{"meta":{"query_hash":"95db5a6f7e4e","filters":{"venue":"Journal of Structural and Functional Genomics"},"cohort_total":41,"direct_labels_cover":0,"predictions_cover":41,"exported":41,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/95db5a6f7e4e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Structural+and+Functional+Genomics"},"results":[{"id":"W1513446941","doi":"10.1023/a:1021261026670","title":"Role for NMR in structural genomics","year":2002,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences","keywords":"Structural genomics; Genomics; National laboratory; Functional genomics; Computational biology; Biology; Engineering; Genetics; Genome; Engineering physics; Biochemistry; Protein structure; Gene","score_opus":0.01320816260975611,"score_gpt":0.20827084317933703,"score_spread":0.19506268056958093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1513446941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957231,0.0029496087,0.00060135545,0.00016571995,0.00032055,0.000112155176,0.000025144538,0.0000014982986,0.00010084523],"genre_scores_gemma":[0.99334866,0.0002954715,0.0050642956,0.00015371056,0.0008540227,0.0000031617785,0.000012341169,0.000014080624,0.00025424996],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992805,0.000019122977,0.00031057684,0.00014241083,0.00008848337,0.00015892254],"domain_scores_gemma":[0.999557,0.000019432411,0.00018322798,0.000076720615,0.0000894963,0.000074100666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012104823,0.0001236688,0.00016865943,0.00005963488,0.00008224976,0.00002861425,0.000092341485,0.000108286644,0.00006488896],"category_scores_gemma":[0.000034730772,0.000099755096,0.00010614117,0.00003216707,0.000037153302,0.00001117144,0.000033603177,0.00008998501,0.0000010170571],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046597715,0.0000065862396,0.00144365,0.000013008477,0.0000618736,0.0000020350565,0.00009357966,0.00094299356,0.976875,0.0006168387,0.00021930198,0.019259162],"study_design_scores_gemma":[0.011812629,0.0042759515,0.16787831,0.00007471707,0.00024112164,0.004546291,0.0015164798,0.017593874,0.52114236,0.08572109,0.18323623,0.0019609064],"about_ca_topic_score_codex":0.0000027736307,"about_ca_topic_score_gemma":0.0000065868094,"teacher_disagreement_score":0.4557326,"about_ca_system_score_codex":0.000032610875,"about_ca_system_score_gemma":0.000029681467,"threshold_uncertainty_score":0.40678948},"labels":[],"label_agreement":null},{"id":"W1589570762","doi":"10.1023/a:1026156025612","title":"Coverage of protein sequence space by current structural genomics targets","year":2003,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Biotechnology Research Institute; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Structural genomics; Protein Data Bank (RCSB PDB); Proteome; Computational biology; Protein superfamily; Homology (biology); Biology; Protein Data Bank; Homologous chromosome; Genome; Cluster analysis; Proteomics; Genetics; Protein structure; Computer science; Gene; Biochemistry; Artificial intelligence","score_opus":0.015035922793876211,"score_gpt":0.22811302812100925,"score_spread":0.21307710532713303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589570762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918141,0.0040288665,0.0017448033,0.00006146766,0.0018675468,0.00015084866,0.00013248465,0.000008440724,0.00019146073],"genre_scores_gemma":[0.99544674,0.00021503397,0.0037755189,0.00004693294,0.0003758161,0.0000014799913,0.000012828817,0.00001642269,0.0001092001],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99841744,0.000076255914,0.00064558536,0.00023302589,0.00036923244,0.00025844193],"domain_scores_gemma":[0.9986385,0.000046709672,0.0007425194,0.00011483919,0.00029967297,0.00015775571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002798285,0.00023699821,0.0003730705,0.00009064058,0.00018432537,0.00006519064,0.00013907567,0.00009852081,0.00040405424],"category_scores_gemma":[0.000078421035,0.00017784965,0.00012330097,0.000107587555,0.00017451891,0.00038886032,0.000039561462,0.0003090268,0.0000037306786],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029020305,0.0000074832037,0.0008202189,0.000052674473,0.00003122685,0.0000046463647,0.00014554131,0.0009503902,0.99041545,0.0044980086,0.00037136907,0.0024128072],"study_design_scores_gemma":[0.003316471,0.0009800347,0.021644998,0.000092210656,0.000176513,0.002737361,0.00034484008,0.00047894198,0.8603922,0.06441714,0.044520274,0.000899029],"about_ca_topic_score_codex":0.000011416378,"about_ca_topic_score_gemma":0.0000020792552,"teacher_disagreement_score":0.13002324,"about_ca_system_score_codex":0.00016174276,"about_ca_system_score_gemma":0.00018466957,"threshold_uncertainty_score":0.7252498},"labels":[],"label_agreement":null},{"id":"W171658374","doi":"10.1023/a:1021352716284","title":"The cadherin superfamily database","year":2002,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Wnt/β-catenin signaling in development and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"SUPERFAMILY; Biology; Computational biology; Cadherin; Annotation; Protein family; Bioinformatics; Database; Genetics; Computer science; Cell; Gene","score_opus":0.01727630489704733,"score_gpt":0.20372120345385347,"score_spread":0.18644489855680613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W171658374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912052,0.0074563427,0.00013604561,0.00030707713,0.0006566883,0.000025179514,0.0000075527123,0.0000012503301,0.00020467752],"genre_scores_gemma":[0.99433523,0.0024043322,0.0005941344,0.00021470424,0.00087797525,8.830666e-7,0.000010537435,0.000007211905,0.001554981],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995112,0.000012800201,0.00018574466,0.00008116808,0.00010760071,0.000101483005],"domain_scores_gemma":[0.99967915,0.000014160208,0.00009299257,0.000065228756,0.00009641468,0.000052031723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000108284374,0.0000752928,0.000068137495,0.00001468602,0.00017045265,0.00003360135,0.00008579469,0.000040261864,0.000072393734],"category_scores_gemma":[0.000019238858,0.00004593058,0.00004778165,0.000027630245,0.00007222478,0.000006697396,0.000043265667,0.000093174494,0.0000026451132],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003915425,0.000008399667,0.0063463664,0.000008488562,0.00018671264,0.0000064798623,0.000088061955,0.00024871694,0.94645643,0.00027082115,0.030493164,0.015494836],"study_design_scores_gemma":[0.0021336193,0.000568872,0.078896366,0.000021126316,0.00007894188,0.0015399315,0.00047093112,0.00072487374,0.06985785,0.0012258623,0.84400773,0.00047390978],"about_ca_topic_score_codex":0.0000017687572,"about_ca_topic_score_gemma":0.0000023884472,"teacher_disagreement_score":0.87659854,"about_ca_system_score_codex":0.000014372641,"about_ca_system_score_gemma":0.000030057628,"threshold_uncertainty_score":0.18729948},"labels":[],"label_agreement":null},{"id":"W1767701883","doi":"10.1023/a:1011320027914","title":"Calmodulin Target Database","year":2000,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Protein Kinase Regulation and GTPase Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":548,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Medical Research Council; Howard Hughes Medical Institute","keywords":"Calmodulin; Calcium-binding protein; Computational biology; Biology; Subclass; Protein structure; Calcium; Biochemistry; Genetics; Chemistry","score_opus":0.009679894184016628,"score_gpt":0.21521363712396085,"score_spread":0.20553374293994423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1767701883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99641246,0.0019509363,0.0011267154,0.00013724918,0.0001409337,0.000033652563,0.000025120486,0.0000016204677,0.00017132169],"genre_scores_gemma":[0.99291617,0.00021749175,0.0051438217,0.00024522637,0.0008781681,4.747185e-7,0.000063372456,0.0000069233874,0.0005283683],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995204,0.000015948495,0.00019441012,0.000092676666,0.00009384748,0.00008267436],"domain_scores_gemma":[0.9996967,0.0000040619457,0.00008474612,0.00006216205,0.00007160636,0.00008072908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009381465,0.00007485834,0.000086961416,0.000026397589,0.0000732252,0.000016374663,0.00004290042,0.000048576283,0.00046194333],"category_scores_gemma":[0.000012515315,0.000058686524,0.000058324764,0.000027870934,0.000040872827,0.00000826803,0.000017449544,0.0000777858,0.0000030041779],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010218605,0.00001549584,0.0014037925,0.000015597298,0.00009083727,0.000014995384,0.000029470633,0.0061226767,0.9598226,0.00036006994,0.0014820189,0.029620584],"study_design_scores_gemma":[0.0047350526,0.0010071128,0.08161319,0.000052497966,0.00010860246,0.004686469,0.00013932271,0.004606328,0.2696043,0.00752779,0.6251308,0.00078854815],"about_ca_topic_score_codex":0.000002088907,"about_ca_topic_score_gemma":6.537241e-7,"teacher_disagreement_score":0.6902183,"about_ca_system_score_codex":0.000009851759,"about_ca_system_score_gemma":0.000051182364,"threshold_uncertainty_score":0.50579554},"labels":[],"label_agreement":null},{"id":"W1779770448","doi":"10.1023/a:1011348803324","title":"NMR Structure Determination and Structure-Based Functional Characterization of Conserved Hypothetical Protein MTH1175 from Methanobacterium thermoautotrophicum","year":2000,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Thermotoga maritima; Methanobacterium; Structural genomics; Biology; Ribonuclease; Hyperthermophile; Protein family; Peptide sequence; Conserved sequence; Nuclear magnetic resonance spectroscopy; Protein structure; Biochemistry; Bacteria; Sequence alignment; Gene; Archaea; Genetics; Stereochemistry; Chemistry; RNA; Escherichia coli","score_opus":0.010704088225939913,"score_gpt":0.19143395201483077,"score_spread":0.18072986378889086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1779770448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969905,0.000148677,0.0011416315,0.00024552867,0.0007189241,0.0001878974,0.0005320576,0.000015503821,0.000019252182],"genre_scores_gemma":[0.99507755,0.000018740946,0.0037209166,0.00017713761,0.0007575192,0.0000020195057,0.00015680936,0.000022962677,0.00006635958],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982106,0.00012539182,0.0007202798,0.00030731715,0.0004285371,0.00020783665],"domain_scores_gemma":[0.99867976,0.00009434428,0.000607024,0.00014555066,0.00033236505,0.00014095104],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014744526,0.0002825272,0.00043093375,0.00014202348,0.00018544364,0.00010139543,0.00010908746,0.00022035222,0.0037449943],"category_scores_gemma":[0.00003915197,0.00021117924,0.000102132464,0.00011743546,0.0002751272,0.00043893055,0.000029054545,0.00028183302,0.0000019201548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015261252,0.000010699916,0.0007732678,0.000033841985,0.000038382004,0.0000036848828,0.00009316778,0.00042167908,0.98890984,0.000204634,0.000007501448,0.0079771485],"study_design_scores_gemma":[0.0019876387,0.00043221712,0.4825209,0.00005324884,0.0001569555,0.00035388186,0.000037207636,0.0029014538,0.5012292,0.009515472,0.00048480442,0.00032701294],"about_ca_topic_score_codex":0.000020797648,"about_ca_topic_score_gemma":0.000009636185,"teacher_disagreement_score":0.48768067,"about_ca_system_score_codex":0.000068981,"about_ca_system_score_gemma":0.00014179666,"threshold_uncertainty_score":0.99716574},"labels":[],"label_agreement":null},{"id":"W1820111519","doi":"10.1023/a:1024674220425","title":"Solution structure of the yeast ubiquitin-like modifier protein Hub1","year":2003,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto; Ontario Institute for Cancer Research","funders":"Pacific Northwest National Laboratory; Battelle; National Institute of General Medical Sciences; Biological and Environmental Research; National Institutes of Health; U.S. Department of Energy","keywords":"Saccharomyces cerevisiae; Nuclear Overhauser effect; Two-dimensional nuclear magnetic resonance spectroscopy; Nuclear magnetic resonance spectroscopy; Yeast; Ubiquitin; Chemistry; Spectroscopy; Structural genomics; Nuclear magnetic resonance; Biochemistry; Protein structure; Stereochemistry; Physics; Gene","score_opus":0.012140963366007756,"score_gpt":0.19742696215736188,"score_spread":0.18528599879135413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1820111519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961594,0.00032051594,0.0006874207,0.00010466868,0.0023688343,0.00011188275,0.000041083702,0.0000046834703,0.00020154199],"genre_scores_gemma":[0.99764514,0.000007390104,0.0016003716,0.00009960446,0.00041675786,5.6118284e-7,0.000002281257,0.0000094504,0.00021841827],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988787,0.00007282594,0.00042305535,0.00013610352,0.00032838108,0.00016090271],"domain_scores_gemma":[0.99904305,0.000019966228,0.00049970415,0.00012431794,0.0002451572,0.000067816174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016979901,0.00014042947,0.00020522252,0.00005746477,0.0002038195,0.000038056456,0.00011665284,0.00009946292,0.00038048756],"category_scores_gemma":[0.00005441981,0.00008276096,0.000110724905,0.00010661908,0.00015435176,0.00021439705,0.000037186746,0.00023133148,0.0000014999096],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015102603,0.000004429393,0.0005862896,0.000021085252,0.000020529977,7.8830493e-7,0.000116106785,0.0008553225,0.99247724,0.004967905,0.00028053063,0.00051871885],"study_design_scores_gemma":[0.0014647327,0.0003001091,0.066506304,0.00005613058,0.00012436659,0.0015128457,0.00033755787,0.0001887226,0.8605316,0.060923766,0.0077461274,0.00030773017],"about_ca_topic_score_codex":0.000009298875,"about_ca_topic_score_gemma":0.000010125553,"teacher_disagreement_score":0.13194565,"about_ca_system_score_codex":0.00006300766,"about_ca_system_score_gemma":0.00012899049,"threshold_uncertainty_score":0.4166072},"labels":[],"label_agreement":null},{"id":"W1964082988","doi":"10.1007/s10969-009-9071-1","title":"Structural genomics target selection for the New York consortium on membrane protein structure","year":2009,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"Genentech; National Institutes of Health; National Institute of General Medical Sciences; Magyar Tudományos Akadémia; Broad Institute; York University; University of Wisconsin-Madison","keywords":"Structural genomics; Transmembrane protein; Computational biology; Pipeline (software); Transmembrane domain; Biology; Genome; Membrane protein; Genomics; Selection (genetic algorithm); Protein structure; Bioinformatics; Genetics; Computer science; Gene; Biochemistry; Artificial intelligence; Membrane","score_opus":0.009241040380548059,"score_gpt":0.21255204995862745,"score_spread":0.20331100957807938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964082988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905299,0.0014766101,0.0055154497,0.0010940791,0.000787763,0.00046224231,0.00008874741,0.000007154504,0.00003803798],"genre_scores_gemma":[0.9851063,0.000054401666,0.010463601,0.0008703571,0.0029894235,0.0000024828112,0.00007382114,0.000021774349,0.00041784663],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987861,0.000027489115,0.0004443286,0.00026496028,0.00021005598,0.0002670873],"domain_scores_gemma":[0.9990287,0.000031170854,0.00041976263,0.00015858628,0.00021160784,0.00015016658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012508073,0.00027645097,0.0002649307,0.00006628887,0.0003420234,0.000085548425,0.00019771665,0.00021516338,0.000034522174],"category_scores_gemma":[0.00006655859,0.00017796966,0.00019026425,0.00008371132,0.00008586327,0.000018357054,0.000029976114,0.00032118228,3.7480365e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034148272,0.000006613126,0.00028208064,0.000017435654,0.00023694785,0.0000013174254,0.00007587928,0.019862255,0.9573257,0.003412744,0.0023740209,0.012990191],"study_design_scores_gemma":[0.00989332,0.008217176,0.06419173,0.000064081745,0.00052701187,0.004268938,0.00039851863,0.016669378,0.5966498,0.1330012,0.16433804,0.0017807777],"about_ca_topic_score_codex":0.000006653122,"about_ca_topic_score_gemma":0.000013395559,"teacher_disagreement_score":0.36067584,"about_ca_system_score_codex":0.00006788779,"about_ca_system_score_gemma":0.00028127737,"threshold_uncertainty_score":0.72573924},"labels":[],"label_agreement":null},{"id":"W1969747791","doi":"10.1007/s10969-011-9112-4","title":"Crystal structure of a putative transcriptional regulator SCO0520 from Streptomyces coelicolor A3(2) reveals an unusual dimer among TetR family proteins","year":2011,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Argonne National Laboratory; National Institute of General Medical Sciences; Biological and Environmental Research; National Institutes of Health; University of Chicago","keywords":"TetR; Streptomyces coelicolor; Dimer; Regulator; Repressor; Transcriptional regulation; Biology; DNA; Stereochemistry; Crystallography; Genetics; Chemistry; Streptomyces; Transcription factor; Gene; Bacteria","score_opus":0.025036856855131944,"score_gpt":0.22294152888660548,"score_spread":0.19790467203147355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969747791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971873,0.0011163389,0.000052917603,0.00018210887,0.0004213726,0.00029720066,0.00070121617,0.000008623891,0.000032918604],"genre_scores_gemma":[0.99115527,0.000037196376,0.0074823285,0.00019886288,0.0009329652,3.4582885e-7,0.00008246333,0.000019608678,0.00009095597],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99839556,0.00005961639,0.00069840695,0.00027743986,0.00037562606,0.00019337062],"domain_scores_gemma":[0.99845994,0.000043752094,0.00059077394,0.00012097439,0.00055536773,0.00022919974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001255976,0.00024734758,0.0005381634,0.00016323396,0.000118458316,0.000026388367,0.00010515526,0.00017972275,0.00041344613],"category_scores_gemma":[0.00005884301,0.00016094168,0.00018442768,0.00013521285,0.00030310894,0.00038996877,0.000029225612,0.00039880682,5.673941e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031172514,0.000055386878,0.013111514,0.000049593673,0.00040320886,0.0000129433365,0.0009758203,0.00001373686,0.9798215,0.00024668814,0.00014033193,0.0020520173],"study_design_scores_gemma":[0.0013875022,0.0010309144,0.84394336,0.0000751778,0.00030327347,0.0002857853,0.00059533195,0.000054516597,0.14760104,0.004310893,0.00021705643,0.00019516621],"about_ca_topic_score_codex":0.00013068301,"about_ca_topic_score_gemma":0.000017296032,"teacher_disagreement_score":0.8322205,"about_ca_system_score_codex":0.00007374788,"about_ca_system_score_gemma":0.0001818864,"threshold_uncertainty_score":0.65630114},"labels":[],"label_agreement":null},{"id":"W1972107709","doi":"10.1007/s10969-014-9180-3","title":"The crystal structure of pyrimidine/thiamin biosynthesis precursor-like domain-containing protein CAE31940 from proteobacterium Bordetella bronchiseptica RB50, and evolutionary insight into the NMT1/THI5 family","year":2014,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Argonne National Laboratory; National Institute of General Medical Sciences; Biological and Environmental Research; National Institutes of Health; University of Chicago; U.S. Department of Energy","keywords":"Biology; Protein domain; Bordetella bronchiseptica; Yeast; Protein family; Biochemistry; Computational biology; Microbiology; Genetics; Bacteria; Gene","score_opus":0.006292172234910668,"score_gpt":0.1845157919505316,"score_spread":0.17822361971562095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972107709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99510026,0.0020769062,0.00043323374,0.0006161215,0.0012515113,0.000310164,0.000071330935,0.000011686245,0.00012881566],"genre_scores_gemma":[0.9924364,0.00008383174,0.006125203,0.00014274563,0.0011178853,0.0000046947434,0.000011394404,0.000021924401,0.000055900382],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99806726,0.00020464795,0.0007106678,0.00029557725,0.00045267356,0.0002691903],"domain_scores_gemma":[0.9982262,0.00036260975,0.00074915984,0.00023152905,0.0002998188,0.00013064744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039044544,0.00029010235,0.00037973674,0.00008384273,0.00081505254,0.00016678667,0.00026292336,0.00016820448,0.0000838818],"category_scores_gemma":[0.00013276188,0.00015513205,0.00011859335,0.00011335059,0.0005621655,0.0003280228,0.00014431555,0.00040847666,0.0000013109138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012388547,0.000005788112,0.00079029525,0.000031065214,0.00008308477,0.0000013764516,0.0013344819,0.000119655815,0.9914967,0.0014296913,0.00013277822,0.003336247],"study_design_scores_gemma":[0.003790455,0.0028138107,0.48875597,0.00029492975,0.00055776123,0.0009322165,0.0048370655,0.0011030313,0.23411539,0.17539206,0.08616588,0.0012414211],"about_ca_topic_score_codex":0.00014315953,"about_ca_topic_score_gemma":0.00010198581,"teacher_disagreement_score":0.75738126,"about_ca_system_score_codex":0.00009824534,"about_ca_system_score_gemma":0.00015707412,"threshold_uncertainty_score":0.63261014},"labels":[],"label_agreement":null},{"id":"W1976203775","doi":"10.1007/s10969-012-9134-6","title":"Three structural representatives of the PF06855 protein domain family from Staphyloccocus aureus and Bacillus subtilis have SAM domain-like folds and different functions","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences","keywords":"Bacillus subtilis; Structural genomics; Protein family; Biology; Protein domain; Phylogenetic tree; Protein structure; Computational biology; Bacteria; Genetics; Biochemistry; Gene","score_opus":0.013236724642074357,"score_gpt":0.21551847655862802,"score_spread":0.20228175191655368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976203775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849384,0.013534606,0.00031509565,0.00016353015,0.0006049985,0.00018590949,0.00022298434,9.974256e-7,0.000033519475],"genre_scores_gemma":[0.997457,0.0003398716,0.0014652163,0.00006062503,0.0005908928,0.0000039315387,0.000014321395,0.000013248972,0.000054842196],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99898624,0.00005089346,0.00037369298,0.00020824639,0.0001760364,0.00020488074],"domain_scores_gemma":[0.9992119,0.000037616494,0.00032171243,0.0001615392,0.00013869605,0.00012854127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010902896,0.00021755141,0.00027689993,0.000041139334,0.00026376828,0.000033163058,0.00009923081,0.00010379644,0.000010378456],"category_scores_gemma":[0.000020233289,0.00013462978,0.00011814255,0.000037578408,0.0003530223,0.000009194571,0.00024030823,0.00015582041,9.5573895e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005265025,0.000012587377,0.17175727,0.000016406239,0.00042415448,8.1371377e-7,0.00057013606,0.000037051253,0.82383317,0.00027760258,0.00013675347,0.0024075487],"study_design_scores_gemma":[0.0010701056,0.00026611218,0.97758293,0.000011292988,0.00008646152,0.00010693312,0.0017478986,0.000024131006,0.0068353587,0.010052846,0.0020369103,0.0001790081],"about_ca_topic_score_codex":0.00007058802,"about_ca_topic_score_gemma":0.00009358209,"teacher_disagreement_score":0.8169978,"about_ca_system_score_codex":0.000021001977,"about_ca_system_score_gemma":0.00004683848,"threshold_uncertainty_score":0.5490043},"labels":[],"label_agreement":null},{"id":"W1982802055","doi":"10.1007/s10969-011-9121-3","title":"Solution NMR structures reveal unique homodimer formation by a winged helix-turn-helix motif and provide first structures for protein domain family PF10771","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences; Office of Science; National Institutes of Health","keywords":"Structural genomics; Helix-turn-helix; Dimer; Protein structure; DNA; Biology; DNA-binding domain; Protein family; Sequence motif; Crystallography; Helix (gastropod); Structural motif; Bacteroides thetaiotaomicron; Nuclear magnetic resonance spectroscopy; Chemistry; DNA-binding protein; Stereochemistry; Biochemistry; Genetics; Transcription factor; Gene; Bacteroides","score_opus":0.015098550140068038,"score_gpt":0.21601197488834323,"score_spread":0.2009134247482752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982802055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979664,0.0027978015,0.01498535,0.0004305785,0.00128713,0.00057633786,0.00020013055,0.000025773314,0.000032894528],"genre_scores_gemma":[0.9800892,0.00006519729,0.017753499,0.00025079565,0.0016300064,0.000018234196,0.00006902344,0.00002979228,0.00009424607],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99805754,0.000088009176,0.00073682313,0.00027144805,0.00038937907,0.000456779],"domain_scores_gemma":[0.99848354,0.000080097,0.0007420605,0.0001359326,0.00030767755,0.00025066646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052098144,0.0003439003,0.00040712068,0.00016126937,0.00064804277,0.00018818691,0.0001340221,0.0002402099,0.000055213713],"category_scores_gemma":[0.000085050444,0.00025225338,0.00012713956,0.0001039474,0.00017904719,0.0013592339,0.00007040101,0.00033260506,0.0000013786473],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001179767,0.000011681985,0.0007128085,0.00018229352,0.0000599245,0.0000010171527,0.00083081407,0.00027226648,0.98689824,0.0030707696,0.0038990257,0.0028813605],"study_design_scores_gemma":[0.010110687,0.0027809974,0.23465289,0.00027231182,0.0006821218,0.0044044387,0.0030339155,0.0015172613,0.45491874,0.22368115,0.061653744,0.0022917353],"about_ca_topic_score_codex":0.000038845326,"about_ca_topic_score_gemma":0.00001906762,"teacher_disagreement_score":0.5319795,"about_ca_system_score_codex":0.00019277062,"about_ca_system_score_gemma":0.00008581936,"threshold_uncertainty_score":0.99999297},"labels":[],"label_agreement":null},{"id":"W1988950201","doi":"10.1007/s10969-005-5277-z","title":"NMR solution structure of Thermotoga maritima protein TM1509 reveals a Zn-metalloprotease-like tertiary structure","year":2005,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Science Foundation","keywords":"Thermotoga maritima; Consensus sequence; Sequence motif; Multiple sequence alignment; Structural genomics; Sequence alignment; Conserved sequence; Protein structure; Biology; Protein tertiary structure; Peptide sequence; Protein family; Biochemistry; Gene","score_opus":0.008369195511052585,"score_gpt":0.2012453206444952,"score_spread":0.19287612513344263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988950201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99619824,0.0010625296,0.00072987704,0.00036301074,0.0009980041,0.0003190404,0.0002483103,0.000019426177,0.00006155884],"genre_scores_gemma":[0.9834431,0.000024822057,0.0142479455,0.00029183726,0.0017273455,0.0000019600625,0.000030235542,0.000027702481,0.00020505096],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99774605,0.00010210507,0.00093413086,0.00032234896,0.00055995205,0.0003354243],"domain_scores_gemma":[0.9979276,0.000047350175,0.0012012747,0.00021804652,0.00042397543,0.00018174233],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023658313,0.00033892228,0.0005096084,0.00019998511,0.0002501566,0.00008365313,0.00022650456,0.00025447525,0.001588879],"category_scores_gemma":[0.00006973444,0.00024388448,0.0001958953,0.00015652928,0.00021747829,0.00067857804,0.00009521093,0.0004648588,0.0000038046026],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066303514,0.000012152659,0.0010408874,0.00007930244,0.0000751085,0.0000060801794,0.0001790968,0.0010985632,0.99007434,0.00059408386,0.0003796177,0.005797748],"study_design_scores_gemma":[0.0041881646,0.001036384,0.32373196,0.000217533,0.00042884945,0.0045853006,0.00034069063,0.0013450917,0.60771924,0.049425993,0.005915025,0.0010657615],"about_ca_topic_score_codex":0.000024971514,"about_ca_topic_score_gemma":0.000032032767,"teacher_disagreement_score":0.38235506,"about_ca_system_score_codex":0.00015486337,"about_ca_system_score_gemma":0.00015135897,"threshold_uncertainty_score":0.9993238},"labels":[],"label_agreement":null},{"id":"W1989259734","doi":"10.1007/s10969-012-9127-5","title":"Crystal structure of a putative isochorismatase hydrolase from Oleispira antarctica","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Production and Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Argonne National Laboratory; National Institute of General Medical Sciences; Biological and Environmental Research; National Institutes of Health; University of Chicago","keywords":"Hydrolase; Structural genomics; Crystal structure; Chemistry; Biology; Crystallography; Protein structure; Enzyme; Biochemistry","score_opus":0.008212539600205014,"score_gpt":0.21491802162171178,"score_spread":0.20670548202150676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989259734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971671,0.00090818596,0.0008555245,0.0001212162,0.0005686648,0.000038033115,0.0003317185,0.0000013314141,0.000008229757],"genre_scores_gemma":[0.99665844,0.00009881565,0.0013879515,0.0001253504,0.0014036201,2.3777794e-7,0.00029307505,0.000008207753,0.000024325032],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994039,0.000026857077,0.0002641468,0.00009450674,0.00011123904,0.0000993793],"domain_scores_gemma":[0.9993893,0.000009651841,0.00029543336,0.00006616318,0.0001470182,0.000092457434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053198437,0.00009766964,0.00013360614,0.0000395435,0.00005191205,0.000011829273,0.000043860204,0.00007561065,0.000069382295],"category_scores_gemma":[0.00003248976,0.000077094206,0.00006269132,0.000038971557,0.00006268453,0.00002713213,0.00003425323,0.00010827737,4.525177e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041749186,0.000014136945,0.008829606,0.000008792866,0.00009980093,4.164243e-7,0.00019260972,0.00010798411,0.9895094,0.000057757527,0.00017346363,0.00058853225],"study_design_scores_gemma":[0.0010733566,0.00034643858,0.20054187,0.000008266442,0.000100838806,0.000419492,0.00043386387,0.00007242901,0.78748417,0.0009145825,0.008413118,0.0001915406],"about_ca_topic_score_codex":0.000005770761,"about_ca_topic_score_gemma":8.545701e-7,"teacher_disagreement_score":0.2020252,"about_ca_system_score_codex":0.000015113039,"about_ca_system_score_gemma":0.000039462557,"threshold_uncertainty_score":0.31438103},"labels":[],"label_agreement":null},{"id":"W1994346628","doi":"10.1007/s10969-007-9019-2","title":"Insights into the biology of Escherichia coli through structural proteomics","year":2007,"lang":"en","type":"review","venue":"Journal of Structural and Functional Genomics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Queen's University; National Research Council Canada; Biotechnology Research Institute","funders":"","keywords":"Structural genomics; Biology; Escherichia coli; Computational biology; Proteomics; Function (biology); Functional genomics; Organism; Genomics; Structural biology; Model organism; Bacterial protein; Genome; Biochemistry; Genetics; Protein structure; Bacteria; Gene","score_opus":0.03257521711177249,"score_gpt":0.2860169434024889,"score_spread":0.25344172629071643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994346628","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107484356,0.89008003,0.0008969196,0.000027294012,0.0011087301,0.0003250807,0.000020423395,0.0000017504657,0.00005541127],"genre_scores_gemma":[0.0073153614,0.9842004,0.006173296,0.000084277555,0.0020297782,0.0000071633617,0.000067140805,0.000035187757,0.00008737615],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983581,0.0001369732,0.0009094112,0.00024603753,0.00016375932,0.00018573293],"domain_scores_gemma":[0.99814516,0.00007153823,0.0012625449,0.0002157458,0.00022948137,0.00007551542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022221074,0.0003499531,0.00086495886,0.00007743278,0.000168344,0.000026797437,0.00031577377,0.00047642455,0.00001809653],"category_scores_gemma":[0.000059702932,0.00019219272,0.00044469183,0.00010969299,0.00025394317,0.000011005124,0.0001476185,0.00037693145,9.705388e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090233306,0.000022396955,0.000040531027,0.002725725,0.0021553333,0.000010718944,0.0004820792,0.00005675169,0.23886067,0.0091030635,0.0002811251,0.7453593],"study_design_scores_gemma":[0.00032856409,0.0005317479,0.000072581155,0.0002890184,0.00036663015,0.0003493371,0.00007515246,0.000004180426,0.009654809,0.009466328,0.9785507,0.00031100464],"about_ca_topic_score_codex":0.000011276974,"about_ca_topic_score_gemma":0.000007679727,"teacher_disagreement_score":0.9782695,"about_ca_system_score_codex":0.000044810506,"about_ca_system_score_gemma":0.0003445579,"threshold_uncertainty_score":0.78373915},"labels":[],"label_agreement":null},{"id":"W1996739157","doi":"10.1007/s10969-010-9095-6","title":"Fully automated high-quality NMR structure determination of small 2H-enriched proteins","year":2010,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; U.S. Public Health Service; National Institutes of Health","keywords":"Structural genomics; Crystal structure; Chemistry; Crystallography; Protein structure; Protonation; High resolution; Nuclear magnetic resonance spectroscopy; Stereochemistry; Biochemistry","score_opus":0.0076591753840881795,"score_gpt":0.2310563185159668,"score_spread":0.22339714313187864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996739157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947064,0.00017009067,0.004152763,0.00008745945,0.00062347425,0.00013889614,0.00008436784,0.000008628402,0.000027920685],"genre_scores_gemma":[0.9701082,0.000023938032,0.028997116,0.00007616707,0.00064805336,0.0000012588476,0.00008225461,0.000013772135,0.000049243772],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989344,0.000038864102,0.0005140885,0.00017937274,0.00018357919,0.00014969324],"domain_scores_gemma":[0.99868435,0.000018370029,0.0006092976,0.00015748323,0.0004309869,0.00009954171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017367817,0.0001753652,0.00025414932,0.00007647876,0.00009124743,0.000027836637,0.00014031302,0.00025373878,0.000030308716],"category_scores_gemma":[0.00011096455,0.00013444338,0.000109453715,0.00007134036,0.00012720887,0.000015989763,0.00007095272,0.00030165006,2.221605e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043353677,0.000008694353,0.0022872265,0.000035972862,0.000059830105,0.0000021987921,0.000031920004,0.00021941513,0.9893278,0.0011037604,0.000023895174,0.0064657787],"study_design_scores_gemma":[0.0028028768,0.0010369776,0.69845074,0.000016325876,0.00013188388,0.0014087266,0.0000937983,0.002763634,0.26598588,0.025220953,0.0015487187,0.00053947297],"about_ca_topic_score_codex":0.000017403227,"about_ca_topic_score_gemma":0.000067641944,"teacher_disagreement_score":0.7233419,"about_ca_system_score_codex":0.000018546769,"about_ca_system_score_gemma":0.00015319083,"threshold_uncertainty_score":0.5482442},"labels":[],"label_agreement":null},{"id":"W1999196452","doi":"10.1007/s10969-010-9083-x","title":"Efficient condensed-phase production of perdeuterated soluble and membrane proteins","year":2010,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences; U.S. Public Health Service","keywords":"Membrane protein; Membrane; Escherichia coli; Chemistry; Protein structure; Biochemistry; Biophysics; Crystallography; Biology","score_opus":0.006285261081451179,"score_gpt":0.22156421216153346,"score_spread":0.2152789510800823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999196452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99798346,0.00037963528,0.00044777038,0.00014405114,0.0008873872,0.00012069163,0.000011825293,0.0000017858162,0.000023371571],"genre_scores_gemma":[0.9960836,0.000049552214,0.0031544564,0.000035490826,0.0005402492,0.0000011130298,0.00001673215,0.000007656842,0.000111144815],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938303,0.000013697688,0.0002625805,0.00013565445,0.000109650224,0.00009535727],"domain_scores_gemma":[0.9993558,0.000005938039,0.00022789139,0.00008527962,0.0002525548,0.00007255512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012841073,0.00010317893,0.0001490782,0.000048124853,0.000081336766,0.000018186838,0.000045260167,0.00009828725,0.000013313072],"category_scores_gemma":[0.000052085044,0.000077582445,0.000048589027,0.00003927357,0.0001392148,0.0000059741196,0.000040325718,0.000170805,1.2696438e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059164275,0.000016891558,0.0003467587,0.000025530524,0.00005616832,0.0000016618104,0.00004792277,0.0007567159,0.9957501,0.0002662826,0.00004027183,0.002100053],"study_design_scores_gemma":[0.004546342,0.0017372834,0.022819884,0.000025867617,0.0001430371,0.004652128,0.00018717904,0.0060095033,0.95205545,0.0020506496,0.005367455,0.00040520183],"about_ca_topic_score_codex":0.000003253171,"about_ca_topic_score_gemma":0.0000061645815,"teacher_disagreement_score":0.04369463,"about_ca_system_score_codex":0.0000063323596,"about_ca_system_score_gemma":0.00008178023,"threshold_uncertainty_score":0.31637204},"labels":[],"label_agreement":null},{"id":"W2002288604","doi":"10.1007/s10969-011-9114-2","title":"The success of structural genomics","year":2011,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Structural genomics; Genomics; Computational biology; Genome Biology; Functional genomics; Data science; Biology; Computer science; Genome; Genetics; Protein structure; Gene; Biochemistry","score_opus":0.021238899856874823,"score_gpt":0.24365658385208339,"score_spread":0.22241768399520856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002288604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969019,0.0016302931,0.00030652102,0.00010888484,0.0006584225,0.00006546873,0.000024253284,0.0000010960135,0.0003031232],"genre_scores_gemma":[0.99608123,0.0011949908,0.0019190597,0.000072048744,0.0005333431,5.398416e-7,0.000013607396,0.000008259287,0.00017688972],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989292,0.000025561532,0.00049959467,0.000097904325,0.0002486571,0.00019907333],"domain_scores_gemma":[0.9990276,0.000029214278,0.00033110115,0.00012999588,0.0003406774,0.00014139527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027665735,0.000119310884,0.00016188333,0.000047595982,0.00016496018,0.000029804014,0.0002410167,0.00010546741,0.000032737364],"category_scores_gemma":[0.00008452436,0.00006998496,0.000117106436,0.000047849626,0.0003860746,0.0000106639045,0.00013397726,0.00016621828,0.0000010192929],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005938906,0.00005651568,0.061563022,0.00022357465,0.0012692524,0.000014239624,0.0016700983,0.00026413446,0.7729087,0.0034455452,0.00352964,0.14911637],"study_design_scores_gemma":[0.0027955987,0.0026998923,0.75985616,0.000027808073,0.00013749361,0.0012358981,0.0019646194,0.0012925866,0.16934778,0.014173848,0.045909476,0.0005588345],"about_ca_topic_score_codex":0.000012113894,"about_ca_topic_score_gemma":0.000013185044,"teacher_disagreement_score":0.69829315,"about_ca_system_score_codex":0.000021168142,"about_ca_system_score_gemma":0.0001709206,"threshold_uncertainty_score":0.28539038},"labels":[],"label_agreement":null},{"id":"W2005913854","doi":"10.1007/s10969-009-9076-9","title":"Protein crystallization analysis on the World Community Grid","year":2010,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"National Institutes of Health; National Institute of General Medical Sciences; Conquer Cancer Foundation","keywords":"Crystallization; Protein crystallization; Throughput; Computer science; Grid; Random forest; Set (abstract data type); Image (mathematics); Artificial intelligence; Pattern recognition (psychology); Mathematics; Engineering","score_opus":0.009274677604603711,"score_gpt":0.22991663857703923,"score_spread":0.22064196097243552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005913854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979104,0.000043803662,0.0012794886,0.00027013195,0.000056060962,0.00005278329,0.000004390414,0.0000024095032,0.0003805687],"genre_scores_gemma":[0.9978477,0.000018146618,0.000955825,0.0002572439,0.0004265811,0.0000014298386,0.00004033766,0.000005471286,0.00044729913],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994861,0.000059686008,0.00020311412,0.00007234591,0.000111942725,0.000066822395],"domain_scores_gemma":[0.99938405,0.00002517109,0.00020709926,0.00016791094,0.00017536616,0.00004037905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003006029,0.00008159327,0.00011311403,0.00011061431,0.0001881074,0.00004307452,0.00011452701,0.000047864192,0.000079797865],"category_scores_gemma":[0.000061847604,0.000050123992,0.00013989845,0.0001677642,0.00007848896,0.0000067106735,0.000049704522,0.00034975735,4.2526884e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011727663,0.000012714732,0.0021183456,0.0000023879481,0.00033040025,6.456936e-7,0.00001722497,0.0002761484,0.9949979,0.0004914253,0.0010291337,0.0006063622],"study_design_scores_gemma":[0.00063971936,0.0006255564,0.20445032,0.000011178166,0.0008461359,0.00015745868,0.0002465986,0.0010838697,0.7203551,0.005526921,0.06567059,0.00038657323],"about_ca_topic_score_codex":0.000011741685,"about_ca_topic_score_gemma":0.00024090633,"teacher_disagreement_score":0.27464285,"about_ca_system_score_codex":0.000010391798,"about_ca_system_score_gemma":0.000026996418,"threshold_uncertainty_score":0.2043997},"labels":[],"label_agreement":null},{"id":"W2006446553","doi":"10.1007/s10969-005-5243-9","title":"Automatic Classification and Pattern Discovery in High-throughput Protein Crystallization Trials","year":2005,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Crystallization; Protein crystallization; Throughput; Identification (biology); Computer science; Data mining; Process (computing); Pattern recognition (psychology); Artificial intelligence; Biology; Chemistry","score_opus":0.027300690248202256,"score_gpt":0.268737495241601,"score_spread":0.24143680499339876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006446553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9614514,0.0002307568,0.037392706,0.0007114173,0.000028326209,0.00011764328,0.000023839817,0.000010212907,0.00003367114],"genre_scores_gemma":[0.97667116,0.0001891892,0.022587338,0.000047009817,0.00036984836,0.000013595812,0.00002220054,0.00000937611,0.00009028027],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999094,0.000016844779,0.0005769443,0.00011997988,0.00010727616,0.00008492907],"domain_scores_gemma":[0.9992755,0.000055971406,0.00049713586,0.00006911276,0.000059987837,0.000042289044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019546003,0.0000994262,0.00022080357,0.000056935314,0.00006999409,0.00006052291,0.00004812402,0.00007290778,0.00007354377],"category_scores_gemma":[0.000043414,0.000078080746,0.000040682095,0.000048270325,0.00004235453,0.00036897574,0.000024981255,0.00016288883,3.9089292e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013895998,0.000029100887,0.0045603067,0.000089422705,0.000039349674,0.0000014666563,0.00012868512,0.0009508109,0.8687559,0.007331341,0.00004482426,0.117929876],"study_design_scores_gemma":[0.009903496,0.00038291857,0.33312866,0.00065925805,0.00030024073,0.0012214782,0.0012344597,0.10852177,0.22543217,0.30361742,0.014058101,0.0015400418],"about_ca_topic_score_codex":0.0000073603574,"about_ca_topic_score_gemma":0.0000063352504,"teacher_disagreement_score":0.6433237,"about_ca_system_score_codex":0.00011645418,"about_ca_system_score_gemma":0.000038186885,"threshold_uncertainty_score":0.31840402},"labels":[],"label_agreement":null},{"id":"W2011846385","doi":"10.1007/s10969-014-9189-7","title":"Structural characterization of the putative ABC-type 2 transporter from Thermotoga maritima MSB8","year":2014,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Drug Transport and Resistance Mechanisms","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Argonne National Laboratory; National Institute of General Medical Sciences; Wellcome Trust; Biological and Environmental Research; National Institutes of Health; University of Chicago","keywords":"Thermotoga maritima; ATP-binding cassette transporter; Efflux; Permease; Biology; Biochemistry; Dimer; Cyclic nucleotide-binding domain; Transporter; Peptide sequence; Chemistry; Gene","score_opus":0.00995485286388935,"score_gpt":0.19622063338310833,"score_spread":0.18626578051921897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011846385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99745166,0.00009597247,0.00070881785,0.00046184153,0.0010451261,0.00009888123,0.00006250817,0.0000036596957,0.00007151837],"genre_scores_gemma":[0.9983386,0.00004663703,0.0006272151,0.00023149097,0.0005143729,3.3717038e-7,0.00007230211,0.000011247704,0.00015783646],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99914986,0.000021365171,0.00038451247,0.000101775746,0.00024380446,0.000098688244],"domain_scores_gemma":[0.9992714,0.00002556122,0.0003242359,0.00007907847,0.00022823174,0.00007149266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008198152,0.00012070904,0.00027798087,0.000044163295,0.000089963745,0.0000113827045,0.00006317989,0.00007140878,0.0001937282],"category_scores_gemma":[0.000008099165,0.00006642475,0.00013701602,0.00007427622,0.00010354716,0.00010409904,0.0000061845208,0.00019891575,5.046927e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002079128,0.000012453942,0.037404828,0.000055879955,0.00023487528,0.0000068534046,0.00077858433,0.00008186993,0.9502877,0.0008880444,0.000009758494,0.008160019],"study_design_scores_gemma":[0.0011705533,0.00017380917,0.9781097,0.000047525653,0.00018392749,0.00011916498,0.00010521666,0.0004350611,0.0145851495,0.004556263,0.00043458777,0.00007904303],"about_ca_topic_score_codex":0.000007345413,"about_ca_topic_score_gemma":0.0000034862592,"teacher_disagreement_score":0.9407049,"about_ca_system_score_codex":0.000029730776,"about_ca_system_score_gemma":0.000068294095,"threshold_uncertainty_score":0.27087227},"labels":[],"label_agreement":null},{"id":"W2011850983","doi":"10.1007/s10969-012-9123-9","title":"Canadian macromolecular crystallography facility: a suite of fully automated beamlines","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Light Source (Canada); University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Saskatchewan","keywords":"Beamline; Automation; Undulator; Suite; Computer science; Engineering; Physics; Optics; Beam (structure); Mechanical engineering; Geography","score_opus":0.008762474943783394,"score_gpt":0.2042243243349998,"score_spread":0.19546184939121639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011850983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967584,0.0011327862,0.0002548169,0.00011522759,0.0014302351,0.00005713869,0.0001421156,0.000015373995,0.00009390544],"genre_scores_gemma":[0.99784553,0.000024553965,0.0015493658,0.00012585106,0.00039812308,5.492281e-7,0.000018003677,0.000006433099,0.000031582957],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99895763,0.00003461228,0.0004268583,0.00010269751,0.00022056446,0.00025764122],"domain_scores_gemma":[0.9990605,0.000030436957,0.0002953263,0.00008490746,0.0002613033,0.00026750908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026638884,0.00013606524,0.00023882733,0.00020614217,0.00012817576,0.000034668446,0.00008441235,0.00009024181,0.0003086244],"category_scores_gemma":[0.00003327183,0.00010113229,0.00011471928,0.00013445222,0.00009970243,0.00029708323,0.00002458961,0.0001296205,0.0000030883903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021506584,0.000008487978,0.021221751,0.00003892759,0.00007350445,0.000006345303,0.0002856514,0.00051200006,0.97560114,0.00046278178,0.00065046904,0.00092386134],"study_design_scores_gemma":[0.0020731504,0.000743381,0.85391957,0.000047968948,0.00036099445,0.0039975746,0.00084770046,0.000688259,0.10132948,0.005674264,0.029582614,0.0007350438],"about_ca_topic_score_codex":0.0012246552,"about_ca_topic_score_gemma":0.00058210664,"teacher_disagreement_score":0.8742717,"about_ca_system_score_codex":0.000080110716,"about_ca_system_score_gemma":0.0001539481,"threshold_uncertainty_score":0.4124055},"labels":[],"label_agreement":null},{"id":"W2028079766","doi":"10.1007/s10969-013-9159-5","title":"Solution NMR structures provide first structural coverage of the large protein domain family PF08369 and complementary structural coverage of dark operative protochlorophyllide oxidoreductase complexes","year":2013,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Photosynthetic Processes and Mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Protochlorophyllide; Structural genomics; Oxidoreductase; Structural biology; Domain (mathematical analysis); Chemistry; Protein structure; Crystallography; Biochemistry; Enzyme","score_opus":0.007981530459450707,"score_gpt":0.21997556828644665,"score_spread":0.21199403782699594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028079766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99629754,0.00051901257,0.0009041908,0.00019041418,0.0002484079,0.0012469043,0.00056539325,0.0000026354953,0.000025473548],"genre_scores_gemma":[0.9971233,0.000075118245,0.0022615688,0.00015019771,0.00023931783,0.000023583767,0.00008283277,0.000018940316,0.000025130428],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983686,0.000075470816,0.00068371865,0.00027672862,0.00032621223,0.00026921966],"domain_scores_gemma":[0.99856997,0.000022593344,0.0007363417,0.00019033902,0.00035962937,0.0001211465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014142718,0.00029408064,0.0004006684,0.000059294805,0.00033439873,0.0000585936,0.00023174638,0.000112584814,0.00006204452],"category_scores_gemma":[0.000040960156,0.00018730992,0.00014790214,0.00007643852,0.00029771382,0.00006146888,0.00026080376,0.00022639692,1.4662173e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007365247,0.000012912859,0.0014019995,0.00015027361,0.00017790642,0.0000015152011,0.00023797965,0.00038586065,0.9941984,0.0016142647,0.00006821498,0.0010141801],"study_design_scores_gemma":[0.00436429,0.0016024229,0.14962439,0.00012236442,0.00012297822,0.00076722476,0.0011725738,0.0007890448,0.7697638,0.06975582,0.0013823337,0.0005327185],"about_ca_topic_score_codex":0.00012407349,"about_ca_topic_score_gemma":0.000047475387,"teacher_disagreement_score":0.22443454,"about_ca_system_score_codex":0.00004697247,"about_ca_system_score_gemma":0.00018121558,"threshold_uncertainty_score":0.7638277},"labels":[],"label_agreement":null},{"id":"W2030909614","doi":"10.1007/s10969-005-1363-5","title":"High-throughput production of prokaryotic membrane proteins","year":2005,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"Canada Research Chairs; Ontario Genomics Institute; Genome Canada","keywords":"Escherichia coli; Membrane protein; Biology; Transmembrane protein; Thermophile; Biochemistry; Thermotoga maritima; Integral membrane protein; Membrane; Gene; Enzyme","score_opus":0.00960853867886387,"score_gpt":0.20267470403158272,"score_spread":0.19306616535271884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030909614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99685806,0.0008817644,0.0009600459,0.00056743465,0.0005559033,0.00013693573,0.000005773162,0.0000018986948,0.000032188564],"genre_scores_gemma":[0.9833324,0.00022499384,0.014338653,0.00005699928,0.0016347247,0.0000023476432,0.000008605647,0.000009939962,0.0003913645],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992735,0.000026594349,0.0003247424,0.00013084312,0.00014604918,0.00009829836],"domain_scores_gemma":[0.9993731,0.0000060624157,0.00030189875,0.00009236636,0.00017433337,0.000052261435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017128565,0.00010277339,0.00016229815,0.000044148073,0.000062476436,0.000010729493,0.000065869484,0.00007861085,0.000037708796],"category_scores_gemma":[0.00004779004,0.00007703721,0.00007690432,0.000038612296,0.000059012742,0.000015424612,0.000030276766,0.00007952192,0.0000010752535],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044014893,0.000015228486,0.00021040726,0.000026485446,0.000073451556,6.775033e-7,0.000029228882,0.0012117393,0.987138,0.00042209646,0.00012313016,0.010309447],"study_design_scores_gemma":[0.00046178207,0.00047500228,0.0069011124,0.00001685939,0.000038798822,0.00045877366,0.00003783123,0.000023687147,0.9847737,0.001393731,0.0053068693,0.00011185412],"about_ca_topic_score_codex":0.0000040423283,"about_ca_topic_score_gemma":0.000003062497,"teacher_disagreement_score":0.013525684,"about_ca_system_score_codex":0.000017562568,"about_ca_system_score_gemma":0.00007278906,"threshold_uncertainty_score":0.31414863},"labels":[],"label_agreement":null},{"id":"W2031800434","doi":"10.1007/s10969-005-9004-6","title":"The crystal structure of Rv0793, a hypothetical monooxygenase from M.␣tuberculosis","year":2006,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Biochemical and Molecular Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Lawrence Berkeley National Laboratory","keywords":"Mycobacterium tuberculosis; Tuberculosis; Polyketide; Biology; Streptomyces coelicolor; Microbiology; Oxidoreductase; Open reading frame; Bacteria; Computational biology; Function (biology); Escherichia coli; Monooxygenase; Structural genomics; Genetics; Protein structure; Gene; Streptomyces; Biochemistry; Peptide sequence; Biosynthesis; Cytochrome P450; Enzyme","score_opus":0.005991765149452562,"score_gpt":0.2057240224097127,"score_spread":0.19973225726026012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031800434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99560004,0.003374117,0.0003478651,0.00032102643,0.00015809537,0.000048351565,0.0000935286,0.0000010584891,0.000055921602],"genre_scores_gemma":[0.99787664,0.00018905448,0.0010783601,0.000060548617,0.0006590721,4.2664897e-7,0.000045534813,0.000009673567,0.00008070753],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916774,0.000031248615,0.00031099873,0.00013268912,0.00020898033,0.00014835675],"domain_scores_gemma":[0.9994407,0.000033898727,0.00015342816,0.00011180067,0.0001800042,0.00008012414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006554293,0.00011217869,0.00013851542,0.000024655383,0.0001099046,0.000030160725,0.00012200645,0.000114313305,0.000025621077],"category_scores_gemma":[0.000039308445,0.00006736706,0.00013460056,0.000043180862,0.00021389229,0.0000047687463,0.000084424544,0.00016707533,3.2186463e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005171832,0.000010149859,0.0008024313,0.000005197792,0.000092559996,0.0000021981969,0.00000636468,0.00012756373,0.99582785,0.00044565758,0.0007676585,0.0013951613],"study_design_scores_gemma":[0.0011085067,0.00036678702,0.04447492,0.000009423872,0.000065839806,0.00034850166,0.000072612536,0.00014198704,0.9094081,0.02472032,0.019094378,0.00018860452],"about_ca_topic_score_codex":0.000036928457,"about_ca_topic_score_gemma":0.000016708718,"teacher_disagreement_score":0.086419754,"about_ca_system_score_codex":0.000014516367,"about_ca_system_score_gemma":0.00006926578,"threshold_uncertainty_score":0.2747149},"labels":[],"label_agreement":null},{"id":"W2032362701","doi":"10.1007/s10969-011-9117-z","title":"Solution NMR structure of Dsy0195 homodimer from Desulfitobacterium hafniense: first structure representative of the YabP domain family of proteins involved in spore coat assembly","year":2011,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"Pacific Northwest National Laboratory; Biological and Environmental Research; National Institute of General Medical Sciences; University of Miami; U.S. Department of Energy","keywords":"Protein structure; Heteronuclear single quantum coherence spectroscopy; Biology; Domain (mathematical analysis); Spore; Biochemistry; Protein family; Nuclear magnetic resonance spectroscopy; Chemistry; Crystallography; Cell biology; Stereochemistry; Microbiology; Gene","score_opus":0.01804347108160921,"score_gpt":0.2053337360740678,"score_spread":0.1872902649924586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032362701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99730706,0.0014977347,0.000079063415,0.000045471705,0.00036576067,0.00018046833,0.00050894974,4.1982207e-7,0.0000150470505],"genre_scores_gemma":[0.99612045,0.00017582311,0.0034456884,0.000028314613,0.00018141064,8.5940854e-7,0.000028279046,0.000011303544,0.000007882167],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988373,0.000054840995,0.0006025159,0.00018654906,0.00018209759,0.00013673292],"domain_scores_gemma":[0.99857545,0.00002248613,0.00082449074,0.00018703335,0.0003451955,0.00004534252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082421466,0.0001751976,0.00035041204,0.000060050366,0.00007025704,0.0000057816205,0.00018105349,0.00015173841,0.000013286663],"category_scores_gemma":[0.000035373203,0.00011763455,0.0001368546,0.00009417824,0.00028143893,0.000006987332,0.0001502403,0.00016474875,3.298418e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089210324,0.000016943668,0.079115584,0.000027622877,0.00021073494,0.0000010093858,0.0009704884,0.00039726356,0.91808945,0.00007447566,0.000050473143,0.00015386479],"study_design_scores_gemma":[0.00077376177,0.0002379621,0.68543035,0.000025254418,0.000049180173,0.000022383116,0.0007809155,0.000017697303,0.30874604,0.0037381072,0.000083635525,0.00009472247],"about_ca_topic_score_codex":0.00028651764,"about_ca_topic_score_gemma":0.0004003232,"teacher_disagreement_score":0.6093434,"about_ca_system_score_codex":0.000023899667,"about_ca_system_score_gemma":0.00013313595,"threshold_uncertainty_score":0.47969976},"labels":[],"label_agreement":null},{"id":"W2048205675","doi":"10.1007/s10969-007-9027-2","title":"The scientific impact of the Structural Genomics Consortium: a protein family and ligand-centered approach to medically-relevant human proteins","year":2007,"lang":"en","type":"review","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Knut och Alice Wallenbergs Stiftelse; Karolinska Institutet; Wellcome Trust; VINNOVA; Stiftelsen för Strategisk Forskning; Canadian Institutes of Health Research; Genome Canada; Ontario Innovation Trust","keywords":"Structural genomics; Computational biology; Genomics; Biology; Protein family; Human proteins; Proteomics; Protein structure; Genome; Gene; Data science; Genetics; Computer science; Biochemistry","score_opus":0.049956712173686794,"score_gpt":0.2998952348970853,"score_spread":0.2499385227233985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048205675","genre_codex":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60806185,0.38884896,0.000119478114,0.00003174587,0.0016106466,0.0011030425,0.00016232664,0.0000075097278,0.000054421424],"genre_scores_gemma":[0.45523706,0.5248087,0.00987282,0.0002533855,0.0076859533,0.00010608896,0.00017791013,0.00031446456,0.0015435799],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966051,0.00017547546,0.0015560307,0.0004576631,0.0007583973,0.00044736246],"domain_scores_gemma":[0.9970076,0.00013481123,0.0017610469,0.0003771616,0.00042618826,0.0002931693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012129929,0.0005096969,0.0011435732,0.00022470602,0.0010970874,0.000412945,0.00058525236,0.00028812996,0.00002105291],"category_scores_gemma":[0.00013113262,0.00022839755,0.000582306,0.00032549253,0.0009351087,0.00017851136,0.00031310596,0.000777225,0.00000166196],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018720627,0.00008426177,0.00028109286,0.006066108,0.0016880416,0.000020030553,0.001589387,0.00039998617,0.5096936,0.0060177497,0.0019520232,0.4703356],"study_design_scores_gemma":[0.006570128,0.004305041,0.046756744,0.008772718,0.004460847,0.014873889,0.0013419356,0.0003609837,0.0067438665,0.020127837,0.8818318,0.00385421],"about_ca_topic_score_codex":0.00003488251,"about_ca_topic_score_gemma":0.000015960493,"teacher_disagreement_score":0.8798798,"about_ca_system_score_codex":0.00035518952,"about_ca_system_score_gemma":0.00086731307,"threshold_uncertainty_score":0.9313782},"labels":[],"label_agreement":null},{"id":"W2057310817","doi":"10.1007/s10969-012-9130-x","title":"Target selection for structural genomics based on combining fold recognition and crystallisation prediction methods: application to the human proteome","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Karolinska Institutet; University of Toronto","keywords":"Human proteome project; Proteome; Structural genomics; Protein Data Bank (RCSB PDB); Computational biology; Protein crystallization; Protein Data Bank; Genomics; Biology; Crystallization; Computer science; Proteomics; Crystallography; Genome; Protein structure; Bioinformatics; Genetics; Chemistry; Gene; Biochemistry","score_opus":0.03411956348305664,"score_gpt":0.27346887615640875,"score_spread":0.2393493126733521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057310817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84444267,0.00012410947,0.15324257,0.00020523729,0.0012884749,0.00055261183,0.00009792801,0.00001804176,0.000028331673],"genre_scores_gemma":[0.9483458,0.0000053699587,0.049183138,0.00029284786,0.00200683,0.00004649539,0.00007665092,0.000019466159,0.000023393839],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99878585,0.00009990156,0.00045961677,0.00020855549,0.00022012516,0.00022597119],"domain_scores_gemma":[0.9989341,0.00013092005,0.00045271186,0.00009000316,0.000256402,0.00013589834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009365116,0.00018108274,0.00020147204,0.00014693454,0.0006120347,0.000110821136,0.00007079028,0.000108632004,0.00006095923],"category_scores_gemma":[0.00006706884,0.00012648161,0.000070777285,0.00011347485,0.000051806954,0.00040801906,0.000023078632,0.00019238288,0.00000191089],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007824809,0.000011870847,0.0020686341,0.000039626222,0.000033827306,6.604969e-8,0.00070717453,0.009468883,0.9758155,0.00085241173,0.00024677868,0.00997275],"study_design_scores_gemma":[0.0066754725,0.0047661928,0.4151274,0.0001204108,0.00074673863,0.0010317585,0.0020660334,0.10266645,0.36464906,0.07110648,0.029696807,0.0013471844],"about_ca_topic_score_codex":0.000014732715,"about_ca_topic_score_gemma":0.000004395135,"teacher_disagreement_score":0.6111664,"about_ca_system_score_codex":0.0001929877,"about_ca_system_score_gemma":0.00004401935,"threshold_uncertainty_score":0.515777},"labels":[],"label_agreement":null},{"id":"W2067847540","doi":"10.1007/s10969-009-9067-x","title":"Independently inducible system of gene expression for condensed single protein production (cSPP) suitable for high efficiency isotope enrichment","year":2009,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Virus-based gene therapy research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences; U.S. Public Health Service","keywords":"Chemistry; Protein biosynthesis; lac operon; Structural genomics; Biochemistry; Isotope; Stable isotope ratio; Gene expression; Gene; Protein structure","score_opus":0.019907680456250704,"score_gpt":0.2518646028660169,"score_spread":0.2319569224097662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067847540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99459964,0.0008547555,0.0033780634,0.00015695239,0.0003261423,0.00063176866,0.00003955672,0.0000027677838,0.000010360519],"genre_scores_gemma":[0.9949576,0.00001737045,0.0040069874,0.000033523425,0.000656023,0.000014923855,0.000043697797,0.0000113476935,0.00025849818],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989986,0.000029450128,0.00037596622,0.00020841972,0.00020648977,0.00018108798],"domain_scores_gemma":[0.99898267,0.000011723615,0.00033282972,0.000119959645,0.00048350482,0.00006932587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037096627,0.000120635625,0.00019522302,0.00008317101,0.0001317982,0.000023357581,0.00009918186,0.00011124457,0.0000059395156],"category_scores_gemma":[0.00005218657,0.00009444789,0.000091767615,0.00005701679,0.000037292037,0.000014887563,0.000019892705,0.00008784848,1.8256449e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066034566,0.000048578833,0.000053182903,0.000060300074,0.000049257753,4.2559438e-7,0.000038786075,0.0014904796,0.98999023,0.000065262655,0.00012732287,0.001472721],"study_design_scores_gemma":[0.0016214738,0.006345448,0.00084511563,0.000026356134,0.000021871438,0.000079297184,0.00012877973,0.00008095513,0.98996544,0.00041221676,0.00036777873,0.00010528579],"about_ca_topic_score_codex":0.0000020056445,"about_ca_topic_score_gemma":0.0000014033717,"teacher_disagreement_score":0.006296869,"about_ca_system_score_codex":0.00007285167,"about_ca_system_score_gemma":0.00014557852,"threshold_uncertainty_score":0.3851473},"labels":[],"label_agreement":null},{"id":"W2075697623","doi":"10.1007/s10969-005-9001-9","title":"Crystal structures of a phosphotransacetylase from Bacillus subtilis and its complex with acetyl phosphate","year":2005,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Basic Energy Sciences; National Institute of General Medical Sciences; National Institutes of Health; U.S. Department of Energy","keywords":"Cofactor; Bacillus subtilis; Enzyme; Biochemistry; Dehydrogenase; Transferase; Phosphate; Acetyl-CoA; Oxidoreductase; Substrate (aquarium); Binding site; Stereochemistry; Isocitrate dehydrogenase; Active site; Chemistry; Biology; Bacteria","score_opus":0.015230629731186458,"score_gpt":0.20502133398984274,"score_spread":0.18979070425865627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075697623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957591,0.002763811,0.00050233456,0.00019170131,0.00041786945,0.00008385604,0.00021491063,0.000009182499,0.000057189518],"genre_scores_gemma":[0.99282444,0.00019043533,0.0062329494,0.00014732362,0.00053125183,6.71044e-7,0.00001531305,0.000014574045,0.00004306993],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987559,0.00002758883,0.00048037915,0.00021647711,0.00032891313,0.00019079054],"domain_scores_gemma":[0.9989922,0.00006912734,0.00043790974,0.00009070406,0.00025397772,0.00015605033],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010835455,0.00021688582,0.0003743935,0.000073712195,0.00015174503,0.000060104496,0.00010034265,0.00009076845,0.0010324694],"category_scores_gemma":[0.000014323639,0.00014451981,0.00007189022,0.000080544014,0.00017511606,0.0004175432,0.000034475735,0.0001960996,0.0000015515486],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023637742,0.000009384415,0.00081306574,0.00002965779,0.000106992484,0.000006695826,0.0005633692,0.0025569228,0.9889192,0.00064820924,0.00016502201,0.0038177348],"study_design_scores_gemma":[0.0071711396,0.0019033374,0.20687489,0.000067048,0.00045472741,0.0022808257,0.0009685516,0.002776855,0.76391566,0.0054921135,0.007377285,0.0007175568],"about_ca_topic_score_codex":0.00004401054,"about_ca_topic_score_gemma":0.00005825235,"teacher_disagreement_score":0.22500351,"about_ca_system_score_codex":0.00004960457,"about_ca_system_score_gemma":0.00007982106,"threshold_uncertainty_score":0.99988073},"labels":[],"label_agreement":null},{"id":"W2075773207","doi":"10.1007/s10969-005-3789-1","title":"Crystal structure of the hypothetical protein TA1238 from Thermoplasma acidophilum: A new type of helical super-bundle","year":2005,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto; University Health Network","funders":"Argonne National Laboratory; National Institute of General Medical Sciences","keywords":"Thermoplasma acidophilum; Crystallography; Bundle; Crystal structure; Type (biology); Chemistry; Biology; Materials science; Biochemistry; Ecology; Enzyme","score_opus":0.015910516625773745,"score_gpt":0.21016764220136686,"score_spread":0.1942571255755931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075773207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977913,0.00043660478,0.00015471052,0.00049645005,0.00084491377,0.0001063159,0.00010164986,0.0000044665644,0.00006358355],"genre_scores_gemma":[0.9937151,0.000011516703,0.004664507,0.000094214214,0.0013723592,2.1708902e-7,0.000004404138,0.000012433437,0.0001252295],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986836,0.00005155193,0.0005573805,0.0001595491,0.00039092355,0.00015702216],"domain_scores_gemma":[0.9990262,0.000060816164,0.00042245022,0.00015604628,0.00022374224,0.00011076156],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000089405585,0.0001647049,0.00031668937,0.000052303036,0.00009615095,0.000029454995,0.00019781273,0.00013662862,0.0011727543],"category_scores_gemma":[0.00006391617,0.00009511577,0.00013784048,0.00011328952,0.00022128725,0.00019227163,0.000078485195,0.00027024417,0.0000024733981],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007644613,0.000012992738,0.001035555,0.000011839961,0.000039908457,5.540012e-7,0.00018564102,0.0006605,0.9947903,0.0010769914,0.00025130206,0.0011699388],"study_design_scores_gemma":[0.0016771968,0.0006683623,0.10290654,0.000056423927,0.00013621127,0.0005919686,0.0001930316,0.00024310588,0.86089534,0.029188517,0.0032042111,0.00023909556],"about_ca_topic_score_codex":0.000039596547,"about_ca_topic_score_gemma":0.000026840387,"teacher_disagreement_score":0.13389498,"about_ca_system_score_codex":0.000051165556,"about_ca_system_score_gemma":0.00020713391,"threshold_uncertainty_score":0.9997403},"labels":[],"label_agreement":null},{"id":"W2084106291","doi":"10.1007/s10969-010-9093-8","title":"Engineering of a wheat germ expression system to provide compatibility with a high throughput pET-based cloning platform","year":2010,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Viral Infectious Diseases and Gene Expression in Insects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences","keywords":"Wheat germ; Structural genomics; Biology; Cloning (programming); Expression vector; Escherichia coli; Computational biology; Fusion protein; Cell-free protein synthesis; Protein biosynthesis; Biochemistry; Cell biology; Gene; Protein structure; Computer science","score_opus":0.005906233445938529,"score_gpt":0.20553292598271128,"score_spread":0.19962669253677276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084106291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99727726,0.00008681433,0.0019618028,0.000030082248,0.00048700237,0.00010422832,0.000025641028,0.000004629332,0.00002251576],"genre_scores_gemma":[0.99272233,0.0000034931686,0.006785191,0.00004687012,0.00040380404,0.0000030377412,0.000013748652,0.000010979124,0.000010534367],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992887,0.000009532161,0.0002865911,0.00015337748,0.00014716045,0.000114666465],"domain_scores_gemma":[0.9993092,0.0000182409,0.00022230708,0.00012387129,0.00019811133,0.00012828865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009158552,0.00012552783,0.00018095573,0.00004955238,0.00008780902,0.000023637116,0.000068551286,0.000057261437,0.000013772672],"category_scores_gemma":[0.000028612263,0.00008440681,0.000074917814,0.000044361554,0.000037154852,0.000013806003,0.000045287903,0.00015032556,2.619444e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010445517,0.000014649168,0.0046892096,0.00008812945,0.000037278412,0.00000399321,0.000027990469,0.019239157,0.97441494,0.00011065352,0.00010990586,0.00021952903],"study_design_scores_gemma":[0.00258775,0.0019855343,0.090730034,0.0002441234,0.00008035884,0.0010356292,0.00021885622,0.0033331418,0.8970905,0.00011093486,0.002190995,0.0003921535],"about_ca_topic_score_codex":0.000022018883,"about_ca_topic_score_gemma":0.0000118624075,"teacher_disagreement_score":0.086040825,"about_ca_system_score_codex":0.000023794006,"about_ca_system_score_gemma":0.0001192447,"threshold_uncertainty_score":0.344201},"labels":[],"label_agreement":null},{"id":"W2088061860","doi":"10.1007/s10969-012-9136-4","title":"Crystal structure of a catalytically active GG(D/E)EF diguanylate cyclase domain from Marinobacter aquaeolei with bound c-di-GMP product","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Bacterial biofilms and quorum sensing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"Brookhaven National Laboratory; National Institute of General Medical Sciences","keywords":"Allosteric regulation; GTP'; Enzyme; Chemistry; Second messenger system; Domain (mathematical analysis); Crystallography; Stereochemistry; Biochemistry","score_opus":0.005926118764505403,"score_gpt":0.19115358542107957,"score_spread":0.18522746665657416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088061860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9985003,0.00041805068,0.000081405626,0.00010679631,0.00055159105,0.00008516866,0.00021014446,0.0000020769403,0.000044450015],"genre_scores_gemma":[0.99579024,0.00003575,0.002207072,0.000079448226,0.0016842623,2.2994907e-7,0.00013744125,0.000018517088,0.000047046135],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99901235,0.00003080449,0.00034905385,0.00019018316,0.00017813646,0.00023947468],"domain_scores_gemma":[0.99912226,0.000016262882,0.00037685435,0.00013828771,0.00017872851,0.00016758096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000068669724,0.0002053686,0.00027227442,0.000046062694,0.00012410145,0.00003463504,0.000081435566,0.00012366833,0.0000475777],"category_scores_gemma":[0.000018342182,0.00013921683,0.00009573608,0.00004820369,0.0001801262,0.000040513696,0.00014339892,0.0001970458,3.814499e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002666876,0.000019149053,0.011918085,0.000012916481,0.00028617337,0.000003574125,0.00018370202,0.000032681215,0.98313767,0.00007443037,0.000042098163,0.0016226404],"study_design_scores_gemma":[0.0016670568,0.0005785985,0.54242146,0.000027943686,0.00016217756,0.0011176802,0.000219821,0.0000106415955,0.44971293,0.0006181605,0.003124768,0.00033876425],"about_ca_topic_score_codex":0.00003942014,"about_ca_topic_score_gemma":0.000027670625,"teacher_disagreement_score":0.53342474,"about_ca_system_score_codex":0.000033490323,"about_ca_system_score_gemma":0.000104067854,"threshold_uncertainty_score":0.56770974},"labels":[],"label_agreement":null},{"id":"W2089640001","doi":"10.1007/s10969-006-9008-x","title":"Crystal Structure of the Vitamin B12 Biosynthetic Cobaltochelatase, CbiXS, from Archaeoglobus Fulgidus","year":2006,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Porphyrin Metabolism and Disorders","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council","keywords":"Cobalamin; Tetrapyrrole; Biosynthesis; Histidine; Biochemistry; Lyase; Chemistry; Biology; Stereochemistry; Enzyme; Vitamin B12","score_opus":0.0037118086300047225,"score_gpt":0.17770394040004917,"score_spread":0.17399213177004444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089640001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99473435,0.0034441533,0.00026906474,0.000115590236,0.0007373744,0.00005950953,0.00058566016,0.0000012602942,0.000053035554],"genre_scores_gemma":[0.99809515,0.00009713478,0.0008641497,0.00009790902,0.0006725458,2.575665e-7,0.0000936934,0.000008895362,0.00007026997],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99916625,0.000033599317,0.00033833002,0.00014298937,0.00018508272,0.00013374293],"domain_scores_gemma":[0.9993494,0.000016555667,0.0003259041,0.00014285985,0.00010915644,0.000056113506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005314963,0.00013872242,0.00017985146,0.000035009343,0.00008894265,0.000015768186,0.00015352045,0.00010417735,0.000044378135],"category_scores_gemma":[0.000027073189,0.000088375906,0.00013764975,0.000059549613,0.00020922178,0.000008955254,0.00009428583,0.00013479708,2.865961e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002966817,0.0000119033175,0.009884372,0.000008682171,0.000072011564,0.0000013434828,0.000021081261,0.0009812126,0.9864874,0.00042799296,0.0010231277,0.00078422483],"study_design_scores_gemma":[0.001950317,0.00019470212,0.79647887,0.000018348455,0.00016180945,0.00046446934,0.00021973305,0.00007335674,0.16025718,0.020462288,0.01943049,0.00028846107],"about_ca_topic_score_codex":0.00006905329,"about_ca_topic_score_gemma":0.00004022196,"teacher_disagreement_score":0.82623017,"about_ca_system_score_codex":0.000011539194,"about_ca_system_score_gemma":0.00009343006,"threshold_uncertainty_score":0.3603865},"labels":[],"label_agreement":null},{"id":"W2090727546","doi":"10.1007/s10969-011-9115-1","title":"Solution NMR structure of MED25(391–543) comprising the activator-interacting domain (ACID) of human mediator subunit 25","year":2011,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Herpesvirus Infections and Treatments","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"Transactivation; Heteronuclear molecule; Protein subunit; Activator (genetics); Biology; Mediator; Protein structure; Cell biology; Protein domain; Heteronuclear single quantum coherence spectroscopy; Molecular biology; Gene; Biochemistry; Transcription factor; Chemistry; Nuclear magnetic resonance spectroscopy; Stereochemistry","score_opus":0.03355596472384254,"score_gpt":0.260084532259546,"score_spread":0.22652856753570344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090727546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983503,0.00034042477,0.00033452595,0.00007373059,0.0005089256,0.000098497476,0.000027293576,0.0000040709224,0.00026220022],"genre_scores_gemma":[0.997358,0.000032952117,0.0021845785,0.000032847976,0.00034937594,3.3041243e-7,0.000009289416,0.000011950389,0.000020655978],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989463,0.0000452003,0.0005454252,0.000097858785,0.00023724769,0.000127935],"domain_scores_gemma":[0.99873906,0.00007639858,0.00070333295,0.000108484644,0.00027929406,0.00009340508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014398883,0.0001388821,0.00033185264,0.0001286757,0.00018847936,0.000010248917,0.00006067067,0.00008407758,0.0003551354],"category_scores_gemma":[0.000036190035,0.00008272749,0.00014384979,0.00010297742,0.00014854367,0.00015924426,0.000036059708,0.00032566395,5.9859576e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021558513,0.00017702687,0.116333626,0.00016396052,0.0019230386,0.000029308334,0.005512991,0.000073327974,0.8457734,0.0029181005,0.00017856283,0.024760835],"study_design_scores_gemma":[0.00500979,0.0014806242,0.8088897,0.0002654841,0.00080913614,0.00291847,0.0044734874,0.00028410467,0.16372395,0.009639002,0.00222758,0.00027867165],"about_ca_topic_score_codex":0.00008969309,"about_ca_topic_score_gemma":0.000020025082,"teacher_disagreement_score":0.6925561,"about_ca_system_score_codex":0.000103433464,"about_ca_system_score_gemma":0.000095121206,"threshold_uncertainty_score":0.38884836},"labels":[],"label_agreement":null},{"id":"W2108076107","doi":"10.1007/s10969-008-9041-z","title":"Structure of an acetyl-CoA binding protein from Staphylococcus aureus representing a novel subfamily of GCN5-related N-acetyltransferase-like proteins","year":2008,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"Pacific Northwest National Laboratory; Battelle; National Institute of General Medical Sciences; Biological and Environmental Research; National Institutes of Health; U.S. Department of Energy","keywords":"Subfamily; Biology; Acetyltransferases; Cysteine; Acetyltransferase; Biochemistry; Residue (chemistry); Transferase; Stereochemistry; Enzyme; Acetylation; Chemistry; Gene","score_opus":0.01702220829124329,"score_gpt":0.2103631739380425,"score_spread":0.1933409656467992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108076107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969741,0.00035230906,0.00074317766,0.000036439687,0.0009988038,0.00031566792,0.0005326206,0.000016704702,0.00003018942],"genre_scores_gemma":[0.9879014,0.00002489858,0.011442645,0.000023294082,0.0004704421,0.0000017416058,0.00004982851,0.000026518186,0.000059215345],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976287,0.000076328266,0.0011063593,0.00033936734,0.0005728071,0.00027646465],"domain_scores_gemma":[0.99803317,0.00006646187,0.001051128,0.00023673795,0.00044871637,0.00016380576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022554492,0.00028672325,0.0005876676,0.00021778833,0.00026525863,0.000037170626,0.00023028346,0.00022240671,0.00031003682],"category_scores_gemma":[0.00006358589,0.00021984469,0.0001837019,0.0002493049,0.00029715558,0.00059167994,0.00006237688,0.00042567827,7.73966e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008829876,0.000028101662,0.002017201,0.000054113127,0.000111234105,0.000011265318,0.0006316805,0.001790831,0.9939318,0.00020721673,0.000024861212,0.0003087365],"study_design_scores_gemma":[0.0021955972,0.00066692266,0.04812055,0.00008652151,0.00010315582,0.0004048288,0.00046361078,0.0003193939,0.94537616,0.0018847962,0.00009490753,0.00028355495],"about_ca_topic_score_codex":0.00017658167,"about_ca_topic_score_gemma":0.00003388597,"teacher_disagreement_score":0.048555613,"about_ca_system_score_codex":0.00007246567,"about_ca_system_score_gemma":0.00021602641,"threshold_uncertainty_score":0.8965006},"labels":[],"label_agreement":null},{"id":"W2142745444","doi":"10.1007/s10969-011-9107-1","title":"Crystal structure of secretory protein Hcp3 from Pseudomonas aeruginosa","year":2011,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Vibrio bacteria research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Structural Genomics Consortium; University of Toronto","funders":"Argonne National Laboratory; National Institute of General Medical Sciences","keywords":"Pseudomonas aeruginosa; Type VI secretion system; Biology; Secretion; Microbiology; Effector; Virulence; Flagellum; Cell envelope; Bacteria; Peptide sequence; Cell biology; Genetics; Gene; Biochemistry; Escherichia coli","score_opus":0.01597394300057982,"score_gpt":0.21333696824884563,"score_spread":0.19736302524826582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142745444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99817455,0.0010535013,0.0001612626,0.000031959582,0.00025664922,0.00007990159,0.0001653445,0.0000015279281,0.00007528798],"genre_scores_gemma":[0.995498,0.00009753817,0.0036414145,0.000028903063,0.00062688586,6.5228824e-7,0.00003504748,0.000009976104,0.000061553874],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992142,0.000032629858,0.0003035263,0.00014000376,0.00017274215,0.00013693601],"domain_scores_gemma":[0.9992954,0.000009422647,0.00026895158,0.00009950308,0.00023607734,0.00009065463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058842274,0.00012995386,0.00020027845,0.00004833967,0.00006710454,0.00001192744,0.00010750168,0.000095363524,0.00015269475],"category_scores_gemma":[0.000044228684,0.000096535936,0.00009584852,0.00003312068,0.00016344652,0.0000127858875,0.00011525881,0.00015052482,3.539962e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094940595,0.0000074717905,0.004745561,0.000015608557,0.00022258841,0.000004208396,0.00013921973,0.000011370929,0.993102,0.00008308883,0.00014825368,0.0005711865],"study_design_scores_gemma":[0.0012573088,0.0007674286,0.38595197,0.000022313418,0.000051784864,0.00021064914,0.00035761532,0.000015783082,0.6044935,0.004141022,0.0025201829,0.00021041503],"about_ca_topic_score_codex":0.000031592066,"about_ca_topic_score_gemma":0.000014674605,"teacher_disagreement_score":0.38860852,"about_ca_system_score_codex":0.000020152986,"about_ca_system_score_gemma":0.00011669663,"threshold_uncertainty_score":0.39366212},"labels":[],"label_agreement":null},{"id":"W2146732641","doi":"10.1007/s10969-011-9122-2","title":"Solution NMR structures reveal a distinct architecture and provide first structures for protein domain family PF04536","year":2011,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences; Office of Science; National Institutes of Health","keywords":"Protein structure; Structural similarity; Protein domain; Sequence alignment; Protein family; Structural genomics; Biology; Crystallography; Heteronuclear single quantum coherence spectroscopy; Residue (chemistry); Peptide sequence; Nuclear magnetic resonance spectroscopy; Chemistry; Computational biology; Biochemistry; Stereochemistry","score_opus":0.021306286739727398,"score_gpt":0.21110617341875962,"score_spread":0.18979988667903222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146732641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9853428,0.0009594885,0.011724147,0.00022615603,0.0010321339,0.00045238738,0.00012689734,0.00002307734,0.00011290814],"genre_scores_gemma":[0.9562236,0.000016307398,0.04219117,0.00013706383,0.0012877478,0.000012261483,0.00001812195,0.000026759059,0.00008696332],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983083,0.000056101977,0.0006238641,0.00035726538,0.0003112913,0.00034319772],"domain_scores_gemma":[0.9987517,0.00006676448,0.0005915944,0.00014428151,0.0002488985,0.00019675828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029159166,0.0003248068,0.00040346824,0.00015435477,0.0005289739,0.00011920638,0.00015780266,0.00018128338,0.000104878294],"category_scores_gemma":[0.00008605374,0.00022310557,0.00013691475,0.00008712992,0.00028084446,0.00034187574,0.00008276699,0.00032099325,8.2280405e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053818435,0.000018266695,0.0019885125,0.00032926162,0.00014328567,0.000016352533,0.0020897214,0.00028551187,0.95900697,0.016101649,0.0011718749,0.013466768],"study_design_scores_gemma":[0.0032473658,0.0014621093,0.36630476,0.0000810525,0.00022485075,0.0023164798,0.0007037811,0.00019205287,0.029804207,0.58584976,0.009077296,0.00073628285],"about_ca_topic_score_codex":0.0000547641,"about_ca_topic_score_gemma":0.000064309825,"teacher_disagreement_score":0.92920274,"about_ca_system_score_codex":0.000089025154,"about_ca_system_score_gemma":0.000112745016,"threshold_uncertainty_score":0.90979815},"labels":[],"label_agreement":null},{"id":"W2159028403","doi":"10.1007/s10969-009-9064-0","title":"Unique opportunities for NMR methods in structural genomics","year":2009,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Structural Genomics Consortium","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Structural genomics; Structural biology; Genomics; Computational biology; Protein structure; Biology; Biochemistry; Genome; Gene","score_opus":0.02975699021587422,"score_gpt":0.2929266165796197,"score_spread":0.2631696263637455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159028403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9779037,0.0015964176,0.019270482,0.0004962825,0.0004045408,0.00015356933,0.00004129938,0.0000031309287,0.00013055361],"genre_scores_gemma":[0.8967323,0.00044575208,0.100825116,0.00078923727,0.00092144415,0.000002375922,0.00007261677,0.000016206512,0.00019500713],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990423,0.000046383357,0.0004480454,0.00017293805,0.000090507725,0.00019987789],"domain_scores_gemma":[0.9993045,0.00002970604,0.0002722782,0.00010696792,0.00018076059,0.00010583815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002699815,0.00018066063,0.00025689593,0.00010452617,0.00009573523,0.000038433674,0.00012394928,0.00016431324,0.000007979406],"category_scores_gemma":[0.00005261629,0.00014604974,0.00013330189,0.000046330515,0.00007300993,0.000019424662,0.00003854456,0.00017739112,6.2037095e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002373482,0.0000129448335,0.0015832788,0.00004024455,0.00016638234,0.000017078086,0.00018042089,0.0051288023,0.8340833,0.011591614,0.00041370004,0.1444087],"study_design_scores_gemma":[0.0105296,0.0061627105,0.3223817,0.00007828935,0.00031330885,0.0068943775,0.0022721472,0.014937023,0.116603486,0.40044555,0.11718931,0.0021924854],"about_ca_topic_score_codex":0.000003020687,"about_ca_topic_score_gemma":0.000007650312,"teacher_disagreement_score":0.7174799,"about_ca_system_score_codex":0.000057712885,"about_ca_system_score_gemma":0.00018279774,"threshold_uncertainty_score":0.59557354},"labels":[],"label_agreement":null},{"id":"W2165120792","doi":"10.1007/s10969-012-9131-9","title":"Crystal structures of putative phosphoglycerate kinases from B. anthracis and C. jejuni","year":2012,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Phosphoglycerate kinase; Campylobacter jejuni; Bacillus anthracis; Context (archaeology); Biology; Phosphoglycerate mutase; Protein structure; Biochemistry; Glycolysis; Enzyme; Bacteria; Genetics","score_opus":0.014995294211277906,"score_gpt":0.2272977872880978,"score_spread":0.2123024930768199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165120792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939443,0.0036776506,0.00036059055,0.00005719645,0.001648788,0.000049602717,0.00018771099,0.0000057342613,0.000068453126],"genre_scores_gemma":[0.99507797,0.00014337184,0.0037403707,0.00007536555,0.00091281265,4.4936323e-7,0.00001627746,0.000010091086,0.000023274535],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989874,0.000040460025,0.0004196809,0.00013237921,0.00023700086,0.00018310949],"domain_scores_gemma":[0.9989918,0.00012526741,0.00047947574,0.000068714566,0.00018981996,0.00014492594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001501418,0.00016383058,0.00030209235,0.00008090399,0.00014239627,0.000048367918,0.00006492312,0.00008162123,0.00042482326],"category_scores_gemma":[0.000045249653,0.00011409475,0.00006563658,0.00006659592,0.0002219642,0.000548489,0.00005418916,0.00015994582,0.0000011350485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010460084,0.000011087205,0.014353913,0.000025503961,0.00008678968,0.0000037881907,0.0012607017,0.00027572687,0.9760426,0.0017522105,0.00019568014,0.0049459543],"study_design_scores_gemma":[0.0012079129,0.00036202892,0.5943903,0.000019076317,0.00015851892,0.0006623888,0.0014044682,0.000086207736,0.37858662,0.021876618,0.0009872604,0.00025863375],"about_ca_topic_score_codex":0.000060257633,"about_ca_topic_score_gemma":0.0000049084165,"teacher_disagreement_score":0.59745604,"about_ca_system_score_codex":0.000036221256,"about_ca_system_score_gemma":0.000045785255,"threshold_uncertainty_score":0.4652649},"labels":[],"label_agreement":null},{"id":"W4234286444","doi":"10.1007/s10969-004-3789-6","title":"Crystal structure of the hypothetical protein TA1238 from Thermoplasma acidophilum: a new type of helical super-bundle","year":2004,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Porphyrin Metabolism and Disorders","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Structural Genomics Consortium; University Health Network","funders":"Argonne National Laboratory","keywords":"Thermoplasma acidophilum; Antiparallel (mathematics); Coiled coil; Crystallography; Protein structure; Crystal structure; Biology; Sequence (biology); Stereochemistry; Chemistry; Biophysics; Biochemistry; Physics; Enzyme","score_opus":0.010008160577533023,"score_gpt":0.20289442635413768,"score_spread":0.19288626577660467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234286444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977689,0.0013327864,0.0001930816,0.00023644626,0.00027988595,0.00007590502,0.00008021826,8.679585e-7,0.000031953285],"genre_scores_gemma":[0.9974671,0.00006093499,0.0018630618,0.000081951635,0.00045559206,1.7090208e-7,0.000013010795,0.000009041291,0.00004912684],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927425,0.00002286534,0.00030399614,0.00011621455,0.0001780897,0.00010455272],"domain_scores_gemma":[0.9994535,0.000008323771,0.00021167201,0.00012132899,0.00012418839,0.00008097492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000038500162,0.000115817966,0.00019196549,0.000024284771,0.000045657976,0.00000959613,0.00013910134,0.000115584015,0.000063455234],"category_scores_gemma":[0.000051072442,0.000070995164,0.00012902418,0.000058729842,0.00016606566,0.000008349941,0.000072224124,0.00013999843,2.833392e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067241397,0.000019160538,0.0017816004,0.000007849092,0.00007961646,4.820249e-7,0.00005094904,0.00061441417,0.9955189,0.000709492,0.000063806125,0.00048129278],"study_design_scores_gemma":[0.0036722713,0.0008834896,0.21002282,0.00003477992,0.00012562973,0.0003781863,0.0002405025,0.000018338387,0.72458327,0.05609816,0.0036901785,0.0002523941],"about_ca_topic_score_codex":0.000035056266,"about_ca_topic_score_gemma":0.000011753862,"teacher_disagreement_score":0.27093568,"about_ca_system_score_codex":0.000009933658,"about_ca_system_score_gemma":0.00025432897,"threshold_uncertainty_score":0.2895099},"labels":[],"label_agreement":null},{"id":"W426015217","doi":"10.1023/b:jsfg.0000029244.65028.71","title":"2003 NIH Protein Structure Initiative Workshop in Protein Production and Crystallization for Structural and Functional Genomics","year":2004,"lang":"en","type":"article","venue":"Journal of Structural and Functional Genomics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"National Institute of General Medical Sciences","keywords":"Structural genomics; Genomics; Functional genomics; Crystallization; Computational biology; Biology; Protein structure; Genetics; Genome; Engineering; Biochemistry; Gene; Chemical engineering","score_opus":0.01934834248250878,"score_gpt":0.22376160785547122,"score_spread":0.20441326537296245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W426015217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921803,0.0008515911,0.004014919,0.00066197134,0.0012832991,0.0008721529,0.00010274205,0.000016452139,0.000016607968],"genre_scores_gemma":[0.9856588,0.000060314753,0.012630834,0.00014923772,0.0012870482,0.000019218141,0.00005577566,0.00002897097,0.000109762004],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981568,0.00005837101,0.0007052269,0.00044954562,0.0003186058,0.0003114752],"domain_scores_gemma":[0.99839395,0.00004058292,0.0005915233,0.00010979466,0.00071115437,0.00015299456],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029798405,0.00033177552,0.0003941951,0.00025068154,0.00039035297,0.0001781836,0.00007544641,0.00022227947,0.00010979524],"category_scores_gemma":[0.00035073902,0.00026553497,0.000056818357,0.000258369,0.00024668957,0.0007722055,0.000063327025,0.0003829181,5.019261e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019696422,0.000011697099,0.0007022535,0.00012883662,0.000054638593,0.0000050226126,0.0008543653,0.008455876,0.98181015,0.003877762,0.00016114887,0.001968591],"study_design_scores_gemma":[0.014470269,0.0025224872,0.25055102,0.0006832603,0.00040481496,0.005396996,0.006114906,0.0025431016,0.39297742,0.31810883,0.003885957,0.0023409512],"about_ca_topic_score_codex":0.00001831957,"about_ca_topic_score_gemma":0.00013512553,"teacher_disagreement_score":0.58883274,"about_ca_system_score_codex":0.0002582836,"about_ca_system_score_gemma":0.00030097694,"threshold_uncertainty_score":0.9999797},"labels":[],"label_agreement":null}]}