{"meta":{"query_hash":"09521ba2f298","filters":{"venue":"Journal of Cheminformatics"},"cohort_total":43,"direct_labels_cover":0,"predictions_cover":43,"exported":43,"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/09521ba2f298","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Cheminformatics"},"results":[{"id":"W1495258543","doi":"10.1186/s13321-015-0085-3","title":"ChemDoodle Web Components: HTML5 toolkit for chemical graphics, interfaces, and informatics","year":2015,"lang":"en","type":"review","venue":"Journal of Cheminformatics","topic":"Various Chemistry Research Topics","field":"Chemistry","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Canada; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"HTML5; JavaScript; Computer science; World Wide Web; Graphics; Multimedia; Web application; Computer graphics; Computer graphics (images)","score_opus":0.0822703604728123,"score_gpt":0.35068284433762875,"score_spread":0.2684124838648164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1495258543","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":[0.0009095944,0.9858796,0.000078777615,0.000046264344,0.00022070865,0.00043512165,0.00047732706,0.00005593893,0.011896638],"genre_scores_gemma":[0.000054447915,0.9921098,0.005801448,0.00003698043,0.0006585475,0.00003560768,0.0004008357,0.00009967797,0.0008026721],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940679,0.000010285308,0.0038527271,0.00016897764,0.0011901779,0.00070991094],"domain_scores_gemma":[0.99321073,0.0005303718,0.0037899832,0.0006719184,0.0010865281,0.0007104786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012341934,0.0008176999,0.0030114097,0.000256697,0.000085087595,0.00031162723,0.0014677469,0.0010617656,0.00007313111],"category_scores_gemma":[0.0012394361,0.0006654758,0.0008000862,0.0002713128,0.00029184026,0.0006794288,0.0005484528,0.0020492857,0.000012463057],"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":[0.00010436697,0.00028215811,0.0000051110765,0.267072,0.0017831249,0.0000226868,0.0017080974,0.000001311512,0.00044376045,0.00011280724,0.06958638,0.6588782],"study_design_scores_gemma":[0.0014315633,0.000059975322,1.1387337e-8,0.010911226,0.00096518296,0.0015105577,0.00042767957,0.0005746333,0.0035729401,0.00016503016,0.9797533,0.0006279144],"about_ca_topic_score_codex":8.4983634e-7,"about_ca_topic_score_gemma":2.434181e-7,"teacher_disagreement_score":0.9101669,"about_ca_system_score_codex":0.0005750855,"about_ca_system_score_gemma":0.001360834,"threshold_uncertainty_score":0.99957967},"labels":[],"label_agreement":null},{"id":"W1722424871","doi":"10.1186/1758-2946-5-s1-p40","title":"A 3D-QSAR model for cannabinoid receptor (CB2) ligands derived from aligned pharmacophors","year":2013,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Pharmacological Receptor Mechanisms and Effects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"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":"Pharmacophore; Cannabinoid receptor; Cannabinoid receptor type 2; Positron emission tomography; Radioligand; Neuroscience; Drug discovery; Cannabinoid; Computational biology; Quantitative structure–activity relationship; Receptor; Chemistry; Computer science; Biology; Biochemistry; Stereochemistry; Agonist","score_opus":0.012406226783392487,"score_gpt":0.26236953832106275,"score_spread":0.24996331153767026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1722424871","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":[0.9790602,0.00023318591,0.019372987,0.00021330804,0.00041525252,0.00034100987,0.000051110197,0.00000810835,0.0003048457],"genre_scores_gemma":[0.9706963,0.00033874242,0.026586704,0.0013626303,0.0005189852,0.00005136668,0.00007566138,0.000024422743,0.00034523563],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99875575,0.000007635823,0.0006089867,0.000108857545,0.00020962626,0.00030916676],"domain_scores_gemma":[0.99867094,0.00003827184,0.00050530356,0.00013903843,0.0003692276,0.00027720822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024147204,0.00020783808,0.00030756267,0.000043735345,0.00006520088,0.000047277135,0.00032169247,0.00019537423,0.000170312],"category_scores_gemma":[0.00018737924,0.00016128675,0.00022587473,0.00005578238,0.000039595903,0.00003662954,0.000078705954,0.00011831564,0.000018765202],"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":[0.00015130606,0.00006921427,0.0000065195695,0.000048754257,0.00010166945,5.2145174e-7,0.00030317783,0.00044959428,0.9341132,0.0000022249656,0.059987396,0.004766426],"study_design_scores_gemma":[0.0016085174,0.00036931783,0.0000074041413,0.000023779574,0.000072515475,0.000008629779,0.00012628324,0.047508743,0.9431547,0.00021883233,0.006700659,0.00020064967],"about_ca_topic_score_codex":0.0000042377483,"about_ca_topic_score_gemma":4.574873e-7,"teacher_disagreement_score":0.05328674,"about_ca_system_score_codex":0.00004093539,"about_ca_system_score_gemma":0.0001450803,"threshold_uncertainty_score":0.6577083},"labels":[],"label_agreement":null},{"id":"W174610764","doi":"10.1186/1758-2946-4-s1-p3","title":"Targeting protein-protein interactions using methods of cheminformatics","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cheminformatics; Computer science; Computational biology; Data science; Data mining; Bioinformatics; Biology","score_opus":0.036522105356600616,"score_gpt":0.34954319290856406,"score_spread":0.31302108755196345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W174610764","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":[0.9877315,0.00054216944,0.0058381194,0.0002967271,0.00033534077,0.0004121454,0.0000063917005,0.000013855435,0.00482374],"genre_scores_gemma":[0.6726769,0.000017025826,0.3266177,0.000072218616,0.00037452122,2.8278706e-7,0.000002781695,0.000011182096,0.00022737919],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99784654,0.000011626975,0.0014861523,0.000036892765,0.0003372766,0.0002815072],"domain_scores_gemma":[0.9973243,0.00007694269,0.0016474593,0.00018507325,0.00057979306,0.00018646594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014138148,0.00016655345,0.00052517804,0.00018302114,0.000054806973,0.000020130406,0.00014210025,0.00010523272,0.00016320538],"category_scores_gemma":[0.0014797708,0.00011513191,0.00021205752,0.00024379836,0.000060318318,0.00095166545,0.000066745546,0.00048678883,0.0000058087026],"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":[0.00007895549,0.0001095865,0.00005599273,0.0010766069,0.00012415924,9.4402026e-7,0.0022717298,0.000006179161,0.9812602,0.000025097888,0.0009233059,0.01406728],"study_design_scores_gemma":[0.00039203383,0.000071992305,0.000023451172,0.00085143355,0.00019547525,0.0004677746,0.0011536772,0.00087396137,0.9864313,0.000024824203,0.009392053,0.00012201914],"about_ca_topic_score_codex":0.0000024843207,"about_ca_topic_score_gemma":2.6022033e-8,"teacher_disagreement_score":0.32077956,"about_ca_system_score_codex":0.000114094895,"about_ca_system_score_gemma":0.00011939502,"threshold_uncertainty_score":0.4694943},"labels":[],"label_agreement":null},{"id":"W1850375728","doi":"10.1186/s13321-015-0092-4","title":"Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Computer science; Cheminformatics; Interpretability; Quantitative structure–activity relationship; Feature selection; Applicability domain; Visual analytics; Data mining; Machine learning; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Property (philosophy); Software; Feature (linguistics); Process (computing); Generality; Domain (mathematical analysis); Visualization; Bioinformatics; Mathematics","score_opus":0.0632942398036562,"score_gpt":0.3859116379978224,"score_spread":0.32261739819416624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1850375728","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03652942,0.00006597223,0.9609706,0.00021196829,0.00054573006,0.00021189188,0.000002240915,0.00002828872,0.001433895],"genre_scores_gemma":[0.03950497,0.000012615807,0.95990235,0.00031870158,0.00015452223,0.000007725563,0.000004681391,0.000013963356,0.0000804607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997089,0.000050549297,0.0016895467,0.00010342866,0.0007138501,0.00035361006],"domain_scores_gemma":[0.996581,0.000822238,0.0010068592,0.00022210438,0.0010873331,0.00028044652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004599899,0.00022403403,0.00051490776,0.0004963413,0.000049208258,0.00025751427,0.0008831806,0.00012800885,0.0000041145977],"category_scores_gemma":[0.002000207,0.00020154584,0.00021152753,0.0008757816,0.000037040154,0.0031667347,0.00017020227,0.000333707,0.0000053641556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006408967,0.0011814979,0.0026694466,0.0017971676,0.00062584144,0.000018282328,0.06090997,0.22525062,0.006005872,0.017935006,0.050073594,0.6328918],"study_design_scores_gemma":[0.0016256099,0.00026135036,0.0000751764,0.00008154478,0.000033755063,0.00015734362,0.0009791657,0.93560004,0.048541795,0.0052680215,0.0071443673,0.0002318141],"about_ca_topic_score_codex":0.0000025874801,"about_ca_topic_score_gemma":0.0000013276424,"teacher_disagreement_score":0.71034944,"about_ca_system_score_codex":0.00045816175,"about_ca_system_score_gemma":0.00082862156,"threshold_uncertainty_score":0.8218801},"labels":[],"label_agreement":null},{"id":"W2017222169","doi":"10.1186/1758-2946-6-1","title":"Prediction of novel drug indications using network driven biological data prioritization and integration","year":2014,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Prioritization; Data integration; Data science; Data mining; Drug; Risk analysis (engineering); Management science; Pharmacology; Medicine; Engineering","score_opus":0.03665510091314504,"score_gpt":0.25880139960248577,"score_spread":0.22214629868934072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017222169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42613077,0.00024017699,0.5727218,0.0000506713,0.00017493647,0.00010742489,0.000045546563,0.0000030544122,0.0005256508],"genre_scores_gemma":[0.9381517,0.00043775345,0.060686197,0.0000694736,0.00037836004,4.4683824e-7,0.00026233803,0.0000051136085,0.0000085758775],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999112,0.000008773511,0.00062240724,0.000053176052,0.000110462715,0.00009319173],"domain_scores_gemma":[0.99880576,0.000024447167,0.0007428138,0.00021438842,0.0001606881,0.000051924697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056044443,0.00007810976,0.0001458935,0.000038420556,0.0000491813,0.000021369826,0.0001993897,0.00009467916,0.0000015719376],"category_scores_gemma":[0.00014655471,0.000062691586,0.000028720206,0.00007282665,0.0000646066,0.000035856636,0.00012433107,0.000104237384,1.5360688e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046678082,0.0007383655,0.021364134,0.000695274,0.00075736246,5.7453815e-7,0.0042047617,0.039967936,0.7311539,0.00542725,0.054658547,0.14056513],"study_design_scores_gemma":[0.0019382433,0.00065070874,0.0031720349,0.0002956332,0.0001530504,0.00020739925,0.0006012032,0.9612254,0.018924285,0.0006570945,0.011926628,0.00024834528],"about_ca_topic_score_codex":7.929791e-7,"about_ca_topic_score_gemma":0.0000012548613,"teacher_disagreement_score":0.92125744,"about_ca_system_score_codex":0.000009787385,"about_ca_system_score_gemma":0.00005404222,"threshold_uncertainty_score":0.25564888},"labels":[],"label_agreement":null},{"id":"W2019688884","doi":"10.1186/1758-2946-4-24","title":"mol2chemfig, a tool for rendering chemical structures from molfile or SMILES format to LATE X code","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"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 Waterloo","funders":"","keywords":"Computer science; Python (programming language); Rendering (computer graphics); Documentation; Programming language; Source code; Software; Graphics; Computer graphics (images); Coding (social sciences)","score_opus":0.041670292449581564,"score_gpt":0.3269340572626618,"score_spread":0.28526376481308025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019688884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33982942,0.00009245877,0.658865,0.00027193615,0.00041440738,0.00014355812,0.00004040511,0.00002607585,0.00031679973],"genre_scores_gemma":[0.24327321,0.0000096225685,0.75571746,0.0005301877,0.0003752227,0.000008302822,0.0000078409985,0.000012611146,0.00006553759],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981075,0.000010495404,0.0009085161,0.00008299094,0.00052346213,0.00036705693],"domain_scores_gemma":[0.9979316,0.0007617534,0.0005477842,0.0002782429,0.00023358873,0.0002470229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057704234,0.00018483563,0.00034354397,0.00012397722,0.00005769979,0.00022510554,0.00085812993,0.00008137089,0.000017072245],"category_scores_gemma":[0.0006963305,0.00013837445,0.00016786637,0.00020838891,0.000019594656,0.002390468,0.00029549986,0.00019344174,0.0000056403815],"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":[0.0015653922,0.0006120249,0.0004876366,0.0014507013,0.0010965314,0.000034334367,0.078595445,0.0744599,0.096729614,0.036846686,0.1130932,0.5950285],"study_design_scores_gemma":[0.0017822315,0.00016990892,0.00053065806,0.00022686268,0.00007762223,0.00044124798,0.0004976294,0.24376693,0.67256373,0.027900273,0.051363736,0.0006791663],"about_ca_topic_score_codex":8.868469e-7,"about_ca_topic_score_gemma":2.5930837e-7,"teacher_disagreement_score":0.5943494,"about_ca_system_score_codex":0.00014651552,"about_ca_system_score_gemma":0.00014189379,"threshold_uncertainty_score":0.56427467},"labels":[],"label_agreement":null},{"id":"W2083474203","doi":"10.1186/1758-2946-6-s1-p43","title":"Exploiting solvent effects in drug design and optimization","year":2014,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vertex Pharmaceuticals (Canada)","funders":"","keywords":"Ligand (biochemistry); Solvent; Computer science; Molecule; Computational chemistry; Binding energy; Chemistry; Computational science; Physics; Atomic physics; Organic chemistry","score_opus":0.012668857480028543,"score_gpt":0.2551218885689458,"score_spread":0.24245303108891725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083474203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022269214,0.000038813705,0.97686887,0.00014100644,0.00012404959,0.00006104408,3.6617504e-8,0.0000076425795,0.0004893469],"genre_scores_gemma":[0.19681747,0.000013710691,0.80300355,0.0001216411,0.00003463614,0.0000010435007,1.8431483e-7,0.0000029589949,0.0000048187294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908274,0.000051495124,0.0004576934,0.000044172026,0.00025837452,0.00010552153],"domain_scores_gemma":[0.99837,0.0010123033,0.00037623403,0.00008993453,0.00009223341,0.00005933264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016840859,0.000070354734,0.00015480968,0.00014258696,0.000025927526,0.00010249846,0.0002461341,0.000021710119,6.873886e-7],"category_scores_gemma":[0.0004794027,0.000061349165,0.000030819734,0.00016232724,0.000013089436,0.0011140319,0.000086730994,0.000119464654,7.925939e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004223418,0.000016703316,0.000029148267,0.00007186444,0.0000050349345,0.0000025694633,0.002396401,0.9608854,0.0000657665,0.0025641066,0.00015675546,0.03380201],"study_design_scores_gemma":[0.0003957102,0.000039240582,0.00010898089,0.00013081728,0.000003933074,0.00006364938,0.000053835876,0.98659235,0.006992491,0.0054801414,0.000073349554,0.00006550598],"about_ca_topic_score_codex":3.9266874e-7,"about_ca_topic_score_gemma":5.678014e-8,"teacher_disagreement_score":0.17454825,"about_ca_system_score_codex":0.00004343869,"about_ca_system_score_gemma":0.000053963497,"threshold_uncertainty_score":0.25017464},"labels":[],"label_agreement":null},{"id":"W2103126992","doi":"10.1186/s13321-015-0064-8","title":"Creation of a free, Internet-accessible database: the Multiple Target Ligand Database","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"Fundamental Research Funds for the Central Universities","keywords":"Computer science; The Internet; Database; World Wide Web","score_opus":0.04316942399164634,"score_gpt":0.3173300065991756,"score_spread":0.27416058260752924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103126992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07583115,0.00022590335,0.9190818,0.0004747779,0.00039915665,0.0000943881,0.000030021518,0.000011593717,0.0038512216],"genre_scores_gemma":[0.40962735,0.000028661254,0.5897903,0.00022034488,0.00014746674,0.0000022037623,0.000022847304,0.00000758185,0.00015326001],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818224,0.00003530164,0.0008324826,0.000065280205,0.0007519676,0.00013272637],"domain_scores_gemma":[0.99717444,0.00057809893,0.0010265926,0.00053873943,0.00055789086,0.00012423565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018850082,0.00010858571,0.0002215032,0.00012967692,0.000029345483,0.00013739346,0.0016014315,0.00003122253,0.0000062545355],"category_scores_gemma":[0.0017863371,0.000071541544,0.000078312616,0.00034640825,0.00006118948,0.0027738716,0.00061059487,0.00020676696,0.0000045866377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007639077,0.001515096,0.007920303,0.00173306,0.0008355214,0.00010827727,0.0760114,0.13807566,0.016071511,0.055601973,0.60777164,0.093591645],"study_design_scores_gemma":[0.0012971505,0.000110100074,0.0002738736,0.00021105977,0.000026848096,0.00018100622,0.000499354,0.78193045,0.19808517,0.0048464816,0.012396805,0.00014168287],"about_ca_topic_score_codex":0.000010723796,"about_ca_topic_score_gemma":0.0000016701299,"teacher_disagreement_score":0.6438548,"about_ca_system_score_codex":0.000056185163,"about_ca_system_score_gemma":0.00037790652,"threshold_uncertainty_score":0.29758847},"labels":[],"label_agreement":null},{"id":"W2110732896","doi":"10.1186/1758-2946-3-16","title":"Semantic Web integration of Cheminformatics resources with the SADI framework","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canarie; Pfizer","keywords":"Computer science; Cheminformatics; Interoperability; Workflow; Semantic Web; Ontology; SPARQL; Web service; RDF; World Wide Web; Social Semantic Web; Data science; Database; Chemistry","score_opus":0.10075100365193504,"score_gpt":0.3231345185300068,"score_spread":0.22238351487807176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110732896","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":[0.7551349,0.00011736688,0.10748832,0.00081478845,0.0008357665,0.0002515582,0.000013207029,0.000024769372,0.13531935],"genre_scores_gemma":[0.96219146,0.000019190491,0.03673821,0.00017694663,0.000081235215,7.8068587e-7,0.0000013459853,0.0000057844723,0.0007850621],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960254,0.000016417647,0.001724969,0.00008374441,0.0019558736,0.0001935954],"domain_scores_gemma":[0.994824,0.00092418405,0.0026106648,0.0007265409,0.0008188605,0.00009576027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058175726,0.00013926005,0.00034198596,0.0002880949,0.000115655974,0.0002626429,0.0015008663,0.00006400691,0.00016777085],"category_scores_gemma":[0.0025111975,0.00006494075,0.0001359241,0.0008901011,0.00021546106,0.0008016237,0.00021779099,0.0003192269,0.000036172485],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040121775,0.0003650359,0.003468985,0.00032599235,0.0003661912,0.00001845615,0.26668856,0.00040983333,0.0006009344,0.005627299,0.4298818,0.2918457],"study_design_scores_gemma":[0.0028341599,0.0016351858,0.006435337,0.0029705812,0.0007369293,0.00082693726,0.34033623,0.11864591,0.09374271,0.03236471,0.3982816,0.0011897045],"about_ca_topic_score_codex":0.0000020467096,"about_ca_topic_score_gemma":0.0000027199121,"teacher_disagreement_score":0.290656,"about_ca_system_score_codex":0.000026371185,"about_ca_system_score_gemma":0.00008998412,"threshold_uncertainty_score":0.30063194},"labels":[],"label_agreement":null},{"id":"W2110899240","doi":"10.1186/1758-2946-1-4","title":"A constructive approach for discovering new drug leads: Using a kernel methodology for the inverse-QSAR problem","year":2009,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":53,"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 Waterloo","funders":"","keywords":"Quantitative structure–activity relationship; Kernel (algebra); Feature vector; Molecular descriptor; Computer science; Support vector machine; Kernel method; Feature (linguistics); Artificial intelligence; Inverse; Algorithm; Pattern recognition (psychology); Mathematics; Machine learning","score_opus":0.09032694935977614,"score_gpt":0.348785861803831,"score_spread":0.25845891244405483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110899240","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005937594,0.00011089404,0.99192834,0.00073106994,0.00029922594,0.00047763402,0.000004924135,0.000013987501,0.00049634144],"genre_scores_gemma":[0.010630715,0.000008977364,0.98849285,0.0004976506,0.0002944421,0.0000053715726,0.000001496254,0.000007966671,0.000060543953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843925,0.000040633226,0.00080459984,0.00011339367,0.00032698177,0.00027512872],"domain_scores_gemma":[0.9962044,0.0021392587,0.0009951064,0.0002271422,0.00032930367,0.00010481315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021165917,0.0001699157,0.00037936497,0.00012903819,0.00014086929,0.00019435455,0.00089302036,0.00005665287,7.7251923e-7],"category_scores_gemma":[0.00062894414,0.000117773954,0.00027446842,0.00025708103,0.00006730517,0.0014504102,0.00010772203,0.00022042521,2.501976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002744389,0.00011391002,0.000023758366,0.0003630991,0.00033913172,0.0000022593895,0.033413842,0.6748015,0.0019380496,0.060387805,0.010623738,0.21771845],"study_design_scores_gemma":[0.0010933719,0.00011252466,0.00002267201,0.00005545693,0.00007876349,0.00037774356,0.0013444122,0.9233211,0.0073242835,0.064822316,0.0012880039,0.00015929878],"about_ca_topic_score_codex":0.000002853208,"about_ca_topic_score_gemma":5.304055e-7,"teacher_disagreement_score":0.24851964,"about_ca_system_score_codex":0.0001360203,"about_ca_system_score_gemma":0.00060101936,"threshold_uncertainty_score":0.48026827},"labels":[],"label_agreement":null},{"id":"W2118054110","doi":"10.1186/1758-2946-2-8","title":"Basic primitives for molecular diagram sketching","year":2010,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quebec Labrador Foundation","funders":"","keywords":"Computer science; Software; Construct (python library); Set (abstract data type); Process (computing); Interface (matter); Theoretical computer science; Programming language; Parallel computing","score_opus":0.003713436710431373,"score_gpt":0.2402804689753334,"score_spread":0.23656703226490203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118054110","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":[0.98504084,0.00010248018,0.012282415,0.0002049681,0.00009667068,0.00005799891,0.0000064002083,0.0000026459409,0.0022055511],"genre_scores_gemma":[0.9851271,0.00005593184,0.014123926,0.00026284668,0.0003160922,0.0000031341783,0.000014119455,0.000011581052,0.00008530394],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921346,0.000003118435,0.00042546346,0.000059615417,0.00014915057,0.00014922224],"domain_scores_gemma":[0.9991427,0.000052834424,0.00035763285,0.00015672085,0.00018901977,0.00010109105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002929372,0.00010389278,0.00019027317,0.000037149883,0.00003540052,0.000035161884,0.00020679105,0.00011354939,0.000015430356],"category_scores_gemma":[0.00081001216,0.000081472135,0.00030730802,0.000047746813,0.000039889346,0.000011134572,0.00003906295,0.00015670276,0.0000011622732],"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":[0.000022185735,0.00003922498,0.00014191637,0.000037758095,0.00008912064,8.363561e-7,0.00006454118,0.000006855873,0.9779138,0.00008687142,0.0015676805,0.020029241],"study_design_scores_gemma":[0.0003223675,0.00006782123,0.000052460084,0.00001684607,0.000069561145,0.000037606205,0.00006926402,0.00020514737,0.96243733,0.0002899153,0.036323473,0.00010819379],"about_ca_topic_score_codex":2.7870612e-7,"about_ca_topic_score_gemma":6.623298e-7,"teacher_disagreement_score":0.034755792,"about_ca_system_score_codex":0.0000061776555,"about_ca_system_score_gemma":0.00004976253,"threshold_uncertainty_score":0.33223373},"labels":[],"label_agreement":null},{"id":"W2128119041","doi":"10.1186/1758-2946-4-9","title":"A chemical specialty semantic network for the Unified Medical Language System","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","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":"New York Institute of Technology","funders":"","keywords":"Unified Medical Language System; Computer science; Ontology; Semantics (computer science); Semantic network; Natural language processing; Information retrieval; Artificial intelligence; Data mining; Programming language","score_opus":0.012390122717380214,"score_gpt":0.2734242568030976,"score_spread":0.2610341340857174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128119041","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":[0.8966529,0.011904403,0.0783807,0.0024428135,0.0034676369,0.0004745387,0.000024181862,0.000044372067,0.0066084703],"genre_scores_gemma":[0.987142,0.00011098963,0.0076582315,0.0004701998,0.0044588135,0.0000049157456,0.000013230081,0.000011014339,0.00013054938],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882907,0.0000102929125,0.00049472257,0.000040790543,0.00032926747,0.0002958456],"domain_scores_gemma":[0.9990647,0.0001703173,0.0003234363,0.00017068084,0.00009057472,0.00018032109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011538115,0.000103162085,0.0002068221,0.000015772324,0.000058266352,0.000017063772,0.00034674007,0.00021881223,0.000013619783],"category_scores_gemma":[0.00081303436,0.00005936135,0.0001565456,0.00006412881,0.00011197979,0.000006325105,0.00007548393,0.00018584004,0.0000036000695],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009924368,0.00038097496,0.002500484,0.0017619254,0.0013947794,0.00002679957,0.0066475626,0.000067840265,0.03931373,0.0020344642,0.75084406,0.19403492],"study_design_scores_gemma":[0.004053226,0.00053211,0.0008036747,0.00066205184,0.0004974558,0.0030628138,0.014596933,0.0035360372,0.23305164,0.00006563998,0.7384957,0.0006426967],"about_ca_topic_score_codex":7.1201464e-7,"about_ca_topic_score_gemma":8.5068444e-7,"teacher_disagreement_score":0.19373792,"about_ca_system_score_codex":0.000020193225,"about_ca_system_score_gemma":0.00010435222,"threshold_uncertainty_score":0.24206857},"labels":[],"label_agreement":null},{"id":"W2144342206","doi":"10.1186/s13321-015-0056-8","title":"Atom-Atom-Path similarity and Sphere Exclusion clustering: tools for prioritizing fragment hits","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre","funders":"","keywords":"Fragment (logic); Cluster analysis; Similarity (geometry); Atom (system on chip); Path (computing); Computer science; Data mining; Information retrieval; Combinatorics; Algorithm; Artificial intelligence; Mathematics; Parallel computing","score_opus":0.06401385121419086,"score_gpt":0.3221815610132692,"score_spread":0.2581677097990784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144342206","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16943452,0.00020531805,0.8280441,0.0005482189,0.0004097259,0.00016303663,0.0000040710543,0.000018276309,0.0011727122],"genre_scores_gemma":[0.13640897,0.000035994322,0.86290526,0.00039779674,0.00019255195,0.000003048597,0.0000024206633,0.000009617483,0.000044361943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983326,0.000020105097,0.0007379124,0.00009279689,0.00060887117,0.0002076693],"domain_scores_gemma":[0.9979306,0.0005353052,0.00059636554,0.00019790257,0.00049804355,0.00024178169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015727591,0.00014386371,0.00028739276,0.00007802418,0.00008050266,0.00038395682,0.00048808483,0.00007069206,0.0000015756643],"category_scores_gemma":[0.0004425829,0.00012482876,0.00009528848,0.00015023281,0.000026478265,0.002376235,0.00046642433,0.00019191696,0.0000014681384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029132652,0.00036133194,0.00051390735,0.0016608288,0.0002189068,0.00008287924,0.041441288,0.039045256,0.0013396532,0.019951018,0.024780842,0.87031275],"study_design_scores_gemma":[0.0024521167,0.00037545981,0.0007431518,0.00038898847,0.000040307055,0.00076838356,0.0013476486,0.9033938,0.005487935,0.015583233,0.069045484,0.00037349653],"about_ca_topic_score_codex":6.919194e-7,"about_ca_topic_score_gemma":5.432602e-7,"teacher_disagreement_score":0.86993927,"about_ca_system_score_codex":0.00016272362,"about_ca_system_score_gemma":0.00034186288,"threshold_uncertainty_score":0.5090369},"labels":[],"label_agreement":null},{"id":"W2145210171","doi":"10.1186/1758-2946-6-s1-o9","title":"Development of cannabinoid receptor (CB 2 R) ligands for application in PET studies - where to attach the radiolabel?","year":2014,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Pharmacological Receptor Mechanisms and Effects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"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":"Cannabinoid receptor; Positron emission tomography; Receptor; Chemistry; Cannabinoid; High resolution; Ligand (biochemistry); Docking (animal); Carbazole; Stereochemistry; Biochemistry; Nuclear medicine; Medicine; Organic chemistry; Antagonist","score_opus":0.016062371692487018,"score_gpt":0.3144542415294359,"score_spread":0.2983918698369489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145210171","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":[0.99241084,0.00029657516,0.006502425,0.00031275616,0.0001328941,0.00024468405,0.0000031102782,0.0000014780152,0.00009521824],"genre_scores_gemma":[0.9783071,0.00024237396,0.020786693,0.00034752305,0.00017222369,0.0000478648,0.00000870499,0.000007822249,0.000079681],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991651,0.0000055751166,0.00050547364,0.00005364908,0.00013411653,0.00013606521],"domain_scores_gemma":[0.9992401,0.000048134472,0.00033711555,0.00009474468,0.00021641546,0.00006346334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085026544,0.000091634094,0.00020564333,0.0000324654,0.000040020765,0.000007400591,0.0002067782,0.000049689257,0.000002419999],"category_scores_gemma":[0.0003119556,0.000056722063,0.00006155201,0.0000727338,0.000020454758,0.0000073301544,0.000056886423,0.00007678941,0.0000014093157],"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":[0.00011547438,0.000038957434,0.000051824245,0.00018006889,0.000059363334,8.009091e-8,0.0010939941,0.00011381806,0.9638678,0.00003512959,0.013785554,0.020657962],"study_design_scores_gemma":[0.00051615114,0.00028108835,0.00004959194,0.000047470472,0.000014419048,0.0000068904474,0.0004977424,0.00021695613,0.87535083,0.000038482845,0.122908466,0.00007190528],"about_ca_topic_score_codex":3.047982e-7,"about_ca_topic_score_gemma":0.000004672109,"teacher_disagreement_score":0.10912291,"about_ca_system_score_codex":0.000037912963,"about_ca_system_score_gemma":0.000071237126,"threshold_uncertainty_score":0.23130585},"labels":[],"label_agreement":null},{"id":"W2146172880","doi":"10.1186/1758-2946-4-5","title":"Blind trials of computer-assisted structure elucidation software","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Molecular spectroscopy and chirality","field":"Chemistry","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); Canadian Institute for Advanced Research","funders":"","keywords":"Software; Computer science; Set (abstract data type); Process (computing); Data mining; Data science; Information retrieval","score_opus":0.03362422348583312,"score_gpt":0.31109870900897996,"score_spread":0.27747448552314685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146172880","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":[0.98460215,0.0002380788,0.011827138,0.00003437734,0.00028312422,0.000044891054,0.00004772359,0.000011854057,0.0029106298],"genre_scores_gemma":[0.96158326,0.00002417623,0.037658934,0.00005538467,0.0005870011,3.8409928e-7,0.000036128207,0.000009534878,0.000045192937],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977591,0.000014268529,0.0015853303,0.000034271758,0.00042600563,0.00018101966],"domain_scores_gemma":[0.99683315,0.00014124645,0.0024789835,0.00020487898,0.00021531283,0.00012644836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008100082,0.00013227791,0.00054640084,0.000061340404,0.000031603206,0.000026637501,0.00021915842,0.00015589026,0.0006025227],"category_scores_gemma":[0.00048756704,0.00010158474,0.00026166104,0.000090175046,0.00003303358,0.00040056428,0.0000374338,0.00027981855,0.0000018960935],"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":[0.0010784344,0.0007127368,0.010218759,0.0036984768,0.0010883686,0.000008241828,0.009981812,0.00018683102,0.87570596,0.00027683016,0.013202302,0.08384123],"study_design_scores_gemma":[0.0012805277,0.000050676867,0.00044932842,0.00014657986,0.00013079768,0.00014523938,0.00017759691,0.00009549031,0.993686,0.00011852591,0.0036050798,0.00011416302],"about_ca_topic_score_codex":4.4101458e-7,"about_ca_topic_score_gemma":2.4260586e-7,"teacher_disagreement_score":0.11798002,"about_ca_system_score_codex":0.00005629361,"about_ca_system_score_gemma":0.00007275584,"threshold_uncertainty_score":0.65972006},"labels":[],"label_agreement":null},{"id":"W2146538435","doi":"10.1186/1758-2946-3-19","title":"Linked open drug data for pharmaceutical research and development","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":187,"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","funders":"Pfizer","keywords":"Data science; Computer science; Task (project management); Open data; Data sharing; External Data Representation; Web application; World Wide Web; Data mining; Medicine; Engineering; Alternative medicine; Artificial intelligence","score_opus":0.4477610663788747,"score_gpt":0.4690782952067872,"score_spread":0.021317228827912482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146538435","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540431,0.0034515643,0.019179657,0.0012908878,0.00062419,0.00089018163,0.000072177456,0.00001513941,0.0204331],"genre_scores_gemma":[0.49496198,0.0006026084,0.5020807,0.0004651792,0.00039962327,0.0000128697075,0.000114848466,0.000020526139,0.0013416894],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917006,0.000008947189,0.0003907795,0.00007797948,0.00017255628,0.00017969591],"domain_scores_gemma":[0.9992051,0.000059475762,0.00014640359,0.00023143337,0.00023139922,0.00012619629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777505,0.000066938424,0.00014062737,0.00003823934,0.00007179774,0.000040130868,0.00086413964,0.000088817294,0.000011230195],"category_scores_gemma":[0.0004975687,0.000048997837,0.000016244883,0.000038652473,0.0001562989,0.000019234427,0.00080140145,0.00016315699,0.0000017958907],"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":[0.001490536,0.0005223246,0.0011414177,0.0005934747,0.00050506426,0.000013723633,0.008481905,3.241893e-7,0.021891367,0.00020359074,0.35903448,0.6061218],"study_design_scores_gemma":[0.0011480149,0.0002950776,0.0001586787,0.00005146884,0.000014607404,0.00008879074,0.0014220707,0.000106652726,0.15697303,0.00023458357,0.83940715,0.00009987457],"about_ca_topic_score_codex":7.8147923e-7,"about_ca_topic_score_gemma":0.0000012379456,"teacher_disagreement_score":0.60602194,"about_ca_system_score_codex":0.000008497494,"about_ca_system_score_gemma":0.00021931081,"threshold_uncertainty_score":0.19980739},"labels":[],"label_agreement":null},{"id":"W2155459813","doi":"10.1186/1758-2946-3-20","title":"Chemical Entity Semantic Specification: Knowledge representation for efficient semantic cheminformatics and facile data integration","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Cheminformatics; Representation (politics); Semantic Web; Semantics (computer science); Knowledge representation and reasoning; Chemical database; Domain (mathematical analysis); Data science; Information retrieval; Artificial intelligence; Chemistry; Programming language","score_opus":0.08371741914909708,"score_gpt":0.32162875154499426,"score_spread":0.23791133239589718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155459813","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":[0.8880899,0.00008016077,0.106048286,0.00008714356,0.00078373536,0.0003975903,0.000047964357,0.00004116911,0.0044240598],"genre_scores_gemma":[0.8973515,0.00003889011,0.10220225,0.00003223688,0.00020201814,0.0000069626003,0.00005239133,0.000013162204,0.0001005725],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977262,0.000018298935,0.0013524431,0.0001698947,0.0004672389,0.000265946],"domain_scores_gemma":[0.99721754,0.00021833336,0.0013475086,0.0005972754,0.00047787302,0.00014146576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021523437,0.00018980105,0.00037424246,0.00012785046,0.00012708266,0.00021456744,0.00090269477,0.000098286546,0.0001879064],"category_scores_gemma":[0.001484284,0.00015313848,0.00006375415,0.00019392908,0.0001883864,0.0012296875,0.00030059388,0.0001811922,0.000051105995],"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":[0.00023601775,0.0003910358,0.00039734578,0.0016929256,0.000040998075,0.000003652591,0.037515495,0.00027490687,0.9374316,0.0011965388,0.009706947,0.0111125475],"study_design_scores_gemma":[0.00064458937,0.00007780271,0.0003221415,0.00018574737,0.00009137793,0.00020345947,0.001499304,0.15684381,0.8385962,0.0003673696,0.0009419913,0.00022615085],"about_ca_topic_score_codex":0.0000048505667,"about_ca_topic_score_gemma":0.0000010579972,"teacher_disagreement_score":0.15656891,"about_ca_system_score_codex":0.00006951664,"about_ca_system_score_gemma":0.00011103843,"threshold_uncertainty_score":0.6244806},"labels":[],"label_agreement":null},{"id":"W2169151607","doi":"10.1186/1758-2946-2-s1-p35","title":"Prediction of highly-connected 'hub'-proteins in protein interaction networks using QSAR","year":2010,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quantitative structure–activity relationship; Computer science; Interpretability; Cheminformatics; Computational biology; Machine learning; Proteome; Artificial intelligence; Drug discovery; Virtual screening; Data mining; Chemistry; Biology; Biochemistry; Computational chemistry","score_opus":0.027586025133478874,"score_gpt":0.2815810124379254,"score_spread":0.25399498730444653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169151607","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":[0.5705808,0.000008312507,0.4285649,0.000057849797,0.00039667787,0.00010390059,0.0000010823044,0.000008744252,0.00027776198],"genre_scores_gemma":[0.776325,0.0000025797297,0.2235163,0.000020729169,0.00012286066,0.0000015346003,0.0000011043612,0.0000047427216,0.0000051825414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982856,0.00003155625,0.0010554653,0.000066432236,0.00041184,0.00014910869],"domain_scores_gemma":[0.9980356,0.00019902938,0.0011272782,0.00020854539,0.00036193957,0.00006761473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010896414,0.00010760708,0.00023997512,0.0003045858,0.000029689598,0.0000696683,0.00044495583,0.00009697189,0.000007034063],"category_scores_gemma":[0.00044139105,0.00009678975,0.00008922807,0.00049002294,0.000032610988,0.0019558955,0.00010605855,0.00057709386,7.790111e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015455103,0.00042278226,0.0009020228,0.00034269676,0.000107906315,0.000020513115,0.005260295,0.60230166,0.3143534,0.008587497,0.00026871776,0.06727796],"study_design_scores_gemma":[0.00045297857,0.00007696345,0.0012631253,0.00019906044,0.000007919688,0.00013659493,0.00007508107,0.9056948,0.09016311,0.001699578,0.00015504415,0.00007574838],"about_ca_topic_score_codex":0.00000676151,"about_ca_topic_score_gemma":0.0000028113705,"teacher_disagreement_score":0.30339316,"about_ca_system_score_codex":0.00009055862,"about_ca_system_score_gemma":0.00018370103,"threshold_uncertainty_score":0.39469716},"labels":[],"label_agreement":null},{"id":"W2518754389","doi":"10.1186/s13321-016-0156-0","title":"Post-acquisition filtering of salt cluster artefacts for LC-MS based human metabolomic studies","year":2016,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Agriculture and Agri-Food Canada; Lawson Health Research Institute","funders":"Agriculture and Agri-Food Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Metabolomics; Metabolome; Mass spectrometry; Metabolite; Electrospray ionization; Chromatography; Chemistry; Liquid chromatography–mass spectrometry; Computer science; Analytical Chemistry (journal)","score_opus":0.018617142550887603,"score_gpt":0.29418090206411834,"score_spread":0.27556375951323075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518754389","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":[0.9867776,0.0011921513,0.010599547,0.0005434763,0.00025096256,0.00015568102,0.000066790315,0.0000034011034,0.00041036954],"genre_scores_gemma":[0.98959535,0.0005560726,0.009050569,0.00030870346,0.00024463426,0.0000065596,0.000012948704,0.000014123386,0.00021104098],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99882543,0.000008975435,0.0007382474,0.000074606156,0.00016607236,0.00018665021],"domain_scores_gemma":[0.998277,0.00006941272,0.00081097113,0.00017777506,0.0006081294,0.000056684938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046846727,0.00014796214,0.00040659326,0.00010865665,0.000056653673,0.000011354466,0.00016466956,0.00007783532,0.00001356683],"category_scores_gemma":[0.00034491118,0.00009389046,0.00022549045,0.00004676226,0.00007756879,0.000022591583,0.000073474665,0.00004941823,8.778319e-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":[0.00018023665,0.000034966462,0.00006378395,0.00018716425,0.00031978736,3.6742028e-7,0.00013583132,0.000012965173,0.99365807,0.00008198254,0.0039429856,0.0013818517],"study_design_scores_gemma":[0.0016798255,0.00062435854,0.00027267303,0.00009555582,0.00011353576,0.000017531456,0.00022801124,0.000027883942,0.98453593,0.00021557367,0.012058795,0.00013035255],"about_ca_topic_score_codex":2.818757e-7,"about_ca_topic_score_gemma":0.0000011400653,"teacher_disagreement_score":0.009122174,"about_ca_system_score_codex":0.00002411419,"about_ca_system_score_gemma":0.00005112538,"threshold_uncertainty_score":0.38287422},"labels":[],"label_agreement":null},{"id":"W2548357532","doi":"10.1186/s13321-016-0174-y","title":"ClassyFire: automated chemical classification with a comprehensive, computable taxonomy","year":2016,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1587,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Metabolomics Innovation Centre; Alberta Innovates; Athabasca University; Ottawa Hospital; University of Ottawa; University of Alberta","funders":"Alberta Innovates; National Institutes of Health; Genome Alberta; U.S. National Library of Medicine; University of Alberta; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Taxonomy (biology); Class (philosophy); Druggability; Information retrieval; Chemical database; Artificial intelligence; Data science; Chemistry","score_opus":0.04246514513245019,"score_gpt":0.27671566847275636,"score_spread":0.23425052334030616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548357532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10486756,0.000034206394,0.890677,0.0012183926,0.00018543118,0.00014411319,0.0000027050053,0.00014190208,0.0027287123],"genre_scores_gemma":[0.52902836,0.000012448156,0.47059113,0.0002300384,0.000081221144,0.0000055241553,0.000001571981,0.000009204754,0.00004050544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981908,0.00002886727,0.0008103041,0.00011303862,0.0006198549,0.00023713244],"domain_scores_gemma":[0.9972426,0.0006378684,0.00095306744,0.00031944673,0.0006832212,0.00016378824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036287683,0.0001713569,0.00032618275,0.00015280543,0.000047723704,0.00013581014,0.0008087388,0.00006953075,0.000007867893],"category_scores_gemma":[0.00010315726,0.00010263293,0.00009628348,0.00039795067,0.000094596326,0.0017973323,0.00014641507,0.00016586304,0.000024775985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052871,0.0010389573,0.0021211838,0.00063975673,0.00090522144,0.00013252233,0.0030174654,0.022995645,0.10911271,0.056396857,0.13239034,0.67072064],"study_design_scores_gemma":[0.0026330152,0.00022436673,0.0021042211,0.00039432157,0.0000370605,0.0012995658,0.00012322684,0.89747036,0.056421634,0.0018079206,0.037077323,0.00040697874],"about_ca_topic_score_codex":3.7263746e-7,"about_ca_topic_score_gemma":5.4479784e-8,"teacher_disagreement_score":0.8744747,"about_ca_system_score_codex":0.00018554542,"about_ca_system_score_gemma":0.00035850916,"threshold_uncertainty_score":0.41852495},"labels":[],"label_agreement":null},{"id":"W2603853601","doi":"10.1186/s13321-017-0207-1","title":"Critical Assessment of Small Molecule Identification 2016: automated methods","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Academy of Finland; Leibniz-Gemeinschaft; Deutsche Forschungsgemeinschaft; Metabolomics Innovation Centre; European Commission","keywords":"Computer science; Identification (biology); CONTEST; Machine learning; Annotation; Ranking (information retrieval); Artificial intelligence; Metadata; Data mining; Information retrieval; Data science; World Wide Web","score_opus":0.04345306440196599,"score_gpt":0.4468853515237422,"score_spread":0.4034322871217762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603853601","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014065349,0.000035034725,0.978816,0.0006090649,0.0005348738,0.000055050074,0.000002202581,0.000027323907,0.0058551366],"genre_scores_gemma":[0.25711596,0.000011021512,0.7427555,0.000044032367,0.000037165573,0.00000107338,7.774818e-7,0.0000042071224,0.000030310637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981001,0.00007022702,0.0011111556,0.0000744274,0.0004962886,0.00014782153],"domain_scores_gemma":[0.99595225,0.0006947928,0.0017350093,0.00061058305,0.0009030925,0.00010428203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003002667,0.00010483086,0.0002907833,0.00014276593,0.00012344525,0.00039125903,0.00151003,0.00005850248,0.0000060044085],"category_scores_gemma":[0.002331357,0.000090827554,0.00014456159,0.000101120386,0.00010088961,0.0018082334,0.00030376445,0.00019268207,0.0000028555892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058703645,0.0012861784,0.00089615886,0.0020277197,0.0006906356,0.00007889093,0.007877853,0.031895634,0.17473798,0.24638794,0.016645392,0.5174169],"study_design_scores_gemma":[0.00025779768,0.00005331823,0.008185129,0.00009775092,0.000027806323,0.00008075585,0.000041319097,0.8714378,0.11262805,0.0068960255,0.00019763372,0.00009662846],"about_ca_topic_score_codex":0.0000014542993,"about_ca_topic_score_gemma":9.196629e-8,"teacher_disagreement_score":0.83954215,"about_ca_system_score_codex":0.00007037338,"about_ca_system_score_gemma":0.0004056337,"threshold_uncertainty_score":0.377292},"labels":[],"label_agreement":null},{"id":"W2605952223","doi":"10.1186/s13321-017-0209-z","title":"SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":509,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Benchmark (surveying); Computer science; Binding affinities; Binary number; Boosting (machine learning); Drug discovery; Drug target; Affinities; Gradient boosting; Machine learning; Binary classification; Artificial intelligence; Data mining; Bioinformatics; Support vector machine; Random forest; Mathematics; Chemistry; Biology","score_opus":0.061090638483814026,"score_gpt":0.3506717947180562,"score_spread":0.2895811562342422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605952223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33123264,0.00006072224,0.6654793,0.00010093815,0.00054239377,0.00014435813,0.000017702407,0.00002470625,0.0023972038],"genre_scores_gemma":[0.30242434,0.00000625333,0.6971593,0.000049244507,0.00026756365,0.0000032347416,0.000004036769,0.000013291575,0.00007272822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978514,0.000022566357,0.0010361973,0.00012718978,0.000562957,0.00039971303],"domain_scores_gemma":[0.995802,0.00083327846,0.0023911784,0.0004203856,0.00042063903,0.00013251846],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002596968,0.00020551581,0.000396856,0.0001372718,0.0009208538,0.0010872344,0.0014234016,0.000057171063,0.0000011232423],"category_scores_gemma":[0.0020519497,0.00017884128,0.00022467246,0.00010537767,0.00009116451,0.0031131275,0.00052143814,0.00027908772,5.4133733e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024598042,0.00050770317,0.022200298,0.00377555,0.0007814259,0.000066438064,0.1478195,0.6253841,0.0022829743,0.011540638,0.0015687313,0.18382664],"study_design_scores_gemma":[0.0005870513,0.000046430338,0.0002742142,0.00023126374,0.000024663705,0.00032043832,0.0014033816,0.9899146,0.0044506914,0.0021406892,0.00040309888,0.00020347863],"about_ca_topic_score_codex":0.000004961287,"about_ca_topic_score_gemma":3.4389788e-7,"teacher_disagreement_score":0.3645305,"about_ca_system_score_codex":0.00013540265,"about_ca_system_score_gemma":0.0002050542,"threshold_uncertainty_score":0.99994975},"labels":[],"label_agreement":null},{"id":"W2727000434","doi":"10.1186/s13321-017-0242-y","title":"A posteriori metadata from automated provenance tracking: integration of AiiDA and TCOD","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":30,"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":"Horizon 2020 Framework Programme; European Commission; SCIEX; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Metadata; Protocol (science); Interoperability; Interface (matter); Field (mathematics); Process (computing); Proof of concept","score_opus":0.022860132749665727,"score_gpt":0.305870177292973,"score_spread":0.28301004454330725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727000434","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":[0.99642503,0.00005336688,0.001868397,0.00020912813,0.00047338055,0.000079890764,0.00003531123,0.00002458396,0.0008309223],"genre_scores_gemma":[0.94913995,0.000026189342,0.05065461,0.000039574374,0.00007548411,8.1781286e-7,0.000002879949,0.000006864955,0.000053654414],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984145,0.000019706027,0.0008959926,0.000083693696,0.00043410296,0.0001519678],"domain_scores_gemma":[0.9962709,0.00009423121,0.0028464638,0.00042911677,0.00028344025,0.000075824246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167897,0.00012595164,0.00038214613,0.000057714627,0.0001437079,0.0006531468,0.00079622015,0.00006334599,0.000063566404],"category_scores_gemma":[0.0016907575,0.000090643094,0.00004628152,0.000038548016,0.00020025104,0.003113195,0.00017614386,0.00013931317,0.0000061026376],"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":[0.000046011177,0.000019323925,0.00038564298,0.00008700228,0.000008568598,0.0000037575346,0.0017814268,0.000037867572,0.99460596,0.00008976558,0.00026400303,0.002670672],"study_design_scores_gemma":[0.00047765483,0.00012346,0.011180662,0.00035657716,0.000041882835,0.000089011504,0.000238165,0.015365019,0.9712143,0.00040123434,0.00039250488,0.00011952655],"about_ca_topic_score_codex":0.000040126764,"about_ca_topic_score_gemma":0.0000029505093,"teacher_disagreement_score":0.04878621,"about_ca_system_score_codex":0.000025741338,"about_ca_system_score_gemma":0.00009122652,"threshold_uncertainty_score":0.629831},"labels":[],"label_agreement":null},{"id":"W2745961286","doi":"10.1186/s13321-017-0234-y","title":"Comparative analysis of chemical similarity methods for modular natural products with a hypothetical structure enumeration algorithm","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; McMaster University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Cheminformatics; Chemical space; Chemical similarity; Computer science; Natural product; Similarity (geometry); Enumeration; Modular design; Data mining; Drug discovery; Biochemical engineering; Algorithm; Structural similarity; Artificial intelligence; Bioinformatics; Chemistry; Mathematics; Biology; Engineering","score_opus":0.0263425672799847,"score_gpt":0.3490112789775224,"score_spread":0.3226687116975377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745961286","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":[0.98592734,0.00027347208,0.010646886,0.0022020866,0.00017934431,0.0005033786,0.000077774646,0.0000071618592,0.00018252831],"genre_scores_gemma":[0.62843806,0.0000074954323,0.3713139,0.000054705168,0.00013552958,2.2333964e-7,0.000019341853,0.000004057822,0.000026685308],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987836,0.000012279608,0.0006609708,0.00009986486,0.0002891623,0.00015411667],"domain_scores_gemma":[0.99693197,0.00011188556,0.0011884831,0.0003511381,0.0013339105,0.000082627135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049491157,0.00015952744,0.0009075613,0.0001505449,0.000081525875,0.000053545013,0.00020957505,0.00011540614,0.000014106511],"category_scores_gemma":[0.0010074143,0.00009303703,0.0002243914,0.00018687884,0.00018055928,0.0003204473,0.000034689376,0.0003413813,1.2604139e-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":[0.0007239667,0.00012536549,0.000054806875,0.0003623079,0.002509079,0.00000283319,0.0012044932,0.00002076026,0.9525944,0.000041287854,0.00057586347,0.04178486],"study_design_scores_gemma":[0.0008964211,0.00021148671,0.000572041,0.00008879452,0.0029765053,0.00012942155,0.000098031865,0.026351584,0.967682,0.00007613672,0.00080474064,0.00011281838],"about_ca_topic_score_codex":0.0000013410029,"about_ca_topic_score_gemma":4.4344205e-7,"teacher_disagreement_score":0.360667,"about_ca_system_score_codex":0.00005098624,"about_ca_system_score_gemma":0.00012714123,"threshold_uncertainty_score":0.379394},"labels":[],"label_agreement":null},{"id":"W2905553692","doi":"10.1186/s13321-018-0319-2","title":"SIA: a scalable interoperable annotation server for biomedical named entities","year":2018,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"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":"Bundesministerium für Wirtschaft und Energie; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Annotation; Interoperability; Workflow; Scalability; Server; Information extraction; Named-entity recognition","score_opus":0.013462996530450582,"score_gpt":0.27915431022398707,"score_spread":0.2656913136935365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905553692","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":[0.97150344,0.00036979292,0.023788406,0.000614025,0.0007697864,0.00010932399,0.000015066159,0.000011373465,0.0028187947],"genre_scores_gemma":[0.96881336,0.000101079844,0.027703384,0.00054453773,0.000977862,0.0000055217233,0.000043030705,0.00001224111,0.0017989817],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911433,0.0000062060185,0.0004571986,0.00005713909,0.00018817536,0.00017696981],"domain_scores_gemma":[0.9991532,0.000027617676,0.0002682646,0.00011428292,0.00034674368,0.00008988581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039366668,0.00008978418,0.00016845934,0.0000561098,0.000058844584,0.000034526285,0.00019798112,0.000154659,0.00003277705],"category_scores_gemma":[0.00052885915,0.000065933426,0.000099002806,0.00006928802,0.00023558122,0.00001477646,0.000050862865,0.00008740738,0.000007058787],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008893787,0.00034614812,0.0006160965,0.000691291,0.00053255627,0.0000066037314,0.004277355,0.000007814628,0.22162968,0.00017179102,0.6358796,0.13495173],"study_design_scores_gemma":[0.0015070845,0.0020097916,0.0000849683,0.00013155218,0.000048001617,0.00014552446,0.0017080181,0.00078401377,0.40019858,0.00027953237,0.59294426,0.00015865664],"about_ca_topic_score_codex":8.912826e-7,"about_ca_topic_score_gemma":0.000001492396,"teacher_disagreement_score":0.1785689,"about_ca_system_score_codex":0.00001665114,"about_ca_system_score_gemma":0.0001052699,"threshold_uncertainty_score":0.2688687},"labels":[],"label_agreement":null},{"id":"W2907470641","doi":"10.1186/s13321-018-0324-5","title":"BioTransformer: a comprehensive computational tool for small molecule metabolism prediction and metabolite identification","year":2019,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":513,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Eidgenössische Anstalt für Wasserversorgung Abwasserreinigung und Gewässerschutz; Genome Alberta; Agence Nationale de la Recherche; Alberta Innovates; Alberta Innovates - Health Solutions; Joint Programming Initiative A healthy diet for a healthy life; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Identification (biology); In silico; Computational biology; Metabolomics; Data mining; Machine learning; Bioinformatics; Chemistry; Biology; Biochemistry","score_opus":0.00830872921048072,"score_gpt":0.23225723172089133,"score_spread":0.2239485025104106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907470641","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":[0.9664196,0.0021973844,0.030271305,0.000112700654,0.0002812537,0.00029189952,0.000092251,0.0000035919388,0.00033005554],"genre_scores_gemma":[0.9766408,0.0017200762,0.020782996,0.00024321335,0.00021295638,0.000010021792,0.00014608983,0.000015353922,0.00022848672],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990301,0.0000071178165,0.0005848545,0.00008835447,0.00015439506,0.00013517974],"domain_scores_gemma":[0.9989191,0.000031158954,0.00042980793,0.00010800815,0.00046240454,0.000049507074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026276964,0.000121416786,0.0002615514,0.000095383344,0.000049537917,0.000041120173,0.000099941004,0.000076923985,0.0000039884194],"category_scores_gemma":[0.00006547109,0.00010370001,0.0001321508,0.000072288065,0.000036494665,0.000023768807,0.000032324984,0.00007626066,0.000001581922],"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":[0.00023682116,0.00006582936,0.00049984246,0.0003108935,0.0005951822,2.9119914e-7,0.00042772383,0.0005189803,0.98849034,0.002097409,0.0015109709,0.0052457107],"study_design_scores_gemma":[0.004192153,0.0004903492,0.011130222,0.00003686945,0.00042337994,0.00017449989,0.00072353607,0.005496242,0.8411136,0.0015513182,0.1342979,0.00036990718],"about_ca_topic_score_codex":3.4881438e-7,"about_ca_topic_score_gemma":1.4585812e-7,"teacher_disagreement_score":0.14737673,"about_ca_system_score_codex":0.000009144994,"about_ca_system_score_gemma":0.000051285533,"threshold_uncertainty_score":0.42287636},"labels":[],"label_agreement":null},{"id":"W2963037859","doi":"10.1186/s13321-019-0349-4","title":"DNAmod: the DNA modification database","year":2019,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Canada Research Chairs; Princess Margaret Cancer Centre; Fleming College; University of Toronto","funders":"Canadian Institutes of Health Research; China Scholarship Council; Ontario Ministry of Research, Innovation and Science; Government of Ontario; University of Toronto; Canadian Cancer Society; Ontario Institute for Cancer Research; Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Computer science; Database; Computational biology; DNA; Biology; Genetics","score_opus":0.010571237936122725,"score_gpt":0.2545547639121071,"score_spread":0.24398352597598436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963037859","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":[0.98636585,0.00035881563,0.0032441227,0.0004028603,0.00019248415,0.000100845726,0.000009732796,0.0000019986937,0.009323303],"genre_scores_gemma":[0.99722147,0.00032366664,0.00088986947,0.00028605264,0.00017794968,0.0000026117123,0.000030386544,0.0000063880566,0.0010616248],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937904,0.0000054179163,0.0003240182,0.000041046846,0.00016386106,0.00008664535],"domain_scores_gemma":[0.9990982,0.000010486278,0.00034606835,0.0003391398,0.00016748828,0.000038638325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002832938,0.000063144325,0.000079778416,0.000023124938,0.000034334167,0.000026844657,0.00026574353,0.00004685115,0.000035344467],"category_scores_gemma":[0.00004568078,0.00003988339,0.00007028232,0.000056210276,0.000027379034,0.000017205259,0.000033945595,0.0000920294,0.000026101014],"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":[0.00006747806,0.00005788792,0.00042958837,0.00006321524,0.00007977964,4.139845e-7,0.00042169043,0.00047206332,0.94507796,0.000574304,0.042203434,0.010552174],"study_design_scores_gemma":[0.00066418125,0.00013744576,0.0007813471,0.000034470075,0.000038791768,0.00010727271,0.00088790857,0.0015705511,0.66344357,0.00009323581,0.33209705,0.0001441744],"about_ca_topic_score_codex":5.2276675e-7,"about_ca_topic_score_gemma":2.7195534e-7,"teacher_disagreement_score":0.28989363,"about_ca_system_score_codex":0.0000140201155,"about_ca_system_score_gemma":0.00008496025,"threshold_uncertainty_score":0.16263975},"labels":[],"label_agreement":null},{"id":"W2994270865","doi":"10.1186/s13321-019-0398-8","title":"The chemfp project","year":2019,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Air (Canada)","funders":"","keywords":"Computer science; x86; Benchmark (surveying); Cheminformatics; Data mining; Implementation; Software; Information retrieval; Parallel computing; Operating system; Programming language","score_opus":0.009351925075971965,"score_gpt":0.27854023117147897,"score_spread":0.269188306095507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994270865","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26015168,0.0005067436,0.60976744,0.0036377523,0.0032445218,0.00046562025,0.0000016479227,0.000059986898,0.12216461],"genre_scores_gemma":[0.4892328,0.00014565201,0.5072028,0.00095002615,0.0003708394,0.0000034187453,9.299037e-7,0.00001572862,0.002077789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998846,0.0000131947845,0.0004896272,0.000036049623,0.00048134386,0.00013381202],"domain_scores_gemma":[0.9983978,0.00057872565,0.0005055169,0.00025363316,0.00022661914,0.000037693695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108675,0.00006881,0.00012608473,0.00005814465,0.000050269537,0.00019909021,0.0009677685,0.000024597663,0.0000036672357],"category_scores_gemma":[0.00019598639,0.000040402763,0.000098783945,0.00023385583,0.000020582273,0.00096716534,0.00015244765,0.00017868976,0.00003447822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009765834,0.00018375766,0.0007085281,0.0003712579,0.00034044177,0.000023080944,0.01896125,0.019681465,0.0016813868,0.1888597,0.10167729,0.6674142],"study_design_scores_gemma":[0.0012771435,0.00028185485,0.00095860387,0.00014206092,0.000020934845,0.001027033,0.0009768632,0.65263325,0.038489714,0.032034334,0.27180573,0.00035248837],"about_ca_topic_score_codex":2.542416e-7,"about_ca_topic_score_gemma":5.3756303e-8,"teacher_disagreement_score":0.6670617,"about_ca_system_score_codex":0.000047805126,"about_ca_system_score_gemma":0.0002911891,"threshold_uncertainty_score":0.19198315},"labels":[],"label_agreement":null},{"id":"W3044334750","doi":"10.1186/s13321-020-00450-7","title":"A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions","year":2020,"lang":"en","type":"review","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":391,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Drug repositioning; Computer science; Drug discovery; Process (computing); Data science; Multidisciplinary approach; Drug development; Computational model; Drug; Field (mathematics); Risk analysis (engineering); Artificial intelligence; Bioinformatics; Medicine; Pharmacology","score_opus":0.2181327886717617,"score_gpt":0.3515936227001733,"score_spread":0.1334608340284116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044334750","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":[1.0006365e-7,0.9578421,0.03416902,0.0005456329,0.00017324065,0.00025922802,0.00002068876,0.000020483252,0.006969477],"genre_scores_gemma":[9.1288723e-7,0.8903353,0.1093511,0.00012376714,0.00010222539,0.000008767922,0.000044095905,0.000015439526,0.000018358944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996305,0.00016038574,0.002498222,0.00016666284,0.0007076909,0.00016205531],"domain_scores_gemma":[0.9941668,0.00097678,0.003891917,0.0003016914,0.0004529719,0.00020982271],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014976416,0.00033850656,0.00179736,0.000285606,0.000061960214,0.00013719905,0.0008187839,0.00010911162,0.000004166084],"category_scores_gemma":[0.00027100777,0.00028557572,0.00047770664,0.00039437198,0.00008915738,0.0012865394,0.00030478608,0.00057143095,0.0000013740514],"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":[0.0000010245094,0.000036447655,6.8297807e-9,0.11312725,0.00019216958,0.000015919166,0.00080582406,0.000094795585,7.1878516e-9,0.018118931,0.0023965673,0.86521107],"study_design_scores_gemma":[0.00011569905,0.000051957588,3.481725e-7,0.07955093,0.000379804,0.0026388355,0.00021756576,0.0038427194,7.6722426e-7,0.0037368904,0.9092293,0.00023518312],"about_ca_topic_score_codex":5.805091e-7,"about_ca_topic_score_gemma":1.1612425e-7,"teacher_disagreement_score":0.90683275,"about_ca_system_score_codex":0.00013842575,"about_ca_system_score_gemma":0.0026330354,"threshold_uncertainty_score":0.99995965},"labels":[],"label_agreement":null},{"id":"W3045213199","doi":"10.1186/s13321-020-00449-0","title":"rMSIcleanup: an open-source tool for matrix-related peak annotation in mass spectrometry imaging and its application to silver-assisted laser desorption/ionization","year":2020,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Natural Sciences and Engineering Research Council of Canada; Universitat Rovira i Virgili; Horizon 2020; Ministerio de Economía y Competitividad","keywords":"Mass spectrometry imaging; Mass spectrometry; Computer science; Annotation; Workflow; Matrix-assisted laser desorption/ionization; Matrix (chemical analysis); Principal component analysis; Desorption; Analyte; MALDI imaging; Chemistry; Analytical Chemistry (journal); Data mining; Artificial intelligence; Chromatography; Database","score_opus":0.009794563412108884,"score_gpt":0.26528218273723764,"score_spread":0.25548761932512876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045213199","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":[0.93715966,0.000291255,0.061060887,0.00082400243,0.000046017427,0.00044153765,0.000014009786,0.000006440568,0.00015619109],"genre_scores_gemma":[0.98096013,0.00020413184,0.018114422,0.0004282416,0.00011936036,0.000012907866,0.0000800674,0.000017242919,0.000063503416],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896973,0.000012255999,0.00060026324,0.00012716465,0.00014056562,0.00015002696],"domain_scores_gemma":[0.99907476,0.000020277465,0.00043295117,0.00010275286,0.0002634549,0.00010577984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038762594,0.00012360424,0.00022471743,0.00011873056,0.00006026409,0.00008587623,0.00020563038,0.00006615155,0.00000488064],"category_scores_gemma":[0.00032513496,0.00011826933,0.000041222058,0.00033869164,0.000012515989,0.00007798811,0.00009099448,0.0000942108,0.0000018422957],"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":[0.00019981989,0.0000534432,0.0007849898,0.00008185464,0.000046460602,6.3194886e-7,0.0005729125,0.0008786519,0.9900018,0.00016435656,0.00066317327,0.0065518892],"study_design_scores_gemma":[0.0053311763,0.0013453529,0.009863999,0.000073486095,0.0001620338,0.00009546483,0.0027798777,0.058852397,0.90354156,0.00053607137,0.01679883,0.0006197509],"about_ca_topic_score_codex":7.3802073e-7,"about_ca_topic_score_gemma":0.0000012780812,"teacher_disagreement_score":0.086460255,"about_ca_system_score_codex":0.00003580354,"about_ca_system_score_gemma":0.00003947175,"threshold_uncertainty_score":0.48228836},"labels":[],"label_agreement":null},{"id":"W3155267227","doi":"10.1186/s13321-021-00527-x","title":"Twitter integration of chemistry software tools","year":2021,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Japan Society for the Promotion of Science","keywords":"Cheminformatics; Computer science; Software; Data science; World Wide Web; Social media; Social software; Measure (data warehouse); Chemistry; Data mining","score_opus":0.13531568106620018,"score_gpt":0.36827355986071786,"score_spread":0.23295787879451768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155267227","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":[0.7636255,0.000119957105,0.20282772,0.00072493026,0.0011430877,0.000050620103,0.00001916832,0.000011814593,0.031477194],"genre_scores_gemma":[0.9164962,0.000019877303,0.07388017,0.00038145742,0.00020843981,4.2685502e-7,0.000019408191,0.000005913086,0.008988081],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99723554,0.000009729571,0.0012986612,0.00007640617,0.0012819216,0.00009771756],"domain_scores_gemma":[0.99660647,0.0005280793,0.0010953584,0.0004763603,0.0012286848,0.000065061635],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026016457,0.00006606662,0.00022876955,0.00008211505,0.000032674627,0.00029475303,0.0005703085,0.000037319605,0.0004322835],"category_scores_gemma":[0.008825139,0.000044999382,0.00013995773,0.00046251333,0.000039884475,0.000630901,0.00019016936,0.00013062372,0.00002511292],"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":[0.000024291856,0.00012375692,0.0006588419,0.000118057826,0.000057822508,0.000027579441,0.004552528,0.00043471242,0.025713013,0.000057386307,0.5055724,0.46265963],"study_design_scores_gemma":[0.00057238375,0.000035298017,0.0010480208,0.0002483728,0.000043499727,0.00023440957,0.011144866,0.003222381,0.8793874,0.004402228,0.099506706,0.00015443632],"about_ca_topic_score_codex":2.2335294e-7,"about_ca_topic_score_gemma":1.5681775e-7,"teacher_disagreement_score":0.8536744,"about_ca_system_score_codex":0.000026024247,"about_ca_system_score_gemma":0.00013029034,"threshold_uncertainty_score":0.99952394},"labels":[],"label_agreement":null},{"id":"W4220847490","doi":"10.1186/s13321-022-00596-6","title":"Deep learning-driven prediction of drug mechanism of action from large-scale chemical-genetic interaction profiles","year":2022,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; Cystic Fibrosis Canada","keywords":"Computer science; Mechanism (biology); Scale (ratio); Action (physics); Drug discovery; Artificial intelligence; Machine learning; Data science; Bioinformatics; Biology","score_opus":0.015299762500538215,"score_gpt":0.26690328197015045,"score_spread":0.25160351946961224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220847490","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":[0.5121275,0.00002953786,0.48704866,0.000051367828,0.0004318518,0.00006753087,0.0000133836065,0.0000122439105,0.00021790249],"genre_scores_gemma":[0.8609643,0.000022579154,0.13887495,0.000019277117,0.00007202625,0.0000044103517,0.000016127804,0.000006596944,0.000019740331],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980139,0.00007040756,0.0009569034,0.000082175335,0.0007580462,0.00011856612],"domain_scores_gemma":[0.9974812,0.0002789953,0.0017209678,0.00017106415,0.0002922736,0.000055491364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058683165,0.000101325466,0.00026314773,0.0001911822,0.00006661474,0.000026489219,0.0004890787,0.000037049198,0.00005306969],"category_scores_gemma":[0.00012796227,0.00010066303,0.00014906545,0.000288599,0.000020476917,0.0008276978,0.00029074805,0.00040542928,0.0000011954536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021228957,0.0006808839,0.0010456344,0.00041098302,0.00028678917,0.0000057069524,0.045577496,0.70973355,0.18585466,0.0016763719,0.0010520741,0.053463574],"study_design_scores_gemma":[0.00039373332,0.00011349886,0.00043574857,0.000044308006,0.000030828953,0.000060325532,0.0023381442,0.717417,0.27570724,0.0030588724,0.00033762795,0.00006268409],"about_ca_topic_score_codex":0.0000038002202,"about_ca_topic_score_gemma":3.165475e-7,"teacher_disagreement_score":0.34883675,"about_ca_system_score_codex":0.00015723368,"about_ca_system_score_gemma":0.00011212265,"threshold_uncertainty_score":0.4104919},"labels":[],"label_agreement":null},{"id":"W4322102662","doi":"10.1186/s13321-023-00698-9","title":"ABT-MPNN: an atom-bond transformer-based message-passing neural network for molecular property prediction","year":2023,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Manitoba","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Cystic Fibrosis Canada; Manitoba Medical Service Foundation","keywords":"Computer science; Interpretability; Message passing; Molecular graph; Theoretical computer science; Embedding; Artificial neural network; Graph embedding; Artificial intelligence; Graph; Distributed computing","score_opus":0.02954166971114737,"score_gpt":0.3017053752043101,"score_spread":0.27216370549316277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322102662","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11526793,0.00002933861,0.8823461,0.000838005,0.0005875521,0.00023113082,0.000009546388,0.00008399932,0.0006063912],"genre_scores_gemma":[0.35050023,0.00001180221,0.64812726,0.0007564825,0.00045292568,0.000020047268,0.00003956353,0.00003141589,0.000060274153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788684,0.00003251753,0.0008849828,0.000113657945,0.0007386673,0.0003433556],"domain_scores_gemma":[0.99837726,0.00031963515,0.0005005165,0.0002456948,0.0003871639,0.00016974828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016978605,0.00017023108,0.0002822873,0.00018717641,0.00014724769,0.00026167618,0.00064607005,0.000076447286,0.000002520042],"category_scores_gemma":[0.00011147342,0.00012327034,0.00021986,0.00067223667,0.00003801564,0.0021018793,0.000037779668,0.0002528169,0.000002652762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007076633,0.00006712381,0.00005057814,0.00024350881,0.000061746694,0.000020059339,0.0018527602,0.8688375,0.0017707229,0.0012825188,0.007782562,0.11796017],"study_design_scores_gemma":[0.00077567203,0.00025775682,0.00034724237,0.00010185051,0.00003413082,0.00007991971,0.000109980865,0.97230077,0.018746566,0.0032040572,0.0038890922,0.00015296064],"about_ca_topic_score_codex":6.7756304e-7,"about_ca_topic_score_gemma":3.1863235e-7,"teacher_disagreement_score":0.23523228,"about_ca_system_score_codex":0.00009096505,"about_ca_system_score_gemma":0.00036412475,"threshold_uncertainty_score":0.50268185},"labels":[],"label_agreement":null},{"id":"W4399175963","doi":"10.1186/s13321-024-00853-w","title":"Identifying uncertainty in physical–chemical property estimation with IFSQSAR","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; The Scarborough Hospital; ARC Resources (Canada)","funders":"","keywords":"Property (philosophy); Computer science; Estimation; Data mining; Data science; Systems engineering; Engineering","score_opus":0.009905848516422483,"score_gpt":0.2654185823120778,"score_spread":0.2555127337956553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399175963","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":[0.99283284,0.0006996205,0.0035493341,0.00017758865,0.000111613685,0.00007791891,0.0000032670384,0.0000055170312,0.0025422766],"genre_scores_gemma":[0.9922578,0.00022015444,0.007107608,0.000043871878,0.0001768537,0.0000028594302,0.000009472139,0.0000099610115,0.00017146049],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925244,0.000004656879,0.0003404011,0.00007056499,0.00019436491,0.000137545],"domain_scores_gemma":[0.9996063,0.000017271579,0.00014031123,0.00010092614,0.00009091143,0.000044277655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022768108,0.00010792708,0.00019583995,0.000086149055,0.00001797443,0.000054874778,0.00011884115,0.000049079325,0.0000036189815],"category_scores_gemma":[0.0000982253,0.000060454146,0.000077086384,0.00016253731,0.000041295792,0.000023650748,0.00004702567,0.00016889622,0.0000027676895],"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":[0.00024851778,0.00018394712,0.00025745475,0.0008460167,0.00041497874,0.000043651817,0.0028871354,0.0021736065,0.9367302,0.00052735984,0.007761585,0.04792554],"study_design_scores_gemma":[0.0011164906,0.00047338204,0.00014826658,0.0004964938,0.00013326567,0.00039229429,0.0010552262,0.045689125,0.9241969,0.0011581399,0.024776448,0.00036396462],"about_ca_topic_score_codex":0.0000014169328,"about_ca_topic_score_gemma":0.0000012430862,"teacher_disagreement_score":0.047561575,"about_ca_system_score_codex":0.00003461411,"about_ca_system_score_gemma":0.00008915312,"threshold_uncertainty_score":0.24652486},"labels":[],"label_agreement":null},{"id":"W4401589835","doi":"10.1186/s13321-024-00892-3","title":"Metis: a python-based user interface to collect expert feedback for generative chemistry models","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":7,"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":"Horizon 2020; Engineering and Physical Sciences Research Council; Vetenskapsrådet; UK Research and Innovation; Knut och Alice Wallenbergs Stiftelse; Finnish Center for Artificial Intelligence; European Commission; Chalmers Tekniska Högskola","keywords":"Computer science; Python (programming language); Graphical user interface; Human–computer interaction; Interface (matter); User interface; Generative grammar; Generative model; Human-in-the-loop; Software engineering; Data science; Artificial intelligence; Programming language","score_opus":0.030714670423141927,"score_gpt":0.33359502077316355,"score_spread":0.30288035035002164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401589835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069650216,0.00044762378,0.9884219,0.0019126942,0.000462383,0.00019856225,0.0000131869665,0.000043122374,0.001535472],"genre_scores_gemma":[0.07819162,0.000014324237,0.9198524,0.0009854689,0.00025528777,0.000027716702,0.0000026151783,0.000021285809,0.0006493187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983682,0.000016675227,0.0007528566,0.00013702604,0.00049887656,0.00022636828],"domain_scores_gemma":[0.99808836,0.00078538724,0.00024232212,0.0002410497,0.00046459652,0.00017827256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079938944,0.00018600082,0.0003068756,0.00015360695,0.00005706991,0.00048100206,0.0007764824,0.00006743371,0.000014267132],"category_scores_gemma":[0.00026075917,0.0001549807,0.00022764417,0.0005051119,0.00002331769,0.001231416,0.00014307353,0.00020175404,0.0000075254065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009545411,0.000081377504,4.3134318e-7,0.0004903393,0.0002031833,0.000015461355,0.013257717,0.8366096,0.011968655,0.0024411597,0.10973568,0.025100954],"study_design_scores_gemma":[0.0002788735,0.00007558076,5.0767113e-7,0.00022103958,0.000012457461,0.000060724204,0.00014611222,0.7154567,0.26859733,0.0027781248,0.012233894,0.00013864113],"about_ca_topic_score_codex":6.1021467e-7,"about_ca_topic_score_gemma":1.6788219e-7,"teacher_disagreement_score":0.2566287,"about_ca_system_score_codex":0.00025855153,"about_ca_system_score_gemma":0.0007332294,"threshold_uncertainty_score":0.63199294},"labels":[],"label_agreement":null},{"id":"W4403833137","doi":"10.1186/s13321-024-00911-3","title":"Towards the prediction of drug solubility in binary solvent mixtures at various temperatures using machine learning","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"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; Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Leslie Dan Faculty of Pharmacy, University of Toronto; Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Canada First Research Excellence Fund; University of Toronto","keywords":"Solubility; Machine learning; Computer science; Solvent; Binary number; Gradient boosting; Hildebrand solubility parameter; Artificial intelligence; Biochemical engineering; Materials science; Chemistry; Mathematics; Organic chemistry; Random forest","score_opus":0.023630155489136693,"score_gpt":0.28875265640825043,"score_spread":0.2651225009191137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403833137","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":[0.91895056,0.0020806438,0.077195786,0.0005121582,0.00078131503,0.00010458295,0.000007833819,0.000024207802,0.00034289618],"genre_scores_gemma":[0.96200156,0.000073266594,0.037747677,0.000050127474,0.00008259818,8.234315e-7,0.0000025175814,0.000005858928,0.00003559805],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834585,0.000069716225,0.0008030002,0.00007656767,0.0005675156,0.00013733312],"domain_scores_gemma":[0.9988397,0.00044460892,0.00036049128,0.00016788811,0.00014275499,0.000044593886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018021282,0.00011199518,0.00021210601,0.00018872996,0.00007581795,0.00013130534,0.00046848296,0.00004139772,0.000006177066],"category_scores_gemma":[0.00024367469,0.000072577284,0.00014281143,0.0004088272,0.000050204162,0.00079771166,0.00029000078,0.0005078211,6.785696e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010144968,0.00021299926,0.0027964818,0.0013143321,0.00022350046,0.00009735425,0.052779887,0.8863504,0.03148442,0.002239624,0.0022235722,0.020175997],"study_design_scores_gemma":[0.00016989966,0.000054187924,0.0012524712,0.00026021275,0.000020296444,0.00034268823,0.00013256882,0.9589044,0.03593063,0.0022931183,0.0005752585,0.00006430125],"about_ca_topic_score_codex":0.000016420197,"about_ca_topic_score_gemma":0.0000022106863,"teacher_disagreement_score":0.072553985,"about_ca_system_score_codex":0.00023250781,"about_ca_system_score_gemma":0.00031177085,"threshold_uncertainty_score":0.2959616},"labels":[],"label_agreement":null},{"id":"W4407140906","doi":"10.1186/s13321-025-00962-0","title":"Improving drug repositioning with negative data labeling using large language models","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Drug repositioning; Drug; Data mining; Natural language processing; Data science; Medicine; Pharmacology","score_opus":0.024940952440858137,"score_gpt":0.32035736894867095,"score_spread":0.2954164165078128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407140906","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070782796,0.00014384287,0.9260804,0.0001290106,0.00013708723,0.000058781563,0.000006123865,0.000019173132,0.0026427868],"genre_scores_gemma":[0.25756475,0.0000029842042,0.74208856,0.00023061121,0.000045099572,3.6244387e-7,0.00000385222,0.0000047814387,0.000059022612],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986566,0.000026009275,0.00062176486,0.000105698855,0.00040907477,0.00018090695],"domain_scores_gemma":[0.99801797,0.0003905023,0.0007333148,0.0004699116,0.0003333088,0.000054967877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013258635,0.00011134621,0.00021313022,0.00017707716,0.00013137839,0.00028688964,0.0010174572,0.000028518018,0.0000013718302],"category_scores_gemma":[0.0002783719,0.00009025695,0.00004226475,0.00041044218,0.000021072992,0.0032649087,0.00061465765,0.00026422486,4.654704e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058158894,0.00012339956,0.00007680999,0.0004502568,0.00028229752,0.000091733025,0.027068133,0.91374063,0.0019986378,0.016468192,0.001185493,0.03845625],"study_design_scores_gemma":[0.0004661363,0.000013169521,0.0000076044544,0.0003647425,0.00003700094,0.00011957431,0.0014579848,0.9843794,0.010438008,0.0025838546,0.000034980658,0.000097508426],"about_ca_topic_score_codex":0.000010346192,"about_ca_topic_score_gemma":0.0000017367214,"teacher_disagreement_score":0.18678196,"about_ca_system_score_codex":0.00011132334,"about_ca_system_score_gemma":0.00048343075,"threshold_uncertainty_score":0.36805716},"labels":[],"label_agreement":null},{"id":"W4408693799","doi":"10.1186/s13321-025-00979-5","title":"An interpretable deep geometric learning model to predict the effects of mutations on protein–protein interactions using large-scale protein language model","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; Lawson Health Research Institute; University of Manitoba; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Scale (ratio); Artificial intelligence; Machine learning","score_opus":0.004592795866963382,"score_gpt":0.28068493732233607,"score_spread":0.2760921414553727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408693799","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":[0.60549605,0.000039239505,0.39256844,0.00003938149,0.000035818113,0.00042344816,0.0000067019923,0.000007678932,0.0013832196],"genre_scores_gemma":[0.9419887,0.000003115225,0.056825586,0.00015349315,0.000046167777,0.0000299861,0.000019540113,0.000017982098,0.0009154473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984952,0.000037157875,0.0008037224,0.00009088867,0.00032444438,0.00024857323],"domain_scores_gemma":[0.99847156,0.000049123515,0.0007020334,0.0003655113,0.00031102897,0.000100763384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056915253,0.00018958637,0.00027051094,0.00035235166,0.00015477298,0.000063195905,0.0004382721,0.000119126256,0.000005052233],"category_scores_gemma":[0.001374512,0.00014360122,0.00014572365,0.00040545387,0.000043165688,0.00006540283,0.00014405652,0.0005619621,0.0000020099285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099808734,0.0001256433,0.000060173265,0.0004717925,0.00008713307,6.2223603e-7,0.0040553617,0.5207611,0.4722017,0.00004938801,0.00010810461,0.0019791685],"study_design_scores_gemma":[0.00035639692,0.0003187895,0.000010738018,0.0004149175,0.000044780274,0.000009449468,0.0008511692,0.6234721,0.37425002,0.00005640056,0.0001238337,0.00009138699],"about_ca_topic_score_codex":0.000003918121,"about_ca_topic_score_gemma":0.0000035115477,"teacher_disagreement_score":0.3364926,"about_ca_system_score_codex":0.00006539605,"about_ca_system_score_gemma":0.00019228761,"threshold_uncertainty_score":0.58558875},"labels":[],"label_agreement":null},{"id":"W4411371888","doi":"10.1186/s13321-025-00958-w","title":"Crossover operators for molecular graphs with an application to virtual drug screening","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institutes of Health; German Network for Bioinformatics Infrastructure; Novo Nordisk Fonden; Universität Leipzig; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; Max Kade Foundation; Alexander von Humboldt-Stiftung","keywords":"Crossover; Computer science; Theoretical computer science; Context (archaeology); Algorithm; Artificial intelligence","score_opus":0.007400817636468401,"score_gpt":0.2996973154753661,"score_spread":0.2922964978388977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411371888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15331116,0.000013571256,0.8455198,0.0004077541,0.000083707935,0.00017257816,0.0000022579159,0.000013791078,0.00047541334],"genre_scores_gemma":[0.35224307,9.472129e-7,0.6465817,0.0010885568,0.000023005656,0.000010287813,0.0000022976908,0.000005357953,0.00004478247],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890155,0.000011923232,0.0004868393,0.00009010076,0.00036227205,0.00014732311],"domain_scores_gemma":[0.99868405,0.00018408486,0.0002789266,0.00024942565,0.000489633,0.000113895396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000673933,0.0001090382,0.00018203414,0.00022341483,0.00007981957,0.00024662455,0.0006994518,0.000029830751,6.5440594e-7],"category_scores_gemma":[0.000107775704,0.00008869436,0.00007527508,0.0005300308,0.000022176797,0.0012968149,0.00010251841,0.00011513201,9.3720763e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028856948,0.00013401572,0.00014631379,0.00012202533,0.0001643064,0.000005126884,0.005099574,0.55949277,0.0029402985,0.20924278,0.0033227275,0.2190415],"study_design_scores_gemma":[0.0017619499,0.00044847553,0.00040725767,0.0001954504,0.000049096627,0.000060499235,0.00065554754,0.83746403,0.133735,0.01652527,0.008372128,0.00032529616],"about_ca_topic_score_codex":0.0000010119079,"about_ca_topic_score_gemma":6.0241507e-7,"teacher_disagreement_score":0.27797127,"about_ca_system_score_codex":0.000048895003,"about_ca_system_score_gemma":0.00022820773,"threshold_uncertainty_score":0.3616851},"labels":[],"label_agreement":null},{"id":"W4412435986","doi":"10.1186/s13321-025-01038-9","title":"SuperMetal: a generative AI framework for rapid and precise metal ion location prediction in proteins","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Vanderbilt University","keywords":"Metal ions in aqueous solution; Generative grammar; Computer science; Ion; Generative model; Metal; Zinc; Chemistry; Artificial intelligence","score_opus":0.009415692670339681,"score_gpt":0.2635056148016386,"score_spread":0.2540899221312989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412435986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48462713,0.0012764317,0.51200527,0.0005187313,0.00027855398,0.00071192195,0.0000148978925,0.0000043196706,0.0005627504],"genre_scores_gemma":[0.9343913,0.00040835125,0.06428118,0.0003127468,0.00022301145,0.00006807685,0.00002278387,0.000010154544,0.00028235035],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992468,0.000014737757,0.0004583726,0.00006774037,0.00010725576,0.0001051004],"domain_scores_gemma":[0.99939317,0.00003221034,0.0002201539,0.000106966036,0.0002104468,0.000037037727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004140669,0.00009633007,0.00017090327,0.000095481846,0.000038661732,0.000030017502,0.000088845474,0.0001649805,0.000005761035],"category_scores_gemma":[0.00048455768,0.000080693244,0.00006574273,0.0000983604,0.000025958974,0.000028691851,0.000027363676,0.000105798026,3.2191076e-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":[0.00040483027,0.00009238475,0.00015092379,0.00033445033,0.00014676072,6.2245357e-7,0.0007016133,0.00014822661,0.9538426,0.0013079228,0.0013064364,0.04156324],"study_design_scores_gemma":[0.00057746115,0.00033477132,0.00008667547,0.0001907791,0.000044377655,0.000017873728,0.00023374926,0.00083138293,0.9882433,0.004581426,0.0047854166,0.000072787814],"about_ca_topic_score_codex":4.3241153e-7,"about_ca_topic_score_gemma":9.486013e-7,"teacher_disagreement_score":0.44976422,"about_ca_system_score_codex":0.000021183565,"about_ca_system_score_gemma":0.0001138308,"threshold_uncertainty_score":0.32905748},"labels":[],"label_agreement":null},{"id":"W4413807406","doi":"10.1186/s13321-025-01073-6","title":"FusionCLM: enhanced molecular property prediction via knowledge fusion of chemical language models","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; Western University; Lawson Health Research Institute; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Property (philosophy); Artificial intelligence; Ensemble learning; Inference; Machine learning; Representation (politics); Feature (linguistics); Feature learning; Deep learning; Data mining","score_opus":0.009688278155474715,"score_gpt":0.28108803723704645,"score_spread":0.2713997590815717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413807406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16505103,0.00018427243,0.8198065,0.0001354183,0.00024878155,0.00009171663,0.000001903629,0.000017516571,0.014462823],"genre_scores_gemma":[0.8475435,0.000019932673,0.15216158,0.000100148995,0.000039654726,0.0000021972783,0.000002727241,0.000004718666,0.00012557168],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984515,0.00002654486,0.0008713493,0.000082447565,0.0004331051,0.00013508416],"domain_scores_gemma":[0.9984957,0.00015605654,0.0005071478,0.0002621867,0.00050850224,0.00007042393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062003284,0.000118930635,0.00027588243,0.00020693615,0.000026847554,0.000037938247,0.00064038695,0.0000796187,0.000004971604],"category_scores_gemma":[0.0001809544,0.00008283663,0.00014504786,0.00046743252,0.00003829422,0.0008877436,0.00032020232,0.00021289714,0.0000019916163],"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":[0.000059569233,0.00026877061,0.0000044152366,0.00045652603,0.00008462689,0.000006249261,0.00931282,0.024707874,0.72355294,0.0056461487,0.0015798432,0.23432018],"study_design_scores_gemma":[0.00031619708,0.000032752316,0.000008271265,0.00016523967,0.00001509261,0.000023250259,0.000072592295,0.45850542,0.5348874,0.0058252444,0.00009654317,0.000052016567],"about_ca_topic_score_codex":0.0000010499265,"about_ca_topic_score_gemma":7.460952e-8,"teacher_disagreement_score":0.68249243,"about_ca_system_score_codex":0.000099324825,"about_ca_system_score_gemma":0.00037793105,"threshold_uncertainty_score":0.337798},"labels":[],"label_agreement":null},{"id":"W4414507809","doi":"10.1186/s13321-025-01084-3","title":"Cache: Utilizing ultra-large library screening in Rosetta to identify novel binders of the WD-repeat domain of Leucine-Rich Repeat Kinase 2","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"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":"National Institutes of Health; Alexander von Humboldt-Stiftung; Enamine; Max Kade Foundation; University of Toronto; Bundesministerium für Bildung und Forschung; German Network for Bioinformatics Infrastructure; Deutscher Akademischer Austauschdienst; Structural Genomics Consortium; Vanderbilt University; Deutsche Forschungsgemeinschaft; Universität Leipzig; Michael J. Fox Foundation for Parkinson's Research","keywords":"Enamine; Virtual screening; Benchmark (surveying); Drug discovery; Domain (mathematical analysis); Docking (animal); Chemical space","score_opus":0.019745294908351658,"score_gpt":0.3157505918754207,"score_spread":0.29600529696706906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414507809","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":[0.58841866,0.00012814031,0.40591398,0.0011426762,0.0003186874,0.0001605016,0.000012130874,0.000011009838,0.003894232],"genre_scores_gemma":[0.812109,0.0000112961325,0.18725532,0.00050167734,0.000027252743,0.0000014880151,0.0000018537007,0.0000084157555,0.0000836903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99725854,0.00005385501,0.0015811747,0.000121883735,0.0007269148,0.0002576076],"domain_scores_gemma":[0.99750817,0.00065869425,0.0010306325,0.0005105155,0.00020538103,0.00008658496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017192567,0.00016801772,0.00042673523,0.00052427704,0.000060207934,0.00010216334,0.0014771932,0.00007792552,0.0000047318235],"category_scores_gemma":[0.0006968392,0.00013066825,0.00021486051,0.0016464092,0.00005280347,0.0016624273,0.00054233556,0.0003800694,5.5529625e-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":[0.000641059,0.0018692325,0.06489809,0.004404094,0.0009895994,0.00008233999,0.07946678,0.44580615,0.23413485,0.05992981,0.027945448,0.07983257],"study_design_scores_gemma":[0.0036373609,0.00013447246,0.06345556,0.0032835088,0.00007903428,0.00017249811,0.0059839473,0.08704156,0.8274775,0.006575278,0.0017018843,0.00045737103],"about_ca_topic_score_codex":0.000005178974,"about_ca_topic_score_gemma":0.0000017978635,"teacher_disagreement_score":0.59334266,"about_ca_system_score_codex":0.00006843111,"about_ca_system_score_gemma":0.0004193686,"threshold_uncertainty_score":0.53284967},"labels":[],"label_agreement":null},{"id":"W4415517900","doi":"10.1186/s13321-025-01104-2","title":"VNFlow: integration of variational autoencoders and normalizing flows for novel molecular design","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"National Research Council Canada; Defence Research and Development Canada","keywords":"Generative grammar; Key (lock); Inverse; Range (aeronautics); Sampling (signal processing); Generative model; Inverse problem; Chemical space","score_opus":0.0154423853595157,"score_gpt":0.28014446830229384,"score_spread":0.26470208294277814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415517900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12563102,0.00003284385,0.87323004,0.00018702036,0.0003225364,0.00012070569,0.0000068242352,0.000007024952,0.00046198594],"genre_scores_gemma":[0.23872435,0.0000071752575,0.761066,0.00013284135,0.00002878172,0.0000035376813,0.000001719955,0.0000041995672,0.00003138454],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987095,0.000015198717,0.00078460184,0.0000589667,0.00030037563,0.00013135774],"domain_scores_gemma":[0.9984316,0.00030358913,0.0007477268,0.00010026906,0.00037557984,0.000041226605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018948644,0.00009405724,0.00023317774,0.00014231773,0.00006425909,0.00009000773,0.0002519023,0.00005584731,0.000028873465],"category_scores_gemma":[0.0012827554,0.000075907075,0.00005188013,0.00012793201,0.000059617978,0.00052419695,0.000047813443,0.00008512984,8.918957e-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":[0.0000523574,0.000020486597,0.000015415155,0.00017658916,0.0000096391095,2.9347967e-7,0.0008842716,0.05089595,0.9441741,0.0028566585,0.00032072788,0.0005935193],"study_design_scores_gemma":[0.00045190807,0.00007391313,0.00009418636,0.00015675499,0.000032791988,0.000023154736,0.00015082218,0.41547835,0.58166933,0.0015796204,0.00022584212,0.00006332162],"about_ca_topic_score_codex":0.0000030338365,"about_ca_topic_score_gemma":2.9551805e-7,"teacher_disagreement_score":0.3645824,"about_ca_system_score_codex":0.00004144602,"about_ca_system_score_gemma":0.00019909022,"threshold_uncertainty_score":0.30954006},"labels":[],"label_agreement":null}]}