{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":65,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":65,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"8b096c79865a","filters":{"venue":"Bioinformatics Advances"}},"results":[{"id":"W4324045291","doi":"10.1093/bioadv/vbad030","title":"scAnnotate: an automated cell-type annotation tool for single-cell RNA-sequencing data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association; Genome British Columbia; Western Canada Research Grid; Compute Canada","keywords":"Annotation; Dropout (neural networks); Computer science; Artificial intelligence; Data mining; Computational biology; Machine learning; Biology","authors":[{"name":"Xiangling Ji","is_ca":true},{"name":"Danielle Tsao","is_ca":true},{"name":"Kailun Bai","is_ca":true},{"name":"Min Tsao","is_ca":true},{"name":"Li Xing","is_ca":true},{"name":"Xuekui Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04813062175676968,"gpt":0.3011984307456495,"spread":0.2530678089888798,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003400637,0.002040654,0.001337015,0.002245262,0.0009397334,0.001670138,0.003731194,0.001511318,0.008733037],"category_scores_gemma":[0.01100445,0.001022628,0.002062341,0.001499379,0.0008482298,0.002181752,0.002122577,0.001550197,0.004140528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009838481,"about_ca_system_score_gemma":0.001855157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003602521,"about_ca_topic_score_gemma":0.005941258,"domain_scores_codex":[0.9981053,0.0002843727,0.0001785291,0.0005754976,0.0007513388,0.0001049803],"domain_scores_gemma":[0.9949486,0.002747027,0.0004714935,0.0008374827,0.0007658826,0.0002294932],"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":[0.003693575,0.0004794372,0.03714185,0.004032816,0.001421098,0.002026865,0.001825595,0.09563646,0.1340853,0.009972158,0.2130277,0.4966572],"study_design_scores_gemma":[0.0002972528,0.0002193654,0.007063444,0.0001850815,0.0001569387,0.0006173449,0.0001969616,0.8203353,0.08733579,0.01075703,0.07256046,0.0002750108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01663311,0.0004122509,0.6966674,0.0002511601,0.0002089489,0.0002583163,0.0116966,0.2728042,0.001068005],"genre_scores_gemma":[0.1454065,0.0006321632,0.7678858,0.0006852947,0.0001098551,0.001635037,0.05560656,0.0235144,0.004524392],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.008733037,"threshold_uncertainty_score":0.02921492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4377047057","doi":"10.1093/bioadv/vbad059","title":"A self-knowledge distillation-driven CNN-LSTM model for predicting disease outcomes using longitudinal microbiome data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Gut microbiota and health","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":"Public Health Ontario; University of Toronto; Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Manitoba Medical Service Foundation","keywords":"Microbiome; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Inference; Machine learning; Data mining; Bioinformatics; Biology","authors":[{"name":"Daryl L. X. Fung","is_ca":true},{"name":"Xu Li","is_ca":true},{"name":"Carson K. Leung","is_ca":true},{"name":"Pingzhao Hu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06966997547000747,"gpt":0.3625614829663176,"spread":0.2928915074963101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000920728,0.001067779,0.0006155326,0.0004870672,0.0002266886,0.0004926865,0.001222538,0.0008505936,0.001700835],"category_scores_gemma":[0.001852243,0.0003590427,0.0006828412,0.0005271791,0.0002535559,0.0007337882,0.000668769,0.00147738,0.000616479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007783441,"about_ca_system_score_gemma":0.001325668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01632929,"about_ca_topic_score_gemma":0.01925622,"domain_scores_codex":[0.9998261,0.00003577297,0.00001177278,0.0000605243,0.00002595567,0.00003976217],"domain_scores_gemma":[0.9996173,0.0001863206,0.00004066033,0.00002860569,0.0001009637,0.00002617484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004530369,0.00031228,0.0132074,0.000156659,0.0002666005,0.0002093207,0.00007807723,0.7749876,0.00462091,0.002487436,0.00813315,0.1950876],"study_design_scores_gemma":[0.000006325848,0.00001863684,0.0003148321,0.000005909912,0.00001429122,0.00000813888,0.000002678737,0.9983999,0.0003889209,0.0006569748,0.0001795588,0.000003791224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3119004,0.005523939,0.6611302,0.003517664,0.0006801338,0.0001360051,0.005441878,0.006336471,0.005333259],"genre_scores_gemma":[0.9307638,0.0008957603,0.05628261,0.0006908376,0.0001742732,0.0001931939,0.004962567,0.00009173774,0.005945221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01632929,"threshold_uncertainty_score":0.0324685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400726464","doi":"10.1093/bioadv/vbae097","title":"Knowledge graph embeddings in the biomedical domain: are they useful? A look at link prediction, rule learning, and downstream polypharmacy tasks","year":2024,"lang":"en","type":"review","venue":"Bioinformatics Advances","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Engineering and Physical Sciences Research Council; UK Research and Innovation; Institute for Catastrophic Loss Reduction; Science and Technology Facilities Council; European Commission; Dell EMC; Accenture; Cisco Systems","keywords":"Computer science; Interpretability; Embedding; Machine learning; Artificial intelligence; Knowledge graph; Field (mathematics); Downstream (manufacturing); Graph; Data science; Theoretical computer science","authors":[{"name":"Aryo Pradipta Gema","is_ca":false},{"name":"Dominik Grabarczyk","is_ca":false},{"name":"W. Wulf","is_ca":false},{"name":"Piyush Borole","is_ca":false},{"name":"Javier A. Alfaro","is_ca":true},{"name":"Pasquale Minervini","is_ca":false},{"name":"Antonio Vergari","is_ca":false},{"name":"Ajitha Rajan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02197307786622078,"gpt":0.3223211017238577,"spread":0.3003480238576369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002895473,0.0008630966,0.0004769985,0.001170819,0.0004252832,0.001522708,0.001318018,0.001545793,0.005110261],"category_scores_gemma":[0.02289539,0.0003762984,0.0006591138,0.001321582,0.0008543758,0.004387149,0.001519656,0.002256882,0.001571539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009708271,"about_ca_system_score_gemma":0.00130276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005761968,"about_ca_topic_score_gemma":0.009630891,"domain_scores_codex":[0.9990282,0.000442938,0.00006511956,0.0001962682,0.0002104496,0.00005697009],"domain_scores_gemma":[0.9906669,0.006618336,0.0004519797,0.001232341,0.0007428924,0.0002874495],"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":[0.0008448013,0.0008804149,0.02204187,0.001370891,0.000202047,0.0007199949,0.0005147214,0.374067,0.004829827,0.0238044,0.05571169,0.5150124],"study_design_scores_gemma":[0.0001082693,0.0001855978,0.002039194,0.0002178972,0.00004857046,0.0002533343,0.0002003074,0.9251048,0.005915553,0.05048806,0.01540108,0.00003734511],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.3388295,0.009167101,0.5852919,0.01847987,0.0009908555,0.000658032,0.01047421,0.01962203,0.01648664],"genre_scores_gemma":[0.5050237,0.003715019,0.4677291,0.001506512,0.0001868204,0.0003505219,0.01653469,0.0009758081,0.003977823],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.005761968,"threshold_uncertainty_score":0.01709551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380867105","doi":"10.1093/bioadv/vbad072","title":"GDockScore: a graph-based protein–protein docking scoring function","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of New Brunswick","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Docking (animal); Computer science; Macromolecular docking; Graph; Protein–ligand docking; Artificial intelligence; Machine learning; Computational biology; Virtual screening; Theoretical computer science; Protein structure; Bioinformatics; Drug discovery; Biology; Biochemistry","authors":[{"name":"Matthew McFee","is_ca":true},{"name":"Philip M. Kim","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00998602961376684,"gpt":0.2305397237886313,"spread":0.2205536941748644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001141615,0.001945736,0.001372466,0.001035839,0.0006750459,0.001205106,0.003712493,0.001730812,0.0180219],"category_scores_gemma":[0.003941837,0.0005466195,0.001393736,0.001207625,0.0004523991,0.001231538,0.001872714,0.002051404,0.00797872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059742,"about_ca_system_score_gemma":0.00179621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006671816,"about_ca_topic_score_gemma":0.01048496,"domain_scores_codex":[0.9994167,0.0001595469,0.00002804966,0.0001229491,0.0002148702,0.000057941],"domain_scores_gemma":[0.9993969,0.0002289087,0.00004459828,0.0001157176,0.0001487757,0.00006507032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007000072,0.0004512964,0.006638595,0.00146778,0.0005959661,0.0002898292,0.0000876853,0.4170858,0.01235958,0.02779166,0.370189,0.1623428],"study_design_scores_gemma":[0.0001502095,0.0001286223,0.0008503451,0.00005251489,0.00004385997,0.00009656038,0.0000164257,0.958926,0.005246223,0.01639875,0.01802772,0.00006267588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0747885,0.002281837,0.7340847,0.001757537,0.0006987393,0.0006555878,0.05815373,0.1090957,0.01848375],"genre_scores_gemma":[0.3858513,0.001506863,0.451376,0.001184035,0.0001260606,0.001536606,0.1293502,0.0130341,0.01603487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0180219,"threshold_uncertainty_score":0.06028932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391244160","doi":"10.1093/bioadv/vbae010","title":"MMDRP: drug response prediction and biomarker discovery using multi-modal deep learning","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Ministry of Colleges and Universities","keywords":"Biomarker discovery; Modal; Drug discovery; Deep learning; Biomarker; Artificial intelligence; Computer science; Drug response; Machine learning; Drug; Computational biology; Medicine; Biology; Bioinformatics; Pharmacology; Proteomics; Chemistry","authors":[{"name":"Farzan Taj","is_ca":true},{"name":"Lincoln Stein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02440852627287932,"gpt":0.3178043947498375,"spread":0.2933958684769581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00216083,0.001171319,0.0009682585,0.0009631243,0.00043135,0.001219118,0.003094207,0.001745855,0.00568681],"category_scores_gemma":[0.005076543,0.0007358736,0.001204089,0.0009052443,0.0006189903,0.0013888,0.002376306,0.00270228,0.001895297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00143273,"about_ca_system_score_gemma":0.002592762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00627236,"about_ca_topic_score_gemma":0.007117576,"domain_scores_codex":[0.9993685,0.0001704096,0.00004003946,0.0001942154,0.0001613741,0.00006545023],"domain_scores_gemma":[0.9990442,0.0005128217,0.00009509763,0.0001232739,0.0001386738,0.00008597921],"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":[0.0009799522,0.0005888407,0.006421093,0.0008524355,0.0005069228,0.0004176818,0.00007496051,0.4325953,0.007239099,0.008673718,0.08435358,0.4572964],"study_design_scores_gemma":[0.00007801095,0.00006954655,0.0002934143,0.00002029525,0.00002448491,0.00006874942,0.000006057792,0.9853689,0.00341027,0.006600247,0.004046183,0.00001393797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03611347,0.002817919,0.8806986,0.005716927,0.0003353246,0.0005368738,0.009346946,0.05870959,0.005724442],"genre_scores_gemma":[0.3301085,0.001310722,0.6442678,0.003047827,0.0002597139,0.001164168,0.01160428,0.0009995985,0.007237447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00627236,"threshold_uncertainty_score":0.01902431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4288051411","doi":"10.1093/bioadv/vbac049","title":"More accurate estimation of cell composition in bulk expression through robust integration of single-cell information","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","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":"University of Ottawa; Health Canada","funders":"","keywords":"Covariance; Collinearity; Univariate; Computer science; Expression (computer science); RNA-Seq; Data mining; Analysis of covariance; Computational biology; Algorithm; Biological system; Gene expression; Mathematics; Gene; Multivariate statistics; Transcriptome; Biology; Statistics; Machine learning; Genetics","authors":[{"name":"Ali Karimnezhad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01643830154938968,"gpt":0.2404196319931348,"spread":0.2239813304437452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001943915,0.0008887338,0.001110425,0.001285655,0.0003382315,0.001142838,0.0009659256,0.0007192242,0.0009817675],"category_scores_gemma":[0.003818455,0.0003352456,0.0009792593,0.001397158,0.0005619185,0.001224709,0.0009678344,0.001412537,0.0009785052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006004267,"about_ca_system_score_gemma":0.001052782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003633265,"about_ca_topic_score_gemma":0.004489945,"domain_scores_codex":[0.9993165,0.0001078234,0.00003402896,0.0002996744,0.0001971887,0.00004484093],"domain_scores_gemma":[0.9984248,0.0006100856,0.0002197164,0.0002846711,0.0003945887,0.00006625392],"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":[0.0005764641,0.0002916857,0.04251423,0.0007677971,0.0002953281,0.0001790263,0.0004198123,0.181776,0.3351158,0.00677544,0.007913248,0.4233752],"study_design_scores_gemma":[0.00002561718,0.00007400794,0.01352002,0.00004726887,0.00006410451,0.0001218688,0.0001118023,0.9104332,0.0579706,0.01056539,0.006997712,0.00006832205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07429156,0.001130914,0.9193898,0.0001847717,0.00006309466,0.00005662477,0.001842972,0.002107662,0.0009326508],"genre_scores_gemma":[0.3534779,0.001260608,0.6319083,0.0003672006,0.0001079939,0.0002388878,0.009830318,0.000636172,0.002172543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003633265,"threshold_uncertainty_score":0.01028055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4323816133","doi":"10.1093/bioadv/vbad028","title":"Predicting phenotypes from novel genomic markers using deep learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Single-nucleotide polymorphism; Convolutional neural network; Biology; Computational biology; SNP; Pearson product-moment correlation coefficient; Genetics; Phenotype; DNA sequencing; Artificial intelligence; Genotype; Computer science; DNA; Statistics; Gene; Mathematics","authors":[{"name":"Shivani Sehrawat","is_ca":true},{"name":"Keyhan Najafian","is_ca":true},{"name":"Lingling Jin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01358583109972697,"gpt":0.240774630662151,"spread":0.2271887995624241,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000532596,0.0008368145,0.0004100376,0.0006123199,0.0001319801,0.000459185,0.0005101967,0.0004888792,0.001018171],"category_scores_gemma":[0.0009403693,0.0001721095,0.000491426,0.0005193902,0.0001980905,0.0003871756,0.0004542373,0.0007748614,0.0003082716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005013613,"about_ca_system_score_gemma":0.0004770347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004786521,"about_ca_topic_score_gemma":0.006207034,"domain_scores_codex":[0.9998382,0.00003404199,0.0000092616,0.00006313523,0.00003125364,0.00002402359],"domain_scores_gemma":[0.9994969,0.0002778687,0.00005740344,0.00003827728,0.0001023693,0.00002716586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002296969,0.0003513714,0.03473981,0.0001167039,0.0002158657,0.0001741463,0.00003656496,0.7547123,0.01918478,0.001181433,0.002264089,0.1867932],"study_design_scores_gemma":[0.000004305356,0.00001953439,0.002290075,0.000005594844,0.00001337861,0.00001137453,0.000003958431,0.9944102,0.002235333,0.0008227651,0.0001789479,0.000004600447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5847438,0.001119593,0.407235,0.0005244191,0.00008305607,0.00005405478,0.001935923,0.002156856,0.002147261],"genre_scores_gemma":[0.9600359,0.0001830846,0.03632152,0.0001243736,0.00001720092,0.0000430107,0.001783535,0.00003482694,0.001456574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004786521,"threshold_uncertainty_score":0.009517312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404509197","doi":"10.1093/bioadv/vbae166","title":"The ISCB competency framework v. 3: a revised and extended standard for bioinformatics education and training","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Common Fund; National Human Genome Research Institute; UK Research and Innovation; European Commission; Government of Ontario; European Molecular Biology Laboratory; National Institutes of Health; Ontario Institute for Cancer Research","keywords":"Computer science; Bioinformatics; Computational biology; Biology","authors":[{"name":"Cath Brooksbank","is_ca":false},{"name":"Michelle D. Brazas","is_ca":true},{"name":"Nicola Mulder","is_ca":false},{"name":"Russell Schwartz","is_ca":false},{"name":"Verena Ras","is_ca":false},{"name":"Sarah Morgan","is_ca":false},{"name":"Marta Lloret-Llinares","is_ca":false},{"name":"Patricia Carvajal-López","is_ca":false},{"name":"Lee Larcombe","is_ca":false},{"name":"Amel Ghouila","is_ca":false},{"name":"Tom Hancocks","is_ca":false},{"name":"Venkata Satagopam","is_ca":false},{"name":"Javier De Las Rivas","is_ca":false},{"name":"Gaston K. Mazandu","is_ca":false},{"name":"Bruno Gaëta","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.015503383659866,"gpt":0.3227780611302261,"spread":0.3072746774703601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05426238,0.001297927,0.001397897,0.007762475,0.003495394,0.008857183,0.005230506,0.004944379,0.01268198],"category_scores_gemma":[0.1341381,0.001253751,0.002710307,0.006022143,0.004164551,0.006671175,0.008783949,0.007551425,0.01410048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01338761,"about_ca_system_score_gemma":0.07683695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04055117,"about_ca_topic_score_gemma":0.0437572,"domain_scores_codex":[0.9460854,0.02290525,0.006991913,0.002041048,0.01796886,0.004007513],"domain_scores_gemma":[0.8931125,0.03530245,0.005166961,0.006351893,0.0516577,0.008408382],"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":[0.0001736252,0.0006954541,0.007408202,0.003462703,0.00006219243,0.000311888,0.009261735,0.004113421,0.002849838,0.1960829,0.3927091,0.3828689],"study_design_scores_gemma":[0.00007480198,0.0001614754,0.009412096,0.006805873,0.0000370773,0.0005600265,0.002516015,0.002692211,0.002076054,0.05155806,0.9238946,0.0002117255],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01887384,0.004409798,0.5751832,0.05335769,0.00422166,0.01680736,0.01504838,0.01188675,0.3002113],"genre_scores_gemma":[0.05376933,0.00371747,0.835743,0.01115569,0.0003996954,0.01758732,0.02928435,0.002942223,0.0454009],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05426238,"threshold_uncertainty_score":0.2869704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405910570","doi":"10.1093/bioadv/vbae184","title":"Predicting CRISPR-Cas9 off-target effects in human primary cells using bidirectional LSTM with BERT embedding","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada; McGill University","funders":"National Research Council Canada","keywords":"CRISPR; Embedding; Primary (astronomy); Computer science; Computational biology; Biology; Artificial intelligence; Genetics; Gene; Physics","authors":[{"name":"Orhan Sari","is_ca":true},{"name":"Ziying Liu","is_ca":true},{"name":"Youlian Pan","is_ca":true},{"name":"Xiaojian Shao","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004768933118316525,"gpt":0.2879238221660577,"spread":0.2831548890477412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002743312,0.0005434441,0.0003798454,0.0001842133,0.000111564,0.0003642576,0.0003908041,0.0005954269,0.001608564],"category_scores_gemma":[0.0006896622,0.0001822717,0.0004000503,0.0002095526,0.0001429012,0.0002249929,0.0003041945,0.0005976264,0.0007470228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000551421,"about_ca_system_score_gemma":0.0005031612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005844672,"about_ca_topic_score_gemma":0.008363593,"domain_scores_codex":[0.9998978,0.00001738732,0.000005742496,0.00003530752,0.00002399495,0.00001978153],"domain_scores_gemma":[0.9998711,0.00006291822,0.0000117249,0.00001246831,0.00003134759,0.00001038179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005698156,0.0001919521,0.006403488,0.000304934,0.0001152403,0.0003798241,0.00006856099,0.6439549,0.1508508,0.001624597,0.008939242,0.1865967],"study_design_scores_gemma":[0.000006996403,0.00005500983,0.0007002869,0.000006635746,0.00001067249,0.00003441022,0.00001046529,0.9603297,0.03744112,0.0007364281,0.0006582135,0.00001004138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5225441,0.003058367,0.4490979,0.0009815026,0.0002551504,0.0001086344,0.006874354,0.01106845,0.006011527],"genre_scores_gemma":[0.9472758,0.0005791791,0.04430568,0.0002238899,0.00001658814,0.0001011386,0.003134378,0.0001288357,0.004234552],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005844672,"threshold_uncertainty_score":0.0116213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408714891","doi":"10.1093/bioadv/vbaf044","title":"Biological databases in the age of generative artificial intelligence","year":2024,"lang":"en","type":"editorial","venue":"Bioinformatics Advances","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Montreal Clinical Research Institute","funders":"H2020 European Research Council","keywords":"Stewardship (theology); Computer science; Data science; Generative grammar; Biological data; Database; Artificial intelligence; Political science","authors":[{"name":"Mihai Pop","is_ca":false},{"name":"Teresa K. Attwood","is_ca":false},{"name":"Judith A. Blake","is_ca":false},{"name":"Philip E. Bourne","is_ca":false},{"name":"Ana Conesa","is_ca":false},{"name":"Terry Gaasterland","is_ca":false},{"name":"Lawrence Hunter","is_ca":false},{"name":"Carl Kingsford","is_ca":false},{"name":"Oliver Kohlbacher","is_ca":false},{"name":"Thomas Lengauer","is_ca":false},{"name":"Scott Markel","is_ca":false},{"name":"Yves Moreau","is_ca":false},{"name":"William Stafford Noble","is_ca":false},{"name":"Christine Orengo","is_ca":false},{"name":"B. F. Francis Ouellette","is_ca":true},{"name":"Laxmi Parida","is_ca":false},{"name":"Nataša Pržulj","is_ca":false},{"name":"Teresa M. Przytycka","is_ca":false},{"name":"Shoba Ranganathan","is_ca":false},{"name":"Russell Schwartz","is_ca":false},{"name":"Alfonso Valencia","is_ca":false},{"name":"Tandy Warnow","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2320234359275722,"gpt":0.440254693494518,"spread":0.2082312575669458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01220698,0.00168908,0.001749706,0.003918005,0.002718979,0.01199041,0.003839566,0.01041589,0.01046745],"category_scores_gemma":[0.05581266,0.0009099577,0.001532039,0.00223593,0.004993423,0.00758166,0.002286339,0.02322469,0.008561528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004072995,"about_ca_system_score_gemma":0.003546436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002313116,"about_ca_topic_score_gemma":0.004182947,"domain_scores_codex":[0.9925393,0.001473177,0.0008945845,0.000745534,0.004128772,0.0002185279],"domain_scores_gemma":[0.9227352,0.04797946,0.001925375,0.002296005,0.02132694,0.003736929],"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":[0.00001327119,0.000004718774,0.00001728825,0.0001952544,0.000009473604,0.00006237857,0.00003655956,0.00004518729,0.00003250686,0.002974429,0.9885479,0.008061],"study_design_scores_gemma":[0.00001234866,0.000005376426,0.00004812546,0.0003521336,0.00001201951,0.0001008515,0.00003114666,0.0001408481,0.00004968345,0.005460049,0.9937776,0.000009892061],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.00004870569,0.01414856,0.001257187,0.1344664,0.8470035,0.00002022154,0.00009399097,0.0001430673,0.002818412],"genre_scores_gemma":[0.001024956,0.01323812,0.0008393666,0.03152535,0.9447349,0.00003229181,0.00006700795,0.0001261598,0.008411869],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.01220698,"threshold_uncertainty_score":0.06455743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201257126","doi":"10.1093/bioadv/vbab021","title":"CRIS: complete reconstruction of immunoglobulin <i>V-D-J</i> sequences from RNA-seq data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Chronic Lymphocytic Leukemia Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Terry Fox Research Institute; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Cancer Institute; National Human Genome Research Institute; Canadian Institutes of Health Research","keywords":"RNA-Seq; Computational biology; Antibody; Biology; Genetics; Gene; Transcriptome; Gene expression","authors":[{"name":"Rashedul Islam","is_ca":true},{"name":"Misha Bilenky","is_ca":true},{"name":"Andrew P. Weng","is_ca":true},{"name":"Joseph M. Connors","is_ca":false},{"name":"Martin Hirst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06140797670486976,"gpt":0.3298371960912405,"spread":0.2684292193863708,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002654186,0.001566924,0.0009262268,0.00171118,0.001019113,0.001802534,0.001318952,0.0008360876,0.008799198],"category_scores_gemma":[0.004982423,0.0008489799,0.001622543,0.001367025,0.000637539,0.0006786304,0.001382864,0.001816901,0.006654984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007570364,"about_ca_system_score_gemma":0.00233057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003851274,"about_ca_topic_score_gemma":0.00837692,"domain_scores_codex":[0.9989322,0.0001632189,0.00007124204,0.0004787444,0.0002528367,0.0001018242],"domain_scores_gemma":[0.9983521,0.0007476914,0.0002097587,0.0002700549,0.0002931067,0.0001274137],"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":[0.003291176,0.0003903222,0.03727564,0.006620242,0.002056088,0.001526267,0.001582268,0.06833608,0.3813102,0.01234677,0.3258109,0.159454],"study_design_scores_gemma":[0.0008173066,0.000679709,0.06122572,0.0006861822,0.000839385,0.001388347,0.0009572487,0.3239836,0.2142834,0.02644174,0.3681389,0.0005584211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1048068,0.001743467,0.2635551,0.0009765985,0.0005467453,0.0008241833,0.4966648,0.1219938,0.008888498],"genre_scores_gemma":[0.137736,0.0005257324,0.3117578,0.000683657,0.0001183469,0.001004891,0.5357265,0.00955023,0.002896754],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008799198,"threshold_uncertainty_score":0.02943623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4281294657","doi":"10.1093/bioadv/vbac038","title":"HPiP: an R/Bioconductor package for predicting host–pathogen protein–protein interactions from protein sequences using ensemble machine learning approach","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bioconductor; Computational biology; Host (biology); Computer science; Machine learning; Biology; Artificial intelligence; Bioinformatics; Genetics; Gene","authors":[{"name":"Matineh Rahmatbakhsh","is_ca":true},{"name":"Mohamed Taha Moutaoufik","is_ca":true},{"name":"Alla Gagarinova","is_ca":true},{"name":"Mohan Babu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02130643004791029,"gpt":0.2605602040231485,"spread":0.2392537739752382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006751296,0.006319617,0.004742845,0.004103277,0.001013266,0.003201097,0.007877031,0.00206431,0.06751598],"category_scores_gemma":[0.01889426,0.002553332,0.003208584,0.004191857,0.001467622,0.003089604,0.004584645,0.005752142,0.07267103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001358292,"about_ca_system_score_gemma":0.004958086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004505225,"about_ca_topic_score_gemma":0.004328412,"domain_scores_codex":[0.9965578,0.0009578752,0.0003180977,0.0009349127,0.0009253668,0.0003059752],"domain_scores_gemma":[0.990838,0.004656652,0.00101448,0.001208003,0.00176292,0.0005199584],"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":[0.001380052,0.0002068137,0.003356125,0.0077783,0.002166166,0.000673559,0.0003990186,0.01292669,0.007079184,0.01247819,0.8788764,0.07267949],"study_design_scores_gemma":[0.001634912,0.0005747308,0.01036451,0.00226816,0.001611182,0.001388386,0.000301367,0.3138036,0.03109899,0.07040036,0.5659431,0.0006106934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004633309,0.002383856,0.3169932,0.001144543,0.001082474,0.0007283534,0.09295665,0.5744668,0.005610931],"genre_scores_gemma":[0.04741552,0.003003228,0.5731032,0.002170511,0.0004443779,0.00719675,0.1615308,0.1929571,0.01217845],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.06751598,"threshold_uncertainty_score":0.2258634,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210673729","doi":"10.1093/bioadv/vbab044","title":"From pairwise to multiple spliced alignment","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"RNA Research and Splicing","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 de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Pairwise comparison; RNA splicing; Gene; Computer science; Computational biology; Alignment-free sequence analysis; Gene family; Gene Annotation; Heuristic; Context (archaeology); Annotation; Gene prediction; Genome; Genetics; Biology; Sequence alignment; Artificial intelligence; RNA; Peptide sequence","authors":[{"name":"Safa Jammali","is_ca":true},{"name":"Abigaïl Djossou","is_ca":true},{"name":"Wend-Yam D D Ouédraogo","is_ca":true},{"name":"Yannis Nevers","is_ca":false},{"name":"Ibrahim Chegrane","is_ca":true},{"name":"Aïda Ouangraoua","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01044655336417397,"gpt":0.2654293748247018,"spread":0.2549828214605278,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003186053,0.002332221,0.001573808,0.003041289,0.001315271,0.002488064,0.003500081,0.00194556,0.01479196],"category_scores_gemma":[0.01526651,0.001135407,0.001852799,0.005501601,0.001575696,0.005667357,0.00524468,0.003609798,0.01194178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027853,"about_ca_system_score_gemma":0.00169858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009432979,"about_ca_topic_score_gemma":0.001602993,"domain_scores_codex":[0.9949514,0.001699024,0.000509337,0.001424713,0.001230632,0.000184972],"domain_scores_gemma":[0.9943996,0.002302676,0.0005485609,0.001405038,0.001106201,0.0002377986],"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":[0.000374727,0.0001787807,0.003001233,0.002221612,0.0002595717,0.0006265247,0.00057197,0.07331861,0.0143904,0.1902388,0.06264161,0.6521761],"study_design_scores_gemma":[0.0000715041,0.0001265445,0.0006194878,0.000250336,0.00006068995,0.000906173,0.0002188018,0.2781536,0.01442354,0.6314972,0.07359052,0.00008165449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002797267,0.0006070846,0.9872652,0.0003641861,0.0002147884,0.0001059995,0.001138381,0.005078015,0.002429042],"genre_scores_gemma":[0.02878523,0.0004757555,0.9637349,0.0002000175,0.0001737317,0.0002239101,0.003299015,0.001918599,0.001188827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01479196,"threshold_uncertainty_score":0.04948407,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401200522","doi":"10.1093/bioadv/vbae108","title":"Investigating alignment-free machine learning methods for HIV-1 subtype classification","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Canada Research Chairs","keywords":"Human immunodeficiency virus (HIV); Computer science; Artificial intelligence; Machine learning; Virology; Computational biology; Medicine; Biology","authors":[{"name":"Kaitlyn E Wade","is_ca":true},{"name":"Lianghong Chen","is_ca":true},{"name":"Chutong Deng","is_ca":true},{"name":"Gen Zhou","is_ca":true},{"name":"Pingzhao Hu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03916500014261359,"gpt":0.355114292073487,"spread":0.3159492919308735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00336022,0.001104507,0.0008435746,0.001280412,0.0005940628,0.0009599759,0.001401212,0.001164922,0.003024326],"category_scores_gemma":[0.008936033,0.0002706061,0.0007775089,0.001545884,0.0003115548,0.001956793,0.0007874288,0.001809457,0.001851667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006939724,"about_ca_system_score_gemma":0.001316748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005052104,"about_ca_topic_score_gemma":0.004642503,"domain_scores_codex":[0.9983599,0.0007051565,0.0001257564,0.0003356621,0.0003402267,0.0001332942],"domain_scores_gemma":[0.995796,0.00248242,0.0002305107,0.0004310427,0.0009319414,0.0001280856],"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":[0.0006407876,0.0005192994,0.0138916,0.0004080459,0.0002870484,0.0001051284,0.0001523479,0.1881226,0.003921225,0.005463066,0.01896689,0.7675221],"study_design_scores_gemma":[0.00003391672,0.0001034154,0.0009669155,0.00003700069,0.00002436011,0.00003765983,0.00005083812,0.9890066,0.00170423,0.006366316,0.001658233,0.00001045198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2404646,0.01259392,0.7230846,0.003769597,0.001112401,0.0004649046,0.002408758,0.007580484,0.008520785],"genre_scores_gemma":[0.5899628,0.001938963,0.3925028,0.001224923,0.0004750338,0.000381836,0.007585577,0.0004940524,0.005434072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005052104,"threshold_uncertainty_score":0.01777077,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387731260","doi":"10.1093/bioadv/vbad150","title":"Single-cell gene set scoring with nearest neighbor graph smoothed data (gssnng)","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of California, San Francisco; Cancer Research UK; McGill University","keywords":"Smoothing; Computer science; Visualization; Data mining; Graph; Significance analysis of microarrays; Python (programming language); Data visualization; Software; Sample size determination; Gene expression profiling; Computational biology; Gene expression; Gene; Theoretical computer science; Mathematics; Genetics; Biology; Statistics","authors":[{"name":"David L. Gibbs","is_ca":false},{"name":"Michael Strasser","is_ca":false},{"name":"Sui Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04017187588871809,"gpt":0.2551354453461746,"spread":0.2149635694574565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001704648,0.0009055354,0.00110375,0.001898375,0.0006990896,0.00141548,0.001521293,0.0007458712,0.02061485],"category_scores_gemma":[0.006668814,0.0004789479,0.001132019,0.002514898,0.000490424,0.0009123267,0.001374836,0.001436621,0.009150783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006270853,"about_ca_system_score_gemma":0.001115454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003936604,"about_ca_topic_score_gemma":0.007176939,"domain_scores_codex":[0.9987593,0.0001687445,0.00007714523,0.0003836182,0.0005344359,0.00007675445],"domain_scores_gemma":[0.9982216,0.0005346331,0.0001711412,0.0006289969,0.0003613252,0.00008234601],"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":[0.001125019,0.0002699261,0.02594977,0.002510712,0.0007457929,0.0004870938,0.001088758,0.0594249,0.08039721,0.02717447,0.3120746,0.4887516],"study_design_scores_gemma":[0.0001834012,0.0002477799,0.02825684,0.000157211,0.0001866075,0.0005636909,0.0003392203,0.6083136,0.1132848,0.06156058,0.186535,0.0003713068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.061309,0.000474567,0.7238144,0.0003547363,0.0005019521,0.0003311413,0.06464841,0.1422673,0.006298517],"genre_scores_gemma":[0.1618671,0.0003373275,0.7223117,0.0002165403,0.00007954859,0.001062075,0.08948225,0.01815032,0.006493183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02061485,"threshold_uncertainty_score":0.06896359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411436820","doi":"10.1093/bioadv/vbaf140","title":"Prediction of the infecting organism in peritoneal dialysis patients with acute peritonitis using interpretable Tsetlin Machines","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Dialysis and Renal Disease Management","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Infection and Immunity","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Peritoneal dialysis; Peritonitis; Organism; Medicine; Dialysis; Intensive care medicine; Computational biology; Internal medicine; Biology; Genetics","authors":[{"name":"Olga Tarasyuk","is_ca":false},{"name":"Anatoliy Gorbenko","is_ca":false},{"name":"Matthias Eberl","is_ca":true},{"name":"Nicholas Topley","is_ca":true},{"name":"Jingjing Zhang","is_ca":true},{"name":"Rishad Shafik","is_ca":false},{"name":"Alex Yakovlev","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007110007031997439,"gpt":0.2391215279493388,"spread":0.2320115209173414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001325222,0.00067783,0.0003720708,0.001545157,0.0001991398,0.001200955,0.0004653623,0.0007311385,0.002028626],"category_scores_gemma":[0.008083405,0.0001536076,0.0004702834,0.0007698979,0.0003931968,0.0006231195,0.000703795,0.0006979496,0.0005802543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000497226,"about_ca_system_score_gemma":0.000544973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001246846,"about_ca_topic_score_gemma":0.001303958,"domain_scores_codex":[0.9994824,0.0002077705,0.00006193392,0.000123325,0.00008075318,0.00004376399],"domain_scores_gemma":[0.9968837,0.002170953,0.0004048272,0.0001610507,0.0002657839,0.0001135278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001952489,0.0003852321,0.3261933,0.0005976891,0.0002593544,0.001310216,0.0004501471,0.3831198,0.009290096,0.005578571,0.02181752,0.2490456],"study_design_scores_gemma":[0.00003416949,0.0001368432,0.01356484,0.00007502524,0.00003780905,0.0003658773,0.0001148508,0.9653446,0.005507224,0.01156044,0.003228013,0.00003027324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7140981,0.001973081,0.2647927,0.002972755,0.0003369181,0.0002277229,0.007913418,0.003581024,0.004104294],"genre_scores_gemma":[0.9473579,0.0003015837,0.04748429,0.0002296401,0.00008511681,0.00009159759,0.003810488,0.0000552396,0.0005840956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.002028626,"threshold_uncertainty_score":0.007008493,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388928478","doi":"10.1093/bioadv/vbad166","title":"Adversarial training improves model interpretability in single-cell RNA-seq analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","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":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University Health Network; University of Toronto; Sinai Health System; University of Waterloo","funders":"","keywords":"Interpretability; Robustness (evolution); Machine learning; Computer science; Artificial intelligence; Classifier (UML); Data mining; Biology; Gene","authors":[{"name":"Mehrshad Sadria","is_ca":true},{"name":"Anita T. Layton","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02329046184857348,"gpt":0.2499431431405594,"spread":0.2266526812919859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007594518,0.001765064,0.001077563,0.0008227328,0.0007272533,0.00185777,0.001708047,0.001638933,0.003742182],"category_scores_gemma":[0.02562204,0.0006094853,0.001638022,0.0005067999,0.002152226,0.002133806,0.002121814,0.003851682,0.001432575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642873,"about_ca_system_score_gemma":0.001753934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005785941,"about_ca_topic_score_gemma":0.00595714,"domain_scores_codex":[0.9981647,0.0008567994,0.00009107392,0.0004904,0.0002620672,0.0001351001],"domain_scores_gemma":[0.9859439,0.01121852,0.0004792253,0.001466603,0.0005544196,0.0003373639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005723744,0.0001152681,0.007758822,0.000319564,0.0002054945,0.0002221519,0.0002043125,0.920059,0.01213115,0.006642899,0.009621131,0.04214784],"study_design_scores_gemma":[0.00001441274,0.00003106429,0.0005758715,0.00002766064,0.00001487074,0.00002366639,0.00001838639,0.9842095,0.003980874,0.01032033,0.0007680986,0.0000151949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2109013,0.001966981,0.7518146,0.004741183,0.0006101856,0.0001577318,0.003916095,0.0196945,0.006197461],"genre_scores_gemma":[0.7915248,0.0005879335,0.191877,0.002058506,0.0001646523,0.0001919356,0.007098487,0.003042121,0.003454645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007594518,"threshold_uncertainty_score":0.04016411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416098230","doi":"10.1093/bioadv/vbaf287","title":"ntRoot: computational inference of human ancestry at scale from genomic data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research","keywords":"Inference; Scale (ratio); Genomics; Big data; Genetic data; Computational model","authors":[{"name":"René L. Warren","is_ca":true},{"name":"Lauren Coombe","is_ca":true},{"name":"Johnathan Wong","is_ca":true},{"name":"Parham Kazemi","is_ca":true},{"name":"İnanç Birol","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03687343643295704,"gpt":0.3371535968671262,"spread":0.3002801604341692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00389218,0.001270411,0.001532765,0.001973413,0.001054351,0.002489845,0.002796586,0.00125177,0.01611913],"category_scores_gemma":[0.02649202,0.001070075,0.001821867,0.002267493,0.001006447,0.002112293,0.003208457,0.001981931,0.006823548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009336567,"about_ca_system_score_gemma":0.001947847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007481275,"about_ca_topic_score_gemma":0.01558463,"domain_scores_codex":[0.9983276,0.0005693478,0.00009580488,0.0005353505,0.0004017382,0.00007016458],"domain_scores_gemma":[0.9938487,0.004246867,0.00031865,0.001005681,0.0003642534,0.0002158834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002201695,0.0002424762,0.03812981,0.002556392,0.002157713,0.001477766,0.001520816,0.3783853,0.01739988,0.05403427,0.1909368,0.3109571],"study_design_scores_gemma":[0.0002935062,0.00005884377,0.002726693,0.000150402,0.0001529841,0.0003607238,0.0001382218,0.899912,0.003911083,0.06640628,0.02581201,0.00007719776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02825265,0.0008645536,0.8795162,0.001095383,0.0003300411,0.0002004093,0.03098816,0.05424539,0.004507287],"genre_scores_gemma":[0.1473089,0.0006544394,0.7852114,0.0007804244,0.0002492692,0.0006374892,0.0508207,0.009894628,0.004442687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01611913,"threshold_uncertainty_score":0.05392385,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391463569","doi":"10.1093/bioadv/vbae016","title":"HiTaxon: a hierarchical ensemble framework for taxonomic classification of short reads","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ministry of Agriculture, Food and Rural Affairs; University of Toronto; Compute Canada; Canada Foundation for Innovation; Ontario Ministry of Agriculture, Food and Rural Affairs; Government of Ontario","keywords":"Metagenomics; Biological classification; Computer science; Taxonomy (biology); Taxonomic rank; Microbiome; Key (lock); Artificial intelligence; Taxon; Data mining; Machine learning; Biology; Bioinformatics; Evolutionary biology; Ecology; Genetics","authors":[{"name":"Bhavish Verma","is_ca":true},{"name":"John Parkinson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02636127204626749,"gpt":0.2936164668138977,"spread":0.2672551947676303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003612215,0.001224294,0.001227741,0.002175285,0.001077015,0.001822117,0.002465397,0.001047555,0.003507971],"category_scores_gemma":[0.007924109,0.0005922991,0.001433382,0.001900719,0.0003980615,0.002353329,0.002306624,0.00189313,0.001940784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008909837,"about_ca_system_score_gemma":0.001650782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01090243,"about_ca_topic_score_gemma":0.0199101,"domain_scores_codex":[0.9984371,0.0004212247,0.00009281177,0.0004062571,0.0005151764,0.0001274317],"domain_scores_gemma":[0.9980583,0.0007331216,0.0001325484,0.0003204748,0.0005935733,0.0001620536],"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":[0.0007987773,0.0002925016,0.01267719,0.0005466886,0.0009962793,0.0003022982,0.0006801671,0.2315353,0.01369596,0.01354803,0.03747499,0.6874518],"study_design_scores_gemma":[0.00002643437,0.0001122389,0.001807992,0.00005399456,0.00008946095,0.00008038287,0.00007174172,0.9624233,0.003188485,0.02303291,0.009069691,0.00004336641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009856259,0.0005440034,0.97297,0.0001711872,0.00009950044,0.000148397,0.002736465,0.01243416,0.001039973],"genre_scores_gemma":[0.1361879,0.0005438092,0.8359277,0.0003918887,0.0002008779,0.0006111762,0.02162432,0.001468991,0.003043415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01090243,"threshold_uncertainty_score":0.02167797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417501327","doi":"10.1093/bioadv/vbaf301","title":"Perspectives in computational mass spectrometry: recent developments and key challenges","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Chan Zuckerberg Initiative; Wellcome Trust; Wellcome","keywords":"Grand Challenges; Key (lock); Field (mathematics); Cornerstone; Computational model","authors":[{"name":"Timo Sachsenberg","is_ca":false},{"name":"Lindsay K. Pino","is_ca":false},{"name":"Marie A. Brunet","is_ca":true},{"name":"Isabell Bludau","is_ca":false},{"name":"Oliver Kohlbacher","is_ca":false},{"name":"Juan Antonio Vizcaíno","is_ca":false},{"name":"Wout Bittremieux","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02159284074302592,"gpt":0.2865238643842546,"spread":0.2649310236412287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02842241,0.001358037,0.001767836,0.002319123,0.001364782,0.007683088,0.003949089,0.006464001,0.005189551],"category_scores_gemma":[0.03284678,0.0007555176,0.001688038,0.003387685,0.007666285,0.01617402,0.005293545,0.01367406,0.001829206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00247997,"about_ca_system_score_gemma":0.004505331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001859618,"about_ca_topic_score_gemma":0.001707918,"domain_scores_codex":[0.9933161,0.003640568,0.0004050706,0.0007376272,0.001592082,0.0003085229],"domain_scores_gemma":[0.9307951,0.05647907,0.0009676792,0.002523022,0.00688991,0.00234516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002269674,0.0002025959,0.001768751,0.005385989,0.0002715334,0.0002850374,0.0005981519,0.01130636,0.0007588398,0.4614202,0.1192364,0.3985393],"study_design_scores_gemma":[0.00007666787,0.0001526292,0.0008713884,0.003853383,0.00006074728,0.0006487043,0.0008877157,0.01852554,0.00063977,0.5438932,0.4302601,0.000130234],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001648539,0.6597819,0.06125617,0.2647212,0.006132471,0.00004181671,0.000193589,0.0003026713,0.005921568],"genre_scores_gemma":[0.02692788,0.8313617,0.08568402,0.02575717,0.02748744,0.0001988364,0.0004461739,0.0002546609,0.001882182],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.02842241,"threshold_uncertainty_score":0.1503139,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384397972","doi":"10.1093/bioadv/vbad091","title":"Measuring the relative contribution to predictive power of modern nucleotide substitution modeling approaches","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Substitution (logic); Predictive power; Model selection; Inference; Statistical model; Set (abstract data type); Computer science; Mixture model; Bayesian probability; Nucleotide; Probabilistic logic; Phylogenetic tree; Bayesian inference; Range (aeronautics); Selection (genetic algorithm); Computational biology; Econometrics; Mathematics; Artificial intelligence; Biology; Genetics; Engineering; Physics","authors":[{"name":"Thomas Bujaki","is_ca":true},{"name":"Katharine Van Looyen","is_ca":true},{"name":"Nicolas Rodrigue","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03347243952663514,"gpt":0.2359122800225138,"spread":0.2024398404958787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07561967,0.001863949,0.001703117,0.006283282,0.001072996,0.003977268,0.002001483,0.002870263,0.00107349],"category_scores_gemma":[0.1638394,0.001014518,0.001634933,0.003597273,0.002651523,0.007061936,0.004511448,0.00354637,0.0003986782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023266,"about_ca_system_score_gemma":0.001175758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002899837,"about_ca_topic_score_gemma":0.002792161,"domain_scores_codex":[0.968388,0.02030847,0.001434043,0.002590375,0.006634798,0.0006443023],"domain_scores_gemma":[0.8244265,0.1520184,0.004559124,0.01421413,0.003629679,0.001152233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008940798,0.0003251935,0.0782557,0.0003811295,0.001812282,0.0001935369,0.0006657401,0.7716626,0.007346649,0.02099749,0.0007071843,0.1167584],"study_design_scores_gemma":[0.00002428233,0.0002333934,0.01216994,0.00008563233,0.0001889569,0.0001867634,0.00008811573,0.9608293,0.003024375,0.02250418,0.0005723292,0.00009285432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4326097,0.002857574,0.5574609,0.001325851,0.00008844532,0.0001095689,0.0004109982,0.001007614,0.004129196],"genre_scores_gemma":[0.9109496,0.0007021092,0.08672384,0.0001788379,0.00009367681,0.0000885047,0.0007308124,0.0002064873,0.0003261221],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07561967,"threshold_uncertainty_score":0.3999198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402914764","doi":"10.1093/bioadv/vbae146","title":"Chronogram: an R package for data curation and analysis of infection and vaccination cohort studies","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Infection and Immunity","funders":"Medical Research Council; Francis Crick Institute; Cancer Research UK; Wellcome Trust; London School of Hygiene and Tropical Medicine","keywords":"Cohort; Vaccination; R package; Cohort study; Data curation; Biology; Data science; Environmental health; Computational biology; Medicine; Virology; Computer science; Internal medicine","authors":[{"name":"David Greenwood","is_ca":false},{"name":"Marianne Shawe‐Taylor","is_ca":false},{"name":"Hermaleigh Townsley","is_ca":false},{"name":"Joshua Gahir","is_ca":false},{"name":"Nikita Sahadeo","is_ca":false},{"name":"Yakubu Alhassan","is_ca":false},{"name":"Charlotte Chaloner","is_ca":false},{"name":"Oliver Galgut","is_ca":false},{"name":"Gavin Kelly","is_ca":false},{"name":"David L.V. Bauer","is_ca":false},{"name":"Emma Wall","is_ca":true},{"name":"Mary Wu","is_ca":false},{"name":"Edward J Carr","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03960482596782377,"gpt":0.3467256947207792,"spread":0.3071208687529554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0148731,0.002784797,0.002908408,0.005889757,0.0008842655,0.004284471,0.003532998,0.001109299,0.1055726],"category_scores_gemma":[0.08603369,0.002294684,0.003942277,0.006696691,0.001080969,0.002839045,0.003913156,0.003177947,0.05181833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009935858,"about_ca_system_score_gemma":0.007320491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005311936,"about_ca_topic_score_gemma":0.008494134,"domain_scores_codex":[0.9926565,0.003239366,0.0009684504,0.001858243,0.0009916855,0.0002857314],"domain_scores_gemma":[0.9464774,0.03701696,0.003718967,0.007759396,0.003870139,0.001157163],"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":[0.001000866,0.00004624992,0.007293614,0.007365088,0.002352263,0.0003885599,0.000440199,0.004031384,0.001726645,0.009263721,0.9078072,0.0582841],"study_design_scores_gemma":[0.001208291,0.0001431001,0.01093796,0.001827706,0.001426518,0.0008141098,0.0001927838,0.01777668,0.004511944,0.05467481,0.906176,0.0003100503],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.002235344,0.001515847,0.2729053,0.00147814,0.0008089153,0.001128594,0.5224113,0.1924047,0.005111836],"genre_scores_gemma":[0.03341392,0.002293463,0.4366195,0.002167432,0.0006289349,0.01010808,0.3572281,0.1498281,0.007712427],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1055726,"threshold_uncertainty_score":0.3531756,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201645418","doi":"10.1093/bioadv/vbab018","title":"Balanced Functional Module Detection in genomic data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Outcome (game theory); Property (philosophy); Computer science; Set (abstract data type); Consistency (knowledge bases); Variable (mathematics); Feature selection; Data mining; Artificial intelligence; Theoretical computer science; Machine learning; Mathematics","authors":[{"name":"David Tritchler","is_ca":true},{"name":"Lorin M. Towle-Miller","is_ca":false},{"name":"Jeffrey C. Miecznikowski","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01469638284561246,"gpt":0.2381064015665066,"spread":0.2234100187208941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00287147,0.0006925195,0.0006533646,0.00250713,0.000413815,0.0009664973,0.001168138,0.0006772401,0.001077227],"category_scores_gemma":[0.01348576,0.0002822829,0.0007536644,0.001834965,0.0007326192,0.001157125,0.001200623,0.0006628048,0.0002831568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007161457,"about_ca_system_score_gemma":0.0007242648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001539884,"about_ca_topic_score_gemma":0.001382547,"domain_scores_codex":[0.998696,0.0005385125,0.000074128,0.0003652942,0.000245992,0.00008003652],"domain_scores_gemma":[0.9927573,0.005439354,0.0006694795,0.000400209,0.0005641711,0.0001696245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000633514,0.0002200138,0.06881217,0.0008546255,0.0004063547,0.0009957245,0.0004672366,0.5496022,0.03367623,0.03894751,0.004567619,0.3008168],"study_design_scores_gemma":[0.00002211647,0.00007829147,0.005838377,0.00003585484,0.0000471454,0.0002375534,0.00005872804,0.9129856,0.00789231,0.07059115,0.002191219,0.00002170148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09933917,0.0003827587,0.896844,0.0002777314,0.00002511252,0.00009977612,0.001610933,0.0008755811,0.0005449195],"genre_scores_gemma":[0.6890998,0.0002908884,0.3047521,0.0002141347,0.00006061105,0.0002583938,0.004540132,0.0001122387,0.0006716647],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00287147,"threshold_uncertainty_score":0.01518595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226251181","doi":"10.1093/bioadv/vbac030","title":"Expanding the Galaxy’s reference data","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Sherbrooke; BC Centre for Disease Control","funders":"National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; National Cancer Institute; National Institutes of Health; European Commission; Vlaamse regering; National Research Foundation; UK Research and Innovation; Cleveland Clinic","keywords":"Computer science; Galaxy; Task (project management); Interface (matter); Reference data; Information retrieval; Database; Astrophysics; Operating system; Physics; Engineering","authors":[{"name":"VIJAY NAGAMPALLI","is_ca":false},{"name":"Jayadev Joshi","is_ca":false},{"name":"Nate Coraor","is_ca":false},{"name":"Jennifer Hillman‐Jackson","is_ca":false},{"name":"Dave Bouvier","is_ca":false},{"name":"Marius van den Beek","is_ca":false},{"name":"Ignacio Eguinoa","is_ca":false},{"name":"Frederik Coppens","is_ca":false},{"name":"John Davis","is_ca":false},{"name":"Michał Stolarczyk","is_ca":false},{"name":"Nathan C. Sheffield","is_ca":false},{"name":"Simon Gladman","is_ca":false},{"name":"Gianmauro Cuccuru","is_ca":false},{"name":"Björn Grüning","is_ca":false},{"name":"Nicola Soranzo","is_ca":false},{"name":"Helena Rasche","is_ca":false},{"name":"Bradley W. Langhorst","is_ca":false},{"name":"Matthias Bernt","is_ca":false},{"name":"Daniel Fornika","is_ca":true},{"name":"David Anderson de Lima Morais","is_ca":true},{"name":"M. Barrette","is_ca":true},{"name":"Peter Van Heusden","is_ca":false},{"name":"Mauro Petrillo","is_ca":false},{"name":"Antonio Puertas Gallardo","is_ca":false},{"name":"Alex Patak","is_ca":false},{"name":"Hans-Rudolf Hotz","is_ca":false},{"name":"Daniel Blankenberg","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03741575304613087,"gpt":0.2864572823709869,"spread":0.2490415293248561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008820063,0.002264489,0.002328244,0.008677315,0.002753458,0.007385784,0.008899019,0.003634826,0.05813423],"category_scores_gemma":[0.03517934,0.002299678,0.003103843,0.01191781,0.001228217,0.007303915,0.01136101,0.005709644,0.1071623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003094531,"about_ca_system_score_gemma":0.005915713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02502164,"about_ca_topic_score_gemma":0.02540175,"domain_scores_codex":[0.9915016,0.001330418,0.0007529081,0.002108167,0.00353454,0.0007723345],"domain_scores_gemma":[0.978265,0.002178986,0.0007865389,0.01140635,0.005809323,0.00155373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002814845,0.00003393369,0.0034546,0.000814414,0.0001731543,0.0001931907,0.0004999128,0.001015072,0.003961211,0.0112516,0.9294353,0.04888617],"study_design_scores_gemma":[0.00007540942,0.00002302878,0.001914677,0.0001546534,0.00005742507,0.00009175904,0.00006971551,0.001023239,0.003701149,0.006491419,0.9863274,0.00007009719],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.007551462,0.002508709,0.08171578,0.003539497,0.001941751,0.00029846,0.571268,0.2756305,0.05554591],"genre_scores_gemma":[0.01397077,0.0006315576,0.0761793,0.002004811,0.0002346153,0.0005438075,0.846826,0.0508244,0.008784768],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05813423,"threshold_uncertainty_score":0.1944784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4323066661","doi":"10.1093/bioadv/vbad023","title":"GPTree Cluster: phylogenetic tree cluster generator in the context of supertree inference","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Supertree; Phylogenetic tree; Computational phylogenetics; Tree (set theory); Context (archaeology); Phylogenetic network; Tree rearrangement; Cluster analysis; Inference; Biology; Computer science; Sister group; Python (programming language); Phylogenetics; Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics; Genetics; Clade","authors":[{"name":"Aleksandr Koshkarov","is_ca":true},{"name":"Nadia Tahiri","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01512226752613497,"gpt":0.2575465096804743,"spread":0.2424242421543393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002365585,0.001799093,0.001072882,0.00162657,0.001387436,0.002060723,0.005888713,0.001795054,0.02970112],"category_scores_gemma":[0.01109193,0.001429227,0.001973164,0.002028246,0.00108879,0.003298974,0.003269627,0.003428506,0.01492656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031371,"about_ca_system_score_gemma":0.002524586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003858309,"about_ca_topic_score_gemma":0.005481808,"domain_scores_codex":[0.9991435,0.0001984469,0.00006225603,0.0002558838,0.000219996,0.0001198474],"domain_scores_gemma":[0.9979631,0.0008565043,0.0001159697,0.0004656357,0.0004164386,0.0001823791],"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":[0.001834841,0.0003991845,0.007685082,0.00274011,0.0005639683,0.001211777,0.001959474,0.09498314,0.01435804,0.057264,0.5924896,0.2245108],"study_design_scores_gemma":[0.0005884899,0.0001229287,0.001536618,0.0002076442,0.0001172991,0.000517111,0.000183209,0.7371923,0.01538607,0.09700627,0.1469816,0.0001604519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.008603968,0.0002219624,0.6518512,0.0005684937,0.0003786825,0.0004117501,0.01446955,0.3195783,0.003916099],"genre_scores_gemma":[0.07403416,0.0003016629,0.790679,0.0005325533,0.0001016773,0.001498105,0.04923282,0.07910884,0.004511214],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02970112,"threshold_uncertainty_score":0.09936011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409105075","doi":"10.1093/bioadv/vbaf021","title":"Transfer learning improves performance in volumetric electron microscopy organelle segmentation across tissues","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"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; Lunenfeld-Tanenbaum Research Institute; Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Transfer of learning; Segmentation; Benchmark (surveying); Artificial intelligence; Annotation; Pattern recognition (psychology); Deep learning; Identification (biology); Organelle; Endoplasmic reticulum; Image segmentation; Volume (thermodynamics); Microscopy; Biology; Pathology; Physics","authors":[{"name":"Ronald Xie","is_ca":true},{"name":"Ben Mulcahy","is_ca":true},{"name":"Ali Izadi‐Darbandi","is_ca":true},{"name":"Sagar Marwah","is_ca":true},{"name":"Yuna Lee","is_ca":true},{"name":"Güneş Parlakgül","is_ca":false},{"name":"Gökhan S. Hotamışlıgil","is_ca":false},{"name":"Sonya A. MacParland","is_ca":true},{"name":"Mei Zhen","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004681615284073407,"gpt":0.3218662588925711,"spread":0.3171846436084977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002527051,0.002356404,0.001076275,0.001287549,0.000786201,0.001498705,0.002230401,0.002391391,0.003113858],"category_scores_gemma":[0.006014111,0.0004391251,0.001273251,0.0008998296,0.0008903764,0.001940969,0.002134476,0.002031195,0.002448954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001472733,"about_ca_system_score_gemma":0.001265898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01055773,"about_ca_topic_score_gemma":0.01046983,"domain_scores_codex":[0.998985,0.0001740981,0.00005325983,0.0004500071,0.0001866798,0.0001508808],"domain_scores_gemma":[0.9984052,0.0006224765,0.000101324,0.0003565068,0.0003819334,0.0001326562],"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":[0.001100657,0.0006087762,0.009339671,0.0005550233,0.0004393586,0.0003958599,0.0001932312,0.4317418,0.03403027,0.001775732,0.03291909,0.4869005],"study_design_scores_gemma":[0.0000417461,0.0001599073,0.001636286,0.00003546292,0.00003881683,0.00009415356,0.00006455652,0.9772056,0.0158948,0.003061343,0.001740753,0.00002646417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.557834,0.007093919,0.3431749,0.002621969,0.000792623,0.000334468,0.004572022,0.0708968,0.01267936],"genre_scores_gemma":[0.8357439,0.0007633924,0.1371126,0.001163365,0.0001404139,0.0001583626,0.01388828,0.00240263,0.008627009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01055773,"threshold_uncertainty_score":0.02099258,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407174948","doi":"10.1093/bioadv/vbaf014","title":"Leveraging LASSO-based methodologies for enhanced SNP analysis in plant genomes","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Guelph; Algoma University; Thompson Rivers University","funders":"Natural Sciences and Engineering Research Council of Canada; Thompson Rivers University","keywords":"Lasso (programming language); SNP; Computational biology; Genome; Biology; Genomic selection; Computer science; Genetics; Single-nucleotide polymorphism; Genotype; World Wide Web; Gene","authors":[{"name":"Nisha Puthiyedth","is_ca":true},{"name":"Farshad Zeinalinesaz","is_ca":true},{"name":"Dongdong Hou","is_ca":true},{"name":"Yue Zhang","is_ca":true},{"name":"Wenjun Lin","is_ca":true},{"name":"Yan Yan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04697469140103604,"gpt":0.3454984677685396,"spread":0.2985237763675035,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004985654,0.0009268589,0.001185168,0.0007881611,0.0004846257,0.001476721,0.001468447,0.0009879044,0.003408349],"category_scores_gemma":[0.009851917,0.0005058634,0.001423918,0.0009791384,0.0007046638,0.0009989908,0.00185497,0.002319611,0.001500543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000365416,"about_ca_system_score_gemma":0.00077607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001441436,"about_ca_topic_score_gemma":0.00191356,"domain_scores_codex":[0.9978835,0.001285195,0.0000876286,0.0002861931,0.0003762896,0.00008114831],"domain_scores_gemma":[0.9946623,0.003767097,0.0003501294,0.0005232205,0.0005454991,0.0001517179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002567834,0.0001511548,0.005046796,0.0004913057,0.0004031889,0.0003211612,0.0002782561,0.7232251,0.02118978,0.03407813,0.01194427,0.2026141],"study_design_scores_gemma":[0.0000139158,0.00001445844,0.0003031886,0.00001452024,0.00000886995,0.00001912329,0.00001356757,0.9832652,0.0009627156,0.01340179,0.001969762,0.00001294921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005888176,0.0001668316,0.9915493,0.0002746348,0.00004009542,0.00001962472,0.0003066491,0.001305996,0.0004486942],"genre_scores_gemma":[0.1222027,0.0002429168,0.8727369,0.0003906012,0.0001357387,0.000231826,0.002025935,0.0009463652,0.0010869],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004985654,"threshold_uncertainty_score":0.02636701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396722621","doi":"10.1093/bioadv/vbae066","title":"Network depth affects inference of gene sets from bacterial transcriptomes using denoising autoencoders","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","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":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Artificial intelligence; Transcriptome; Noise reduction; Pattern recognition (psychology); Computer science; Gene; Computational biology; Biology; Gene expression; Genetics","authors":[{"name":"Willow Kion-Crosby","is_ca":false},{"name":"Lars Barquist","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01522251531141121,"gpt":0.2686701019971908,"spread":0.2534475866857796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00216643,0.0006157444,0.0004343069,0.0005009403,0.000349155,0.0006816689,0.0007453095,0.0006804668,0.001074874],"category_scores_gemma":[0.007825028,0.0004224835,0.000659317,0.0003718256,0.0005669957,0.0009112491,0.0008112426,0.001751024,0.0003415401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008603323,"about_ca_system_score_gemma":0.0008609913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008806705,"about_ca_topic_score_gemma":0.01135293,"domain_scores_codex":[0.9995869,0.0001417108,0.00001972572,0.0001267868,0.00008233322,0.00004251636],"domain_scores_gemma":[0.9964824,0.002663103,0.0001229371,0.0002911294,0.0003518133,0.00008862929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000536061,0.0001358766,0.01934957,0.0001884672,0.000187985,0.00008955252,0.0001557203,0.8755084,0.04526722,0.002937261,0.002748403,0.05289551],"study_design_scores_gemma":[0.000008797399,0.00001615622,0.001479479,0.000008005777,0.000008968901,0.000007407205,0.00001700139,0.9902816,0.006139428,0.001755444,0.0002716153,0.0000060733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7279734,0.0005182108,0.2623709,0.001023307,0.0000784872,0.00005513833,0.001995769,0.003898863,0.002086001],"genre_scores_gemma":[0.8472287,0.00017376,0.1462544,0.0002754965,0.00002037629,0.00006988779,0.004811284,0.0002868902,0.0008791458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008806705,"threshold_uncertainty_score":0.01751089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4379276041","doi":"10.1093/bioadv/vbad068","title":"DataCurator.jl: efficient, portable and reproducible validation, curation and transformation of large heterogeneous datasets using human-readable recipes compiled into machine-verifiable templates","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"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; Simon Fraser University","funders":"","keywords":"Computer science; Executable; Scalability; Python (programming language); Preprocessor; Workflow; Data mining; Verifiable secret sharing; Data curation; Database; Programming language","authors":[{"name":"Ben Cardoen","is_ca":true},{"name":"Hanene Ben Yedder","is_ca":true},{"name":"Sieun Lee","is_ca":false},{"name":"Ivan R. Nabi","is_ca":true},{"name":"Ghassan Hamarneh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09799458101637326,"gpt":0.4068712497562927,"spread":0.3088766687399195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01245636,0.003507793,0.002660649,0.003507976,0.00175021,0.00596305,0.005597734,0.001691314,0.05162053],"category_scores_gemma":[0.03450952,0.004077805,0.003769364,0.002629879,0.002894021,0.004989835,0.01013978,0.006130868,0.08045998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00157964,"about_ca_system_score_gemma":0.005893007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003436417,"about_ca_topic_score_gemma":0.003879301,"domain_scores_codex":[0.9913855,0.001358859,0.001000771,0.002297995,0.003323874,0.0006330079],"domain_scores_gemma":[0.9788825,0.007056053,0.001726542,0.007499284,0.003902416,0.0009332133],"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":[0.001048883,0.0001678982,0.005118283,0.003222468,0.0004845072,0.0006346257,0.001455697,0.005220192,0.03225213,0.01170167,0.8247947,0.113899],"study_design_scores_gemma":[0.0005610252,0.0001760805,0.005261947,0.001073597,0.0001656897,0.0005964122,0.0002586407,0.03354993,0.09839428,0.03000199,0.829333,0.0006273643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002458513,0.0002965585,0.2534351,0.0005888614,0.00036797,0.0004974583,0.04499031,0.6928097,0.00455554],"genre_scores_gemma":[0.02048361,0.0005580814,0.3250799,0.001770215,0.0001482403,0.003259474,0.1455885,0.4930097,0.01010239],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.9944023,"threshold_uncertainty_score":0.1726879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3217126935","doi":"10.1093/bioadv/vbab032","title":"An expectation–maximization approach to quantifying protein stoichiometry with single-molecule imaging","year":2021,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Advanced Fluorescence Microscopy Techniques","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":"University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Photobleaching; Maximization; Rendering (computer graphics); Benchmark (surveying); Single-molecule experiment; Software; Algorithm; Resampling; Biological system; Artificial intelligence; Fluorescence; Physics; Mathematics; Optics; Mathematical optimization","authors":[{"name":"Artittaya Boonkird","is_ca":true},{"name":"Daniel Nino","is_ca":true},{"name":"Joshua N. Milstein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01365889790151077,"gpt":0.2865778349318525,"spread":0.2729189370303417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004759419,0.001723282,0.00157649,0.001153879,0.0006377432,0.001560466,0.003335775,0.002029627,0.002906242],"category_scores_gemma":[0.0102676,0.001216188,0.001485904,0.001636592,0.001289341,0.001461112,0.001545449,0.002684959,0.001735163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001299451,"about_ca_system_score_gemma":0.002231064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004031857,"about_ca_topic_score_gemma":0.004618132,"domain_scores_codex":[0.9983299,0.0006961291,0.00009236176,0.0004586246,0.0003528097,0.00007005702],"domain_scores_gemma":[0.9966179,0.002285798,0.0002384747,0.0002194918,0.0005113543,0.0001270606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001776525,0.0001417423,0.001388358,0.0004767486,0.0002882907,0.0001772729,0.0001080744,0.8330363,0.01064912,0.02004823,0.009424169,0.1240841],"study_design_scores_gemma":[0.00001099583,0.00001386177,0.0001123357,0.00001102572,0.000009576618,0.00003907635,0.000005505256,0.9854798,0.001774752,0.01136674,0.001164812,0.00001153817],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001711961,0.0001426811,0.9965934,0.0001880865,0.00001996139,0.00004312092,0.0001743648,0.0008059132,0.0003204396],"genre_scores_gemma":[0.04024818,0.0002084396,0.9567257,0.0002755725,0.00007385996,0.0003104773,0.0008724749,0.0003383496,0.0009469911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004759419,"threshold_uncertainty_score":0.02517051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319341254","doi":"10.1093/bioadv/vbad010","title":"NSPA: characterizing the disease association of multiple genetic interactions at single-subject resolution","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","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":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Association (psychology); Subject (documents); Resolution (logic); Genetic association; Computational biology; Computer science; Biology; Genetics; Artificial intelligence; Psychology; Genotype; Single-nucleotide polymorphism; Gene; Library science","authors":[{"name":"Zhendong Sha","is_ca":true},{"name":"Yuanzhu Chen","is_ca":true},{"name":"Ting Hu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01775615102493194,"gpt":0.2633413426690291,"spread":0.2455851916440972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003440966,0.0006975882,0.0007729937,0.00188296,0.0006181184,0.001004194,0.001048664,0.0008771226,0.008351387],"category_scores_gemma":[0.01124045,0.0002891248,0.001295571,0.001812914,0.0006633113,0.0008164129,0.001145626,0.001136199,0.00152708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005549005,"about_ca_system_score_gemma":0.0009367485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005003939,"about_ca_topic_score_gemma":0.006663472,"domain_scores_codex":[0.9988909,0.0004815071,0.00004822504,0.0003894681,0.0001486078,0.00004124521],"domain_scores_gemma":[0.9929357,0.005020401,0.0006384421,0.0008061988,0.0003312763,0.0002679444],"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":[0.001461285,0.0004743554,0.3227488,0.00144372,0.001885194,0.002060543,0.0009565908,0.2161795,0.01777155,0.04768876,0.0928199,0.2945098],"study_design_scores_gemma":[0.0001945309,0.0002936928,0.09025777,0.0001577894,0.0005043321,0.001512895,0.0002234012,0.6815426,0.004138328,0.186373,0.03470636,0.00009529583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2219614,0.002000104,0.7087111,0.003657974,0.0002942407,0.0003317168,0.04990759,0.004681157,0.008454577],"genre_scores_gemma":[0.7620578,0.0008831113,0.1918163,0.0005541579,0.0003473631,0.0006225915,0.03894585,0.0003689661,0.004403759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008351387,"threshold_uncertainty_score":0.02793819,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412626392","doi":"10.1093/bioadv/vbaf178","title":"Gene-set enrichment analysis and visualization on the web using EnrichmentMap:RNASeq","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","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":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"National Institutes of Health","keywords":"Visualization; Computational biology; Set (abstract data type); Biology; Computer science; Genetics; World Wide Web; Data mining; Programming language","authors":[{"name":"Max Franz","is_ca":true},{"name":"Christian Lopes","is_ca":true},{"name":"Mike Kucera","is_ca":true},{"name":"Véronique Voisin","is_ca":true},{"name":"Ruth Isserlin","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01282611854482546,"gpt":0.278922961500048,"spread":0.2660968429552225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001727271,0.002190591,0.001348328,0.004820586,0.001091548,0.002027588,0.001907937,0.0009859293,0.1095631],"category_scores_gemma":[0.003402991,0.0009737557,0.001465388,0.002717142,0.0003971329,0.001599872,0.002266999,0.002233793,0.04142509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004682281,"about_ca_system_score_gemma":0.001211059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002156377,"about_ca_topic_score_gemma":0.003901524,"domain_scores_codex":[0.9986915,0.000140388,0.00008015317,0.0003538616,0.0006009499,0.0001331112],"domain_scores_gemma":[0.9983707,0.0007364229,0.00009920646,0.0002090073,0.0004335289,0.0001510687],"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":[0.0009109913,0.0002522805,0.003438945,0.003198251,0.0005587924,0.0008226699,0.0005074329,0.00214392,0.07282641,0.004661574,0.7567441,0.1539346],"study_design_scores_gemma":[0.0005803027,0.0001902049,0.01596666,0.0006441346,0.000267451,0.001427207,0.0002759143,0.04014242,0.1922854,0.03015869,0.7175361,0.0005254837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01212769,0.001164394,0.2555358,0.001099264,0.000825691,0.000517648,0.1829243,0.5273463,0.01845895],"genre_scores_gemma":[0.0643707,0.001457247,0.5211263,0.002156588,0.0004641794,0.003829487,0.2800864,0.09258807,0.03392101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1095631,"threshold_uncertainty_score":0.3665252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411332264","doi":"10.1093/bioadv/vbaf129","title":"NRGSuite-Qt: a PyMOL plugin for high-throughput virtual screening, molecular docking, normal-mode analysis, the study of molecular interactions, and the detection of binding-site similarities","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Protein Structure and Dynamics","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":"Université de Montréal","funders":"","keywords":"Plug-in; Docking (animal); Virtual screening; Computational biology; Computer science; Binding site; Chemistry; Bioinformatics; Drug discovery; Biology; Operating system; Medicine; Biochemistry","authors":[{"name":"Gabriel Tiago Galdino","is_ca":true},{"name":"Thomas DesCôteaux","is_ca":true},{"name":"Natália Teruel","is_ca":true},{"name":"Rafaël Najmanovich","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004588894427499391,"gpt":0.2638198506195027,"spread":0.2592309561920033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001996538,0.002454257,0.001734912,0.00174853,0.0008113416,0.001733704,0.005187458,0.001204192,0.04208812],"category_scores_gemma":[0.003866293,0.001817592,0.001863397,0.001059238,0.0006194515,0.002543012,0.003667305,0.00371816,0.02436071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008733486,"about_ca_system_score_gemma":0.002072697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003875336,"about_ca_topic_score_gemma":0.004316994,"domain_scores_codex":[0.9987983,0.000166852,0.00007302709,0.0002087933,0.0005868322,0.0001662432],"domain_scores_gemma":[0.9990135,0.0003694047,0.00008706754,0.000210946,0.0001917949,0.0001273415],"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":[0.0008702909,0.0002309325,0.002220074,0.001919918,0.0004377612,0.0005294174,0.0002483384,0.01415756,0.0311556,0.01122133,0.7512476,0.1857611],"study_design_scores_gemma":[0.0007965969,0.0002873954,0.004203495,0.0003607134,0.0001553048,0.001366079,0.00007308227,0.2559774,0.1153637,0.02098237,0.5997424,0.0006916149],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.006955213,0.0009574821,0.3544979,0.0004844908,0.0004254535,0.000243029,0.01968462,0.6121517,0.004600222],"genre_scores_gemma":[0.09037898,0.002650056,0.5574452,0.001238539,0.0002162148,0.002376947,0.1012828,0.2230309,0.02138034],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.04208812,"threshold_uncertainty_score":0.1407988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413890799","doi":"10.1093/bioadv/vbaf169","title":"Opportunities and considerations for using artificial intelligence in bioinformatics education","year":2024,"lang":"en","type":"editorial","venue":"Bioinformatics Advances","topic":"Genetics, Bioinformatics, and Biomedical Research","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":"Public Health Agency of Canada; Ontario Institute for Cancer Research","funders":"National Center for Advancing Translational Sciences; Government of Ontario; Bill and Melinda Gates Foundation; National Institutes of Health; National Science Foundation","keywords":"Scope (computer science); Computer science; Artificial intelligence; Bioinformatics; Data science; Biology","authors":[{"name":"Stephen Piccolo","is_ca":false},{"name":"Aparna Nathan","is_ca":false},{"name":"Michelle D. Brazas","is_ca":true},{"name":"Manoj Kandpal","is_ca":false},{"name":"Aida Miró-Herrans","is_ca":false},{"name":"Adam J. Kleinschmit","is_ca":false},{"name":"Susan McClatchy","is_ca":false},{"name":"Pertunia Mutheiwana","is_ca":false},{"name":"Dusanka Nikolic","is_ca":false},{"name":"Luciana I. Gallo","is_ca":false},{"name":"Rolanda Julius","is_ca":false},{"name":"Marta Lloret-Llinares","is_ca":false},{"name":"Nicola Mulder","is_ca":false},{"name":"Danielle Presgraves","is_ca":false},{"name":"Sonal Shewaramani","is_ca":true},{"name":"Jorge Xool-Tamayo","is_ca":false},{"name":"Frédéric J. J. Chain","is_ca":false},{"name":"Silvia Arantza Sánchez Guerrero","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06368501628049607,"gpt":0.3621898748204531,"spread":0.298504858539957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0163864,0.001997409,0.001262762,0.002733472,0.004397947,0.01194563,0.003250759,0.0175957,0.005838953],"category_scores_gemma":[0.04942352,0.0008266257,0.001512118,0.001370106,0.005129412,0.008527575,0.002469981,0.03176511,0.004966897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00436775,"about_ca_system_score_gemma":0.005805801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002098083,"about_ca_topic_score_gemma":0.00782932,"domain_scores_codex":[0.9891441,0.003037252,0.001234005,0.0008599033,0.005279577,0.0004452445],"domain_scores_gemma":[0.9290324,0.04409353,0.001662846,0.001118392,0.01820947,0.00588329],"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":[0.00002479387,0.00001837898,0.00004817701,0.0002855441,0.000008937147,0.0001473571,0.0001305687,0.00006317958,0.00007795241,0.002110225,0.9845055,0.01257934],"study_design_scores_gemma":[0.0000207829,0.000020681,0.0001752119,0.0005321564,0.00001582367,0.0002401028,0.0002042152,0.0002048587,0.0000895776,0.003754796,0.9947209,0.00002081841],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0000599823,0.006128466,0.0004070562,0.149085,0.8422574,0.00001612205,0.00001638437,0.00005037513,0.001979372],"genre_scores_gemma":[0.0009834225,0.008144169,0.0007500949,0.08917996,0.8905055,0.00003770378,0.00001700924,0.00005621641,0.01032593],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.0175957,"threshold_uncertainty_score":0.08666062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403924852","doi":"10.1093/bioadv/vbae168","title":"Population-aware permutation-based significance thresholds for genome-wide association studies","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","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":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Bundesministerium für Bildung und Forschung","keywords":"Genome-wide association study; Genetic association; Association (psychology); Population; Genetics; Permutation (music); Biology; Computational biology; Evolutionary biology; Single-nucleotide polymorphism; Medicine; Psychology; Genotype; Gene; Environmental health; Physics","authors":[{"name":"Maura John","is_ca":false},{"name":"Arthur Korte","is_ca":false},{"name":"Marco Todesco","is_ca":true},{"name":"Dominik G. Grimm","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01891542148422085,"gpt":0.3156294565846542,"spread":0.2967140351004333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01442979,0.0009412487,0.0013465,0.002163425,0.0008183125,0.00186871,0.002359571,0.001225303,0.009591878],"category_scores_gemma":[0.08006688,0.0008890066,0.001658716,0.003346759,0.001352682,0.001417857,0.001822109,0.003140869,0.003427611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006013829,"about_ca_system_score_gemma":0.00278984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001598435,"about_ca_topic_score_gemma":0.002274323,"domain_scores_codex":[0.9908345,0.006020814,0.0005463621,0.001338083,0.001005783,0.0002544718],"domain_scores_gemma":[0.9666415,0.02460841,0.001315907,0.004781404,0.002125634,0.0005271194],"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":[0.002831911,0.0003860384,0.02523682,0.002385924,0.002132587,0.001411941,0.0006555972,0.1103324,0.04522774,0.06416636,0.07274893,0.6724837],"study_design_scores_gemma":[0.001030496,0.0004917483,0.01202714,0.0002530685,0.0004287348,0.001355431,0.0001574803,0.6231638,0.03535448,0.2744403,0.0510455,0.000251944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007952648,0.000326561,0.9799532,0.0004304303,0.0001928077,0.0002206308,0.001768377,0.008393181,0.0007621389],"genre_scores_gemma":[0.110365,0.0002064399,0.881385,0.0003560157,0.0001966469,0.001221524,0.003170095,0.002189828,0.0009095255],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01442979,"threshold_uncertainty_score":0.07631296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414683622","doi":"10.1093/bioadv/vbaf222","title":"An overview of computational methods for gene prediction in eukaryotes: strengths, limitations, and future directions","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Machine Learning in Bioinformatics","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":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Benchmark (surveying); Gene prediction; Scripting language; Gene; Sequence (biology); DNA sequencing","authors":[{"name":"Abigaïl Djossou","is_ca":true},{"name":"Wend Yam DD Ouedraogo","is_ca":true},{"name":"Aïda Ouangraoua","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02498786159813313,"gpt":0.3762993471727817,"spread":0.3513114855746485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006340667,0.001736046,0.001747301,0.002926584,0.0005530197,0.003235659,0.002820883,0.001469901,0.004452933],"category_scores_gemma":[0.01442825,0.0009896066,0.001651964,0.004172958,0.001020269,0.004109369,0.002130743,0.00447973,0.003751632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001203086,"about_ca_system_score_gemma":0.00227993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002749736,"about_ca_topic_score_gemma":0.002325001,"domain_scores_codex":[0.9980211,0.0006596273,0.0001853348,0.0003796797,0.0006557095,0.00009850568],"domain_scores_gemma":[0.988962,0.008176224,0.0002801354,0.0005802922,0.001702386,0.0002989817],"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":[0.0002122031,0.00008492371,0.002417999,0.01083714,0.0004084301,0.00008336219,0.0001034387,0.0237254,0.002901666,0.03950887,0.06293833,0.8567783],"study_design_scores_gemma":[0.00006878768,0.0002674154,0.00206115,0.006944532,0.000368967,0.0004694894,0.0001224927,0.1289737,0.006836345,0.1415349,0.7121602,0.0001921904],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.003326114,0.672979,0.3005638,0.009207128,0.001959906,0.00009380286,0.002014674,0.003190595,0.006665024],"genre_scores_gemma":[0.02185352,0.6559494,0.3069147,0.003279007,0.00261056,0.0003837024,0.005708843,0.00116346,0.00213681],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006340667,"threshold_uncertainty_score":0.03353304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416548752","doi":"10.1093/bioadv/vbaf286","title":"Are the tools fit for purpose? Network inference algorithms evaluated on a simulated lipidomics network","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"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; University of Ottawa; University of Victoria; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Key (lock); Identification (biology); Feature (linguistics); Pattern recognition (psychology)","authors":[{"name":"Finn Archinuk","is_ca":true},{"name":"Haley Greenyer","is_ca":true},{"name":"Ulrike Stege","is_ca":true},{"name":"Steffany A. L. Bennett","is_ca":true},{"name":"Miroslava Čuperlović‐Culf","is_ca":true},{"name":"Hosna Jabbari","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04178784423895929,"gpt":0.3276315467898132,"spread":0.2858437025508539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005946693,0.0007594896,0.0005665862,0.001202907,0.0006451332,0.001082396,0.001432262,0.001032389,0.003385086],"category_scores_gemma":[0.03725453,0.0002728379,0.0005880965,0.00114624,0.0006259045,0.001643985,0.0009537548,0.001163915,0.0005534962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499201,"about_ca_system_score_gemma":0.00169721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01452123,"about_ca_topic_score_gemma":0.01360727,"domain_scores_codex":[0.998647,0.0007671879,0.00005991581,0.0002452082,0.0001830022,0.00009774185],"domain_scores_gemma":[0.9708347,0.02453323,0.0007812627,0.00143871,0.002045744,0.0003663886],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003922416,0.000181464,0.01104228,0.0002033654,0.0001046513,0.0001007874,0.00010792,0.9412282,0.0009418481,0.006808642,0.003177087,0.03571146],"study_design_scores_gemma":[0.00002275994,0.00002366583,0.0005067743,0.00001305063,0.00001004832,0.00001602584,0.00002083139,0.9952046,0.0005370279,0.003330057,0.0003108029,0.000004392325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5455516,0.0008003803,0.4343726,0.002377456,0.0001532436,0.0003507154,0.003561569,0.00484639,0.007986049],"genre_scores_gemma":[0.7770411,0.0003244762,0.2175916,0.000204014,0.00003007972,0.0002995547,0.00308363,0.0003819878,0.001043515],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9940533,"threshold_uncertainty_score":0.0314495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297231023","doi":"10.1093/bioadv/vbac069","title":"High-throughput design of bacterial anti-sense RNAs using CAREng","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Computational biology; Gene; Antisense RNA; Functional genomics; RNA; Transfer RNA; Genetics; Genome; Genomics","authors":[{"name":"Jazmín Romero","is_ca":true},{"name":"Md. Tanvir Islam","is_ca":true},{"name":"Ryan Taylor","is_ca":true},{"name":"Cathryn Grayson","is_ca":true},{"name":"Andrew Schoenrock","is_ca":true},{"name":"Alex Wong","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01569035333574757,"gpt":0.2419148205237434,"spread":0.2262244671879959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001232016,0.0008539545,0.0007658464,0.0004700314,0.00049613,0.00111809,0.0007600083,0.0006703496,0.004017887],"category_scores_gemma":[0.001585191,0.0007452971,0.0008489859,0.0003725247,0.0005125485,0.0004181405,0.0006992163,0.001516737,0.004503696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001039125,"about_ca_system_score_gemma":0.0009036186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008926977,"about_ca_topic_score_gemma":0.002260083,"domain_scores_codex":[0.9991203,0.0001444762,0.00008854651,0.0001907421,0.0003393571,0.0001167079],"domain_scores_gemma":[0.999319,0.0002197997,0.00009412123,0.0001014232,0.00016304,0.0001026308],"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":[0.0001246096,0.00006506843,0.00022674,0.0003071053,0.0000223607,0.0001289673,0.0001360068,0.003657046,0.9790995,0.001501502,0.002105805,0.01262522],"study_design_scores_gemma":[0.00004252953,0.0001962207,0.0002669696,0.00002941202,0.00002106889,0.0001056778,0.00003458734,0.01059043,0.9593123,0.000388387,0.02896879,0.00004349709],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2563901,0.001769302,0.6971403,0.0008099622,0.0006307469,0.003101492,0.005287173,0.01885124,0.01601965],"genre_scores_gemma":[0.4074933,0.001613961,0.559135,0.0006924542,0.00005171951,0.002808835,0.0103617,0.003285749,0.01455729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004017887,"threshold_uncertainty_score":0.01344121,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415491818","doi":"10.1093/bioadv/vbaf265","title":"MutSeqR: an open source R package for standardized analysis of error-corrected next-generation sequencing data in genetic toxicology","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Carcinogens and Genotoxicity Assessment","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; University of Ottawa; Health Canada","funders":"Health Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Open source; R package; Sequence (biology); License; DNA sequencing; MIT License","authors":[{"name":"Annette Dodge","is_ca":true},{"name":"A. Williams","is_ca":true},{"name":"Danielle LeBlanc","is_ca":true},{"name":"David M. Schuster","is_ca":true},{"name":"Charles C. Valentine","is_ca":false},{"name":"Jesse J. Salk","is_ca":false},{"name":"Alexander Y. Maslov","is_ca":true},{"name":"Chris P. Bradley","is_ca":false},{"name":"Carole L. Yauk","is_ca":true},{"name":"Francesco Marchetti","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0931933158410629,"gpt":0.3659723816727946,"spread":0.2727790658317317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01307483,0.00410602,0.003300408,0.003212394,0.001054124,0.004303691,0.003946426,0.001877403,0.03351233],"category_scores_gemma":[0.04945694,0.001989335,0.003743942,0.002709776,0.00141525,0.002376825,0.004189465,0.003843033,0.03651848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009750884,"about_ca_system_score_gemma":0.004940615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003007138,"about_ca_topic_score_gemma":0.003138478,"domain_scores_codex":[0.9908816,0.004137831,0.0007727932,0.002087762,0.001748581,0.0003715711],"domain_scores_gemma":[0.9801164,0.0119682,0.002638931,0.002473511,0.00220074,0.0006021937],"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":[0.002085651,0.0001833157,0.0220646,0.01212056,0.004734072,0.001411926,0.00135383,0.04036987,0.02772085,0.02548951,0.691388,0.1710778],"study_design_scores_gemma":[0.000997752,0.0005846655,0.01502787,0.00194592,0.001682299,0.001829392,0.0003078115,0.1464503,0.03050788,0.07907954,0.7208772,0.0007094496],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.008383909,0.002567474,0.5701948,0.001398225,0.0006989969,0.0006821913,0.1699008,0.2404834,0.005690208],"genre_scores_gemma":[0.05943394,0.00265668,0.5893158,0.002510309,0.0003569452,0.004176972,0.1858749,0.1481537,0.007520722],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03351233,"threshold_uncertainty_score":0.1121099,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409908023","doi":"10.1093/bioadv/vbaf103","title":"Assessing accuracy and specificity of faecal source library for microbial source-tracking, using SourceTracker as case study","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Fecal contamination and water quality","field":"Environmental 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":"University of Guelph","funders":"Melbourne Water","keywords":"Source tracking; Open source; Tracking (education); Computer science; Psychology; World Wide Web; Software","authors":[{"name":"Timothy J Y Lim","is_ca":false},{"name":"Yussi M Palacios Delgado","is_ca":false},{"name":"Anna Lintern","is_ca":false},{"name":"David McCarthy","is_ca":true},{"name":"Rebekah Henry","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04425365662850683,"gpt":0.3352390906556071,"spread":0.2909854340271003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01564055,0.00132643,0.001274099,0.00268331,0.001100811,0.00319449,0.001473728,0.002078759,0.001786864],"category_scores_gemma":[0.03710006,0.0005675725,0.001004544,0.002135406,0.001527558,0.001532151,0.002955687,0.0009881599,0.002427574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008665117,"about_ca_system_score_gemma":0.001533094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005176714,"about_ca_topic_score_gemma":0.009775301,"domain_scores_codex":[0.9834673,0.003188995,0.001541557,0.003572435,0.007417248,0.0008125057],"domain_scores_gemma":[0.9740276,0.009625304,0.003579443,0.002828136,0.009351073,0.0005885186],"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":[0.001269856,0.0005406227,0.2195844,0.003740498,0.0003982457,0.001493341,0.005319367,0.006471456,0.5699604,0.001492083,0.004386252,0.1853434],"study_design_scores_gemma":[0.00002655784,0.001288382,0.1006777,0.0008503611,0.0003525088,0.002488863,0.002201829,0.02355097,0.8395519,0.001634515,0.02713139,0.0002450879],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7156327,0.003206492,0.26026,0.001112371,0.0002882679,0.001399114,0.006506653,0.003853921,0.007740545],"genre_scores_gemma":[0.6557088,0.001608099,0.3277626,0.0006045959,0.00006333148,0.0008675598,0.007087052,0.001109165,0.005188743],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01564055,"threshold_uncertainty_score":0.08271617,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416751600","doi":"10.1093/bioadv/vbaf307","title":"Omics BioAnalytics: an RShiny application for multimodal biomarker panel discovery and assessment","year":2025,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Paul's Hospital; University of British Columbia; Prevention of Organ Failure; Stornoway Diamond (Canada); Providence Health Care","funders":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Biomarker discovery; Biomarker; Omics; Genomics; Precision medicine","authors":[{"name":"Lea Rieskamp","is_ca":false},{"name":"Scott J. Tebbutt","is_ca":true},{"name":"Bruce M. McManus","is_ca":true},{"name":"Amrit Singh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01336817700406793,"gpt":0.3011272475436773,"spread":0.2877590705396094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003250282,0.00260196,0.001094084,0.002385803,0.0007524542,0.002513063,0.002586327,0.001342815,0.04609185],"category_scores_gemma":[0.007924795,0.001227155,0.001595672,0.00129728,0.0008689215,0.002044307,0.005542272,0.001871189,0.02471834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108506,"about_ca_system_score_gemma":0.002088782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004835111,"about_ca_topic_score_gemma":0.004684636,"domain_scores_codex":[0.9986383,0.0002055247,0.00009040582,0.0003607737,0.0005924349,0.0001126218],"domain_scores_gemma":[0.9980065,0.0007755252,0.0002060219,0.00044809,0.00035792,0.0002059044],"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":[0.003778403,0.0004068003,0.01362858,0.002513745,0.0008207154,0.002017425,0.001143055,0.01907753,0.06370237,0.02316364,0.5371521,0.3325956],"study_design_scores_gemma":[0.0008045635,0.0003638981,0.01427222,0.0009665093,0.0002673046,0.001588678,0.0003243455,0.2997449,0.09796246,0.06023561,0.5229003,0.0005691871],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.007565007,0.0009768103,0.4210743,0.001334124,0.000290351,0.0008726511,0.03192278,0.5230752,0.01288881],"genre_scores_gemma":[0.1376887,0.002258763,0.6362181,0.003935087,0.0004247967,0.003116647,0.0790021,0.111899,0.02545677],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.04609185,"threshold_uncertainty_score":0.1541926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394762701","doi":"10.1093/bioadv/vbae047","title":"Text-mining-based feature selection for anticancer drug response prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","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":"University of Ottawa; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Stem Cell Network","keywords":"Feature selection; Pharmacogenomics; Machine learning; Computer science; Artificial intelligence; Feature (linguistics); Drug response; Selection (genetic algorithm); Support vector machine; Data mining; Bioinformatics; Drug; Biology","authors":[{"name":"Grace C. Wu","is_ca":true},{"name":"Arvin Zaker","is_ca":true},{"name":"Amirhosein Ebrahimi","is_ca":true},{"name":"Shivanshi Tripathi","is_ca":true},{"name":"Arvind Singh Mer","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01249792745781209,"gpt":0.3089335441867941,"spread":0.296435616728982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001223823,0.0008609306,0.0009411618,0.002840277,0.0002536623,0.00064421,0.0007650793,0.0005094383,0.00415109],"category_scores_gemma":[0.005404908,0.0001613228,0.0009310082,0.002698812,0.0001501141,0.0007031786,0.0003885012,0.000483272,0.001647658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003428434,"about_ca_system_score_gemma":0.0006248296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001565691,"about_ca_topic_score_gemma":0.00161231,"domain_scores_codex":[0.9994124,0.0001621627,0.0000881921,0.0001317666,0.000159017,0.00004643671],"domain_scores_gemma":[0.9975803,0.001465361,0.0002534566,0.0001604485,0.0004754924,0.00006505824],"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":[0.001852055,0.0009436571,0.02982819,0.001189018,0.0003686094,0.0006365993,0.0000821283,0.04858506,0.04540935,0.00112098,0.04946841,0.8205159],"study_design_scores_gemma":[0.0002918407,0.0006262112,0.02366352,0.0001274165,0.0003085999,0.0005738197,0.0000701914,0.8898602,0.06225557,0.006647196,0.01548904,0.0000864178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3786573,0.004489935,0.4991043,0.002392975,0.0004638073,0.001277749,0.07495586,0.03351811,0.005140082],"genre_scores_gemma":[0.6706433,0.0007160953,0.2787726,0.0003482848,0.000222403,0.0009622552,0.04586491,0.0004084408,0.002061695],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00415109,"threshold_uncertainty_score":0.01388675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406713780","doi":"10.1093/bioadv/vbae209","title":"<u>Imp</u>utation for <u>Li</u>pidomics and <u>Met</u>abolomics (ImpLiMet): a web-based application for optimization and method selection for missing data imputation","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Occupational Cancer Research Centre; University of Toronto; McGill Genome Centre; National Research Council Canada; McGill University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Computer science; Mathematics; Statistics","authors":[{"name":"Huiting Ou","is_ca":true},{"name":"Anuradha Surendra","is_ca":true},{"name":"Graeme S. V. McDowell","is_ca":true},{"name":"Emily Hashimoto-Roth","is_ca":true},{"name":"Jianguo Xia","is_ca":true},{"name":"Steffany A. L. Bennett","is_ca":true},{"name":"Miroslava Čuperlović‐Culf","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05619849722513385,"gpt":0.4230035011006127,"spread":0.3668050038754789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008406925,0.003169103,0.00304155,0.003212138,0.001992697,0.004705795,0.004611419,0.002876922,0.2249493],"category_scores_gemma":[0.03130928,0.002253625,0.003563582,0.0043432,0.00128758,0.00356732,0.006304353,0.003836476,0.1320377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001478085,"about_ca_system_score_gemma":0.003403348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003116429,"about_ca_topic_score_gemma":0.005046152,"domain_scores_codex":[0.99633,0.0008512606,0.0002916353,0.0009123504,0.001283407,0.0003314442],"domain_scores_gemma":[0.9897612,0.005305578,0.0009947664,0.002149121,0.001240365,0.0005489194],"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":[0.00091093,0.0001191835,0.003911252,0.002016441,0.0003942697,0.0006342753,0.0002928351,0.003547953,0.004601014,0.008136324,0.8979949,0.07744048],"study_design_scores_gemma":[0.0009244058,0.0002350481,0.006169768,0.0009632919,0.0002530745,0.001296162,0.0001660635,0.06593627,0.03854505,0.06098047,0.824046,0.0004843514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004179537,0.001112062,0.2159374,0.002175099,0.001523721,0.0003947366,0.2039749,0.5549043,0.01579824],"genre_scores_gemma":[0.04078936,0.001669485,0.3526665,0.004087312,0.0007821752,0.002688708,0.3154034,0.2603877,0.02152525],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.2249493,"threshold_uncertainty_score":0.7525304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388643693","doi":"10.1093/bioadv/vbad162","title":"aaHash: recursive amino acid sequence hashing","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Dynamic perfect hashing; Hash function; Computer science; String (physics); Universal hashing; Context (archaeology); K-independent hashing; Theoretical computer science; Hash table; Algorithm; Locality-sensitive hashing; Double hashing; Biology; Mathematics; Programming language","authors":[{"name":"Johnathan Wong","is_ca":true},{"name":"Parham Kazemi","is_ca":true},{"name":"Lauren Coombe","is_ca":true},{"name":"René L. Warren","is_ca":true},{"name":"İnanç Birol","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02459884249832153,"gpt":0.2769423388426316,"spread":0.2523434963443101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001559588,0.0007574683,0.0008501002,0.001268564,0.0008456793,0.001643378,0.002415724,0.001133407,0.01693837],"category_scores_gemma":[0.006886318,0.0006179052,0.000836694,0.00157085,0.0008788166,0.00246739,0.002203193,0.001302343,0.0134339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006923464,"about_ca_system_score_gemma":0.001402066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001226617,"about_ca_topic_score_gemma":0.001278794,"domain_scores_codex":[0.9982383,0.0003676695,0.0001460079,0.0003814863,0.0007051698,0.0001612505],"domain_scores_gemma":[0.997191,0.0009309815,0.0002187697,0.0008469391,0.000631637,0.0001808088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0014032,0.0002555515,0.003885852,0.0009243382,0.0001664768,0.0002339513,0.0004327203,0.04434197,0.06225976,0.06431277,0.1067014,0.715082],"study_design_scores_gemma":[0.0003159679,0.0005778402,0.001753275,0.000110726,0.00005184126,0.0007828829,0.0001676066,0.6519503,0.1178334,0.1118869,0.1143462,0.0002229935],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02095841,0.001139685,0.9103141,0.000350193,0.000467328,0.0003513972,0.002382701,0.05623456,0.007801621],"genre_scores_gemma":[0.2345582,0.0004005318,0.7446373,0.0003831976,0.0002590576,0.0004982377,0.006221225,0.003406243,0.00963621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01693837,"threshold_uncertainty_score":0.05666447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413913923","doi":"10.1093/bioadv/vbaf193","title":"Exploration of chaos game representation and integrative deep learning approaches for whole-genome sequencing-based grapevine genetic testing","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Whole genome sequencing; CHAOS (operating system); Representation (politics); Artificial intelligence; Computational biology; Genome; DNA sequencing; Biology; Computer science; Evolutionary biology; Machine learning; Genetics; Gene","authors":[{"name":"Andrew Vu","is_ca":true},{"name":"Brendan Park","is_ca":true},{"name":"Yifeng Li","is_ca":true},{"name":"Ping Liang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1328867625110219,"gpt":0.3066892368213286,"spread":0.1738024743103068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001593954,0.001090521,0.0007712579,0.0007403392,0.0003740664,0.001427242,0.00216909,0.001069847,0.002659797],"category_scores_gemma":[0.004768596,0.0004689544,0.001020641,0.0005000012,0.000578819,0.001668893,0.001520267,0.001837659,0.0004633543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001569747,"about_ca_system_score_gemma":0.001447537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01025,"about_ca_topic_score_gemma":0.01038131,"domain_scores_codex":[0.999491,0.0001747619,0.00002726378,0.0001374613,0.0000957061,0.00007377595],"domain_scores_gemma":[0.9985167,0.0009562097,0.00009231915,0.000133301,0.0002142217,0.00008706841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001827112,0.000238482,0.004808148,0.0001311714,0.0001065718,0.0001971638,0.000137798,0.8764424,0.0037602,0.01226702,0.002530589,0.09919775],"study_design_scores_gemma":[0.000003541635,0.00001310683,0.00007810986,0.000004235784,0.000003386091,0.000005323814,0.000006746903,0.9958587,0.0003999927,0.003444179,0.000179858,0.000002724041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08674359,0.0004962554,0.9035313,0.0009734875,0.00006573535,0.0001539975,0.000533503,0.004456352,0.003045815],"genre_scores_gemma":[0.7010208,0.0002370475,0.2937902,0.0005426427,0.00004107747,0.0003252749,0.001395672,0.0002897852,0.002357455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01025,"threshold_uncertainty_score":0.02038068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409962274","doi":"10.1093/bioadv/vbaf098","title":"<i>bamSliceR</i> : a Bioconductor package for rapid, cross-cohort variant and allelic bias analysis","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"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 Allergy and Infectious Diseases; Hope Foundation; National Institutes of Health; National Cancer Institute; Genome Canada; Van Andel Research Institute","keywords":"Bioconductor; R package; Allele; Cohort; Genetics; Biology; Computational biology; Statistics; Computer science; Medicine; Mathematics; Gene","authors":[{"name":"Yizhou Peter Huang","is_ca":false},{"name":"Lauren Harmon","is_ca":false},{"name":"Eve Gardner","is_ca":false},{"name":"Xiaotu Ma","is_ca":false},{"name":"Josiah Harsh","is_ca":false},{"name":"Zhaoyu Xue","is_ca":false},{"name":"Hong Wen","is_ca":false},{"name":"Marcel Ramos","is_ca":false},{"name":"Sean Davis","is_ca":false},{"name":"Timothy J. Triche","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02104986476681353,"gpt":0.3088681925524286,"spread":0.2878183277856151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01144824,0.005316347,0.00409342,0.005104979,0.001940941,0.005021662,0.009448823,0.002540614,0.1834776],"category_scores_gemma":[0.03469834,0.003220771,0.004359987,0.005706472,0.001741059,0.003453176,0.00580111,0.006071171,0.1449828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001772717,"about_ca_system_score_gemma":0.006816026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008547866,"about_ca_topic_score_gemma":0.01353354,"domain_scores_codex":[0.9948024,0.001270035,0.0005449665,0.001760159,0.001141208,0.0004813835],"domain_scores_gemma":[0.9864466,0.006210429,0.001328618,0.003061224,0.002188635,0.0007645342],"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":[0.0006606361,0.0000633882,0.003000244,0.003175594,0.001105165,0.0003163087,0.0004050937,0.002603209,0.003500032,0.00766982,0.9484396,0.02906096],"study_design_scores_gemma":[0.001661785,0.0002519675,0.01147452,0.002034102,0.001316934,0.001087822,0.0002827047,0.0761434,0.02412562,0.09497623,0.7859688,0.0006761563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002495899,0.001001405,0.2114291,0.001270243,0.001075468,0.0007858558,0.3074285,0.4677104,0.006803308],"genre_scores_gemma":[0.02699541,0.0009705718,0.3710445,0.002800173,0.0003857172,0.008563071,0.2555301,0.319461,0.01424936],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.1834776,"threshold_uncertainty_score":0.6137937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400638857","doi":"10.1093/bioadv/vbae098","title":"loco-pipe: an automated pipeline for population genomics with low-coverage whole-genome sequencing","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"National Institute of General Medical Sciences; North Pacific Research Board","keywords":"Pipeline (software); Genomics; Computer science; Streamlines, streaklines, and pathlines; Population; Set (abstract data type); Pipeline transport; Genome; Computational biology; Biology; Engineering; Genetics; Medicine; Operating system; Gene; Programming language","authors":[{"name":"Zehua T Zhou","is_ca":false},{"name":"Gregory L. Owens","is_ca":true},{"name":"Wesley A. Larson","is_ca":false},{"name":"Runyang Nicolas Lou","is_ca":false},{"name":"Peter H. Sudmant","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0092613412800591,"gpt":0.2608134375166964,"spread":0.2515520962366373,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005268511,0.002173491,0.001862919,0.00245823,0.001621078,0.002674913,0.003580974,0.001412437,0.03570952],"category_scores_gemma":[0.01167732,0.002326324,0.002921171,0.001840069,0.001094177,0.002612645,0.004549201,0.00422691,0.03131896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008843173,"about_ca_system_score_gemma":0.00328438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003004903,"about_ca_topic_score_gemma":0.005161978,"domain_scores_codex":[0.9979891,0.0003724275,0.000145222,0.0008043027,0.0004915826,0.0001973167],"domain_scores_gemma":[0.9963845,0.001586823,0.0003623164,0.0006960665,0.0006254662,0.0003448415],"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":[0.001738307,0.000196057,0.009172753,0.004549984,0.001083813,0.000614134,0.001760623,0.0112988,0.1324856,0.01606878,0.5796013,0.2414297],"study_design_scores_gemma":[0.001049579,0.0003812127,0.01520337,0.0005969519,0.0004926911,0.001157593,0.0003113522,0.1205663,0.125183,0.05601612,0.6783074,0.0007343814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00613911,0.0004807055,0.6989354,0.0004699196,0.0003530217,0.0005375248,0.05450689,0.2341869,0.00439048],"genre_scores_gemma":[0.03208385,0.0004741276,0.7521909,0.001000548,0.0001729545,0.002274775,0.1374216,0.06726786,0.007113366],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03570952,"threshold_uncertainty_score":0.1194603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3179038740","doi":"10.1093/bioadv/vbac033","title":"Sufficient principal component regression for pattern discovery in transcriptomic data","year":2022,"lang":"en","type":"preprint","venue":"Bioinformatics Advances","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","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 British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Subspace topology; Principal component analysis; Context (archaeology); Computer science; Data mining; Regression; Principal component regression; Machine learning; Artificial intelligence; Pattern recognition (psychology); Mathematics; Biology; Statistics","authors":[{"name":"Lei Ding","is_ca":false},{"name":"Gabriel E. Zentner","is_ca":false},{"name":"Daniel J. McDonald","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0465884028724005,"gpt":0.3316644022699577,"spread":0.2850759993975572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008718671,0.001880043,0.002252013,0.002437606,0.0009148821,0.0017616,0.00222493,0.001746604,0.005370094],"category_scores_gemma":[0.04545553,0.001216218,0.001852423,0.003723794,0.002101484,0.00265639,0.002283106,0.003901729,0.005740239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009102399,"about_ca_system_score_gemma":0.003636909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002852281,"about_ca_topic_score_gemma":0.002921645,"domain_scores_codex":[0.9938893,0.003004523,0.0002844089,0.001128426,0.001472963,0.0002203652],"domain_scores_gemma":[0.9763633,0.01739244,0.0009977279,0.002834034,0.001961994,0.0004505242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007180704,0.0003456404,0.006097469,0.001342041,0.0003692704,0.0004518683,0.0002425151,0.5557345,0.009929781,0.09546218,0.04454916,0.2847575],"study_design_scores_gemma":[0.00003061867,0.00002990505,0.0004702323,0.00003801074,0.00001425996,0.00005854672,0.00001534359,0.9254922,0.001417507,0.06980308,0.002614396,0.00001584821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002278398,0.0003332165,0.994165,0.0004564152,0.00003326121,0.00005562184,0.0007279288,0.001541439,0.0004086592],"genre_scores_gemma":[0.1439285,0.001414377,0.8376148,0.0005840682,0.0003856523,0.0009412754,0.01104013,0.001330521,0.002760679],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008718671,"threshold_uncertainty_score":0.04610926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412033208","doi":"10.1093/bioadv/vbaf162","title":"Volcano: a pipeline to characterize long terminal repeat-retrotransposons families in plants","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation, Science and Economic Development Canada","funders":"Beijing Academy of Agricultural and Forestry Sciences; Chinese Academy of Sciences","keywords":"Retrotransposon; Long terminal repeat; Genome; Biology; Pipeline (software); Computational biology; Genetics; Computer science; Gene; Transposable element","authors":[{"name":"Fei Shen","is_ca":true},{"name":"Yong Hou","is_ca":false},{"name":"Xiaozeng Yang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01568206321207271,"gpt":0.2369625222065186,"spread":0.2212804589944458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001156914,0.002123051,0.0007707818,0.002437786,0.001075795,0.001166526,0.001353377,0.0008379339,0.008970122],"category_scores_gemma":[0.002655415,0.0008623814,0.002281394,0.001289331,0.0004645258,0.001549237,0.001241969,0.001120104,0.003888466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008950198,"about_ca_system_score_gemma":0.001332601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005251505,"about_ca_topic_score_gemma":0.00596562,"domain_scores_codex":[0.9995438,0.00005022044,0.00003506975,0.0002181185,0.000095144,0.00005772003],"domain_scores_gemma":[0.9993306,0.0002957913,0.00009514676,0.00008388251,0.0001099464,0.0000845959],"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":[0.003428706,0.0004564187,0.05324189,0.003493943,0.001153385,0.001288121,0.003028689,0.02432789,0.3092259,0.007513368,0.2153193,0.3775224],"study_design_scores_gemma":[0.0008470833,0.0007456836,0.06326465,0.0002648445,0.0005107027,0.001337501,0.000978556,0.5492567,0.1563741,0.01897542,0.2069723,0.000472353],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.06630554,0.0008558254,0.3672434,0.0005301284,0.0001505448,0.0007142241,0.0821604,0.4782313,0.00380866],"genre_scores_gemma":[0.1995642,0.0005344482,0.591001,0.0005183282,0.00009820774,0.001127577,0.1773177,0.02588169,0.003956691],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.008970122,"threshold_uncertainty_score":0.03000802,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313800421","doi":"10.1093/bioadv/vbac099","title":"GlobeCorr: interactive globe-based visualization for correlation datasets","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Health, Environment, Cognitive Aging","field":"Environmental 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":"Public Health Ontario; University of Toronto; McGill University Health Centre; Simon Fraser University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Metadata; Visualization; Computer science; MIT License; Pairwise comparison; Data mining; Correlation; Interactive visualization; Data visualization; Information retrieval; Globe; License; Data science; World Wide Web; Artificial intelligence; Biology","authors":[{"name":"Mariam Arab","is_ca":true},{"name":"Nolan Woods","is_ca":true},{"name":"Emma S. Garlock","is_ca":true},{"name":"Geoffrey L. Winsor","is_ca":true},{"name":"Jaclyn Parks","is_ca":true},{"name":"Baofeng Jia","is_ca":true},{"name":"Dany Doiron","is_ca":true},{"name":"Tim K. Takaro","is_ca":true},{"name":"Jeffrey R. Brook","is_ca":true},{"name":"Fiona S. L. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01610781482344448,"gpt":0.3134939633144855,"spread":0.297386148491041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005472468,0.002799404,0.001812356,0.004678364,0.001365235,0.004516028,0.003754147,0.001692707,0.1145419],"category_scores_gemma":[0.01919118,0.001122407,0.002464475,0.005572009,0.0009900447,0.005013171,0.006493488,0.003122001,0.02835698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000956304,"about_ca_system_score_gemma":0.002334228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006317288,"about_ca_topic_score_gemma":0.008010342,"domain_scores_codex":[0.9978216,0.0005539375,0.0002043596,0.0004765563,0.0007549675,0.0001886582],"domain_scores_gemma":[0.9890627,0.006060927,0.0006064535,0.001899313,0.001713135,0.0006573909],"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":[0.0006816417,0.0001057655,0.002721945,0.001132632,0.0002330474,0.0004415088,0.000754515,0.003106934,0.004912824,0.007380893,0.8986785,0.07984977],"study_design_scores_gemma":[0.001103288,0.0002240521,0.01317596,0.001143067,0.0002985543,0.001228489,0.0006833755,0.13612,0.03067488,0.08082433,0.7338703,0.0006537561],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004612208,0.0004799424,0.2248041,0.00165875,0.0005169341,0.0003819735,0.07721884,0.6786938,0.01163347],"genre_scores_gemma":[0.07582825,0.001307336,0.6047326,0.001880118,0.0004910808,0.002381287,0.1510879,0.1502204,0.01207092],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.1145419,"threshold_uncertainty_score":0.3831808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}