272512,0.0007414729,0.2014562,0.0003700765,0.0002049681,0.0004069511,0.0002836011],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4622687,0.0001071066,0.5369626,0.00008567137,0.00004485946,0.00009655605,0.000008123844,0.0000289396,0.0003975388],"genre_scores_gemma":[0.8899558,0.000002270076,0.1099667,0.00001365171,0.000008199784,0.000003453431,0.00002936842,0.000002942909,0.0000176679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4276871,"threshold_uncertainty_score":0.2979424,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4307995431","doi":"10.1186/s13040-022-00312-y","title":"Towards a potential pan-cancer prognostic signature for gene expression based on probesets and ensemble machine learning","year":2022,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Krembil Foundation; University of Toronto","funders":"","keywords":"Signature (topology); Gene signature; Cancer; Gene; Computational biology; Random forest; Relevance (law); Microarray analysis techniques; Biology; Microarray; Bioinformatics; Computer science; Gene expression; Machine learning; Genetics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01260455096746129,"gpt":0.24221652434108,"spread":0.2296119733736187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002461452,0.0001443909,0.0001184173,0.00003939201,0.000330226,0.00004229559,0.0001489452,0.00009261132,0.00003850543],"category_scores_gemma":[0.00003982246,0.000131638,0.00004849898,0.00005237967,0.00002528711,0.000004692215,0.000285959,0.0001608966,6.305119e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000130115,"about_ca_system_score_gemma":0.00007355584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007029468,"about_ca_topic_score_gemma":0.000004112618,"domain_scores_codex":[0.9991194,0.00004335002,0.0001585831,0.0003158731,0.000127755,0.0002350338],"domain_scores_gemma":[0.9995983,0.00001691745,0.0001049693,0.0001970401,0.00002636652,0.00005639348],"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":[0.000728804,0.0001069779,0.001184474,0.0001103124,0.00005386061,0.000006954318,0.0001755266,0.01000664,0.8711521,0.00001206475,0.008621194,0.1078411],"study_design_scores_gemma":[0.005490372,0.003908546,0.00101478,0.0001855186,0.0001592276,0.00007171091,0.000626083,0.4449203,0.3490658,0.00008911626,0.1932144,0.001254178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.920066,0.007589141,0.06793922,0.0006033455,0.0005937294,0.001317015,0.00152064,0.00004553049,0.0003254049],"genre_scores_gemma":[0.9849222,0.00006871464,0.01149901,0.0003414821,0.0001950654,0.0002174957,0.002437194,0.00002520726,0.0002936457],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5220863,"threshold_uncertainty_score":0.5368041,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391353343","doi":"10.1186/s13040-024-00355-3","title":"Revealing third-order interactions through the integration of machine learning and entropy methods in genomic studies","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; Genentech; IXICO; H. Lundbeck A/S; Servier; National Institutes of Health; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Eisai; Pfizer; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Meso Scale Diagnostics; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Genome-wide association study; Computer science; Epistasis; Single-nucleotide polymorphism; Genetic association; SNP; Computational biology; Artificial intelligence; Data mining; Machine learning; Biology; Genetics; Genotype; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.07409299352930675,"gpt":0.4222588802548448,"spread":0.348165886725538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000721356,0.00008015207,0.0001365697,0.0000389613,0.00007506982,0.0000165626,0.00007056826,0.00005404696,0.000006285318],"category_scores_gemma":[0.0009158523,0.00005627851,0.00002968744,0.0001102386,0.00006314071,0.000006240379,0.000136842,0.0001227341,0.00000107629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000152624,"about_ca_system_score_gemma":0.00002431068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001033919,"about_ca_topic_score_gemma":0.0001655872,"domain_scores_codex":[0.9991493,0.0002578869,0.0002490202,0.0002050298,0.0000291773,0.0001095398],"domain_scores_gemma":[0.9995219,0.0002356507,0.00007670773,0.0001171631,0.00003834053,0.00001023105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002283427,0.00001804879,0.02280844,0.00005669098,0.0002674065,0.000001414291,0.004679339,0.0003074691,0.9187958,0.0006818232,0.001639428,0.05072132],"study_design_scores_gemma":[0.001264318,0.0008207104,0.04622378,0.0008396295,0.0004283289,0.0001304581,0.0644884,0.08568937,0.08552946,0.002496479,0.7110993,0.0009897436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9009496,0.04242424,0.05414287,0.001588596,0.0003675754,0.0001324337,0.00002787268,0.00001311323,0.0003537015],"genre_scores_gemma":[0.8630539,0.005297913,0.1307843,0.0001043485,0.0001098732,0.00001755878,0.0001298941,0.00001098118,0.0004912069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8332663,"threshold_uncertainty_score":0.2294971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402164248","doi":"10.1186/s13040-024-00380-2","title":"Seven quick tips for gene-focused computational pangenomic analysis","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Università degli Studi di Parma; Università degli Studi di Trento","keywords":"Computer science; Data science; Computational biology; Data mining; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02125871234764549,"gpt":0.2961630698224296,"spread":0.2749043574747841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002518511,0.0001286885,0.0001633743,0.0001867725,0.00006427177,0.000106308,0.0002172098,0.00009109627,0.00004638191],"category_scores_gemma":[0.00004206524,0.0001288758,0.0002315903,0.0003056008,0.00003679538,0.000007534934,0.0001185085,0.00003803647,0.00002101112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000204664,"about_ca_system_score_gemma":0.00006856717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002353199,"about_ca_topic_score_gemma":0.00004789048,"domain_scores_codex":[0.9990202,0.00002660703,0.0002109572,0.0004710054,0.00009223869,0.000178952],"domain_scores_gemma":[0.9994524,0.0000362556,0.00004735816,0.0003576672,0.00005786363,0.00004848401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007245418,0.00006893632,0.003640602,0.00008349125,0.004329617,0.00001974656,0.0002729399,0.0006729172,0.7957428,0.0000822881,0.1480214,0.04699275],"study_design_scores_gemma":[0.0005246282,0.0002631042,0.001688889,0.00003107525,0.002530766,0.00002470744,0.000189131,0.07275642,0.4004445,0.0001964098,0.5205456,0.0008047497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5870523,0.003467466,0.4078388,0.0001986331,0.00006102086,0.0002613046,0.0004227065,0.0001096191,0.0005881376],"genre_scores_gemma":[0.9196725,0.00006917906,0.07221414,0.0001853081,0.0002738478,0.00004604709,0.00643196,0.00002895302,0.00107805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3952983,"threshold_uncertainty_score":0.5255404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3040486170","doi":"10.1186/s13040-020-00218-7","title":"An epistatic interaction between pre-natal smoke exposure and socioeconomic status has a significant impact on bronchodilator drug response in African American youth with asthma","year":2020,"lang":"en","type":"article","venue":"BioData Mining","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"National Institute of General Medical Sciences; University of California, San Francisco; National Institutes of Health; National Institute of Environmental Health Sciences; San Francisco State University; National Institute on Minority Health and Health Disparities; Tobacco-Related Disease Research Program; National Heart, Lung, and Blood Institute; Gordon and Betty Moore Foundation; American Asthma Foundation; Alfred P. Sloan Foundation; Robert Wood Johnson Foundation","keywords":"Bronchodilator; Socioeconomic status; Asthma; Smoke; Drug; Drug response; Environmental health; African american; Medicine; Demography; Pharmacology; Internal medicine; Geography; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.03639083565729737,"gpt":0.2904963259645341,"spread":0.2541054903072367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007860764,0.0002895143,0.000337178,0.00009110519,0.0001642275,0.000129828,0.0002195754,0.00004235272,0.0002040929],"category_scores_gemma":[0.0001289491,0.0002581635,0.00003042679,0.000193281,0.0004859431,0.0006823701,0.0001398891,0.0003368543,0.00006778034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007268409,"about_ca_system_score_gemma":0.00008398498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004049294,"about_ca_topic_score_gemma":0.0002372187,"domain_scores_codex":[0.9973215,0.0005786532,0.0003630316,0.0009295096,0.0002461546,0.0005611727],"domain_scores_gemma":[0.9983772,0.0004312582,0.0002825082,0.0003710945,0.000003054333,0.0005348928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002054745,0.00006439527,0.926429,0.00001075074,0.00002353243,0.00003023976,0.03965299,0.000424149,0.002149646,2.715591e-7,0.00003516155,0.02912508],"study_design_scores_gemma":[0.0007489773,0.002134806,0.967228,0.00004124727,0.00001875611,0.000002583136,0.02719919,0.001575907,0.0004700964,0.000001537812,0.0002577641,0.0003211225],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976746,0.000009608879,0.0002845826,0.0007560444,0.00001608596,0.0004293921,0.0007279355,0.00004213778,0.00005954319],"genre_scores_gemma":[0.9978936,0.0000103524,0.001393321,0.0004153615,0.00004263427,0.00002193045,0.0001767261,0.00004177235,0.000004341052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04079897,"threshold_uncertainty_score":0.9999871,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165336562","doi":"10.1186/1756-0381-5-14","title":"Peer2ref: a peer-reviewer finding web tool that uses author disambiguation","year":2012,"lang":"en","type":"article","venue":"BioData Mining","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Computer science; MEDLINE; Information retrieval; Web of science; World Wide Web; Selection (genetic algorithm); Data science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.119280966501619,"gpt":0.3543855559307648,"spread":0.2351045894291458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008672047,0.0001930352,0.0001928262,0.00005392908,0.0001446062,0.00005873799,0.0002794079,0.0002379289,0.0001037746],"category_scores_gemma":[0.002132459,0.0001606168,0.00008761819,0.0001155248,0.0001143357,0.00001818406,0.0002435269,0.00009988646,0.00007114138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001659788,"about_ca_system_score_gemma":0.00005235821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008701321,"about_ca_topic_score_gemma":0.000008877893,"domain_scores_codex":[0.9985997,0.00008202893,0.0002324081,0.0003359055,0.0002934553,0.000456514],"domain_scores_gemma":[0.9991769,0.00004870466,0.0001167921,0.0004454548,0.00008527291,0.0001269324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007813299,0.0002087092,0.1618572,0.0001274085,0.0001551075,0.000005408124,0.001083197,8.838655e-7,0.146172,0.0001271659,0.4069409,0.2832439],"study_design_scores_gemma":[0.0003183759,0.000103442,0.01662976,0.0000706685,0.00004605038,0.00001866093,0.0007237142,0.00005116597,0.01770838,0.000004258349,0.964009,0.0003165425],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895043,0.005100616,0.001766267,0.001180291,0.001330264,0.0001476387,0.0001306577,0.00007072637,0.0007692229],"genre_scores_gemma":[0.9821376,0.000154,0.01211789,0.0003785236,0.0008949597,0.00003063656,0.0007440561,0.00002347984,0.003518814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.557068,"threshold_uncertainty_score":0.6549764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411237205","doi":"10.1186/s13040-025-00455-8","title":"DBSCAN and DBCV application to open medical records heterogeneous data for identifying clinically significant clusters of patients with neuroblastoma","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Neuroblastoma Research and Treatments","field":"Medicine","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 Toronto","funders":"","keywords":"Computer science; Data mining; Neuroblastoma; Medical record; DBSCAN; Data science; Information retrieval; Cluster analysis; Medicine; Internal medicine; Artificial intelligence; Fuzzy clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.07202205426547378,"gpt":0.3988111328466636,"spread":0.3267890785811898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004472953,0.0001430754,0.000332604,0.000148659,0.00008898181,0.00006621576,0.000727019,0.00006168787,0.00001431118],"category_scores_gemma":[0.0008406788,0.0001129678,0.00002408763,0.0002472234,0.00009351678,0.00016415,0.001372043,0.00009498616,0.00000374903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002736906,"about_ca_system_score_gemma":0.0002533742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007846754,"about_ca_topic_score_gemma":0.0000983542,"domain_scores_codex":[0.9981686,0.00005528659,0.0004457711,0.000685449,0.000379014,0.0002658425],"domain_scores_gemma":[0.998108,0.0003342443,0.0001284394,0.0009904358,0.0001270764,0.000311752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01759553,0.001872157,0.4365469,0.001035418,0.0008177769,0.0001220821,0.0001911684,0.000006150436,0.003527207,0.00003521592,0.01249285,0.5257576],"study_design_scores_gemma":[0.05186567,0.02450005,0.8368514,0.004859412,0.001421331,0.00007748537,0.0006570901,0.02433633,0.01231052,0.00007309316,0.04182564,0.001221973],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865062,0.00001717194,0.009224559,0.001044633,0.00008145997,0.002253257,0.0007267643,0.0000251224,0.0001208927],"genre_scores_gemma":[0.9847183,0.00002121217,0.01313304,0.0007197188,0.00002876294,0.0001360024,0.001105656,0.00002459705,0.0001127716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5245356,"threshold_uncertainty_score":0.4606695,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404300486","doi":"10.1186/s13040-024-00400-1","title":"Deciphering the tissue-specific functional effect of Alzheimer risk SNPs with deep genome annotation","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Annotation; Genome-wide association study; Single-nucleotide polymorphism; Genome; Computer science; Computational biology; Biology; Data science; Artificial intelligence; Genetics; Gene; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.01376340837305052,"gpt":0.2323274820777082,"spread":0.2185640737046577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003448005,0.0001210151,0.000100117,0.00002713878,0.00009272188,0.0000575659,0.0001273509,0.00007422415,0.00003576844],"category_scores_gemma":[0.00001101239,0.00007558276,0.00004030297,0.0001049861,0.00007011521,0.000008658042,0.00008100861,0.00008403696,0.00001716973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005906847,"about_ca_system_score_gemma":0.00002359993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000549739,"about_ca_topic_score_gemma":0.000009329157,"domain_scores_codex":[0.9993305,0.00003549143,0.00018318,0.0002002925,0.0001028538,0.0001477061],"domain_scores_gemma":[0.99954,0.00004108788,0.00007502863,0.0002864848,0.00002612198,0.00003125588],"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":[0.0005656263,0.00003240381,0.002445598,0.0001699565,0.001306354,0.00001284014,0.001474757,0.005365742,0.3795955,0.0002747452,0.007181412,0.6015751],"study_design_scores_gemma":[0.001708712,0.00253044,0.02009548,0.0002301253,0.0006804609,0.0001610158,0.001036808,0.02057847,0.1990355,0.00005254113,0.7529113,0.0009791122],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9061316,0.0226211,0.06961823,0.00004474857,0.0003803974,0.0002521784,0.00009509156,0.00002052617,0.000836163],"genre_scores_gemma":[0.9961721,0.0002974911,0.002607555,0.00002600029,0.0003450485,0.00001598541,0.0004632182,0.00001833816,0.00005425745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7457299,"threshold_uncertainty_score":0.3082176,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2610597045","doi":"10.1186/s13040-017-0136-6","title":"Study of Meta-analysis strategies for network inference using information-theoretic approaches","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Gene Regulatory Network Analysis","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":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"Université de Liège; Fonds De La Recherche Scientifique - FNRS","keywords":"Pairwise comparison; Computer science; Data mining; Inference; Set (abstract data type); Reverse engineering; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2128476376645253,"gpt":0.3422631988385581,"spread":0.1294155611740328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005629687,0.0001700856,0.0005198629,0.00008841585,0.000340019,0.0001996672,0.0005709426,0.00008969317,0.00001537447],"category_scores_gemma":[0.0001150709,0.0001457395,0.0004133616,0.0001567887,0.0001165529,0.00004407536,0.000282777,0.00003262347,6.489064e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000515617,"about_ca_system_score_gemma":0.00008053051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000546036,"about_ca_topic_score_gemma":0.0001705438,"domain_scores_codex":[0.9989002,0.00006826757,0.0003947988,0.0002753216,0.0001465078,0.0002149025],"domain_scores_gemma":[0.9979538,0.00003092063,0.0005800706,0.001268362,0.0001212122,0.00004559193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.0001979097,0.0003402522,0.104759,0.0001488743,0.2834823,0.000001878172,0.002256216,0.6001625,0.00283903,0.002761193,0.0008578491,0.002192915],"study_design_scores_gemma":[0.003363457,0.001868506,0.03124565,0.00002308052,0.7075258,0.000008455584,0.04398668,0.1925828,0.01084753,0.00125394,0.004899347,0.002394788],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9562941,0.0005366302,0.04253909,0.00001626934,0.00003909875,0.0002853687,0.00006582367,0.000005890049,0.0002177841],"genre_scores_gemma":[0.9896316,0.000008498205,0.009926555,0.00001549536,0.00008976804,0.00003812946,0.0002590391,0.000008985703,0.00002191351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4240434,"threshold_uncertainty_score":0.5943085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120184682","doi":"10.1186/s13040-014-0032-2","title":"Integrative genomics and transcriptomics analysis of human embryonic and induced pluripotent stem cells","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomic variations and chromosomal abnormalities","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":"Lunenfeld-Tanenbaum Research Institute","funders":"Emil Aaltosen Säätiö; European Commission","keywords":"Embryonic stem cell; Induced pluripotent stem cell; Genomics; Transcriptome; Computational biology; Biology; Human Induced Pluripotent Stem Cells; Stem cell; Data science; Computer science; Genetics; Genome; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01718761907827809,"gpt":0.2301086904694139,"spread":0.2129210713911358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001426719,0.0001134282,0.0002040448,0.00008537683,0.00007682276,0.00002826406,0.0001012306,0.0000836539,0.000004605563],"category_scores_gemma":[0.000005928216,0.0001032928,0.00005050739,0.00008499524,0.00006208806,0.000005549687,0.00008594136,0.00003964555,2.752925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008707048,"about_ca_system_score_gemma":0.00002298124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005547159,"about_ca_topic_score_gemma":0.0001400732,"domain_scores_codex":[0.9993584,0.00004307714,0.0001913441,0.0002431014,0.00004405935,0.0001200745],"domain_scores_gemma":[0.9995872,0.00001167846,0.00009822621,0.0002169661,0.00003651879,0.0000494246],"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":[0.00001295563,0.00001487116,0.004688718,0.00001657993,0.0003540641,1.910166e-7,0.0009614869,0.00001295039,0.9915866,0.0004128346,0.00002751039,0.001911255],"study_design_scores_gemma":[0.0007906079,0.0005902258,0.01588534,0.00002355097,0.0008806955,0.000006160422,0.008538934,0.002159905,0.9667554,0.0000291078,0.003959539,0.0003805297],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998571,0.0002706389,0.0007667626,0.00002490324,0.00003704521,0.00006011386,0.0001404651,0.000003630568,0.0001254461],"genre_scores_gemma":[0.998676,0.0001135899,0.0008288031,0.00004155128,0.00003308839,0.000003738485,0.0001627226,0.000008284695,0.0001322006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02483118,"threshold_uncertainty_score":0.4212157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102718331","doi":"10.1186/1756-0381-7-25","title":"Updating microbial genomic sequences: improving accuracy & innovation","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Vibrio bacteria research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McMaster University","keywords":"Sanger sequencing; Biology; Genome; Whole genome sequencing; Computational biology; Salmonella enterica; Biovar; Genetics; DNA sequencing; Caulobacter crescentus; Salmonella; Gene; Bacterial protein; Bacteria","retraction":null,"screen_n_in":null,"score":{"opus":0.03551480171943568,"gpt":0.3013115225258921,"spread":0.2657967208064564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005214084,0.0001428736,0.0001262923,0.00008077616,0.0001968501,0.0001095574,0.0003109191,0.00008647987,0.00002362895],"category_scores_gemma":[0.001826857,0.0001397748,0.00002940856,0.0001731422,0.000083046,0.00001721418,0.0005351357,0.00007872747,0.0000376564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002519312,"about_ca_system_score_gemma":0.00008845142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005514313,"about_ca_topic_score_gemma":0.00005761783,"domain_scores_codex":[0.998836,0.00006858689,0.0002704584,0.0004017336,0.000100754,0.0003224072],"domain_scores_gemma":[0.9992366,0.00003574771,0.0001591268,0.000417071,0.0001135768,0.00003786593],"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":[0.00002050296,0.000007472854,0.002184808,0.00002374853,0.00002376518,4.103014e-7,0.00006789067,0.000002776413,0.9791818,0.00004559333,0.002058274,0.01638291],"study_design_scores_gemma":[0.00107666,0.0002548998,0.009635469,0.00007304217,0.00002424063,0.00002787599,0.0004889811,0.0002755502,0.6275958,0.00002755604,0.3598436,0.0006763188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949825,0.00009589033,0.00388759,0.0001566417,0.0001666129,0.0001205908,0.0000568384,0.00002282072,0.0005105378],"genre_scores_gemma":[0.9788365,0.00003501246,0.01887232,0.0002570248,0.0006295589,0.00001502101,0.001172549,0.00002119655,0.0001607871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3577853,"threshold_uncertainty_score":0.5699849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405855303","doi":"10.1186/s13040-024-00413-w","title":"Distinct network patterns emerge from Cartesian and XOR epistasis models: a comparative network science analysis","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; National Institutes of Health; Alliance de recherche numérique du Canada","keywords":"Epistasis; Biology; Computational biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03330849453372306,"gpt":0.2784116938249487,"spread":0.2451031992912257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004274067,0.0002135048,0.0002746282,0.00007165325,0.0002873649,0.0002671515,0.0003264686,0.000103139,0.00003171447],"category_scores_gemma":[0.00001006867,0.0001923387,0.00009860232,0.00064345,0.0002102776,0.00002748613,0.0004041116,0.0001061129,0.000005843927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001816702,"about_ca_system_score_gemma":0.00008344557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001571735,"about_ca_topic_score_gemma":0.0006536283,"domain_scores_codex":[0.998446,0.00003568062,0.0003177699,0.00058074,0.0001547673,0.0004650112],"domain_scores_gemma":[0.9991966,0.00003893711,0.00008334286,0.0004802507,0.00004141467,0.0001593949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006680359,0.0002814539,0.3045882,0.0004965123,0.01690841,0.0001880751,0.01623034,0.1059008,0.01688659,0.01020293,0.2332107,0.2944379],"study_design_scores_gemma":[0.0003487282,0.000176527,0.02089196,0.0001873044,0.0009653828,0.00001043769,0.000998963,0.939962,0.0004710957,0.0009652881,0.03415693,0.0008653871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8635348,0.01240464,0.1205096,0.0001449783,0.0005572707,0.0001971711,0.001030335,0.00004484511,0.001576301],"genre_scores_gemma":[0.9911313,0.0002352722,0.006375012,0.0001332537,0.0007391776,0.00001282436,0.001290785,0.00001401441,0.00006838448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8340611,"threshold_uncertainty_score":0.7843345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414606898","doi":"10.1186/s13040-025-00482-5","title":"Proteome mining of Yersinia Enterocolitica for drug targets and computational inhibitor identification with ADMET, anti-inflammation potential and formulation characteristics","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Pharmacological Effects of Natural Compounds","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Alpha Technologies (Canada)","funders":"King Khalid University; National Research Foundation of Korea","keywords":"Yersinia enterocolitica; Proteome; Drug; Yersinia; Proteomics; Drug repositioning; Identification (biology); Drug discovery","retraction":null,"screen_n_in":null,"score":{"opus":0.04233579431491202,"gpt":0.381111791511651,"spread":0.338775997196739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005947805,0.000166419,0.0002563994,0.0001826394,0.0002679354,0.000055656,0.0001146722,0.000144289,0.00001560819],"category_scores_gemma":[0.0001836275,0.0001522786,0.00002968346,0.0001443971,0.0001547549,0.0003548567,0.0001006592,0.0001723552,9.738592e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003835124,"about_ca_system_score_gemma":0.00005486838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002343179,"about_ca_topic_score_gemma":0.000001506087,"domain_scores_codex":[0.9987708,0.0001421426,0.0004239662,0.000313824,0.000124588,0.0002247063],"domain_scores_gemma":[0.9988424,0.0004971825,0.0002914619,0.00008441718,0.0001999832,0.00008457497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002865053,0.0002407671,0.02297523,0.001308196,0.0004040939,0.00001156151,0.0009392452,0.0003689279,0.9171022,0.001472645,0.001890965,0.05042109],"study_design_scores_gemma":[0.01007801,0.0007388022,0.4077592,0.0004137956,0.0009450874,0.00004150854,0.000520467,0.3077599,0.2623098,0.00102617,0.007693428,0.0007138317],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990922,0.0001755654,0.006293623,0.0007441692,0.0003516969,0.001183663,0.0002487655,0.00004278634,0.00003772077],"genre_scores_gemma":[0.9910108,0.00001548152,0.00794734,0.0001825813,0.0001254947,0.00009620801,0.0005429766,0.000009831046,0.00006931811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6547924,"threshold_uncertainty_score":0.6209742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408930421","doi":"10.1186/s13040-025-00441-0","title":"Multivariate longitudinal clustering reveals neuropsychological factors as dementia predictors in an Alzheimer’s disease progression study","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","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 Toronto","funders":"","keywords":"Multivariate statistics; Dementia; Neuropsychology; Multivariate analysis; Cluster analysis; Disease; Longitudinal study; Psychology; Alzheimer's disease; Longitudinal data; Medicine; Computer science; Cognition; Psychiatry; Artificial intelligence; Internal medicine; Data mining; Machine learning; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1037533014192664,"gpt":0.4365110347565466,"spread":0.3327577333372801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002265,0.000242418,0.0003006803,0.0003611789,0.0001510143,0.0001105387,0.0002625486,0.0000654535,0.0002476489],"category_scores_gemma":[0.0003466044,0.0001878154,0.00005910986,0.0004586554,0.00008074514,0.0003001255,0.0004380386,0.0002543933,0.00001696697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000362133,"about_ca_system_score_gemma":0.000100791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006390252,"about_ca_topic_score_gemma":0.00002591357,"domain_scores_codex":[0.997521,0.0003138924,0.0004313784,0.0007650243,0.0004772039,0.0004914923],"domain_scores_gemma":[0.998946,0.00008313994,0.00007929326,0.0004766843,0.00008318915,0.0003316531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001293725,0.002106614,0.9830848,0.00004015846,0.0001825407,0.0005931605,0.0003736189,9.258553e-7,0.001492851,0.000003505222,0.0001194167,0.01070871],"study_design_scores_gemma":[0.002789169,0.001520507,0.992655,0.0003777974,0.000379005,0.000003428853,0.001387394,0.0004637667,0.0001459439,0.000007986671,0.0001154637,0.0001544861],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968883,0.0003123315,0.0001654687,0.0001690726,0.0002219397,0.001530348,0.00002507434,0.0000938036,0.0005936825],"genre_scores_gemma":[0.9989558,0.00001208129,0.0003612821,0.0001379537,0.00005491695,0.00011846,0.0002031622,0.00001822753,0.0001380442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01055422,"threshold_uncertainty_score":0.7658892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410024327","doi":"10.1186/s13040-025-00444-x","title":"Learning the therapeutic targets of acute myeloid leukemia through multiscale human interactome network and community analysis","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interactome; Myeloid leukemia; Computer science; Computational biology; Data science; Medicine; Biology; Cancer research; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.04076467338792138,"gpt":0.3493131891731776,"spread":0.3085485157852562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001390123,0.0001440797,0.0002848686,0.0001297689,0.0007409565,0.0001823489,0.001168092,0.00004591787,0.000008859772],"category_scores_gemma":[0.00008837935,0.0001125832,0.00009672047,0.001322584,0.0001510918,0.0005028647,0.001364973,0.0004469547,0.000001457082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000527354,"about_ca_system_score_gemma":0.00006747779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002753446,"about_ca_topic_score_gemma":0.00006673008,"domain_scores_codex":[0.9978455,0.001168835,0.0003209098,0.0002717111,0.0001767342,0.0002163432],"domain_scores_gemma":[0.9971945,0.001823191,0.0001883131,0.0007037774,0.00006363141,0.0000265438],"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":[0.0001238598,0.0003690728,0.2416635,0.0002061498,0.01275343,0.00002340656,0.08488394,0.2296871,0.01027837,0.07653844,0.002203844,0.3412689],"study_design_scores_gemma":[0.0005039837,0.0001385761,0.3340557,0.0001209673,0.0006688099,0.000006173446,0.001762036,0.6508644,0.001000462,0.006826296,0.003732721,0.0003198425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4945467,0.0004775331,0.5037975,0.000261215,0.0001381684,0.00009036156,0.0000105019,0.00005064473,0.0006273564],"genre_scores_gemma":[0.9351062,0.0000309882,0.06438945,0.0002698486,0.0000245666,0.000006774367,0.00005384624,0.000005238922,0.0001130674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4405595,"threshold_uncertainty_score":0.5698913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387813874","doi":"10.1186/s13040-023-00344-y","title":"Prescription pattern analysis of Type 2 Diabetes Mellitus: a cross-sectional study in Isfahan, Iran","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"","keywords":"Medical prescription; Medicine; Diabetes mellitus; Polypharmacy; Type 2 Diabetes Mellitus; Cross-sectional study; Type 2 diabetes; Internal medicine; Pharmacology; Endocrinology","retraction":null,"screen_n_in":null,"score":{"opus":0.08700440662326508,"gpt":0.3629943011081319,"spread":0.2759898944848668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001266193,0.0001088775,0.0002457072,0.0008716397,0.0000807414,0.0001130215,0.0007183708,0.00006107183,0.00003804608],"category_scores_gemma":[0.0002820478,0.0001098544,0.00005498872,0.003709741,0.00002695673,0.0003489592,0.00041405,0.0001645773,0.00003645115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004041429,"about_ca_system_score_gemma":0.00003965739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001032932,"about_ca_topic_score_gemma":0.0006411014,"domain_scores_codex":[0.9981565,0.0002261758,0.0004600256,0.0004982633,0.000383531,0.0002754561],"domain_scores_gemma":[0.998839,0.000214293,0.0001424653,0.0006643168,0.00008837839,0.00005150991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000360605,0.00003917797,0.9853138,0.00002848369,0.00008339314,0.000006077672,0.002235032,0.001622085,0.00008293132,0.00002082291,0.00004682412,0.01051779],"study_design_scores_gemma":[0.0001246586,0.00009752198,0.7443079,0.00001388095,0.00001662457,1.674854e-7,0.0001348864,0.2551423,0.0000176782,0.000009021073,0.00006088194,0.00007451253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969417,0.0001324342,0.002072762,0.00007120206,0.0004242159,0.0001621046,0.00003021253,0.0001356658,0.00002968288],"genre_scores_gemma":[0.9989523,0.00001138306,0.0007592026,0.00004241146,0.00004413608,0.00001662682,0.0001166376,0.000007685678,0.00004957637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2535202,"threshold_uncertainty_score":0.4479731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416785648","doi":"10.1186/s13040-025-00499-w","title":"Bioinformatics analysis of Rickettsia typhi autoimmune associations and screening of Streptomyces-derived inhibitors","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"vaccines and immunoinformatics approaches","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":"Alpha Technologies (Canada)","funders":"National Research Foundation of Korea; King Khalid University; National Research Foundation","keywords":"Rickettsia typhi; Salmonella typhi; Rickettsia","retraction":null,"screen_n_in":null,"score":{"opus":0.01826554024398858,"gpt":0.2611037845670206,"spread":0.242838244323032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002524674,0.000109965,0.0002848653,0.0002647724,0.00006830418,0.0000221045,0.0001657854,0.0001025988,0.000005618712],"category_scores_gemma":[0.0001677402,0.0001039117,0.0001033429,0.0005796937,0.00005467919,0.00001638507,0.0002483651,0.0000441757,2.308427e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005827248,"about_ca_system_score_gemma":0.00004915645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004070721,"about_ca_topic_score_gemma":0.000008572688,"domain_scores_codex":[0.9991137,0.00001881993,0.0005344091,0.0001174201,0.00008831999,0.0001273685],"domain_scores_gemma":[0.9991636,0.0000306662,0.00036036,0.0003333958,0.00009067101,0.00002126134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001096312,0.0001859089,0.3982491,0.0004315033,0.008894607,4.103027e-7,0.002836842,0.0007057362,0.4941957,0.0005587633,0.002639376,0.09119237],"study_design_scores_gemma":[0.001738049,0.0002847218,0.6705923,0.0002206434,0.002416067,0.000001953425,0.009246805,0.07121705,0.2383644,0.00001492036,0.00536706,0.0005359977],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928825,0.00100361,0.004876008,0.00004696097,0.00004240321,0.00009029498,0.0002097845,0.000007027923,0.000841416],"genre_scores_gemma":[0.9808549,0.0001720711,0.01783847,0.00003070809,0.000009804475,0.000003389458,0.001018655,0.000005173543,0.00006682902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2723432,"threshold_uncertainty_score":0.4237398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4234031396","doi":"10.1186/preaccept-8590947901180703","title":"Integrative genomics and transcriptomics analysis of human embryonic and induced pluripotent stem cells","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomic variations and chromosomal abnormalities","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":"Lunenfeld-Tanenbaum Research Institute","funders":"Emil Aaltosen Säätiö; European Commission","keywords":"Biology; Induced pluripotent stem cell; Genetics; Single-nucleotide polymorphism; Gene; SNP array; Copy-number variation; Genomics; DNA microarray; Transcriptome; Embryonic stem cell; Human genome; Functional genomics; Phenotype; Exon; Genome; Computational biology; Gene expression; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.01718761907827809,"gpt":0.2301086904694139,"spread":0.2129210713911358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001426719,0.0001134282,0.0002040448,0.00008537683,0.00007682276,0.00002826406,0.0001012306,0.0000836539,0.000004605563],"category_scores_gemma":[0.000005928216,0.0001032928,0.00005050739,0.00008499524,0.00006208806,0.000005549687,0.00008594136,0.00003964555,2.752925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008707048,"about_ca_system_score_gemma":0.00002298124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005547159,"about_ca_topic_score_gemma":0.0001400732,"domain_scores_codex":[0.9993584,0.00004307714,0.0001913441,0.0002431014,0.00004405935,0.0001200745],"domain_scores_gemma":[0.9995872,0.00001167846,0.00009822621,0.0002169661,0.00003651879,0.0000494246],"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":[0.00001295563,0.00001487116,0.004688718,0.00001657993,0.0003540641,1.910166e-7,0.0009614869,0.00001295039,0.9915866,0.0004128346,0.00002751039,0.001911255],"study_design_scores_gemma":[0.0007906079,0.0005902258,0.01588534,0.00002355097,0.0008806955,0.000006160422,0.008538934,0.002159905,0.9667554,0.0000291078,0.003959539,0.0003805297],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998571,0.0002706389,0.0007667626,0.00002490324,0.00003704521,0.00006011386,0.0001404651,0.000003630568,0.0001254461],"genre_scores_gemma":[0.998676,0.0001135899,0.0008288031,0.00004155128,0.00003308839,0.000003738485,0.0001627226,0.000008284695,0.0001322006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02483118,"threshold_uncertainty_score":0.4212157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387402455","doi":"10.1186/s13040-023-00343-z","title":"Quantum analysis of squiggle data","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge","funders":"Alberta Innovates; Ministero dello Sviluppo Economico; Government of Alberta; Genome Canada","keywords":"Nanopore sequencing; Computer science; Curse of dimensionality; Algorithm; Quantum; IBM; Quantum computer; Current (fluid); Computer engineering; DNA sequencing; Theoretical computer science; Artificial intelligence; DNA; Electrical engineering; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.07099168818858985,"gpt":0.3082925873008592,"spread":0.2373008991122694,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006403725,0.0001035188,0.0002444406,0.0005426129,0.00009841331,0.00008943352,0.002723737,0.00003654877,0.00001065164],"category_scores_gemma":[0.0001239575,0.0000909655,0.00006427458,0.004041322,0.00003971432,0.0002642546,0.002481024,0.00007228331,0.00003574193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004891492,"about_ca_system_score_gemma":0.00004375719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005657685,"about_ca_topic_score_gemma":0.00001014074,"domain_scores_codex":[0.998628,0.00004641853,0.0002530291,0.0005426208,0.0002624542,0.0002674567],"domain_scores_gemma":[0.9974073,0.0002142316,0.0001180695,0.002168356,0.0000307972,0.00006120925],"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":[0.00001412823,0.0002160708,0.0206552,0.0001196199,0.002673572,0.0003041517,0.007163027,0.02546749,0.005324243,0.02318767,0.07048795,0.8443869],"study_design_scores_gemma":[0.0000707908,0.00002480059,0.01112958,0.00001568628,0.0000685769,0.000002668715,0.00006127136,0.9829391,0.0001205818,0.00009683856,0.005357162,0.0001129212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6940934,0.0002204629,0.302715,0.0009680074,0.0006345537,0.00007813032,0.0004438698,0.0005924657,0.000254075],"genre_scores_gemma":[0.9139639,0.0000192868,0.08502722,0.00009755926,0.00009317348,0.000001548486,0.0007131909,0.00001011554,0.00007398795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9574716,"threshold_uncertainty_score":0.5061426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410588018","doi":"10.1186/s13040-025-00451-y","title":"Correction: Learning the therapeutic targets of acute myeloid leukemia through multiscale human interactome network and community analysis","year":2025,"lang":"en","type":"erratum","venue":"BioData Mining","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Interactome; Myeloid leukemia; Computer science; Computational biology; Artificial intelligence; Data science; Medicine; Biology; Cancer research; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03957594418586434,"gpt":0.3386744091704122,"spread":0.2990984649845479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001805126,0.0003931219,0.0007679686,0.000290058,0.001301921,0.0003994897,0.002247225,0.0002549991,0.00002732972],"category_scores_gemma":[0.0002125047,0.0003245765,0.0002635915,0.001965067,0.0002370071,0.0006024941,0.002525976,0.002425366,0.000002642249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001689889,"about_ca_system_score_gemma":0.0003371575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006931936,"about_ca_topic_score_gemma":0.0002594298,"domain_scores_codex":[0.9956197,0.002356501,0.0006314234,0.000602728,0.0004247971,0.0003648396],"domain_scores_gemma":[0.994803,0.00294549,0.0006866435,0.001345108,0.0001683751,0.00005141281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007145512,0.0002082886,0.006300243,0.0003580178,0.01373333,0.00003021657,0.02892618,0.06431847,0.0001247189,0.002681537,0.7666482,0.1165993],"study_design_scores_gemma":[0.000409087,0.0002355899,0.0393497,0.0007581396,0.002242794,0.00002768707,0.001319197,0.761799,0.00006352577,0.001328611,0.1916581,0.0008085549],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005365666,0.006084919,0.9449604,0.0004849868,0.02707252,0.0004894061,0.0001723938,0.0002784693,0.01509131],"genre_scores_gemma":[0.491446,0.003650848,0.2832406,0.00283348,0.00445588,0.0002177499,0.01330518,0.0002237462,0.2006265],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6974806,"threshold_uncertainty_score":0.9999983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}