{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":647,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":647,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"432751205d30","filters":{"venue":"BMC Bioinformatics"}},"results":[{"id":"W2136850043","doi":"10.1186/1471-2105-4-2","title":"An automated method for finding molecular complexes in large protein interaction networks","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6293,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Tree traversal; Cluster analysis; Protein Interaction Networks; Protein–protein interaction; Interaction network; Data mining; False positive paradox; Computational biology; Theoretical computer science; Algorithm; Artificial intelligence; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01704138690107336,"gpt":0.3135825610453267,"spread":0.2965411741442533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008997343,0.0002363901,0.0002371794,0.0001087851,0.0001150252,0.00009465058,0.0002147225,0.0002888567,0.00001179752],"category_scores_gemma":[0.00009233052,0.0002315356,0.0001143649,0.0001686101,0.00002622229,0.00003202738,0.00005118409,0.0001568626,0.000006476537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003668456,"about_ca_system_score_gemma":0.00008188895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000542931,"about_ca_topic_score_gemma":0.00008420008,"domain_scores_codex":[0.9984769,0.00009401135,0.0006365868,0.0001910204,0.0001066815,0.0004947993],"domain_scores_gemma":[0.9991334,0.00002840776,0.0002508106,0.0004041817,0.00007530789,0.0001078651],"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":[0.0009009779,0.001099661,0.004445292,0.001629429,0.0003876724,0.000007139286,0.00239739,0.7630863,0.1271462,0.06600556,0.008904559,0.02398982],"study_design_scores_gemma":[0.00117663,0.000236767,0.0001221736,0.00004388008,0.00001379582,0.00001699621,0.0005656385,0.9777964,0.01038232,0.0003127588,0.009015976,0.0003166408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0414704,0.00009914846,0.9562183,0.00001165602,0.0001686785,0.0008847251,0.00003279946,0.00006445131,0.001049828],"genre_scores_gemma":[0.4136006,0.00001054201,0.5852294,0.0003366338,0.00006444182,0.0001102589,0.000560301,0.00003246184,0.00005538687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3721302,"threshold_uncertainty_score":0.9441748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050345155","doi":"10.1186/1471-2105-12-35","title":"VennDiagram: a package for the generation of highly-customizable Venn and Euler diagrams in R","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":3262,"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":"Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Venn diagram; Computer science; Visualization; Process (computing); Data mining; Engineering drawing; Theoretical computer science; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07426646512308042,"gpt":0.2469729188522922,"spread":0.1727064537292118,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005270793,0.0000915918,0.000155377,0.0001047233,0.00006006901,0.00007819667,0.0005026483,0.00004872609,0.000003939677],"category_scores_gemma":[0.0001137257,0.00006156685,0.00004689202,0.0003116105,0.00005469313,0.000658184,0.0001509718,0.00005428112,0.00001426605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001600294,"about_ca_system_score_gemma":0.0000434027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006256139,"about_ca_topic_score_gemma":0.0002449992,"domain_scores_codex":[0.9991896,0.00002263628,0.0003721202,0.0001024273,0.0001373378,0.0001758968],"domain_scores_gemma":[0.9990003,0.0001713939,0.0001840527,0.0005535925,0.00005205018,0.00003863499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001377777,0.0009115135,0.0748143,0.001638689,0.0004018249,0.000007791928,0.07465129,0.002728878,0.001093994,0.4099987,0.03626603,0.3973492],"study_design_scores_gemma":[0.0004094891,0.00005744044,0.005492472,0.00001361913,0.00002263812,0.000002584316,0.0001367923,0.9904212,0.001483092,0.0005983244,0.001260914,0.0001013997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008552843,0.0001194929,0.9904323,0.00005645338,0.0001307298,0.0002927179,0.00001565787,0.00002261435,0.0003771832],"genre_scores_gemma":[0.362869,0.00008686276,0.6366571,0.0001693182,0.00004499404,0.00006863374,0.0000346327,0.000008695185,0.00006076527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9876924,"threshold_uncertainty_score":0.2510623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099753867","doi":"10.1186/1471-2105-12-491","title":"MAKER2: an annotation pipeline and genome-database management tool for second-generation genome projects","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2312,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Division of Integrative Organismal Systems; National Institute of General Medical Sciences; National Human Genome Research Institute; University of Utah; Agricultural Research Service; San Francisco State University; Michigan State University; College of Engineering, Michigan State University; U.S. Department of Agriculture; National Institutes of Health; National Science Foundation","keywords":"Annotation; Genome; Genome project; Gene Annotation; Computer science; DNA sequencing; Pipeline (software); Genome browser; Computational biology; Genomics; Database; Data mining; Biology; Gene; Genetics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04623520706017015,"gpt":0.2460322174434468,"spread":0.1997970103832766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002232464,0.0001609063,0.0001179085,0.00005592571,0.0001273897,0.00003614583,0.0001038847,0.00007498726,0.00001123633],"category_scores_gemma":[0.00001826065,0.0001521323,0.00004139064,0.00004446413,0.00004015757,0.000007702984,0.0001062567,0.00002854742,0.000005101242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009658479,"about_ca_system_score_gemma":0.00003062061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002747331,"about_ca_topic_score_gemma":0.00007850584,"domain_scores_codex":[0.9991919,0.00001590813,0.000313341,0.0002016441,0.00007191843,0.0002053295],"domain_scores_gemma":[0.9994278,0.000005368997,0.0001187836,0.000295952,0.00009476463,0.00005736403],"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":[0.0004428236,0.0003253691,0.003056918,0.00164841,0.0003150915,0.000002328215,0.006073337,0.0004085941,0.9678783,0.002341437,0.001452264,0.01605514],"study_design_scores_gemma":[0.01383444,0.007578633,0.2313678,0.0000980104,0.001002753,0.0001721083,0.01344617,0.2295362,0.2523854,0.00131793,0.2437314,0.005529086],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8587013,0.0004689119,0.1376608,0.000009914281,0.0001374513,0.001100164,0.0003948396,0.000009951604,0.001516612],"genre_scores_gemma":[0.540343,0.0004162661,0.4558925,0.0004210395,0.0003108813,0.0001868933,0.001594048,0.00003077434,0.000804621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7154928,"threshold_uncertainty_score":0.6203775,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132548846","doi":"10.1186/1471-2105-13-31","title":"PANDAseq: paired-end assembler for illumina sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":2221,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Amplicon; Computer science; Sequence (biology); Error detection and correction; k-mer; Amplicon sequencing; Sequence assembly; Computational biology; DNA sequencing; Biology; Genetics; Algorithm; DNA; 16S ribosomal RNA; Polymerase chain reaction; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03929258653023519,"gpt":0.2637107171785696,"spread":0.2244181306483344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004521625,0.0001088532,0.0001333017,0.00001926313,0.0002547201,0.00001292735,0.0002425482,0.0001199068,0.002768635],"category_scores_gemma":[0.00006869195,0.00009035718,0.00006172842,0.00008238534,0.0002322694,0.0004377715,0.0001592288,0.00008162004,0.001045357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005627611,"about_ca_system_score_gemma":0.00001621319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004740276,"about_ca_topic_score_gemma":0.000287877,"domain_scores_codex":[0.9992252,0.00005508672,0.0002218603,0.00005741331,0.0000684823,0.0003719473],"domain_scores_gemma":[0.9993553,0.0002170951,0.0001008008,0.0002309808,0.000006682732,0.00008917871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002164227,0.0007774482,0.5860749,0.0005997251,0.0001014743,7.375145e-7,0.02198276,0.00204185,0.01637383,0.004773208,0.3408138,0.02624388],"study_design_scores_gemma":[0.001712412,0.0007426052,0.2585676,0.00004065657,0.00009889065,0.00007507234,0.004213726,0.07457469,0.005212689,0.004660578,0.6487635,0.001337521],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9446518,0.00003598182,0.02057108,0.0001339736,0.000593851,0.0005420264,0.00005960488,0.00008571318,0.03332596],"genre_scores_gemma":[0.8885947,0.00001492932,0.1093696,0.001010532,0.00008647506,0.00003476553,0.0001119779,0.000009893317,0.0007671366],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3275073,"threshold_uncertainty_score":0.9997324,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142056356","doi":"10.1186/1471-2105-3-2","title":"The Comparative RNA Web (CRW) Site: an online database of comparative sequence and structure information for ribosomal, intron, and other RNAs","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1643,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Dalhousie University","funders":"National Institute of General Medical Sciences; University of Texas at Austin; Welch Foundation; National Institutes of Health; National Science Foundation","keywords":"Intron; RNA; Biology; Phylogenetic tree; Nucleic acid structure; Computational biology; Ribosomal RNA; Genetics; Nucleic acid secondary structure; Sequence (biology); Database; Gene; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06946269515937568,"gpt":0.2973266295758393,"spread":0.2278639344164636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001457562,0.000159545,0.0001862554,0.00003289221,0.0001689739,0.00006508346,0.000144923,0.000101245,0.00001020412],"category_scores_gemma":[0.00004791582,0.0001102864,0.00002921935,0.00005301418,0.000193713,0.00006691465,0.00007280901,0.00006249106,0.000002162067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006086358,"about_ca_system_score_gemma":0.00002954502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006128728,"about_ca_topic_score_gemma":0.0001468764,"domain_scores_codex":[0.9992123,0.00004684318,0.0003679567,0.00009861321,0.0001130261,0.0001612874],"domain_scores_gemma":[0.9991968,0.00006302892,0.0002806072,0.0002712866,0.0001178944,0.00007041141],"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":[0.0009602933,0.0001844733,0.00148622,0.001062635,0.0002824459,2.997416e-7,0.01621181,0.0006026751,0.9309926,0.009886715,0.006157303,0.03217251],"study_design_scores_gemma":[0.002187353,0.001344219,0.0004245075,0.00009851771,0.00007899643,0.00004176926,0.006977678,0.4919085,0.4217196,0.0005174453,0.0741449,0.0005564716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9583225,0.0008856179,0.03690265,0.00006633882,0.00007041656,0.0008514258,0.002566267,0.00001251096,0.0003222437],"genre_scores_gemma":[0.8926252,0.0003408097,0.1060242,0.0002895767,0.00007931481,0.00002568941,0.0005523161,0.000009465443,0.00005338749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.509273,"threshold_uncertainty_score":0.449735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903125175","doi":"10.1186/s12859-018-2485-7","title":"Purge Haplotigs: allelic contig reassignment for third-gen diploid genome assemblies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1285,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Wine Australia; Australian Government; Alberta Water Research Institute; Bioplatforms Australia","keywords":"Contig; Genome; Ploidy; Biology; Haplotype; Genetics; Sequence assembly; Purge; Computational biology; Allele; Gene; Transcriptome","retraction":null,"screen_n_in":null,"score":{"opus":0.02474087615458948,"gpt":0.2563884776234654,"spread":0.2316476014688759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002604041,0.0002377304,0.0002312506,0.00005099885,0.0002274636,0.00006294806,0.0002981121,0.0001536974,0.0000102888],"category_scores_gemma":[0.0001047592,0.0002069302,0.0001540772,0.00006276802,0.0001565112,0.000003069931,0.0002176276,0.00004491089,0.00005094955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001990191,"about_ca_system_score_gemma":0.00009571228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007320576,"about_ca_topic_score_gemma":0.00006933269,"domain_scores_codex":[0.9987844,0.00001890556,0.0004354238,0.0002188328,0.0001447861,0.0003976999],"domain_scores_gemma":[0.9990167,0.0000281226,0.0001818477,0.0004671145,0.0001968409,0.0001093672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005890168,0.0003561572,0.006812378,0.0006917991,0.001174144,0.000001140371,0.002642999,0.0003892213,0.7636471,0.001924373,0.2183016,0.003470019],"study_design_scores_gemma":[0.001518819,0.001327854,0.01049988,0.00001945726,0.00009618526,0.00001442412,0.0009748314,0.002693946,0.04431712,0.0004634516,0.9373907,0.0006833439],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7860372,0.003723718,0.1745552,0.0004508551,0.001759093,0.003608725,0.008016101,0.00008700963,0.02176212],"genre_scores_gemma":[0.8201049,0.001303849,0.1677058,0.002449184,0.002208838,0.0004468965,0.003487411,0.0001012254,0.002191874],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.71933,"threshold_uncertainty_score":0.8438367,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594844287","doi":"10.1186/s12859-017-1559-2","title":"Reactome pathway analysis: a high-performance in-memory approach","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":927,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; European Bioinformatics Institute","keywords":"Computer science; DNA microarray; Computational biology; Biology; Genetics; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01424369254937085,"gpt":0.2266288534852671,"spread":0.2123851609358962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005338714,0.000258028,0.0003455399,0.0001817562,0.0002698549,0.0001982636,0.0007681972,0.0002924935,0.000008564676],"category_scores_gemma":[0.00005881764,0.0002287745,0.0001613362,0.0001759722,0.0001441312,0.0000355265,0.0003477026,0.0002015175,0.00004594328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002721529,"about_ca_system_score_gemma":0.000124857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003799241,"about_ca_topic_score_gemma":0.0001304698,"domain_scores_codex":[0.9984741,0.00001918148,0.0006361344,0.0002162872,0.000204233,0.0004500945],"domain_scores_gemma":[0.9978706,0.000009908904,0.0004751769,0.001461385,0.00006250152,0.0001203789],"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":[0.001182075,0.001396407,0.5115099,0.003434364,0.003736941,0.00001839541,0.005962952,0.2159395,0.004798322,0.005198833,0.004659925,0.2421623],"study_design_scores_gemma":[0.002366341,0.0002564051,0.2659318,0.00005451665,0.0002023214,0.00002572078,0.0007231585,0.719676,0.002767647,0.0001203931,0.006887678,0.0009880355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8373311,0.0002667982,0.09567266,0.00004926585,0.0003745451,0.0005661005,0.00006353035,0.00004028272,0.06563574],"genre_scores_gemma":[0.9395639,0.0001239559,0.05889128,0.0002045799,0.0001681358,0.0000303705,0.0003176542,0.00001888262,0.0006812011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5037365,"threshold_uncertainty_score":0.9329152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111607030","doi":"10.1186/1471-2105-10-202","title":"NLStradamus: a simple Hidden Markov Model for nuclear localization signal prediction","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":719,"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":"Nuclear localization sequence; NLS; Hidden Markov model; Nuclear transport; Markov chain; Computational biology; Simple (philosophy); Computer science; Set (abstract data type); Markov model; Artificial intelligence; Biology; Machine learning; Genetics; Cell nucleus; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01034064885787714,"gpt":0.2196102180540038,"spread":0.2092695691961267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008165409,0.0001213351,0.00009190753,0.00003839135,0.0001296215,0.00004304642,0.00009594805,0.0001767636,0.00001942086],"category_scores_gemma":[0.000025401,0.0001146512,0.00008266368,0.00005727396,0.00002279919,0.00001854944,0.00002033716,0.00004816871,0.000008588839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001657183,"about_ca_system_score_gemma":0.00003800949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.882262e-7,"about_ca_topic_score_gemma":0.000003858069,"domain_scores_codex":[0.9993367,0.000008112066,0.0002495621,0.0001242989,0.0001076448,0.0001736449],"domain_scores_gemma":[0.999579,0.000003961866,0.00009477082,0.000193809,0.00007029054,0.00005815989],"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":[0.002598208,0.0003507094,0.001155102,0.0006926798,0.0002121502,7.429394e-7,0.002192993,0.1279342,0.06004418,0.006468222,0.3532727,0.4450782],"study_design_scores_gemma":[0.0005257229,0.0004170691,0.0003963802,0.000006337794,0.00002838573,0.000009579596,0.0001119004,0.9812803,0.0008518189,0.0007320359,0.01550229,0.0001381691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02341065,0.00002708068,0.9742236,0.00004301744,0.0000977616,0.0003253476,0.00008895742,0.00005539286,0.001728248],"genre_scores_gemma":[0.7820001,0.00004057433,0.2141764,0.001534693,0.0004325156,0.00000774197,0.001449674,0.00003497381,0.0003233043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8533461,"threshold_uncertainty_score":0.467534,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070040136","doi":"10.1186/1471-2105-12-436","title":"clusterMaker: a multi-algorithm clustering plugin for Cytoscape","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":669,"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":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Cluster analysis; Computer science; Interactome; Plug-in; Hierarchical clustering; Computational biology; Visualization; Dendrogram; Data mining; Bioinformatics; Biology; Machine learning; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03728483425002162,"gpt":0.2498073105875191,"spread":0.2125224763374975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003157591,0.0002783598,0.0002326256,0.00007188199,0.0001566773,0.00005553394,0.0003622229,0.0002859443,0.00002304335],"category_scores_gemma":[0.0000366641,0.0002577765,0.0002014773,0.00008293785,0.00008335086,0.00002038381,0.00025736,0.0001110647,0.00005453952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002016381,"about_ca_system_score_gemma":0.00009439394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006990816,"about_ca_topic_score_gemma":0.00006708899,"domain_scores_codex":[0.9985479,0.00001527749,0.0006297298,0.0001899383,0.000118873,0.0004983266],"domain_scores_gemma":[0.9989609,0.00001612569,0.0002466726,0.0005156308,0.0001032196,0.0001575078],"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":[0.001795027,0.00132461,0.004746457,0.004384513,0.001285421,0.00001008569,0.01906536,0.006338171,0.007484677,0.002181243,0.066945,0.8844394],"study_design_scores_gemma":[0.001968849,0.0003181995,0.0003686843,0.00003367214,0.00004116826,0.00005005617,0.0006320843,0.9635848,0.002402573,0.0001047393,0.03000211,0.0004931051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00181527,0.0001695465,0.9932709,0.00001067866,0.0004263948,0.0006651672,0.0001105475,0.00004490454,0.003486563],"genre_scores_gemma":[0.0103097,0.00007728738,0.9873353,0.000672279,0.0002794267,0.00009183679,0.0003105745,0.00004608403,0.0008774645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9572466,"threshold_uncertainty_score":0.9999874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150756255","doi":"10.1186/1471-2105-10-106","title":"flowCore: a Bioconductor package for high throughput flow cytometry","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":651,"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; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Data mining; Data management; Throughput; Automation; Data science; Data flow diagram; Software engineering; Database; Operating system; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02186983869540404,"gpt":0.2510222181838827,"spread":0.2291523794884787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001738007,0.0002515716,0.0002380555,0.00007370491,0.0001262845,0.00007210846,0.000291342,0.0002711006,0.00001859632],"category_scores_gemma":[0.0001232656,0.0002217256,0.0001874048,0.00015816,0.00006438914,0.00001755883,0.00003557367,0.00009433247,0.00003321344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000212247,"about_ca_system_score_gemma":0.000105425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004280323,"about_ca_topic_score_gemma":0.00001139533,"domain_scores_codex":[0.9987882,0.00001650545,0.0004293152,0.0002224677,0.0001540972,0.0003894346],"domain_scores_gemma":[0.9991469,0.00002424885,0.0001169423,0.0004895705,0.0001053571,0.0001170218],"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":[0.000920502,0.0007132714,0.002622014,0.0008249846,0.0002325339,0.000003751617,0.0008226311,0.0005247357,0.8889667,0.003291448,0.04044103,0.0606364],"study_design_scores_gemma":[0.006540593,0.003310715,0.003986221,0.00009211194,0.0001611871,0.00005532229,0.0004013524,0.05524718,0.8594603,0.002109128,0.06694614,0.001689779],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2506156,0.0002771928,0.7462328,0.0001462983,0.0006794593,0.0006626701,0.0002748834,0.0000714894,0.001039571],"genre_scores_gemma":[0.5172663,0.0001109683,0.4787593,0.001713307,0.0006471489,0.00002633839,0.000916654,0.00003612833,0.0005238588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2674735,"threshold_uncertainty_score":0.9041709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109327803","doi":"10.1186/1471-2105-3-35","title":"FunSpec: a web-based cluster interpreter for yeast","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":409,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Genome Canada","keywords":"Cluster analysis; Categorical variable; Interpreter; Gene; Computational biology; Computer science; Exposition (narrative); Interpretation (philosophy); DNA microarray; Biology; Genetics; Artificial intelligence; Gene expression; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01484499009857399,"gpt":0.2245644029157306,"spread":0.2097194128171566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001931029,0.0002218992,0.0001788321,0.0000648291,0.00009730881,0.00008310643,0.00027875,0.0002269912,0.00009924559],"category_scores_gemma":[0.00004915379,0.000195219,0.000211427,0.00007205742,0.00007753382,0.0000125344,0.00009853778,0.00009438193,0.0001671489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001899862,"about_ca_system_score_gemma":0.00004460746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.5931e-7,"about_ca_topic_score_gemma":0.0000187832,"domain_scores_codex":[0.9988454,0.00001427663,0.0004878202,0.0001503239,0.000122495,0.000379697],"domain_scores_gemma":[0.9991286,0.00002480441,0.0001705208,0.0004725351,0.00008380745,0.000119694],"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":[0.0007205938,0.0003668204,0.002254962,0.001652382,0.0003104802,0.000001219702,0.001273601,0.009354972,0.004744211,0.001293988,0.9013414,0.07668534],"study_design_scores_gemma":[0.001495806,0.0002321534,0.0000332407,0.00002731622,0.00002163476,0.000009195222,0.00007630511,0.7882516,0.0008832996,0.00005551377,0.2086414,0.0002725453],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01258126,0.0003061009,0.9618547,0.0002407722,0.0006439381,0.0009799658,0.0002513923,0.00006694281,0.02307491],"genre_scores_gemma":[0.5805234,0.00008248194,0.4061393,0.007504635,0.0008340181,0.000180926,0.0006133572,0.00008537542,0.004036556],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7788966,"threshold_uncertainty_score":0.7960799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139259976","doi":"10.1186/1471-2105-4-11","title":"PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":340,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; National Research Council Canada; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Directorate for Biological Sciences; Genome Canada","keywords":"Computer science; Support vector machine; Set (abstract data type); Task (project management); Interaction information; Precision and recall; Recall; Data curation; Interaction network; Artificial intelligence; Protein–protein interaction; Data mining; Machine learning; Database; Information retrieval; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02721208388926301,"gpt":0.2967162964898785,"spread":0.2695042126006155,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003388593,0.0001737139,0.0001518127,0.0000546101,0.0002082324,0.00009160917,0.000149585,0.0002009731,0.00001706475],"category_scores_gemma":[0.0006519047,0.0001119113,0.00008044734,0.0001333257,0.0002301675,0.00001100237,0.00007879123,0.0001462144,0.000003065898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001145068,"about_ca_system_score_gemma":0.0001309635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003060014,"about_ca_topic_score_gemma":0.00001119694,"domain_scores_codex":[0.9990563,0.00004765359,0.0003208321,0.0001670287,0.0001312918,0.0002768908],"domain_scores_gemma":[0.999403,0.00004020818,0.0001291501,0.0002587303,0.00006314738,0.0001057663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001673043,0.001397953,0.007672831,0.00697523,0.001455485,0.00003092031,0.02226786,0.0000810666,0.6320181,0.008468716,0.04537751,0.2725813],"study_design_scores_gemma":[0.003091468,0.001521581,0.0005303692,0.0004715834,0.0001226679,0.0005854395,0.002677689,0.04978728,0.04521612,0.0004898623,0.8946756,0.0008303676],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6141729,0.001295592,0.3804178,0.0005390355,0.0004198246,0.001799626,0.0003144123,0.00006521505,0.0009755974],"genre_scores_gemma":[0.4667232,0.00001367464,0.5308076,0.0003250174,0.0002158819,0.0001609164,0.0003576061,0.00002934719,0.001366794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8492981,"threshold_uncertainty_score":0.4563612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338215681","doi":"10.1186/s12859-016-1015-8","title":"BAGEL: a computational framework for identifying essential genes from pooled library screens","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":325,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Computational biology; DNA microarray; Gene; Computer science; Biology; Genetics; Bioinformatics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01657515414873308,"gpt":0.3018650987314888,"spread":0.2852899445827558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005860726,0.0001401152,0.0001190808,0.00004230714,0.00007101714,0.00006150793,0.0001766697,0.0001495563,0.00005127993],"category_scores_gemma":[0.00008013672,0.0001108725,0.0001158388,0.0000510658,0.00003850888,0.00001806732,0.0001168217,0.00003783796,0.00002639047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004843677,"about_ca_system_score_gemma":0.00006150624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001507024,"about_ca_topic_score_gemma":0.00000382619,"domain_scores_codex":[0.9992265,0.0000101111,0.0002883198,0.0001488305,0.0001161725,0.0002101384],"domain_scores_gemma":[0.9994808,0.00009342258,0.00008110437,0.0002290969,0.0000379318,0.00007765224],"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":[0.001508456,0.0004623228,0.04078789,0.001993165,0.00215821,0.000009460006,0.002046474,0.08496304,0.5888955,0.0295989,0.05785177,0.1897248],"study_design_scores_gemma":[0.005326988,0.0004305218,0.01579257,0.0005670581,0.0002926408,0.00002928832,0.000854621,0.2711196,0.6229974,0.02620051,0.05460589,0.001782915],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04372719,0.0004565919,0.9548656,0.0001068535,0.000242309,0.0001890735,0.000251213,0.00004245027,0.0001186647],"genre_scores_gemma":[0.1527039,0.00007863274,0.8458704,0.0001860733,0.0005023561,0.00002204468,0.0004307829,0.00003014713,0.0001755779],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1879419,"threshold_uncertainty_score":0.4521248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125456570","doi":"10.1186/1471-2105-11-461","title":"Pan-genome sequence analysis using Panseq: an online tool for the rapid analysis of core and accessory genomic regions","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Escherichia coli research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":306,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge; Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada; Canadian Food Inspection Agency","keywords":"Genome; Biology; Genetics; Multilocus sequence typing; Locus (genetics); Population; Phylogenetic tree; Bacterial genome size; Reference genome; Whole genome sequencing; Computational biology; Gene; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.1134047475220261,"gpt":0.3565360867214132,"spread":0.2431313391993871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004480929,0.0001512527,0.0003159206,0.0002153671,0.0002150368,0.00004772189,0.0003638589,0.0001175064,0.000009120797],"category_scores_gemma":[0.0002858093,0.0001084008,0.0002434858,0.0007649867,0.0003153761,0.00001811621,0.0002167655,0.0001216372,2.391671e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001173905,"about_ca_system_score_gemma":0.0001426895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004794443,"about_ca_topic_score_gemma":0.001528589,"domain_scores_codex":[0.9989987,0.00002951801,0.0003969703,0.0001773125,0.000151783,0.0002457403],"domain_scores_gemma":[0.9986748,0.0001247801,0.0002441448,0.0006559424,0.0002347933,0.00006559765],"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":[0.0001425869,0.0001272891,0.0661876,0.0002189346,0.007857469,4.472685e-7,0.00101851,0.009854112,0.9091824,0.0002128843,0.00003838697,0.005159339],"study_design_scores_gemma":[0.0003203705,0.0001543721,0.1571519,0.00000327979,0.003875615,0.000003030344,0.001103459,0.8344489,0.001100617,0.00002289286,0.001582941,0.0002326429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9482881,0.0003313523,0.05034728,0.00003269931,0.0000360147,0.0003311243,0.0006034302,0.000007675214,0.00002235907],"genre_scores_gemma":[0.9115314,0.0006292742,0.08690128,0.000120943,0.00007601946,0.00002750075,0.0006433488,0.0000127898,0.00005744216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9080818,"threshold_uncertainty_score":0.4420458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162224067","doi":"10.1186/1471-2105-9-340","title":"RNA STRAND: The RNA Secondary Structure and Statistical Analysis Database","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":287,"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; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"RNA; Nucleic acid secondary structure; Database; Protein secondary structure; Computer science; Nucleic acid structure; Computational biology; Biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01374187862728997,"gpt":0.2343050137810196,"spread":0.2205631351537296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001694404,0.000154498,0.000173522,0.00004936745,0.0002047841,0.00003809218,0.0001891256,0.0001173488,0.0002474762],"category_scores_gemma":[0.00007950998,0.0001022679,0.0000725412,0.0001272237,0.0001507111,0.00001129465,0.00009932838,0.000109749,0.00001264757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004318281,"about_ca_system_score_gemma":0.00009055339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001245731,"about_ca_topic_score_gemma":0.00004363212,"domain_scores_codex":[0.9991556,0.00005177824,0.0002722302,0.0001493576,0.0001714573,0.0001995972],"domain_scores_gemma":[0.9992825,0.00004611557,0.0000976173,0.000439001,0.00003664665,0.00009816491],"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":[0.00132819,0.0002978783,0.0148869,0.001513218,0.005379991,0.00008207325,0.005142096,0.001842083,0.7510763,0.01161777,0.06910352,0.13773],"study_design_scores_gemma":[0.003971832,0.0009732691,0.03465687,0.00005249299,0.002093477,0.0006207191,0.002235142,0.06455161,0.8120874,0.001585524,0.07499057,0.00218114],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4763693,0.0007796486,0.5178553,0.00006892575,0.000128835,0.0003602727,0.001648636,0.00002170896,0.002767408],"genre_scores_gemma":[0.8419263,0.0004519427,0.1555996,0.000515868,0.0001352941,0.00001066688,0.0007658645,0.00001751731,0.0005769727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.365557,"threshold_uncertainty_score":0.4170366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129978006","doi":"10.1186/1471-2105-9-329","title":"Evaluation of genomic island predictors using a comparative genomics approach","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":284,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Genome Canada; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Genome; Identification (biology); Comparative genomics; Genomics; Computational biology; Precision and recall; Computer science; Sequence (biology); Data mining; Biology; Genetics; Artificial intelligence; Gene; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.1005527452698731,"gpt":0.2917008819532804,"spread":0.1911481366834074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005625109,0.0001427954,0.0001855383,0.00007335793,0.00007757403,0.000009155508,0.0001605254,0.0001060337,0.00001513211],"category_scores_gemma":[0.0000283122,0.000135919,0.00007826338,0.00008275979,0.0001139725,0.000008922517,0.00008926752,0.00005152831,0.00001042609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006866021,"about_ca_system_score_gemma":0.00036526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008225478,"about_ca_topic_score_gemma":0.00001091961,"domain_scores_codex":[0.998863,0.00006745775,0.0003827443,0.0001275595,0.0003822313,0.0001770041],"domain_scores_gemma":[0.9991419,0.00000604198,0.0002361695,0.0002935133,0.0002708802,0.00005148127],"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":[0.0002348524,0.0006762795,0.05345631,0.0006661546,0.001289915,8.285951e-7,0.02007513,0.5134171,0.4046077,0.0000558897,0.003124772,0.002395115],"study_design_scores_gemma":[0.001260822,0.0001340355,0.00835692,0.000005453959,0.0001553176,0.00004250646,0.0008964478,0.9764179,0.01167548,0.00001630187,0.0008329764,0.0002058089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8962848,0.0004488592,0.0993044,8.383773e-7,0.00005901685,0.0004822401,0.00004688721,0.000006813159,0.003366181],"genre_scores_gemma":[0.8089316,0.00007856076,0.1904831,0.00001315728,0.0001014884,0.00001460812,0.0003049302,0.0000150333,0.00005747755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4630008,"threshold_uncertainty_score":0.5542615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080569293","doi":"10.1186/1471-2105-10-442","title":"G+C content dominates intrinsic nucleosome occupancy","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Genome Canada; Ontario Genomics; Ontario Genomics Institute; Canadian Institute for Advanced Research; Howard Hughes Medical Institute","keywords":"Nucleosome; Chromatin; Linker DNA; Biology; DNA; Genome; Genetics; Histone; DNA sequencing; GC-content; Computational biology; DNA microarray; Sequence (biology); Biophysics; Biological system; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01536453061776141,"gpt":0.225525571516338,"spread":0.2101610408985766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001128684,0.0001726791,0.0001582903,0.00004343628,0.00007619507,0.00005616419,0.0002429892,0.0001375685,0.00001630542],"category_scores_gemma":[0.0000570066,0.0001548882,0.0001064894,0.00006348342,0.0000447066,0.00000793044,0.00007797838,0.00007407281,0.00009994175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001818133,"about_ca_system_score_gemma":0.00006185177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002247818,"about_ca_topic_score_gemma":0.000007258182,"domain_scores_codex":[0.9991086,0.00001191874,0.0003640814,0.0001351383,0.0001118006,0.0002684435],"domain_scores_gemma":[0.9992939,0.00000761551,0.0001395503,0.0003908212,0.00007438016,0.00009370336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001262095,0.001823023,0.0562031,0.001249437,0.0005901475,0.00002839898,0.00364936,0.002875396,0.4148111,0.04572724,0.05222027,0.4195604],"study_design_scores_gemma":[0.01540316,0.006724393,0.362086,0.0003280775,0.0003239177,0.0005749869,0.005945148,0.2996205,0.1343221,0.007670471,0.1614988,0.005502504],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9751455,0.0003230651,0.01752552,0.0001163452,0.0002069237,0.0002685428,0.00003486549,0.00003702086,0.00634224],"genre_scores_gemma":[0.9158555,0.0002102525,0.08199435,0.001000616,0.000155491,0.000006200853,0.0001964002,0.00001675544,0.0005643738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4140579,"threshold_uncertainty_score":0.6316159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144847592","doi":"10.1186/1471-2105-15-35","title":"Inferring clonal evolution of tumors from single nucleotide somatic mutations","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sinai Health System; University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genetics; Biology; Somatic cell; DNA microarray; Somatic evolution in cancer; Computational biology; Mutation; Nucleotide; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01003790526440334,"gpt":0.2169162751917296,"spread":0.2068783699273262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001033318,0.0001085819,0.0001368768,0.00004954726,0.0000547612,0.00002243953,0.0001340928,0.0000772809,0.00001396566],"category_scores_gemma":[0.0002508591,0.0001121266,0.00007646469,0.00005988619,0.00006782092,0.000008222251,0.00008700718,0.00004454186,0.0000282882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003682816,"about_ca_system_score_gemma":0.0001142943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007185635,"about_ca_topic_score_gemma":0.0001540561,"domain_scores_codex":[0.9992273,0.0000129098,0.0003944668,0.00009658092,0.0001175936,0.0001511274],"domain_scores_gemma":[0.9993205,0.00006851269,0.0002043117,0.0002761137,0.00006754982,0.00006300597],"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":[0.0002911541,0.00105779,0.28195,0.001505219,0.0004257719,0.000001896916,0.003555122,0.09374399,0.5589092,0.02078397,0.006868924,0.03090698],"study_design_scores_gemma":[0.002938571,0.001028361,0.0858464,0.0002693008,0.000189873,0.00001793291,0.002012526,0.7062094,0.1740765,0.01163427,0.01473505,0.001041825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7457348,0.0001059908,0.2516134,0.00001269294,0.0001639197,0.0001048665,0.00008424313,0.00001184417,0.002168287],"genre_scores_gemma":[0.9246954,0.00001273802,0.07473799,0.00007590318,0.0001902622,0.000006197439,0.0002448597,0.00001334884,0.00002332593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6124654,"threshold_uncertainty_score":0.4572391,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159835316","doi":"10.1186/1471-2105-8-242","title":"Improving gene set analysis of microarray data by SAM-GS","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":263,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Astellas Pharma; Genome Alberta; Canada Research Chairs; Muttart Foundation; University of Alberta; Fondation pour la Recherche Médicale; Roche Organ Transplant Research Foundation; Kidney Foundation of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Gene; Microarray analysis techniques; DNA microarray; Biology; Computational biology; Microarray; Genetics; Gene expression; Gene expression profiling; Significance analysis of microarrays; Phenotype; Microarray databases; Biological pathway","retraction":null,"screen_n_in":null,"score":{"opus":0.01877831092716567,"gpt":0.2585670723938918,"spread":0.2397887614667261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034016,0.0002151977,0.0003270638,0.000169451,0.00007709195,0.00004175743,0.0007520979,0.0002593282,0.00001828293],"category_scores_gemma":[0.00006852375,0.0001977847,0.0001589894,0.0004400599,0.0001062176,0.00002194544,0.000505063,0.0001136845,0.0000146901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001675148,"about_ca_system_score_gemma":0.00009302506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004370524,"about_ca_topic_score_gemma":0.0001572874,"domain_scores_codex":[0.9982576,0.00001450888,0.0009066202,0.0002128616,0.0002025095,0.0004059081],"domain_scores_gemma":[0.9979002,0.00003396072,0.0004958962,0.001337358,0.00009781831,0.0001347167],"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":[0.0005077564,0.0004216986,0.04367388,0.001322794,0.00655836,0.000003392567,0.00233337,0.006668683,0.5773426,0.0003675364,0.2531366,0.1076634],"study_design_scores_gemma":[0.001602454,0.0002925129,0.00324626,0.00002748456,0.001593116,0.00002523556,0.001754068,0.7898915,0.1055094,0.00002533758,0.09492117,0.001111537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09986679,0.0008175154,0.8964236,0.00001328667,0.0001292388,0.0002154042,0.00126716,0.00001691174,0.001250138],"genre_scores_gemma":[0.4164809,0.000424493,0.5523283,0.0009862244,0.0003130683,0.000005507182,0.02861114,0.00005608367,0.0007942995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7832228,"threshold_uncertainty_score":0.8065426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1640378004","doi":"10.1186/1471-2105-6-30","title":"An ant colony optimisation algorithm for the 2D and 3D hydrophobic polar protein folding problem","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":261,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein folding; Polar; Protein structure prediction; Computer science; Folding (DSP implementation); Ant colony optimization algorithms; Ant colony; Computational biology; DNA microarray; Algorithm; Chemistry; Artificial intelligence; Protein structure; Biology; Engineering; Biochemistry; Physics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.007372782569299728,"gpt":0.2365800328822989,"spread":0.2292072503129991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002507653,0.0001488891,0.0001072135,0.00002895459,0.0002080407,0.00007922498,0.0001682205,0.0001529075,0.000002626926],"category_scores_gemma":[0.00002292947,0.0001071752,0.00004695205,0.00004914349,0.00006665617,0.00002508591,0.00006061864,0.00007124827,0.00000206759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000192759,"about_ca_system_score_gemma":0.00007488898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000110623,"about_ca_topic_score_gemma":0.0000440769,"domain_scores_codex":[0.9992546,0.00001769645,0.0002611971,0.0001390977,0.0001042556,0.0002231257],"domain_scores_gemma":[0.999436,0.0000155733,0.0001344909,0.0002887321,0.00006003063,0.00006521893],"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":[0.0002153562,0.0001366685,0.0004737268,0.0005155514,0.0001691747,7.340424e-7,0.001486767,0.01675628,0.1956011,0.001400112,0.0009532417,0.7822914],"study_design_scores_gemma":[0.0006051107,0.0004086123,0.00008669282,0.00001499713,0.00003021792,0.00002380365,0.0001655332,0.9609353,0.02053837,0.0001750735,0.01681608,0.0002001945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09500834,0.0005614203,0.9025057,0.0001059318,0.00005150385,0.001468714,0.00007537123,0.00002609004,0.0001969395],"genre_scores_gemma":[0.08826487,0.00007821541,0.9106774,0.0002637491,0.0002678452,0.0001250222,0.0001795608,0.00001921995,0.0001241392],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9441791,"threshold_uncertainty_score":0.4370479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030006812","doi":"10.1186/1471-2105-10-99","title":"Markov clustering versus affinity propagation for the partitioning of protein interaction graphs","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":234,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Cluster analysis; Computer science; Markov chain; Affinity propagation; Partition (number theory); Theoretical computer science; Data mining; Machine learning; Correlation clustering; Mathematics; Canopy clustering algorithm; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.02334492071945516,"gpt":0.2621829235474462,"spread":0.238838002827991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002970696,0.0001092579,0.00009998326,0.00003289551,0.000135908,0.00004180297,0.0001425534,0.00009867418,0.000004101121],"category_scores_gemma":[0.00008784361,0.00008238751,0.00009995814,0.00007584267,0.00004212311,0.00001993937,0.00004114163,0.00007308865,0.000002612615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001284582,"about_ca_system_score_gemma":0.00004431334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002792059,"about_ca_topic_score_gemma":0.0000392967,"domain_scores_codex":[0.9992546,0.00001338865,0.0003994899,0.00007287969,0.00009373127,0.0001658976],"domain_scores_gemma":[0.9993119,0.00003574069,0.0002817529,0.0002447706,0.00009413237,0.00003174463],"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":[0.009982671,0.0005373745,0.000808339,0.002541036,0.0006676664,4.696001e-7,0.003980491,0.112892,0.06603691,0.01896758,0.01476794,0.7688175],"study_design_scores_gemma":[0.00203969,0.001181435,0.001039272,0.0001043468,0.00006409891,0.000006071344,0.001133982,0.9601766,0.02525057,0.0007639849,0.007937772,0.0003022223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0643014,0.0001496013,0.9314359,0.0001502452,0.0004012023,0.001147055,0.00002548034,0.00002033817,0.002368741],"genre_scores_gemma":[0.9150108,0.00004500929,0.0843836,0.0001227629,0.0001344145,0.00005598535,0.0001566265,0.000008689552,0.0000820987],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8507094,"threshold_uncertainty_score":0.3359665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087937056","doi":"10.1186/1471-2105-10-287","title":"Epitopia: a web-server for predicting B-cell epitopes","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":232,"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":"Tel Aviv University; Killam Trusts","keywords":"Epitope; Computer science; Web server; Web application; Interface (matter); Sequence (biology); Computational biology; Graphical user interface; Data mining; Bioinformatics; Antigen; Biology; The Internet; Operating system; Immunology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01522111856171145,"gpt":0.2332089179338898,"spread":0.2179877993721783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002858566,0.0002261627,0.0002057288,0.00005709556,0.0001567909,0.00009041433,0.00031039,0.0001947473,0.000007507036],"category_scores_gemma":[0.0001145176,0.000194922,0.0001901432,0.00009316863,0.00002352687,0.00002999184,0.00008460007,0.00009021654,0.00002454885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001353337,"about_ca_system_score_gemma":0.0001109467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001698096,"about_ca_topic_score_gemma":0.000006036168,"domain_scores_codex":[0.9987586,0.00001171882,0.0005658219,0.0001440575,0.0001387976,0.0003809762],"domain_scores_gemma":[0.9991137,0.00002185254,0.0002279687,0.0004543121,0.00009362228,0.00008859331],"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":[0.002892345,0.003592145,0.05783951,0.01048222,0.001019354,0.000004814747,0.0100219,0.01641385,0.2193241,0.01985165,0.3123179,0.3462403],"study_design_scores_gemma":[0.007615739,0.003070684,0.006558337,0.0001228987,0.0001616199,0.00006953878,0.002603665,0.639502,0.09975135,0.000774625,0.2382501,0.001519501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.821418,0.001339414,0.1524591,0.0003595496,0.0005994138,0.001750759,0.0001263367,0.0001377797,0.02180964],"genre_scores_gemma":[0.6853251,0.0003737746,0.3091409,0.001485961,0.0007079004,0.00007954496,0.000659318,0.00004491244,0.002182564],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6230881,"threshold_uncertainty_score":0.7948688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295126179","doi":"10.1186/s12859-016-0943-7","title":"Improving cell mixture deconvolution by identifying optimal DNA methylation libraries (IDOL)","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":230,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institutes of Health; National Cancer Institute; University of California, San Francisco; National Institute of General Medical Sciences; Kansas IDeA Network of Biomedical Research Excellence; Child and Family Research Institute","keywords":"DNA methylation; Deconvolution; Methylation; Flow cytometry; Computational biology; Biology; DNA; Computer science; Molecular biology; Algorithm; Genetics; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01219439740062806,"gpt":0.2305355039585823,"spread":0.2183411065579542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002842013,0.0001834193,0.0001295725,0.00006455142,0.0001388663,0.0001052913,0.0001735654,0.00025413,0.00002293537],"category_scores_gemma":[0.000145184,0.0001416517,0.00009365648,0.00009001625,0.00006352113,0.00006091576,0.0001237107,0.00006134227,0.00004063577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002602633,"about_ca_system_score_gemma":0.00009108202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005331465,"about_ca_topic_score_gemma":0.000008360859,"domain_scores_codex":[0.9988821,0.00004554257,0.0004213637,0.0001985182,0.0001792443,0.0002732156],"domain_scores_gemma":[0.9991869,0.00003959061,0.0002759123,0.0003159661,0.00008903127,0.00009257542],"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":[0.00003142244,0.00002272402,0.001549367,0.0001042322,0.00001358219,1.199867e-7,0.000126877,0.0001123046,0.976007,0.00008350598,0.001471594,0.02047725],"study_design_scores_gemma":[0.0006251649,0.0001279773,0.0006648696,0.00002156284,0.0000243274,0.000001353519,0.0001379622,0.009458516,0.9765813,0.0001858699,0.01189482,0.0002763097],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2511953,0.001585318,0.7459984,0.00003801598,0.0002067832,0.000165392,0.00004292903,0.0000291843,0.0007386354],"genre_scores_gemma":[0.7637051,0.000583822,0.232968,0.0001101534,0.0003162948,0.00002408909,0.0005050855,0.00004738513,0.001740105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5130304,"threshold_uncertainty_score":0.5776387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077350268","doi":"10.1186/1471-2105-15-s6-i1","title":"Knowledge Discovery and interactive Data Mining in Bioinformatics - State-of-the-Art, future challenges and research directions","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Discovery Centre; University Health Network","funders":"","keywords":"Data science; State (computer science); Computer science; World Wide Web; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06287523198941182,"gpt":0.3455186186540535,"spread":0.2826433866646417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001937104,0.0002050707,0.0002653303,0.0002601671,0.0001606506,0.0001101649,0.0006422213,0.0001927528,0.000001913262],"category_scores_gemma":[0.001229982,0.0001477966,0.00004627028,0.0002687376,0.0006753905,0.0001003837,0.00184384,0.0003461492,0.00000927897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000233823,"about_ca_system_score_gemma":0.0002062599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009976899,"about_ca_topic_score_gemma":0.0008680184,"domain_scores_codex":[0.9980276,0.0001731999,0.0006875014,0.0002300231,0.0004195399,0.0004621285],"domain_scores_gemma":[0.9982747,0.0002782798,0.0001895228,0.0008964622,0.0001974053,0.000163627],"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":[0.0001659292,0.0002310453,0.00414052,0.002640208,0.00009897683,4.259811e-7,0.01371238,0.0000168059,0.0006710552,0.000338042,0.006524145,0.9714605],"study_design_scores_gemma":[0.003039877,0.001433624,0.0510768,0.0008694528,0.00005597959,0.00008079785,0.03371289,0.4083799,0.005941557,0.0006317917,0.4938087,0.0009686276],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.867849,0.02767397,0.0441788,0.002843943,0.002467442,0.00347356,0.000881976,0.00007807861,0.05055324],"genre_scores_gemma":[0.6703252,0.1161499,0.2054138,0.0004348239,0.001251169,0.0001086057,0.001005816,0.0001274198,0.0051833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9704918,"threshold_uncertainty_score":0.6026971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161701113","doi":"10.1186/1471-2105-7-365","title":"PIPE: a protein-protein interaction prediction engine based on the re-occurring short polypeptide sequences between known interacting protein pairs","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":219,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem affinity purification; Saccharomyces cerevisiae; Protein–protein interaction; Yeast; Computational biology; Interaction network; Biology; Gene; Genetics; Bioinformatics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01760215492765312,"gpt":0.2389834037510581,"spread":0.221381248823405,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008058713,0.0003676527,0.0002462905,0.0001264887,0.0003113109,0.0002035388,0.0003708586,0.0002663024,0.00003120056],"category_scores_gemma":[0.0001753324,0.0002762733,0.0001812866,0.0002130822,0.00009738868,0.00005979853,0.000139623,0.0004568099,0.00003740944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009290737,"about_ca_system_score_gemma":0.0001329232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006077559,"about_ca_topic_score_gemma":0.00008204162,"domain_scores_codex":[0.9979101,0.00008748876,0.0009341653,0.0002558326,0.0003406329,0.0004717679],"domain_scores_gemma":[0.9987123,0.00006697648,0.0004081447,0.0006060833,0.000112466,0.00009400296],"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":[0.002413335,0.00117986,0.02866225,0.004995169,0.000965056,0.00001559609,0.002659531,0.1758518,0.5675234,0.00365718,0.02790008,0.1841768],"study_design_scores_gemma":[0.0007783776,0.0008389488,0.0006610623,0.00121714,0.00005908615,0.00001341424,0.001430069,0.7444789,0.227973,0.0002565743,0.02152647,0.000766941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7094641,0.00007622402,0.2764006,0.0003447693,0.0003113393,0.002711278,0.0001383105,0.000142916,0.01041045],"genre_scores_gemma":[0.9700279,0.000002286897,0.02803907,0.0001873544,0.0007360983,0.0002334018,0.0004105747,0.00003604841,0.0003272371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5686271,"threshold_uncertainty_score":0.9999689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102858485","doi":"10.1186/1471-2105-10-357","title":"AIR: A batch-oriented web program package for construction of supermatrices ready for phylogenomic analyses","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":211,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Norges Forskningsråd; Universitetet i Oslo","keywords":"Phylogenetic tree; Sequence (biology); Biology; Computational biology; Tree (set theory); Phylogenomics; DNA microarray; Evolutionary biology; Phylogenetics; R package; Computer science; Gene; Data mining; Bioinformatics; Genetics; Clade; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0384095315106722,"gpt":0.3222790566447174,"spread":0.2838695251340452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000144287,0.0001788013,0.00025857,0.00007282142,0.0001022693,0.00001700098,0.0001592088,0.0001259225,0.000001134195],"category_scores_gemma":[0.00008113284,0.0001572413,0.0001762819,0.0001002246,0.00009147207,0.000003063227,0.00003786833,0.00002897205,0.000001258404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001116512,"about_ca_system_score_gemma":0.0001074411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002827191,"about_ca_topic_score_gemma":0.00001539977,"domain_scores_codex":[0.9990085,0.00001192079,0.000481879,0.0001581117,0.00008445364,0.0002551006],"domain_scores_gemma":[0.9991452,0.00003395671,0.0002520712,0.000282442,0.0002324284,0.00005395765],"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":[0.0004703861,0.0002662039,0.002847951,0.0006267839,0.0003206823,1.211432e-7,0.0003616558,0.0004003271,0.9341606,0.001427461,0.002615514,0.05650232],"study_design_scores_gemma":[0.005539569,0.008910442,0.008094518,0.0000470721,0.0005838966,0.00003627315,0.003094484,0.02927366,0.794049,0.001054853,0.1482884,0.001027838],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.929397,0.0007989454,0.06634054,0.00006545139,0.0002135102,0.001743141,0.0008357171,0.00001865523,0.0005870376],"genre_scores_gemma":[0.6058356,0.0002159996,0.3931408,0.0000909059,0.0001399014,0.0001024296,0.0004217994,0.00001316092,0.00003938027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3268003,"threshold_uncertainty_score":0.6412115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159348493","doi":"10.1186/1471-2105-9-327","title":"Gene Ontology term overlap as a measure of gene functional similarity","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":205,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Michael Smith Health Research BC","funders":"National Institute of General Medical Sciences; National Institutes of Health; Michael Smith Health Research BC","keywords":"Semantic similarity; Computer science; Similarity (geometry); Term (time); Measure (data warehouse); Data mining; Similarity measure; Ontology; Gene ontology; Information retrieval; Artificial intelligence; Machine learning; Gene; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02404013247122475,"gpt":0.2268267298727449,"spread":0.2027865974015202,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002463395,0.0002411042,0.0002973,0.00007139437,0.0001529215,0.00001392359,0.0002670144,0.0003790996,0.00005299956],"category_scores_gemma":[0.00007476971,0.0002225076,0.0002018559,0.0001126787,0.0002246219,0.00001574846,0.0001364203,0.0001613866,0.00005635674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002392238,"about_ca_system_score_gemma":0.0003570863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001303219,"about_ca_topic_score_gemma":0.00003319125,"domain_scores_codex":[0.9984857,0.00002857681,0.0006874105,0.0001678686,0.0002806706,0.0003497626],"domain_scores_gemma":[0.9987794,0.00002063826,0.0003313026,0.0005398721,0.0001910921,0.0001377306],"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":[0.00594916,0.002840606,0.2880682,0.003589364,0.003639658,0.00008147624,0.009840687,0.02770816,0.4092333,0.009667242,0.1778458,0.06153632],"study_design_scores_gemma":[0.01784044,0.004877083,0.1819941,0.0002125998,0.000579038,0.00713041,0.002169264,0.180003,0.488787,0.002626761,0.1087186,0.005061786],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6587373,0.001238919,0.3181925,0.00008910229,0.0007959438,0.0006147763,0.0001912549,0.00005045878,0.02008974],"genre_scores_gemma":[0.8377615,0.0004806663,0.1581208,0.001246632,0.0005056117,0.00002580526,0.0008827785,0.00003965061,0.0009365445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1790242,"threshold_uncertainty_score":0.9073595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134591904","doi":"10.1186/1471-2105-5-170","title":"PhyME: A probabilistic algorithm for finding motifs in sets of orthologous sequences","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Human Genome Research Institute; W. M. Keck Foundation; National Institutes of Health; National Science Foundation","keywords":"Probabilistic logic; Phylogenetic tree; Motif (music); Expectation–maximization algorithm; Computer science; Computational biology; Biology; Data mining; Algorithm; Gene; Genetics; Artificial intelligence; Maximum likelihood; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0151012122346998,"gpt":0.2562718729200442,"spread":0.2411706606853444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001601445,0.0001293745,0.0001699183,0.00006043829,0.00003800387,0.00001608764,0.0001803212,0.0001374364,0.000001574037],"category_scores_gemma":[0.00009505766,0.0001207578,0.00008050939,0.00009500909,0.00008045487,0.000006203999,0.00006723018,0.00005126831,0.000002410886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003412461,"about_ca_system_score_gemma":0.0001974437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001224369,"about_ca_topic_score_gemma":0.0001055281,"domain_scores_codex":[0.9991372,0.000009042445,0.0004217819,0.0001255449,0.00008396082,0.0002224851],"domain_scores_gemma":[0.9994767,0.00001688703,0.0001841991,0.0002203913,0.00006283669,0.00003898993],"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":[0.0003081305,0.001690368,0.0196593,0.007750935,0.0003925658,0.00002036715,0.01164146,0.6460686,0.1072698,0.01216916,0.0004825982,0.1925467],"study_design_scores_gemma":[0.004208876,0.001204541,0.004475828,0.0002114715,0.00005583942,0.0001097448,0.002326198,0.9419544,0.03575447,0.008425359,0.0004977447,0.0007754979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7821388,0.0001167086,0.2166152,0.00002426695,0.0001071393,0.0005253282,0.0001521852,0.000009770303,0.0003106026],"genre_scores_gemma":[0.4533743,0.0000401214,0.5462078,0.00005735696,0.00002880415,0.00003807752,0.0002056731,0.0000142052,0.00003364772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3295926,"threshold_uncertainty_score":0.4924361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009474665","doi":"10.1186/1471-2105-10-145","title":"flowClust: a Bioconductor package for automated gating of flow cytometry data","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Cluster analysis; Data mining; Data transformation; Throughput; Outlier; Workflow; Artificial intelligence; Database; Data warehouse","retraction":null,"screen_n_in":null,"score":{"opus":0.05296027501363074,"gpt":0.3019501064415164,"spread":0.2489898314278856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002966569,0.0001844317,0.0002352775,0.00007852489,0.00007739493,0.00003588732,0.0005244311,0.0001961248,0.000006273745],"category_scores_gemma":[0.0003139601,0.0001668545,0.0001032223,0.0001680975,0.00005562105,0.00002150468,0.00009685587,0.00006726402,0.000005431638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001176617,"about_ca_system_score_gemma":0.0001203768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005379292,"about_ca_topic_score_gemma":0.00001433695,"domain_scores_codex":[0.9988291,0.00001855921,0.0005326598,0.000200117,0.0001433038,0.0002762786],"domain_scores_gemma":[0.9987603,0.00003257717,0.0001958163,0.0008134816,0.0001171248,0.00008072074],"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":[0.0002940376,0.0003146946,0.002318527,0.0009775921,0.0001294357,8.396637e-7,0.0004770163,0.000793289,0.9617921,0.0001008254,0.01300713,0.01979455],"study_design_scores_gemma":[0.001392602,0.0004886937,0.001013524,0.00005601008,0.00004982225,0.00001051725,0.0001694032,0.7973941,0.1959397,0.00002788513,0.003147644,0.0003100607],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3616964,0.0002959794,0.6345071,0.0000614632,0.0004075319,0.0007929248,0.00133075,0.0001592092,0.0007486587],"genre_scores_gemma":[0.4395728,0.0000373044,0.5573564,0.0003140894,0.0001953971,0.000006406303,0.00242138,0.00002304154,0.00007322838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7966008,"threshold_uncertainty_score":0.6804131,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135842485","doi":"10.1186/1471-2105-9-507","title":"MetaboMiner – semi-automated identification of metabolites from 2D NMR spectra of complex biofluids","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":199,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Genome Alberta; Ministry of Advanced Education, Government of Alberta","keywords":"Metabolomics; Heteronuclear single quantum coherence spectroscopy; NMR spectra database; Proton NMR; Two-dimensional nuclear magnetic resonance spectroscopy; Nuclear magnetic resonance spectroscopy; Chemistry; Heteronuclear molecule; Nuclear magnetic resonance; Spectral line; Biological system; Analytical Chemistry (journal); Chromatography; Stereochemistry; Biology; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02520741091627525,"gpt":0.2568409985779328,"spread":0.2316335876616576,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002246279,0.000207329,0.0004804862,0.0001440586,0.00007045206,0.00001063016,0.0002756171,0.0001283223,0.00005151565],"category_scores_gemma":[0.0001891357,0.0001790722,0.0001911355,0.0002910481,0.0002293049,0.00001442514,0.0001366923,0.00005722701,0.0000130957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007545303,"about_ca_system_score_gemma":0.00007451668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004926149,"about_ca_topic_score_gemma":0.00001461831,"domain_scores_codex":[0.9983563,0.00003910363,0.0009651676,0.0001820445,0.0002401676,0.000217194],"domain_scores_gemma":[0.9985934,0.00003490955,0.0005406507,0.000543954,0.0002281351,0.00005895738],"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":[0.00004266656,0.00009398694,0.005801339,0.00009174928,0.0002585323,2.586551e-7,0.0002257013,0.0001043331,0.989176,0.0006366937,0.003432265,0.0001364479],"study_design_scores_gemma":[0.0007126053,0.0000958947,0.06010178,0.000008669302,0.0001418643,0.000008354389,0.0003389482,0.02233765,0.9088959,0.0001014253,0.007016571,0.0002403574],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662277,0.00315536,0.02811266,0.00002057181,0.0001528534,0.0002522913,0.0005896678,0.00004563703,0.001443225],"genre_scores_gemma":[0.9277614,0.001969974,0.06925501,0.00004976368,0.00009262316,0.000009748315,0.0006215204,0.00001900367,0.0002209833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08028015,"threshold_uncertainty_score":0.7302352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149954962","doi":"10.1186/1471-2105-7-228","title":"A stable gene selection in microarray data analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene selection; Selection (genetic algorithm); Microarray analysis techniques; DNA microarray; Support vector machine; Computer science; Gene; Data mining; Significance analysis of microarrays; Microarray; Sample (material); Computational biology; Biology; Artificial intelligence; Genetics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02232773026539993,"gpt":0.2640294807481557,"spread":0.2417017504827558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001926141,0.00008789197,0.0001008117,0.0001543785,0.00004194013,0.00003584372,0.0002316793,0.00009625354,0.00002245797],"category_scores_gemma":[0.00001981122,0.00008275922,0.00004197379,0.0005328075,0.00001846202,0.00001256509,0.00008988152,0.00004562709,0.00001341755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002043673,"about_ca_system_score_gemma":0.00008718816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008793709,"about_ca_topic_score_gemma":0.0009769851,"domain_scores_codex":[0.999253,0.00002286988,0.000285208,0.0001825471,0.0001011933,0.0001552144],"domain_scores_gemma":[0.9993722,0.000003738002,0.0001072821,0.0004492078,0.00003887327,0.00002874159],"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":[0.00008675913,0.0001789413,0.1282457,0.00007781985,0.0001175736,3.209275e-7,0.0000824724,0.02248474,0.805485,0.0001405166,0.04056619,0.002533964],"study_design_scores_gemma":[0.001223799,0.00007928676,0.1152406,0.00001300717,0.0001906735,0.000008668841,0.0002888941,0.469686,0.2787883,0.0001012521,0.1338769,0.0005027478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2237392,0.0004452696,0.7699481,0.00005883782,0.00009340797,0.0002384751,0.00009645036,0.00002794024,0.005352417],"genre_scores_gemma":[0.8086453,0.0001239797,0.1844859,0.0001869585,0.0002009784,0.00002572018,0.004087811,0.00001668662,0.002226582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5854621,"threshold_uncertainty_score":0.3374823,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042301222","doi":"10.1186/1471-2105-11-562","title":"An improved method for scoring protein-protein interactions using semantic similarity within the gene ontology","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Semantic similarity; Gene ontology; Computer science; Similarity (geometry); Graph; Protein function prediction; Cluster analysis; Ontology; Gene Annotation; Representation (politics); Computational biology; Data mining; Protein function; Information retrieval; Artificial intelligence; Gene; Theoretical computer science; Biology; Genetics; Genome; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02424040538563358,"gpt":0.3072557650958416,"spread":0.283015359710208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009625513,0.0002642467,0.0002353748,0.00005945372,0.0004160193,0.0001441757,0.0004761905,0.0002946827,0.00000901168],"category_scores_gemma":[0.0001574406,0.0001999209,0.0001566718,0.0001005034,0.0001182023,0.00003932417,0.0001604541,0.0004109973,0.000005435151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001863219,"about_ca_system_score_gemma":0.000217145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008299848,"about_ca_topic_score_gemma":0.00126324,"domain_scores_codex":[0.9985305,0.00005551585,0.0006781446,0.0002172325,0.0001101418,0.000408478],"domain_scores_gemma":[0.9983958,0.00003650348,0.0004243721,0.0008425605,0.00016975,0.000131035],"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":[0.0001277935,0.00006936456,0.0001299384,0.0002009429,0.00008517008,2.44334e-7,0.000569314,0.002760611,0.9887889,0.001536352,0.00007680777,0.005654543],"study_design_scores_gemma":[0.0005316267,0.0001978223,0.00007497998,0.0000206426,0.00004979231,0.00006633325,0.0003577452,0.8849036,0.1107417,0.001079257,0.001684064,0.0002923991],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2710638,0.00002272901,0.7270607,0.00006688798,0.0004492281,0.001111182,0.00003997609,0.0000241049,0.0001613102],"genre_scores_gemma":[0.2904429,0.000001445937,0.7085645,0.0002952352,0.000374337,0.0001048067,0.00009223715,0.00002751964,0.00009710943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.882143,"threshold_uncertainty_score":0.8152539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106017862","doi":"10.1186/1471-2105-9-375","title":"Critical assessment of alignment procedures for LC-MS proteomics and metabolomics measurements","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":191,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Cancer Research UK","keywords":"Proteomics; Metabolomics; Computational biology; DNA microarray; Computer science; Bioinformatics; Data science; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.04279125193340434,"gpt":0.310214925530109,"spread":0.2674236735967047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000344627,0.0001845098,0.0003041146,0.00006206064,0.0001455585,0.00001738497,0.00013478,0.0001084515,0.000003373801],"category_scores_gemma":[0.0004929435,0.0001577227,0.00009892549,0.00006508156,0.0001879146,0.00001136029,0.0001366963,0.00005155181,5.578432e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001621212,"about_ca_system_score_gemma":0.0002006225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002756977,"about_ca_topic_score_gemma":0.00000989055,"domain_scores_codex":[0.9988492,0.00001960957,0.0004722014,0.0001788119,0.0002185069,0.0002617076],"domain_scores_gemma":[0.9992523,0.00003196139,0.0001720613,0.0002409421,0.0002209926,0.00008170585],"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":[0.0006281335,0.00115224,0.1311633,0.005217481,0.001397112,0.000001286214,0.001122976,0.0004556373,0.8131938,0.03135704,0.01259501,0.001715932],"study_design_scores_gemma":[0.008109339,0.003508944,0.07237986,0.0001391508,0.0006619539,0.0001761918,0.001470569,0.04655951,0.8315009,0.002214232,0.03142688,0.001852488],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5748603,0.001584781,0.4189731,0.0001471073,0.00027823,0.001583446,0.0001873447,0.00001933613,0.002366393],"genre_scores_gemma":[0.3823165,0.00101536,0.616188,0.0001306836,0.00007953024,0.0001184874,0.00005052503,0.00001685472,0.00008398398],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.197215,"threshold_uncertainty_score":0.6431745,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146389940","doi":"10.1186/1471-2105-6-151","title":"AutoFACT: An Auto matic F unctional A nnotation and C lassification T ool","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University; Université de Montréal","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Perl; Annotation; Computer science; Software; Unix; Genomics; Functional genomics; Bioconductor; Computational biology; Information retrieval; Data mining; Programming language; Biology; Artificial intelligence; Genetics; Genome; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01476743885683266,"gpt":0.2402007987037153,"spread":0.2254333598468827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002625248,0.0001665754,0.0001211592,0.00006321217,0.0001397153,0.0001002789,0.0001285383,0.0001778168,0.00003267912],"category_scores_gemma":[0.00003263434,0.0001533677,0.0000471915,0.00007731368,0.00006895676,0.00005113794,0.0000612017,0.00009061038,0.00008037572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002653783,"about_ca_system_score_gemma":0.00009549822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002550135,"about_ca_topic_score_gemma":0.00004214458,"domain_scores_codex":[0.9990202,0.00002077513,0.0004485348,0.0001393125,0.0001537598,0.0002173925],"domain_scores_gemma":[0.9992838,0.00001146125,0.0001925657,0.000314772,0.00007339057,0.0001240212],"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":[0.0005421051,0.0007290223,0.009468141,0.001377353,0.0003573374,0.000001000374,0.007368306,0.03395743,0.03240152,0.0387845,0.03709325,0.83792],"study_design_scores_gemma":[0.0007000092,0.0001712694,0.008722006,0.00001552439,0.00002631023,0.00003738899,0.0004653121,0.9494085,0.0006000809,0.0003878802,0.03918172,0.0002839435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2654835,0.0002825108,0.7250438,0.0004836411,0.0002922582,0.0006524811,0.00006482346,0.0001022294,0.007594765],"genre_scores_gemma":[0.6684352,0.0001041535,0.3279218,0.0009563377,0.0005259417,0.00004304252,0.001048987,0.00003038109,0.0009342149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9154511,"threshold_uncertainty_score":0.6254151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2511892808","doi":"10.1186/s12859-016-1228-x","title":"The parameter sensitivity of random forests","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"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; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Canadian Institutes of Health Research; Government of Ontario; Movember Foundation","keywords":"Sensitivity (control systems); Random forest; DNA microarray; Computational biology; Computer science; Biology; Artificial intelligence; Genetics; Engineering; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.0154773277249372,"gpt":0.2505137324377511,"spread":0.2350364047128139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003253935,0.00006256019,0.00006593732,0.00001449617,0.00005500836,0.00001074941,0.00008545123,0.00006074132,0.000003744141],"category_scores_gemma":[0.0003010978,0.00002975462,0.00006311337,0.00003762004,0.0000914127,0.00000414774,0.00004676171,0.00001864164,0.00001168087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004862268,"about_ca_system_score_gemma":0.0000486674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001164158,"about_ca_topic_score_gemma":0.00004076216,"domain_scores_codex":[0.999483,0.00004935933,0.0002010371,0.00006240786,0.00009658298,0.0001075955],"domain_scores_gemma":[0.9993484,0.0001054719,0.0001276678,0.0003226717,0.00006362005,0.00003218677],"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":[0.0007704525,0.0000574601,0.03026205,0.00009455199,0.00006847407,2.547119e-7,0.0001629348,0.0001058598,0.7120086,0.001168948,0.03315802,0.2221424],"study_design_scores_gemma":[0.003021918,0.0001774913,0.03629155,0.00006550974,0.00002369951,0.00001476174,0.0002057584,0.01289565,0.7937935,0.0006479201,0.1525908,0.0002715096],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1873881,0.0001628306,0.8097229,0.0002878826,0.000224949,0.000228166,0.00001868296,0.00001129535,0.001955188],"genre_scores_gemma":[0.9943482,0.0001530376,0.004657932,0.00006793193,0.00004914456,0.00001229797,0.000007919632,0.000005516201,0.0006980692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.80696,"threshold_uncertainty_score":0.1213358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082852695","doi":"10.1186/1471-2105-12-414","title":"Three-dimensional modeling of chromatin structure from interaction frequency data using Markov chain Monte Carlo sampling","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research","keywords":"Chromatin; Markov chain Monte Carlo; Chromosome conformation capture; Computational biology; Chromosome; Computer science; Monte Carlo method; Biology; Algorithm; Enhancer; Genetics; Artificial intelligence; DNA; Bayesian probability; Transcription factor; Gene; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06652223994272753,"gpt":0.265972490078861,"spread":0.1994502501361335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001535758,0.0002025971,0.0002121531,0.00005630663,0.00007987767,0.00002397912,0.0004557825,0.0001961397,0.00003662312],"category_scores_gemma":[0.00006029122,0.0001932611,0.00006826787,0.00006443141,0.00004328983,0.00003124416,0.0004290051,0.0001226071,0.000002108895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002800054,"about_ca_system_score_gemma":0.0001325943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007356864,"about_ca_topic_score_gemma":0.001127997,"domain_scores_codex":[0.9987795,0.00001714391,0.0006052527,0.0002282232,0.000161281,0.0002085723],"domain_scores_gemma":[0.9986297,0.00001362155,0.000348232,0.0008412058,0.0001040183,0.00006321754],"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":[0.0003290777,0.0002273052,0.01872737,0.0007628732,0.0006203136,0.000003171283,0.002534253,0.5569487,0.4133093,0.00021296,0.0002611491,0.006063516],"study_design_scores_gemma":[0.0003015912,0.00004938179,0.0005372069,0.00006909652,0.00004503216,0.00001429956,0.0003258194,0.9954017,0.002600754,0.0004310386,0.00001015736,0.0002138693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.739738,0.0001554237,0.259061,0.000001944765,0.0001881816,0.0001293607,0.0006175007,0.000009352175,0.00009917795],"genre_scores_gemma":[0.5430214,0.000009684613,0.456226,0.0000223012,0.00006694168,9.50881e-7,0.0006348862,0.00001613913,0.0000017012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.438453,"threshold_uncertainty_score":0.788096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2501117253","doi":"10.1186/s12859-016-1097-3","title":"Evaluating the necessity of PCR duplicate removal from next-generation sequencing data and a comparison of approaches","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Servier; Brigham Young University; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Transversion; Computational biology; Reference genome; Biology; DNA sequencing; Concordance; Genetics; Exome; Population; Data mining; Computer science; Bioinformatics; Exome sequencing; Gene; Mutation; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.3861978566480501,"gpt":0.3493385526642588,"spread":0.03685930398379128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004260937,0.00008850403,0.0001543835,0.00001294369,0.00007030027,0.00001383685,0.0002582722,0.00005924161,0.000001416285],"category_scores_gemma":[0.0001641679,0.00005118764,0.00002631792,0.00003446421,0.0001277506,0.000004417881,0.000388001,0.00002673988,6.200606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005607859,"about_ca_system_score_gemma":0.00006788268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003484488,"about_ca_topic_score_gemma":0.00008682989,"domain_scores_codex":[0.9992499,0.00004136324,0.0003723945,0.0001336432,0.0001086158,0.00009410609],"domain_scores_gemma":[0.9990092,0.00006109033,0.0003006612,0.0005532337,0.00005433089,0.00002146706],"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":[0.00002718505,0.00001331367,0.01355285,0.00005146454,0.00005542499,1.86794e-8,0.0006853486,0.0002291906,0.9443132,0.00005712328,0.0001096054,0.04090528],"study_design_scores_gemma":[0.0006299813,0.0002476798,0.008155677,0.00004290307,0.00009466381,0.000004722788,0.001770003,0.6646588,0.3235516,0.000190258,0.0004769706,0.0001767829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9640781,0.00126907,0.03413239,0.00005994014,0.00004024877,0.0001386622,0.0001419955,0.000001389524,0.0001381886],"genre_scores_gemma":[0.915427,0.0001230579,0.08426057,0.00001763895,0.00007085047,0.000003249385,0.00008054919,0.000005009175,0.00001202328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6644296,"threshold_uncertainty_score":0.2087371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154003902","doi":"10.1186/s12859-015-0788-5","title":"Evaluation of shotgun metagenomics sequence classification methods using in silico and in vitro simulated communities","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Public Health Agency; Michael Smith Health Research BC; Public Health Agency of Canada; Canadian Institutes of Health Research; University of Connecticut; Genome Canada; Genome British Columbia","keywords":"In silico; Metagenomics; Shotgun; Computational biology; Shotgun sequencing; Biology; DNA microarray; Bioinformatics; Sequence (biology); Computer science; Data mining; Genetics; DNA sequencing; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.2892683905235093,"gpt":0.4055330252369845,"spread":0.1162646347134753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002212587,0.00009695096,0.0001637373,0.00009322071,0.00002317819,0.00001251763,0.00009865018,0.00009207546,5.84376e-7],"category_scores_gemma":[0.0001958385,0.00009618868,0.00002256495,0.0001102533,0.00008820327,0.00000391511,0.00009959427,0.00005386538,2.742753e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005353152,"about_ca_system_score_gemma":0.0001985628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001206753,"about_ca_topic_score_gemma":0.0002146659,"domain_scores_codex":[0.9990506,0.0002382473,0.0003875261,0.00007196833,0.0001362165,0.000115456],"domain_scores_gemma":[0.9993382,0.00003951597,0.0001500887,0.0002208706,0.0002197924,0.00003152463],"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":[0.0001161606,0.00004984572,0.01576887,0.00007991403,0.0000446288,7.953584e-8,0.004212593,0.1430095,0.8231382,0.0000347677,0.000003394487,0.01354207],"study_design_scores_gemma":[0.0007294579,0.00004030814,0.006704669,0.00001070761,0.00004193608,0.000002718667,0.005153257,0.9397218,0.04715857,0.0002594626,0.00006907407,0.0001080719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992045,0.001157378,0.006238217,0.00000625285,0.00004258073,0.0002342055,0.00001600749,0.000001287892,0.000259055],"genre_scores_gemma":[0.8592702,0.0001163102,0.1405323,0.00002141805,0.000008199878,0.000004771251,0.00003862672,0.000006001424,0.000002184364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7967123,"threshold_uncertainty_score":0.3922461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1819658147","doi":"10.1186/1471-2105-6-68","title":"Feature selection and nearest centroid classification for protein mass spectrometry","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Feature selection; Computer science; Dimensionality reduction; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Linear discriminant analysis; Data mining; k-nearest neighbors algorithm; Curse of dimensionality; Centroid; Machine learning; Classifier (UML); Boosting (machine learning); Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.01365895679510542,"gpt":0.2436644381373854,"spread":0.23000548134228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001640006,0.0001458005,0.0001396599,0.00007830958,0.0001432844,0.00005785413,0.00008546784,0.0001368196,0.000005320635],"category_scores_gemma":[0.0001195159,0.0001304962,0.00006119344,0.0001266482,0.00003524697,0.00001316242,0.0000397501,0.00007779924,0.00000675411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002670808,"about_ca_system_score_gemma":0.00004249934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.299107e-7,"about_ca_topic_score_gemma":0.00003307706,"domain_scores_codex":[0.9993008,0.00001310881,0.0001828907,0.0001668036,0.00009607821,0.00024031],"domain_scores_gemma":[0.9995511,0.000008606517,0.0001314685,0.0001654074,0.00008129534,0.00006208385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001720785,0.00006468454,0.003452421,0.0002565165,0.0001015825,6.201436e-8,0.00007543756,0.00008260139,0.9704976,0.007034984,0.01122585,0.007036148],"study_design_scores_gemma":[0.002428524,0.0008555139,0.0158313,0.00002667948,0.00009409094,0.00003054866,0.0006510934,0.1349262,0.2685142,0.0004237349,0.5755057,0.0007123827],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3545909,0.001726755,0.6369594,0.001959745,0.0001748881,0.001575685,0.0001048868,0.00006168092,0.002846152],"genre_scores_gemma":[0.2325186,0.0003765782,0.7641679,0.0001760599,0.0005523437,0.00008952177,0.0001904386,0.00002265034,0.001905947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7019835,"threshold_uncertainty_score":0.5321482,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1775447850","doi":"10.1186/1471-2105-7-471","title":"The accuracy of several multiple sequence alignment programs for proteins","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Multiple sequence alignment; Alignment-free sequence analysis; Indel; Sequence alignment; Computer science; Benchmark (surveying); Inference; Software; Data mining; Range (aeronautics); Sequence (biology); Machine learning; Artificial intelligence; Biology; Genetics; Gene; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.01566479295557471,"gpt":0.2533747827090948,"spread":0.2377099897535201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001578201,0.0001199156,0.00009818331,0.00001225096,0.0001225513,0.00003597446,0.0002294632,0.00009927691,5.308138e-7],"category_scores_gemma":[0.0001383721,0.00008027865,0.00009723424,0.0000505674,0.0001070588,0.00000783855,0.0000766162,0.00003920227,0.000001422544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001330951,"about_ca_system_score_gemma":0.0001016657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002970349,"about_ca_topic_score_gemma":0.0001595746,"domain_scores_codex":[0.9991924,0.00001214252,0.0003433104,0.00009330923,0.0001301813,0.0002286623],"domain_scores_gemma":[0.9992871,0.0000376978,0.0002210044,0.0003270459,0.00009743705,0.00002966643],"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":[0.002896383,0.001014477,0.04594303,0.004784451,0.0006386853,0.000002971696,0.001378295,0.03383153,0.5032576,0.04532466,0.02342465,0.3375032],"study_design_scores_gemma":[0.003290749,0.001213075,0.002375043,0.00008609363,0.00006483909,0.00004226613,0.0005305374,0.4802581,0.3009483,0.006004185,0.2043802,0.0008065756],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1222942,0.0003171026,0.87306,0.00009175151,0.0001759256,0.00281116,0.000146564,0.00002919252,0.001074052],"genre_scores_gemma":[0.647791,0.00003305341,0.3508202,0.00007534141,0.0001564833,0.000254624,0.0004446645,0.00001621961,0.0004084327],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5254968,"threshold_uncertainty_score":0.3273668,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009153021","doi":"10.1186/1471-2105-10-243","title":"Core Hunter: an algorithm for sampling genetic resources based on multiple genetic measures","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"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":"Natural Sciences and Engineering Research Council of Canada; International Fund for Agricultural Development; European Commission","keywords":"Core (optical fiber); Genetic diversity; Representativeness heuristic; Computer science; Genetic algorithm; Sampling (signal processing); Preference; Data mining; Machine learning; Statistics; Mathematics; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.06288921997742554,"gpt":0.3033216433372166,"spread":0.240432423359791,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003473438,0.0002496156,0.0002597947,0.00009103748,0.0002136942,0.00004618826,0.0002985827,0.0002824263,0.000006250506],"category_scores_gemma":[0.0005003212,0.0002295017,0.0001654274,0.00008522618,0.00005569276,0.000005550759,0.00003110056,0.00008862529,0.00001095697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000266581,"about_ca_system_score_gemma":0.00009055092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008469146,"about_ca_topic_score_gemma":0.00004402499,"domain_scores_codex":[0.9984807,0.00006068562,0.0005540571,0.0002843609,0.0001752533,0.0004449359],"domain_scores_gemma":[0.9987845,0.0001293364,0.0002445582,0.0005412197,0.0001499101,0.0001504218],"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":[0.0003065475,0.0005457242,0.08256928,0.0001263012,0.0001125459,0.000001370353,0.0006492482,0.2147556,0.006298016,0.00004025818,0.005497106,0.689098],"study_design_scores_gemma":[0.00109489,0.001447737,0.1214221,0.00001771845,0.00003569043,0.000006687315,0.0002008484,0.8621216,0.0005709499,0.0001876891,0.01257191,0.0003221089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2568383,0.0001687312,0.7419695,0.00006497792,0.0001281947,0.000455319,0.0001048754,0.00003194032,0.0002381204],"genre_scores_gemma":[0.2582824,0.00003930442,0.7393518,0.001576952,0.0002978743,0.00004111329,0.0003157044,0.00002257638,0.00007226477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6887759,"threshold_uncertainty_score":0.9358809,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1480287196","doi":"10.1186/1471-2105-7-356","title":"New directions in biomedical text annotation: definitions, guidelines and corpus construction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Task (project management); Information retrieval; Natural language processing; Categorization; Set (abstract data type); Biomedical text mining; Executable; Focus (optics); Artificial intelligence; Unified Medical Language System; Text corpus; Text mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03638827609910656,"gpt":0.2788558833373014,"spread":0.2424676072381949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001253207,0.0001048881,0.0001126463,0.0001004408,0.00007273565,0.00003059929,0.00006404593,0.0001870185,0.00001333659],"category_scores_gemma":[0.0002373942,0.00009265472,0.00003305998,0.0001851076,0.0001994557,0.000007173261,0.00004409807,0.00007030617,0.00001227307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001047973,"about_ca_system_score_gemma":0.0001247868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001180169,"about_ca_topic_score_gemma":0.000263921,"domain_scores_codex":[0.9991825,0.00001821956,0.0004092055,0.0001196076,0.0001131846,0.0001572942],"domain_scores_gemma":[0.9996256,0.00002950721,0.0000881013,0.000127362,0.00005932805,0.0000701621],"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":[0.00009850562,0.0001528681,0.0546947,0.0002000894,0.00004063789,0.000004897346,0.0002322914,0.0001241631,0.003986531,0.006740004,0.152099,0.7816263],"study_design_scores_gemma":[0.003625215,0.0005532669,0.06640336,0.0001755859,0.00005594333,0.0006293616,0.002148588,0.01968591,0.003054662,0.006025677,0.8968548,0.0007876422],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2429122,0.007520903,0.7344451,0.00269443,0.001332532,0.0004804686,0.0001386629,0.0002165928,0.01025908],"genre_scores_gemma":[0.0188722,0.00097537,0.9784367,0.0002871386,0.0004337459,0.00001600552,0.0004533347,0.00001175452,0.0005137247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7808387,"threshold_uncertainty_score":0.377835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060064237","doi":"10.1186/1471-2105-12-139","title":"PeakRanger: A cloud-enabled peak caller for ChIP-seq data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Science Foundation","keywords":"Computer science; Cloud computing; Chromatin immunoprecipitation; Massively parallel; Software; Chip; Parallel computing; Multi-core processor; Data mining; Biology; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.05121050092748334,"gpt":0.2519177744359786,"spread":0.2007072735084953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003155233,0.0002129169,0.0001908389,0.0000400122,0.0001173994,0.00004389354,0.000813378,0.0001954861,0.00003899213],"category_scores_gemma":[0.0001032809,0.0001930553,0.000105069,0.00006164599,0.00006458774,0.00001400451,0.0004883462,0.00007606987,0.00004786624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000013463,"about_ca_system_score_gemma":0.0001470693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001574892,"about_ca_topic_score_gemma":0.0001254701,"domain_scores_codex":[0.998821,0.00001573184,0.0004350602,0.0002485232,0.0001147653,0.0003648938],"domain_scores_gemma":[0.9983308,0.00001439121,0.0001870289,0.001257887,0.00009494361,0.0001149847],"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":[0.004211164,0.003473992,0.02654914,0.009951691,0.003423872,0.00002165112,0.0213849,0.002103718,0.1139406,0.0286978,0.7253834,0.0608581],"study_design_scores_gemma":[0.004783,0.001051773,0.005348342,0.00006826566,0.0002633137,0.00008836889,0.002201566,0.6786373,0.007935799,0.001532043,0.2963785,0.001711661],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3742095,0.0007147794,0.5858392,0.0000919933,0.001395662,0.001846167,0.001654265,0.0001115739,0.03413681],"genre_scores_gemma":[0.1487268,0.0003513198,0.840892,0.0008003992,0.0007748466,0.00009349768,0.005704694,0.0001072373,0.002549272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6765336,"threshold_uncertainty_score":0.7872568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087932775","doi":"10.1186/1471-2105-11-403","title":"Data reduction for spectral clustering to analyze high throughput flow cytometry data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":166,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; Mitacs; National Institutes of Health; Michael Smith Health Research BC","keywords":"Throughput; Computer science; Cluster analysis; Reduction (mathematics); Flow cytometry; Data reduction; Data mining; Computational biology; Biology; Mathematics; Artificial intelligence; Molecular biology; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.05461754201277463,"gpt":0.3018674232321299,"spread":0.2472498812193553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710387,0.000180925,0.0001734811,0.00007374451,0.000122216,0.0001027115,0.001160821,0.0001908681,0.00001374339],"category_scores_gemma":[0.000201757,0.000171576,0.00005100953,0.0001543688,0.00005027117,0.00004847679,0.0005963115,0.0001437908,0.0000191837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000120852,"about_ca_system_score_gemma":0.0001037681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003924491,"about_ca_topic_score_gemma":0.0008184512,"domain_scores_codex":[0.998796,0.00001027992,0.0003827785,0.0003590396,0.000143606,0.0003083061],"domain_scores_gemma":[0.9976377,0.00001565294,0.00009637913,0.002061019,0.00006862053,0.0001206588],"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":[0.0007266365,0.0003039707,0.002477241,0.0007762457,0.0002710322,0.000001326668,0.000483718,0.004067125,0.8797627,0.0001701863,0.06212775,0.04883204],"study_design_scores_gemma":[0.001264774,0.0003321707,0.0010088,0.00002680733,0.0001079645,0.00006143624,0.0002620179,0.8421632,0.05061862,0.00005153447,0.1035037,0.0005990215],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1570021,0.00003348495,0.8385878,0.000135099,0.001570914,0.0004158999,0.001925425,0.00003595959,0.000293298],"genre_scores_gemma":[0.1693299,0.00003894081,0.8192587,0.000227657,0.001296845,0.000009344732,0.009631853,0.00003325347,0.0001734911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8380961,"threshold_uncertainty_score":0.6996666,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125816119","doi":"10.1186/1471-2105-6-34","title":"Atlas – a data warehouse for integrative bioinformatics","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":163,"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; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research","keywords":"Atlas (anatomy); Data warehouse; Bioinformatics; Computational biology; Data science; Computer science; Biology; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03051586659518616,"gpt":0.2760682048145316,"spread":0.2455523382193455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006216058,0.0004085742,0.0003463328,0.0001079182,0.000228604,0.0001629472,0.001206681,0.0003404941,0.0000241843],"category_scores_gemma":[0.0002505161,0.0003337047,0.0001807497,0.0001628953,0.0001506758,0.0000934035,0.0007030188,0.0001914835,0.0001928819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004326486,"about_ca_system_score_gemma":0.0002820126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004251376,"about_ca_topic_score_gemma":0.000180417,"domain_scores_codex":[0.9978166,0.00002066621,0.001039046,0.0002721729,0.0002411654,0.000610389],"domain_scores_gemma":[0.9974554,0.00007336321,0.0004278517,0.001634195,0.0001981911,0.000211062],"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":[0.0005634443,0.0003257389,0.0005299027,0.001023313,0.000514809,6.461893e-7,0.003867507,0.01245598,0.0005749587,0.004363798,0.7164817,0.2592981],"study_design_scores_gemma":[0.001000116,0.0002130638,0.0000239532,0.00003301193,0.00004369829,0.00002299366,0.0008553925,0.6118456,0.000889368,0.0001230591,0.3845569,0.0003929028],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002562372,0.0004432157,0.9862539,0.000267416,0.0003745966,0.00112852,0.0009602344,0.0000861098,0.007923666],"genre_scores_gemma":[0.01448252,0.0003112299,0.9754982,0.001757157,0.001010235,0.00007815007,0.005061712,0.00006666124,0.001734111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5993896,"threshold_uncertainty_score":0.9999115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029036185","doi":"10.1186/1471-2105-10-120","title":"Multichromosomal median and halving problems under different genomic distances","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Genome; Breakpoint; Context (archaeology); Generalization; Time complexity; Biology; Computer science; Computational biology; Genetics; Combinatorics; Mathematics; Chromosome; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01240274061496869,"gpt":0.2228328514029068,"spread":0.2104301107879381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008472934,0.0001750834,0.0001416279,0.00004120023,0.00008804608,0.00006540868,0.0001427667,0.00009714915,0.00001044881],"category_scores_gemma":[0.0000186652,0.0001446914,0.00004941519,0.0000430122,0.00006487191,0.000009828411,0.00007448885,0.00006269808,0.00001311753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001986063,"about_ca_system_score_gemma":0.00002825234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002126845,"about_ca_topic_score_gemma":0.00005086823,"domain_scores_codex":[0.9991596,0.00001499905,0.0002701907,0.0001534582,0.0001323037,0.0002694041],"domain_scores_gemma":[0.9995227,0.000009060999,0.00009679326,0.000234288,0.00002856883,0.0001085864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002318758,0.00088978,0.08284508,0.001991072,0.0005678962,0.000009393403,0.00737513,0.006666874,0.7087854,0.002413608,0.002847321,0.1853766],"study_design_scores_gemma":[0.009566296,0.00294972,0.493551,0.0003183965,0.0002888223,0.0001879558,0.005454137,0.4112294,0.04315278,0.003806083,0.02614071,0.003354642],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9266176,0.001174671,0.0699575,0.0001965251,0.0001393918,0.0004218438,0.0000213694,0.00003332389,0.00143777],"genre_scores_gemma":[0.9463533,0.0003635351,0.05253923,0.0002121186,0.0001446392,0.00001083819,0.0001244981,0.00001474779,0.0002370444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6656325,"threshold_uncertainty_score":0.5900342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1793987388","doi":"10.1186/s12859-015-0663-4","title":"Sealer: a scalable gap-closing application for finishing draft genomes","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":156,"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; BC Cancer Agency","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Closing (real estate); Scalability; DNA microarray; Computer science; Genome; Computational biology; Biology; Genetics; Database; Business; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.04185362854053402,"gpt":0.2695208117224522,"spread":0.2276671831819182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002820701,0.0001371606,0.0001384193,0.00003093227,0.0001206434,0.00005343166,0.0001708809,0.0001048738,0.000001085937],"category_scores_gemma":[0.00009564907,0.0001303845,0.0000755829,0.00006256474,0.00004563255,0.000003126018,0.0001222254,0.00003715957,0.00001863703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002072327,"about_ca_system_score_gemma":0.0001427863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007860337,"about_ca_topic_score_gemma":0.00002778159,"domain_scores_codex":[0.9992092,0.00001088045,0.0002811063,0.0001484834,0.0001020464,0.0002482851],"domain_scores_gemma":[0.9992937,0.00002055807,0.0001268403,0.000291155,0.0001661092,0.0001016108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001308668,0.0007649778,0.1771716,0.003294336,0.001206967,0.000001640924,0.01518769,0.05524797,0.3406913,0.01063495,0.1523455,0.2421444],"study_design_scores_gemma":[0.002675287,0.0006679306,0.001953587,0.00003024344,0.0001019813,0.00002364121,0.002731657,0.2059607,0.03144469,0.002444867,0.7511024,0.0008630237],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3854345,0.0048399,0.5925799,0.0003195219,0.0005326503,0.001658834,0.000193288,0.00003644863,0.01440498],"genre_scores_gemma":[0.6085329,0.0002720847,0.3887979,0.000593766,0.0005399536,0.0001906772,0.0003198643,0.00004296276,0.0007098628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5987569,"threshold_uncertainty_score":0.5316924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107815233","doi":"10.1186/1471-2105-9-101","title":"Prediction of mucin-type O-glycosylation sites in mammalian proteins using the composition of k-spaced amino acid pairs","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Program for New Century Excellent Talents in University; China Agricultural University; University of Alberta","keywords":"Glycosylation; Threonine; Computational biology; Serine; Encoding (memory); Binary classification; Support vector machine; Mucin; Computer science; Amino acid; Biology; Bioinformatics; Artificial intelligence; Biochemistry; Phosphorylation","retraction":null,"screen_n_in":null,"score":{"opus":0.05543503999968876,"gpt":0.2762255201344427,"spread":0.2207904801347539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002832156,0.0001054661,0.0001360543,0.0001256607,0.00008493366,0.000008253161,0.0001291711,0.0001327833,0.00001627755],"category_scores_gemma":[0.0001077249,0.0000839408,0.00006067165,0.0003022937,0.000132697,0.00002098183,0.00006148944,0.00009156271,0.000003538711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002593052,"about_ca_system_score_gemma":0.0001275041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005703436,"about_ca_topic_score_gemma":0.00007782375,"domain_scores_codex":[0.998942,0.00007419771,0.0004577692,0.00009781005,0.0002689661,0.0001592359],"domain_scores_gemma":[0.999208,0.00001414251,0.0002378092,0.0002851775,0.0002184106,0.00003646356],"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":[0.0002913037,0.0001103567,0.06946338,0.0002735172,0.00002042283,6.830886e-7,0.00083519,0.005085365,0.9232892,0.00007892393,0.000137307,0.0004143861],"study_design_scores_gemma":[0.0008175485,0.0004005488,0.05296765,0.00004273041,0.00000965184,0.00002548075,0.000335531,0.1835499,0.7614574,0.00001421114,0.0002767677,0.0001026595],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9623961,0.00007173923,0.03646628,0.00002793294,0.00003964661,0.0006077078,0.00003425761,0.000007739214,0.0003485618],"genre_scores_gemma":[0.9771332,0.00004557976,0.02246224,0.00001643178,0.00003434255,0.000008881698,0.0002370586,0.000009207349,0.00005305283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1784645,"threshold_uncertainty_score":0.3423007,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017229033","doi":"10.1186/1471-2105-9-226","title":"SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Structural alignment; Protein structure prediction; Computer science; Structural similarity; Similarity (geometry); Classifier (UML); Protein secondary structure; Structural Classification of Proteins database; Protein structure; Sequence alignment; Mathematics; Biology; Peptide sequence; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01965501526011024,"gpt":0.243559004356052,"spread":0.2239039890959418,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001705368,0.0001911594,0.0002581816,0.00005573832,0.0001273169,0.00001277896,0.0002413241,0.0002023807,0.000002857422],"category_scores_gemma":[0.0001055873,0.0001422493,0.00009120075,0.000127771,0.000339721,0.000042361,0.00006843385,0.00009219444,2.246683e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001545756,"about_ca_system_score_gemma":0.0003021086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000282909,"about_ca_topic_score_gemma":0.00006229347,"domain_scores_codex":[0.9987577,0.00002665197,0.0005709574,0.0001688265,0.0002473384,0.0002285588],"domain_scores_gemma":[0.9988001,0.00002299055,0.0005345315,0.0003046712,0.0002783102,0.00005942376],"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":[0.002222472,0.0001124714,0.1383434,0.004980992,0.0004944292,0.000003970829,0.002726129,0.02931323,0.8164943,0.001677288,0.0003118656,0.003319515],"study_design_scores_gemma":[0.001623916,0.002017355,0.006473346,0.0001891348,0.00008179276,0.000132667,0.0007686585,0.2001817,0.7872614,0.000486801,0.0004279162,0.0003552803],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8785841,0.0001704515,0.1196652,0.00001481244,0.00006688958,0.0007624133,0.0004961073,0.00002080972,0.0002191003],"genre_scores_gemma":[0.8479446,0.00002957301,0.1516053,0.00001922402,0.00007432032,0.00003926175,0.0002322107,0.00001143795,0.00004407235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1708685,"threshold_uncertainty_score":0.5800758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1759632117","doi":"10.1186/1471-2105-5-24","title":"Biochemical Network Stochastic Simulator (BioNetS): software for stochastic modeling of biochemical networks","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"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":"Defense Advanced Research Projects Agency; Alfred P. Sloan Foundation","keywords":"Computer science; Software; Stochastic modelling; Simulation; Programming language; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01449411906631034,"gpt":0.2385294678884628,"spread":0.2240353488221525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003409915,0.0004307427,0.0005423443,0.00009629676,0.0001553448,0.00003463341,0.0004564266,0.0005407029,0.000006506584],"category_scores_gemma":[0.0003754092,0.0004249114,0.0004352872,0.0004313946,0.0001855407,0.00001357353,0.0002542519,0.0001728288,0.000007197136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006437252,"about_ca_system_score_gemma":0.0002942004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005323132,"about_ca_topic_score_gemma":0.000007634624,"domain_scores_codex":[0.997499,0.00002436189,0.001007175,0.0004124516,0.0003131906,0.0007437475],"domain_scores_gemma":[0.9981485,0.00007822763,0.0003675139,0.0007660353,0.0003758829,0.0002638216],"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":[0.0001822604,0.00007103666,0.00005312579,0.0001296329,0.0001583737,1.541441e-7,0.00003616051,0.9962984,0.001668363,0.0001053625,0.001102866,0.0001942369],"study_design_scores_gemma":[0.001534383,0.0002164537,0.00001403076,0.0001158264,0.0002258316,0.00001385099,0.00007293726,0.994579,0.002214383,0.0004569713,0.0000722149,0.0004841278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1059268,0.001531086,0.8916488,0.00001841239,0.0001950759,0.0005731362,0.00004714976,0.00004819482,0.00001130047],"genre_scores_gemma":[0.8171256,0.00001888059,0.1812981,0.0001129546,0.0006530909,0.00004874551,0.0006631977,0.00006098139,0.00001845588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7111988,"threshold_uncertainty_score":0.9998203,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}