{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":49,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":49,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"6edd568916c6","filters":{"venue":"Algorithms for Molecular Biology"}},"results":[{"id":"W4221035067","doi":"10.1186/s13015-022-00210-2","title":"Fast characterization of segmental duplication structure in multiple genome assemblies","year":2022,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC; Canada Foundation for Innovation","keywords":"Computer science; Gene duplication; Characterization (materials science); Genome; Segmental duplication; Computational biology; Data mining; Biology; Genetics; Gene; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.01047950850782903,"gpt":0.2527592989903266,"spread":0.2422797904824976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001730855,0.0001720835,0.0002103252,0.0001609866,0.00009335332,0.000007204369,0.0002746226,0.0001224689,0.00003842956],"category_scores_gemma":[0.00002867071,0.0001940239,0.0001014133,0.000202713,0.00006522267,0.00000456022,0.0002403969,0.00009400321,9.384395e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004909367,"about_ca_system_score_gemma":0.00004880096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001799145,"about_ca_topic_score_gemma":0.00001051754,"domain_scores_codex":[0.9987458,0.0001066981,0.0003147265,0.000444435,0.0001068326,0.000281538],"domain_scores_gemma":[0.9993873,0.00001005059,0.0001840228,0.0003075258,0.00007269258,0.00003839693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006335419,0.00008536788,0.002767141,0.00001634522,0.00005803211,0.000001211942,0.0000719422,0.0003361809,0.991901,0.0001235013,0.000004889654,0.004570992],"study_design_scores_gemma":[0.002329721,0.001265251,0.01967472,0.000003422845,0.00003211703,0.0000292395,0.0002378197,0.002367385,0.9607378,0.0004592745,0.01243197,0.0004312566],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9365355,0.0002690058,0.06121333,0.00008273902,0.0001732548,0.0007546977,0.0009399884,0.00001031526,0.00002113565],"genre_scores_gemma":[0.9838135,0.00003691716,0.005752482,0.0001235659,0.00007697014,0.0003158589,0.009774067,0.0000359756,0.00007062108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05546085,"threshold_uncertainty_score":0.7912066,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040607633","doi":"10.1186/1748-7188-7-3","title":"MRL and SuperFine+MRL: new supertree methods","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; John Simon Guggenheim Memorial Foundation; National Science Foundation","keywords":"Supertree; Heuristics; Matrix representation; Heuristic; Matrix (chemical analysis); Tree (set theory); Representation (politics); Set (abstract data type); Computer science; Algorithm; Range (aeronautics); Mathematical optimization; Mathematics; Combinatorics; Artificial intelligence; Biology; Phylogenetic tree; Engineering; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.0268640034925042,"gpt":0.3475609793836081,"spread":0.3206969758911039,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003445069,0.000260147,0.0002778791,0.00005116993,0.0001069069,0.00001376409,0.0001801167,0.0002632808,0.00001036671],"category_scores_gemma":[0.0001397296,0.0002360578,0.0001438543,0.00006518839,0.0001421183,0.000001451512,0.0002382699,0.00007029508,0.000004362106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000804253,"about_ca_system_score_gemma":0.00005043324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008331992,"about_ca_topic_score_gemma":0.000013084,"domain_scores_codex":[0.9986135,0.0001051664,0.0002271987,0.0004375927,0.00004305525,0.0005734381],"domain_scores_gemma":[0.9992668,0.00004670738,0.00005130483,0.0003474005,0.00007039509,0.0002174029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003229097,0.00003473717,0.004292271,0.000009120632,0.0001941667,5.101294e-7,0.00007283632,0.00000222464,0.9327458,0.002161974,0.000812172,0.05964188],"study_design_scores_gemma":[0.001210078,0.0008103879,0.003567473,0.000003700531,0.0001064685,0.00006718698,0.00008392418,0.00008664872,0.5520718,0.003285737,0.4381875,0.0005192035],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6399492,0.0385433,0.318972,0.0006287415,0.0007439296,0.0005233895,0.00008461824,0.00001356277,0.0005412618],"genre_scores_gemma":[0.6546414,0.001048656,0.3411959,0.001155085,0.001032835,0.0001037481,0.0002135238,0.00007296303,0.0005357802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4373753,"threshold_uncertainty_score":0.9626158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163879391","doi":"10.1186/s13015-015-0033-9","title":"Algorithmic approaches to protein-protein interaction site prediction","year":2015,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Identification (biology); Field (mathematics); Data science; Machine learning; Artificial intelligence; Data mining; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1352234967624475,"gpt":0.3403664008324722,"spread":0.2051429040700247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008336738,0.0002314428,0.0002403203,0.0002661749,0.00008549252,0.0001010829,0.0005910617,0.0001426998,0.000001945199],"category_scores_gemma":[0.0002741907,0.0002293702,0.0001269708,0.0004664106,0.00004703365,0.0003431788,0.0003521765,0.0001560224,0.00006229861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001627117,"about_ca_system_score_gemma":0.0001626675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005422751,"about_ca_topic_score_gemma":0.000003408139,"domain_scores_codex":[0.9979555,0.0003175338,0.0003497614,0.000760371,0.0002205562,0.0003962856],"domain_scores_gemma":[0.9988726,0.00007669965,0.0001259065,0.0004994525,0.0001960134,0.0002293582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001617014,0.0003190328,0.00004978608,0.00004979089,0.0001922368,0.00002788401,0.001160225,0.03652534,0.1475342,0.3075141,0.0004704028,0.5059953],"study_design_scores_gemma":[0.0009173757,0.001135699,0.00007517886,0.00002927258,0.00001416623,0.00005393131,0.00004703998,0.7866747,0.08798602,0.1096659,0.01300752,0.0003932281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05694231,0.00008927801,0.9385893,0.001707313,0.0006813085,0.001529247,0.00004616953,0.0001958803,0.000219194],"genre_scores_gemma":[0.1598713,3.882444e-7,0.8384521,0.000288822,0.0002283591,0.0008861756,0.0001302319,0.00002622088,0.0001163624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7501493,"threshold_uncertainty_score":0.9353445,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132081807","doi":"10.1186/1748-7188-5-5","title":"Fast prediction of RNA-RNA interaction","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Mitacs; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC","keywords":"Computer science; RNA; Heuristic; Set (abstract data type); Computational biology; Translation (biology); Class (philosophy); Variety (cybernetics); Nucleic acid structure; Non-coding RNA; Theoretical computer science; Algorithm; Machine learning; Data mining; Artificial intelligence; Messenger RNA; Gene; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01154169645432993,"gpt":0.2749254580283451,"spread":0.2633837615740152,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000231223,0.0001579239,0.0001784169,0.0000683644,0.00005607868,0.000008233464,0.0001987317,0.0003516519,0.000031436],"category_scores_gemma":[0.0001443074,0.0001496726,0.0001722944,0.00005927918,0.00009344125,0.000004255056,0.00006347122,0.0001093608,0.000005233351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005166743,"about_ca_system_score_gemma":0.00003834439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002041358,"about_ca_topic_score_gemma":0.000008954949,"domain_scores_codex":[0.9990284,0.00005584165,0.0002644692,0.0003575619,0.00006344308,0.0002303125],"domain_scores_gemma":[0.9992693,0.00001959142,0.0001515163,0.00035834,0.0001390222,0.00006221528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007067707,0.00004289253,0.00005708891,0.00001074421,0.00007108461,6.869662e-7,0.00001186018,0.000005105148,0.9385285,0.00169603,0.0001501022,0.05935526],"study_design_scores_gemma":[0.0004290994,0.000723845,0.00006571922,0.000005846714,0.00002773996,0.00002003711,0.00002537306,0.0002090456,0.9693635,0.001670762,0.02733072,0.0001283634],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5908912,0.0001814232,0.4058388,0.0001232334,0.00138648,0.0004531953,0.0001745713,0.00002167827,0.0009294463],"genre_scores_gemma":[0.9731326,0.00004185165,0.02561191,0.000121667,0.0003515664,0.0001258962,0.0004023605,0.00003219284,0.0001799884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3822414,"threshold_uncertainty_score":0.6103472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2339182468","doi":"10.1186/s13015-016-0067-7","title":"The link between orthology relations and gene trees: a correction perspective","year":2016,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Tree (set theory); Converse; Set (abstract data type); Phylogenetic tree; Relation (database); Tree rearrangement; Gene; Perspective (graphical); Computer science; Similarity (geometry); Computational biology; Combinatorics; Biology; Mathematics; Genetics; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01188667940743771,"gpt":0.2770982739300388,"spread":0.2652115945226011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000193803,0.0001572084,0.0001576866,0.00003533011,0.0003001869,0.0000112419,0.0001319143,0.0002038248,0.000001576303],"category_scores_gemma":[0.0002569393,0.00009764516,0.0001019944,0.00005197087,0.0003375949,7.775434e-7,0.0001207684,0.00005245518,0.000003804034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002043945,"about_ca_system_score_gemma":0.00004653446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002945116,"about_ca_topic_score_gemma":0.00006797307,"domain_scores_codex":[0.9989785,0.00008745654,0.0001870759,0.0004231437,0.0000339206,0.0002898816],"domain_scores_gemma":[0.9992728,0.0001468651,0.0000855245,0.0002688121,0.0001699162,0.00005605579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005651333,0.000007255035,0.006651106,0.000001070299,0.0003170809,0.000001005996,0.00006614008,0.000003834244,0.8519154,0.004453929,0.0002708206,0.1362558],"study_design_scores_gemma":[0.003772933,0.004291968,0.0544844,0.00001528613,0.0003182814,0.0001396923,0.0006197501,0.0001430133,0.3885236,0.05993802,0.4867691,0.0009839986],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6699132,0.008868223,0.309255,0.009526385,0.000949376,0.0007436992,0.0002140288,0.00001599047,0.0005141594],"genre_scores_gemma":[0.9931123,0.001054638,0.003904526,0.0001279494,0.0007407738,0.0001498159,0.00005065512,0.0000279813,0.000831367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4864982,"threshold_uncertainty_score":0.3981854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965359119","doi":"10.1186/1748-7188-6-23","title":"ReCoil - an algorithm for compression of extremely large datasets of dna data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data compression; Redundancy (engineering); Algorithm; Encoding (memory); Compression (physics); Volume (thermodynamics); Data compression ratio; Lossless compression; Compression ratio; Sequence (biology); Data mining; Image compression; Artificial intelligence; Biology; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1004202575440594,"gpt":0.3489168214591663,"spread":0.2484965639151069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008489378,0.0002762186,0.0005499246,0.0001728805,0.00012429,0.00001830853,0.003465033,0.0002331923,0.00001888603],"category_scores_gemma":[0.00009244171,0.000237738,0.0001314069,0.0002248623,0.0001452841,0.0006397581,0.00168765,0.0001051811,0.000002009502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001440164,"about_ca_system_score_gemma":0.0001192105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001805842,"about_ca_topic_score_gemma":0.00001047737,"domain_scores_codex":[0.9974455,0.0001526333,0.0006684985,0.001025347,0.0001835088,0.000524572],"domain_scores_gemma":[0.9960935,0.0001504393,0.0004744501,0.002865464,0.0002608661,0.0001553289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009039929,0.0007622934,0.00004454578,0.00008333278,0.0001451099,0.00001027696,0.0002190688,0.000002733669,0.06492332,0.02133523,0.002436023,0.9099477],"study_design_scores_gemma":[0.002650669,0.001888139,0.0001673259,0.00007153607,0.00007714093,0.00002476486,0.00004702355,0.7614823,0.1765105,0.01856839,0.03800045,0.0005117165],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001108476,0.0005476378,0.9819627,0.00002515713,0.0005691184,0.0006680499,0.01501331,0.00006090597,0.00004457804],"genre_scores_gemma":[0.008668174,0.00004512839,0.979298,0.0001145298,0.00008027116,0.00007087379,0.01168196,0.00003096976,0.00001008033],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9094359,"threshold_uncertainty_score":0.9694675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965510019","doi":"10.1186/s13015-019-0152-9","title":"A multi-labeled tree dissimilarity measure for comparing “clonal trees” of tumor progression","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"clone (Java method); Tree (set theory); Measure (data warehouse); Vertex (graph theory); Mutation; Biology; Computational biology; Computer science; Granularity; Combinatorics; Mathematics; Genetics; Gene; Data mining; Graph","retraction":null,"screen_n_in":null,"score":{"opus":0.0228347557084764,"gpt":0.3166128142024556,"spread":0.2937780584939791,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002508287,0.0002403013,0.0004152311,0.00005838824,0.00006400196,0.00001240874,0.0002857313,0.0002316069,0.000005470931],"category_scores_gemma":[0.000210915,0.0002248683,0.0002888227,0.00007074382,0.0001071183,0.000002844414,0.0001409333,0.00008010007,0.000001740407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002225353,"about_ca_system_score_gemma":0.0001402481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002100494,"about_ca_topic_score_gemma":0.00009705697,"domain_scores_codex":[0.9985617,0.00004447517,0.0003532314,0.0005555947,0.00008490556,0.0004001312],"domain_scores_gemma":[0.9989765,0.00005960778,0.0002079306,0.0004095286,0.0002493257,0.00009714006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004844916,0.000216089,0.008138595,0.00006593859,0.0001594942,0.000001352986,0.00001571702,0.00007302127,0.9801797,0.0007099971,0.0002042038,0.009751369],"study_design_scores_gemma":[0.007915832,0.003011509,0.003034006,0.00005735792,0.0001306658,0.00001756978,0.00003840306,0.01649437,0.9476663,0.0007595402,0.02030241,0.0005720329],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7857751,0.001887518,0.2094746,0.0001321795,0.0004622632,0.001665473,0.0004913226,0.00001582032,0.00009574482],"genre_scores_gemma":[0.9197102,0.00002876974,0.07851701,0.0001925606,0.0001466395,0.0002734723,0.001017601,0.00004839895,0.00006538661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.133935,"threshold_uncertainty_score":0.9169863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117719890","doi":"10.1186/s13015-015-0054-4","title":"Inferring interaction type in gene regulatory networks using co-expression data","year":2015,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Toronto","funders":"Canadian Institutes of Health Research; National Center for Research Resources; Institute for Research in Fundamental Sciences; National Institute of General Medical Sciences; Directorate for Biological Sciences; National Institutes of Health","keywords":"Gene regulatory network; Computer science; Benchmark (surveying); Computational biology; Systems biology; In silico; Data type; Genomics; Data mining; Biological network; Gene; Genome; Biology; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.06669697343404381,"gpt":0.356877915823286,"spread":0.2901809423892422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005017637,0.0001842628,0.0002026676,0.00007708932,0.00005026456,0.00002162144,0.0003775065,0.0003568127,0.000002702482],"category_scores_gemma":[0.00007966856,0.0001820054,0.00005182685,0.0001006756,0.0000675335,0.00001286685,0.000364931,0.0001441341,0.00000279833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003934882,"about_ca_system_score_gemma":0.0001010474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003285619,"about_ca_topic_score_gemma":0.00001399745,"domain_scores_codex":[0.9987515,0.00007129809,0.0003404755,0.0004209609,0.00006294245,0.0003527988],"domain_scores_gemma":[0.9989256,0.00001348053,0.0001410532,0.0007110065,0.00009919537,0.0001096129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003359549,0.00007726881,0.001161093,0.00001505593,0.00009837392,0.000008341454,0.00006111813,0.02579806,0.947659,0.0002995676,0.001805216,0.02268093],"study_design_scores_gemma":[0.002863561,0.0008388812,0.0001998439,0.0000642977,0.00005413069,0.0001171794,0.0001750163,0.7244883,0.2379341,0.002079969,0.03038517,0.0007995746],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3438032,0.001490983,0.6533366,0.00002821494,0.000782112,0.0003315455,0.00004167911,0.00001401097,0.0001716591],"genre_scores_gemma":[0.9550809,0.0000695769,0.04080808,0.0003235739,0.0004591322,0.00001547505,0.003179896,0.00003845209,0.00002494814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.709725,"threshold_uncertainty_score":0.7421964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104168759","doi":"10.1186/1748-7188-7-6","title":"Computing evolutionary distinctiveness indices in large scale analysis","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Natural Sciences and Engineering Research Council of Canada; Isaac Newton Institute for Mathematical Sciences","keywords":"Optimal distinctiveness theory; Phylogenetic tree; Taxon; Extinction (optical mineralogy); Endangered species; Supertree; Clade; Evolutionary biology; Sister group; Tree (set theory); Set (abstract data type); Biology; Computer science; Ecology; Combinatorics; Mathematics; Paleontology","retraction":null,"screen_n_in":null,"score":{"opus":0.015726275067789,"gpt":0.2905335002008223,"spread":0.2748072251330333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004328091,0.000123281,0.0002735457,0.0002258909,0.0001839692,0.000005404188,0.0001302234,0.0001241929,0.0001239815],"category_scores_gemma":[0.00005058705,0.0001075945,0.0001258807,0.0005024901,0.0001347742,0.00006912506,0.0000210009,0.00009404567,0.00002654702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007535162,"about_ca_system_score_gemma":0.00001671918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005750736,"about_ca_topic_score_gemma":0.009589319,"domain_scores_codex":[0.9987953,0.0001669657,0.0002062589,0.000243947,0.00006160622,0.0005259031],"domain_scores_gemma":[0.9994937,0.0002017409,0.00007983156,0.0001094732,0.00003749051,0.00007774103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001563684,0.0000360024,0.9948972,0.00000538609,0.0001739357,0.000001751334,0.0002156788,0.0002912899,0.00001813676,0.0004194952,0.00001415097,0.003911364],"study_design_scores_gemma":[0.0003215618,0.00005774839,0.9738978,0.000002552719,0.00009897241,0.00000510263,0.0002819606,0.02284422,0.00002239304,0.0005244404,0.001803599,0.0001396929],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8093021,0.007754997,0.1799558,0.0001576959,0.0004814972,0.0002184252,0.0003015565,0.00003740316,0.001790474],"genre_scores_gemma":[0.9898056,0.00001840563,0.009264231,0.000189287,0.00009202179,0.000004953719,0.0006042449,0.000002279861,0.0000189852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1805035,"threshold_uncertainty_score":0.5351065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133004689","doi":"10.1186/1748-7188-3-16","title":"HuMiTar: A sequence-based method for prediction of human microRNA targets","year":2008,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Computational biology; False positive paradox; Untranslated region; microRNA; Biology; Computer science; Base pair; Sequence (biology); Gene; Pairing; Function (biology); Messenger RNA; Genetics; Data mining; Bioinformatics; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03353231989561144,"gpt":0.3287654067019258,"spread":0.2952330868063144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002616533,0.0002193065,0.0002785242,0.0001010727,0.0001503754,0.000004019889,0.0002174142,0.0003344965,0.000009609535],"category_scores_gemma":[0.0001233677,0.0002275714,0.0003384339,0.00008996386,0.0001989302,0.000003598925,0.00004583877,0.00005187481,9.444321e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002989553,"about_ca_system_score_gemma":0.0001512213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002375891,"about_ca_topic_score_gemma":0.000003878298,"domain_scores_codex":[0.9985782,0.00008794398,0.0003908066,0.0005328713,0.00007435369,0.0003358404],"domain_scores_gemma":[0.9989532,0.00003362194,0.0002186336,0.0003998379,0.0003113185,0.00008342361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001227785,0.00009068467,0.0003003798,0.00005516347,0.0001400307,0.00000183774,0.00001455491,0.0001300423,0.9960843,0.0005568909,0.0006088109,0.001894551],"study_design_scores_gemma":[0.001765847,0.001223038,0.0004724823,0.00001025947,0.00007382063,0.0000252115,0.00000644611,0.002775021,0.9793164,0.001511893,0.01261146,0.0002081188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.19476,0.0008884014,0.8019062,0.00008610407,0.0001519819,0.0009032522,0.001245726,0.0000227836,0.0000355594],"genre_scores_gemma":[0.6185726,0.00002308674,0.3729035,0.0002857799,0.0002598914,0.0004683997,0.007335914,0.00006715777,0.00008364963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4290026,"threshold_uncertainty_score":0.9280093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2940808208","doi":"10.1186/s13015-019-0139-6","title":"Reconciling multiple genes trees via segmental duplications and losses","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Gene duplication; Segmental duplication; Tree (set theory); Genome; Gene; Set (abstract data type); Time complexity; Computer science; Computational biology; Biology; Gene family; Algorithm; Mathematics; Genetics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01218585346680486,"gpt":0.2636286312657858,"spread":0.251442777798981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009467026,0.0001713225,0.0001826219,0.00003614863,0.00009565891,0.00001380505,0.0001332141,0.0001459801,0.000005898137],"category_scores_gemma":[0.00003271383,0.0001649528,0.00009746581,0.00004016004,0.0001026656,9.285502e-7,0.000138073,0.00003846356,0.000007235656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008062449,"about_ca_system_score_gemma":0.00002668097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003177261,"about_ca_topic_score_gemma":0.00004149898,"domain_scores_codex":[0.999031,0.00002837544,0.0001808065,0.0004677966,0.0000333101,0.0002587025],"domain_scores_gemma":[0.9994857,0.00003533521,0.00006690693,0.0002794072,0.00007523777,0.00005745687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002397339,0.00002385712,0.02007599,0.000009504917,0.0001266372,3.866364e-7,0.00001854979,0.00004003602,0.9598296,0.0001484406,0.00003441048,0.01966866],"study_design_scores_gemma":[0.001651266,0.001069625,0.008309515,0.000006572647,0.00006103853,0.0000505643,0.0001370536,0.002003531,0.9283919,0.001381405,0.05642706,0.0005105014],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590185,0.006628571,0.03322255,0.0001626261,0.0002203754,0.0005117115,0.0001160477,0.000006704778,0.0001129271],"genre_scores_gemma":[0.9807357,0.0005625137,0.01773791,0.0003033185,0.0001224784,0.0001241062,0.0002449737,0.00002723183,0.0001417271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05639265,"threshold_uncertainty_score":0.6726581,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978336838","doi":"10.1186/1748-7188-5-39","title":"Sparsification of RNA structure prediction including pseudoknots","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Natural Sciences and Engineering Research Council of Canada; Mitacs; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC","keywords":"Computer science; Computational biology; Data mining; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.016752117223053,"gpt":0.2882554310040272,"spread":0.2715033137809743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002179782,0.0001575241,0.0001749309,0.00006725476,0.00007698134,0.000007644629,0.000231647,0.0004149035,0.00002190993],"category_scores_gemma":[0.0001802459,0.0001496562,0.000121841,0.00007483206,0.00009701445,0.000003553653,0.0000698136,0.00009939892,0.000001552773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005230878,"about_ca_system_score_gemma":0.00004546689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001157031,"about_ca_topic_score_gemma":0.000007039726,"domain_scores_codex":[0.9990065,0.00005318088,0.0002596681,0.0003811815,0.00007159224,0.0002278751],"domain_scores_gemma":[0.9992121,0.00001805162,0.0001653154,0.0003986988,0.0001477358,0.00005807722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000479708,0.00002258879,0.0002138475,0.00001333873,0.00005560141,3.642062e-7,0.00001308934,0.000009245886,0.9741208,0.003998023,0.00006621773,0.02143892],"study_design_scores_gemma":[0.0003866953,0.0003866856,0.0002602582,0.000004955701,0.00002875968,0.00001315653,0.00001031154,0.0002171986,0.9842066,0.007116677,0.00722521,0.0001435427],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7403701,0.0001691589,0.2579493,0.0001158598,0.0006175078,0.0004022252,0.0002191227,0.00001529465,0.000141442],"genre_scores_gemma":[0.9534518,0.00002734751,0.04547888,0.0001019005,0.0002738464,0.00006268242,0.0005306788,0.00002771031,0.00004519425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2130817,"threshold_uncertainty_score":0.6102805,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089039157","doi":"10.1186/1748-7188-3-1","title":"Reconstructing phylogenies from noisy quartets in polynomial time with a high success probability","year":2008,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Polynomial; Time complexity; Data science; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01217716393102334,"gpt":0.2379344202067291,"spread":0.2257572562757058,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001458748,0.0002902208,0.000391237,0.0000644851,0.0001413493,0.0000107208,0.0002574449,0.0002511265,0.00001069382],"category_scores_gemma":[0.00007046047,0.0002599495,0.0001234604,0.0001060832,0.0003719472,0.000001629306,0.0001243467,0.0001016076,0.000004097279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002418448,"about_ca_system_score_gemma":0.0001241182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006061523,"about_ca_topic_score_gemma":0.000181378,"domain_scores_codex":[0.9982908,0.00009508621,0.0003383698,0.000745772,0.00006590513,0.0004640621],"domain_scores_gemma":[0.9992326,0.00005157408,0.0001318176,0.0003966406,0.0001130632,0.00007430623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003130751,0.00008665432,0.04826076,0.000008123066,0.0002336314,0.00001620914,0.0001259277,0.00009720634,0.9460037,0.00006727538,0.00005542419,0.004731956],"study_design_scores_gemma":[0.006386666,0.003579182,0.0461165,0.00002932084,0.0001131106,0.0002466015,0.0001515099,0.0005740562,0.928125,0.006136171,0.007030459,0.001511398],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946092,0.00100016,0.003091512,0.0001236724,0.0001857602,0.0005690616,0.0002637292,0.000009273826,0.0001476599],"genre_scores_gemma":[0.9695195,0.00006370644,0.02949827,0.0001425944,0.0002331915,0.0001614122,0.0003112789,0.00003551062,0.0000345334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02640676,"threshold_uncertainty_score":0.9999853,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2592818772","doi":"10.1186/s13015-017-0096-x","title":"Approximating the correction of weighted and unweighted orthology and paralogy relations","year":2017,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; University of Ottawa","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Maximization; Mathematics; Conjecture; Converse; Approximation algorithm; Graph; Tree (set theory); Satisfiability; Discrete mathematics; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.01396313623744828,"gpt":0.2910071363754212,"spread":0.2770440001379729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003306063,0.0001664943,0.0002301178,0.00005679877,0.0004087645,0.00002462809,0.0002210844,0.0002468972,0.000004535048],"category_scores_gemma":[0.0002057153,0.0001307682,0.0000708978,0.00003925788,0.0005889432,0.000005884754,0.0002193204,0.00009648102,0.000001021756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005703349,"about_ca_system_score_gemma":0.00002994715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005329914,"about_ca_topic_score_gemma":0.00002991662,"domain_scores_codex":[0.9989201,0.0001024845,0.0002753554,0.0003987351,0.00004743746,0.0002558975],"domain_scores_gemma":[0.9989766,0.00005249811,0.0003007819,0.0004994413,0.0001205137,0.00005010096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000110038,0.00006924754,0.02644522,0.00004095523,0.0004266329,0.000004025788,0.000176753,0.0000150249,0.8667229,0.006317934,0.0002316578,0.09943962],"study_design_scores_gemma":[0.0128297,0.007296402,0.164276,0.00009522825,0.001074231,0.0008905199,0.0009537284,0.07104128,0.6142832,0.05010775,0.07474507,0.002406894],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8588789,0.001612703,0.13719,0.0006928088,0.0004239015,0.0006602527,0.00004077041,0.00001303736,0.0004876585],"genre_scores_gemma":[0.977585,0.0002202597,0.02143932,0.00009691463,0.0001050309,0.0001125169,0.000198093,0.00002650038,0.0002163595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2524397,"threshold_uncertainty_score":0.533257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2339509753","doi":"10.1186/s13015-016-0071-y","title":"Sparse RNA folding revisited: space-efficient minimum free energy structure prediction","year":2016,"lang":"en","type":"review","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology","funders":"German Network for Bioinformatics Infrastructure; Universität Leipzig; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft","keywords":"Algorithm; Computer science; Energy minimization; Folding (DSP implementation); TRACE (psycholinguistics); RNA; Bounded function; Computational complexity theory; Mathematics; Theoretical computer science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01856193032896756,"gpt":0.2906377888471313,"spread":0.2720758585181637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003810385,0.000913048,0.00148368,0.0002659185,0.0001798212,0.0000435085,0.0009979416,0.001885227,0.0000610921],"category_scores_gemma":[0.000347564,0.0006936216,0.001122032,0.0001999345,0.0001502752,0.000003806315,0.0004649629,0.0001946862,0.00001290828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007710626,"about_ca_system_score_gemma":0.0002463262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009928135,"about_ca_topic_score_gemma":0.000002385223,"domain_scores_codex":[0.9961393,0.0004371882,0.000842212,0.001535075,0.0001956207,0.0008505996],"domain_scores_gemma":[0.9972898,0.0000886024,0.0006513115,0.001576939,0.0001761316,0.0002172479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003598704,0.00003849135,2.228343e-7,0.000900251,0.0007384155,0.00001403701,0.00000369426,0.000003095398,0.1661607,0.004771606,0.001393389,0.8259401],"study_design_scores_gemma":[0.0005551931,0.0006029842,6.526049e-8,0.001421607,0.0005440373,0.0001063767,0.000003320744,0.00003201629,0.06457978,0.002246345,0.9291762,0.0007321466],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002737718,0.7469869,0.2481344,0.00004358025,0.0009536874,0.001000772,0.002656171,0.00004165048,0.000155462],"genre_scores_gemma":[0.0001325125,0.9830919,0.01063877,0.0001444393,0.001564381,0.000554082,0.003112166,0.0002246959,0.0005370409],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9277827,"threshold_uncertainty_score":0.9995515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165484374","doi":"10.1186/1748-7188-7-31","title":"Gene tree correction for reconciliation and species tree inference","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tree rearrangement; Tree (set theory); Inference; Heuristic; Vertex (graph theory); Gene duplication; Set (abstract data type); Time complexity; Phylogenetic tree; Computer science; Phylogenetic network; Combinatorics; Phylogenomics; Biology; Mathematics; Gene; Artificial intelligence; Genetics; Graph; Clade","retraction":null,"screen_n_in":null,"score":{"opus":0.02559951857724768,"gpt":0.2857459621330662,"spread":0.2601464435558185,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195842,0.0001664352,0.0001779095,0.0000405614,0.0001125154,0.00001138446,0.00008593679,0.000182606,0.000002052403],"category_scores_gemma":[0.0001933299,0.00016002,0.000098998,0.00003959536,0.00009016963,0.000001637107,0.00006806121,0.00003512186,0.000001169324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001358428,"about_ca_system_score_gemma":0.00002705004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001064201,"about_ca_topic_score_gemma":0.00003205999,"domain_scores_codex":[0.9991097,0.00003319164,0.0001831814,0.0003087576,0.0000324285,0.0003327275],"domain_scores_gemma":[0.99949,0.00005388665,0.00008661867,0.0001785774,0.0001206201,0.00007030462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006204983,0.00003041057,0.006024023,0.000009344064,0.0001043483,7.881426e-8,0.00005374372,0.000008282848,0.9361539,0.0006576761,0.0003780643,0.05651803],"study_design_scores_gemma":[0.001209204,0.001229736,0.01777875,0.00000389502,0.00008452309,0.0000177683,0.00009156288,0.0006798354,0.8860848,0.001605594,0.09083707,0.0003772476],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6993155,0.004562579,0.2935932,0.0001633745,0.001275301,0.0006270742,0.0001078679,0.000007718997,0.0003473506],"genre_scores_gemma":[0.9766351,0.0005051292,0.02097296,0.0002422929,0.0005659746,0.0002561159,0.0003693038,0.00002461766,0.0004285028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2773196,"threshold_uncertainty_score":0.6525425,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158241520","doi":"10.1186/1748-7188-6-17","title":"A new, fast algorithm for detecting protein coevolution using maximum compatible cliques","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Coevolution; Computer science; Algorithm; Data mining; Biology; Evolutionary biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0354444934789004,"gpt":0.2909475539826082,"spread":0.2555030605037079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002310585,0.0002906468,0.0003049378,0.00007848143,0.0002142314,0.00001543085,0.0002422753,0.0002850811,0.000005063901],"category_scores_gemma":[0.00006359027,0.0002949811,0.0002412136,0.00008542882,0.0001015152,0.000001821819,0.0001496275,0.00007220916,0.000001582584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002774853,"about_ca_system_score_gemma":0.0001210384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000300291,"about_ca_topic_score_gemma":0.00003693217,"domain_scores_codex":[0.9983925,0.00006115629,0.0003411819,0.0006049545,0.00005584933,0.0005443677],"domain_scores_gemma":[0.9991432,0.00001641076,0.0001815088,0.0003210904,0.0002265558,0.0001112201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008326887,0.00004243088,0.0001653743,0.00001724261,0.0001998358,0.000001040951,0.00007523825,0.00001658391,0.8913823,0.0003320314,0.00005639339,0.1076283],"study_design_scores_gemma":[0.00160589,0.002219292,0.000163256,0.00001656741,0.00009381504,0.00002895649,0.0001226692,0.007442788,0.9640833,0.01534471,0.008350375,0.0005284352],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2214896,0.001170362,0.7757567,0.00002008281,0.0002586617,0.001070387,0.0001310907,0.00001338188,0.00008978997],"genre_scores_gemma":[0.2808745,0.00002710646,0.7180601,0.0001231948,0.0003514554,0.0002640782,0.00015206,0.00006083289,0.00008667837],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1070999,"threshold_uncertainty_score":0.9999502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110150937","doi":"10.1186/1748-7188-5-34","title":"Predicting direct protein interactions from affinity purification mass spectrometry data","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Probabilistic logic; Set (abstract data type); Identification (biology); Data mining; Algorithm; Sensitivity (control systems); Graph; Artificial intelligence; Theoretical computer science; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0173378879299586,"gpt":0.2870760176882253,"spread":0.2697381297582667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003481814,0.0002034575,0.0001955726,0.00006229613,0.0001397708,0.00004343221,0.0006356817,0.0003118159,0.00003154217],"category_scores_gemma":[0.0002939393,0.0001994922,0.00009093255,0.0001201404,0.0001052673,0.0000113374,0.0002660783,0.000289788,0.00001279005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001055166,"about_ca_system_score_gemma":0.00007977833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009195634,"about_ca_topic_score_gemma":0.000117556,"domain_scores_codex":[0.9986283,0.00005145751,0.0003355609,0.0005766086,0.0000655129,0.0003425311],"domain_scores_gemma":[0.9984078,0.00003918165,0.0001913603,0.001148995,0.0001151672,0.00009744681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003643183,0.00004378321,0.0003934265,0.000006269272,0.0001384926,7.635868e-7,0.00001235847,0.00000686773,0.987923,0.0007086435,0.0003518777,0.01037809],"study_design_scores_gemma":[0.001215178,0.0004855383,0.0006705334,0.00001702077,0.0001173905,0.00002253699,0.00006250875,0.02033755,0.8595911,0.01563384,0.1011643,0.0006825861],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3638553,0.0002864951,0.6312839,0.0003177827,0.0009591528,0.0006935066,0.001227362,0.00004284541,0.001333626],"genre_scores_gemma":[0.8124822,0.00002109504,0.1776136,0.0001801455,0.0008872909,0.0001224785,0.0084959,0.00003691818,0.0001603937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4536704,"threshold_uncertainty_score":0.8135056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2976303698","doi":"10.1186/s13015-020-00171-4","title":"Evolution through segmental duplications and losses: a Super-Reconciliation approach","year":2020,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.02459881913070271,"gpt":0.2817939826194368,"spread":0.2571951634887341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001184158,0.0002179458,0.0001998389,0.00003340186,0.0001223805,0.00002351437,0.0001853439,0.0002304749,0.000008275613],"category_scores_gemma":[0.00008763705,0.0002254734,0.0001166802,0.0001354118,0.0001420585,0.000009632851,0.0001335154,0.00007869864,0.000009975574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003091088,"about_ca_system_score_gemma":0.00005976975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002634406,"about_ca_topic_score_gemma":0.000002807133,"domain_scores_codex":[0.9986123,0.00006344821,0.0002455971,0.0006779369,0.00007901771,0.0003216893],"domain_scores_gemma":[0.9994196,0.00001185154,0.00008537355,0.0002574649,0.0001122946,0.0001134724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005066248,0.00008113417,0.001101355,0.00004564408,0.0001597228,8.497879e-7,0.0001798291,0.0000755735,0.989991,0.003612876,0.0004714923,0.004229864],"study_design_scores_gemma":[0.01262431,0.007810949,0.004111094,0.00002641758,0.0006133449,0.0002347902,0.002440575,0.05840942,0.6762274,0.01278992,0.2215699,0.003141868],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1741566,0.001907408,0.8213707,0.0009958174,0.00009499831,0.0008952639,0.0001722872,0.00003769652,0.0003691826],"genre_scores_gemma":[0.8747342,0.0001670532,0.1203796,0.00127113,0.0003909565,0.0004208672,0.002503553,0.00005222281,0.00008037152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7009911,"threshold_uncertainty_score":0.9194537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3192846055","doi":"10.1186/s13015-021-00198-1","title":"INGOT-DR: an interpretable classifier for predicting drug resistance in M. tuberculosis","year":2021,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"European and Developing Countries Clinical Trials Partnership; Foreign, Commonwealth and Development Office; Foreign and Commonwealth Office; Medical Research Council; Genome Canada","keywords":"Interpretability; Computer science; Machine learning; Artificial intelligence; Classifier (UML); Tuberculosis; Mycobacterium tuberculosis; Test set; Data mining; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03067170206095806,"gpt":0.3686188964198777,"spread":0.3379471943589196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009776338,0.0002358957,0.000675405,0.0001976026,0.0001017353,0.00001747968,0.0001841981,0.000321445,0.00003558069],"category_scores_gemma":[0.003022479,0.0002197376,0.0002713007,0.0002993411,0.0001443233,0.00008209826,0.00008079334,0.0003307821,0.000005129259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000137721,"about_ca_system_score_gemma":0.0002296869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001548642,"about_ca_topic_score_gemma":0.0007114502,"domain_scores_codex":[0.9972901,0.0003339848,0.0005549111,0.0008118228,0.0001072298,0.0009019274],"domain_scores_gemma":[0.9981409,0.0006639702,0.00008944659,0.0005237205,0.0003254822,0.0002564475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003325186,0.001433087,0.09273923,0.001084075,0.001553247,0.0004968015,0.001521288,0.00006721335,0.7931073,0.03025883,0.01878221,0.05563151],"study_design_scores_gemma":[0.02077553,0.003629177,0.01658701,0.0008942671,0.0006986395,0.0004953375,0.001911223,0.09130501,0.2834082,0.05230581,0.5259593,0.002030459],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.751792,0.007983208,0.2053337,0.02830315,0.0007655711,0.002612016,0.0003198225,0.0001747417,0.002715859],"genre_scores_gemma":[0.824704,0.000388225,0.1595093,0.007867853,0.0005626688,0.001892901,0.002029158,0.0001422054,0.002903679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5096991,"threshold_uncertainty_score":0.8960637,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2405206615","doi":"10.1186/s13015-016-0065-9","title":"Models and algorithms for genome rearrangement with positional constraints","year":2016,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Generalization; Weighting; Set (abstract data type); Computer science; Function (biology); Polynomial; Binary number; Representation (politics); Algorithm; Time complexity; Combinatorics; Simple (philosophy); Mathematics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.020969453984812,"gpt":0.2789786315493447,"spread":0.2580091775645327,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003680614,0.0003884566,0.0003589317,0.0001174196,0.0001590057,0.00002891422,0.0002652454,0.0002885809,0.0000241996],"category_scores_gemma":[0.00004519046,0.0002829697,0.0001739227,0.00007880978,0.0005178722,0.00001240673,0.0001337827,0.00005835387,0.000004733683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004019689,"about_ca_system_score_gemma":0.0001048484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006896788,"about_ca_topic_score_gemma":0.000005654251,"domain_scores_codex":[0.9977945,0.00006769469,0.0003386509,0.0009616715,0.0001459906,0.000691499],"domain_scores_gemma":[0.9988543,0.00006077915,0.0001462528,0.0004273466,0.0003153282,0.0001959878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002786597,0.00008823864,0.0000933875,0.00003713817,0.0005169002,0.000006350881,0.00002574646,0.00003377543,0.9460416,0.005333109,0.0001611843,0.04738384],"study_design_scores_gemma":[0.04681196,0.02525305,0.002214477,0.0002428476,0.001082846,0.001070471,0.0003903524,0.005687642,0.6014639,0.09060687,0.2195769,0.005598721],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05654349,0.001183028,0.937934,0.001056069,0.0001533549,0.001715697,0.001140681,0.00003537081,0.0002382649],"genre_scores_gemma":[0.6040577,0.0006054549,0.3876633,0.001131017,0.0007420356,0.002175168,0.002429489,0.0002098269,0.0009859342],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5502707,"threshold_uncertainty_score":0.9999623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158093499","doi":"10.1186/1748-7188-7-14","title":"Ubiquity of synonymity: almost all large binary trees are not uniquely identified by their spectra or their immanantal polynomials","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Graph theory and applications","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Division of Mathematical Sciences; Pacific Institute for the Mathematical Sciences; National Science Foundation","keywords":"Adjacency matrix; Combinatorics; Mathematics; Eigenvalues and eigenvectors; Laplacian matrix; Adjacency list; Binary tree; Binary number; Characteristic polynomial; Weight-balanced tree; Invariant (physics); Tree (set theory); Spectrum (functional analysis); Discrete mathematics; Polynomial; Binary search tree; Graph; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.06327891369287991,"gpt":0.3557059889395285,"spread":0.2924270752466486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009036174,0.0003224936,0.0005875739,0.0001130978,0.0001685623,0.00001372851,0.0004158045,0.0002955416,0.00007021544],"category_scores_gemma":[0.0001487601,0.0002351088,0.0003350072,0.0001973864,0.000220097,0.00008820268,0.0001622436,0.0001622526,0.000007791316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002828519,"about_ca_system_score_gemma":0.00003410821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003968347,"about_ca_topic_score_gemma":0.00004201946,"domain_scores_codex":[0.9981297,0.0002528538,0.000510146,0.0003746974,0.00008268032,0.0006498893],"domain_scores_gemma":[0.9982567,0.000511948,0.0003909514,0.0006180283,0.000086452,0.0001358751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002278925,0.001108298,0.0004760757,0.00009466494,0.0005149049,0.00000449289,0.0004941633,2.371981e-7,0.6436481,0.3497628,0.002301937,0.001366448],"study_design_scores_gemma":[0.0008811026,0.0003045138,0.0006957148,0.00003079764,0.0001608594,0.00003627661,0.0004565895,0.00009646119,0.7934501,0.193798,0.009691183,0.0003984014],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9477876,0.0005420474,0.04585665,0.0004445074,0.0002082177,0.001031843,0.003863725,0.0001021496,0.0001632276],"genre_scores_gemma":[0.9918578,0.00008451346,0.006670718,0.0003563572,0.0000754996,0.0002254837,0.0004239435,0.00005910293,0.0002466427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1559648,"threshold_uncertainty_score":0.9587458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098784730","doi":"10.1186/1748-7188-6-16","title":"Efficient unfolding pattern recognition in single molecule force spectroscopy data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Force Microscopy Techniques and Applications","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Bundesministerium für Bildung und Forschung","keywords":"Bacteriorhodopsin; Pairwise comparison; Algorithm; Force spectroscopy; Molecule; Computer science; Sequence (biology); Biological system; Chemistry; Physics; Crystallography; Membrane; Artificial intelligence; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.05206492058926655,"gpt":0.3226739734357409,"spread":0.2706090528464744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000134735,0.0001542545,0.0001701339,0.00008049579,0.00006324173,0.00001468293,0.0003585454,0.00006957101,0.00009797402],"category_scores_gemma":[0.000004791425,0.0001580999,0.00006798496,0.0001441206,0.00005899959,0.00002689793,0.0001557876,0.00009931031,0.00001694252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002255347,"about_ca_system_score_gemma":0.00002034352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004399294,"about_ca_topic_score_gemma":0.000007248128,"domain_scores_codex":[0.9988925,0.00002660672,0.0002426004,0.0004543494,0.00003736875,0.0003465141],"domain_scores_gemma":[0.9993091,0.0000194009,0.0000946377,0.0004918477,0.00003921175,0.00004586504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001650808,0.0004143381,0.0009549454,0.00001037748,0.00004698927,0.000002552161,0.0001105186,0.00001497119,0.939082,0.007751133,0.0001145339,0.05148113],"study_design_scores_gemma":[0.0005660833,0.0002567389,0.00005680038,0.00002573206,0.00003205179,0.000002221761,0.00007968093,0.01677886,0.9558815,0.02530309,0.0007110837,0.0003060925],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1755766,0.00004128032,0.8215598,0.00003576848,0.00005755782,0.0004762732,0.0003824717,0.00004107111,0.001829072],"genre_scores_gemma":[0.876943,0.000001412502,0.1211914,0.0001015792,0.0000611271,0.0002142143,0.001433488,0.00003122627,0.00002255582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7013664,"threshold_uncertainty_score":0.6447126,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1039758599","doi":"10.1186/s13015-015-0053-5","title":"Detecting conserved protein complexes using a dividing-and-matching algorithm and unequally lenient criteria for network comparison","year":2015,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Protein superfamily; Similarity (geometry); Matching (statistics); Computational biology; Drosophila melanogaster; Data mining; Topology (electrical circuits); Artificial intelligence; Biology; Genetics; Mathematics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.05642390626907818,"gpt":0.3395592973962983,"spread":0.2831353911272201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008493951,0.0003017001,0.0004281091,0.00005001724,0.0002695851,0.00008159013,0.0001711308,0.0003046788,7.720964e-7],"category_scores_gemma":[0.0001041654,0.000297115,0.0001142225,0.0000668532,0.0001719064,0.000008412741,0.0002909846,0.0001157685,3.36211e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002187474,"about_ca_system_score_gemma":0.00008158067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007360665,"about_ca_topic_score_gemma":0.00002465379,"domain_scores_codex":[0.9982415,0.0001089534,0.0005017807,0.0004894389,0.00007067424,0.0005876513],"domain_scores_gemma":[0.9990728,0.00005779,0.0002511374,0.000241118,0.0001835274,0.0001935753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004490179,0.00009247292,0.0004446174,0.0002099755,0.0005582059,0.000004002023,0.0006219086,0.001890115,0.8841938,0.004275923,0.0005056071,0.1067543],"study_design_scores_gemma":[0.007256053,0.004432183,0.00006303207,0.0001727297,0.0002753251,0.0001789556,0.001070073,0.7858568,0.1137843,0.0649216,0.0203597,0.001629255],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3145058,0.002096776,0.6821224,0.00008414852,0.0002140132,0.0008705652,0.00007747721,0.00001723046,0.00001159106],"genre_scores_gemma":[0.5528506,0.00001333304,0.4459531,0.0003007598,0.000364491,0.0001484737,0.0003092605,0.00004526139,0.00001470535],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7839667,"threshold_uncertainty_score":0.9999481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110922051","doi":"10.1186/1748-7188-7-32","title":"Towards a practical O(n logn) phylogeny algorithm","year":2012,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Phylogenetics; Algorithm; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.03332692126473845,"gpt":0.3493959329378441,"spread":0.3160690116731056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006494165,0.0003304472,0.0003761206,0.000149341,0.0002012829,0.00008506182,0.0009356121,0.0003082396,0.00002558002],"category_scores_gemma":[0.0001779738,0.0002799143,0.0002232946,0.0003304516,0.0001289324,0.0005873966,0.00076842,0.0002443362,0.000103935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000537744,"about_ca_system_score_gemma":0.0001379028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005719999,"about_ca_topic_score_gemma":6.134592e-7,"domain_scores_codex":[0.9974676,0.0001733094,0.0003727595,0.0006847086,0.0002259792,0.0010756],"domain_scores_gemma":[0.9982035,0.0001606503,0.0001571405,0.0009360499,0.0001726386,0.0003700792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001231951,0.000337346,0.00008892964,0.00001166758,0.0001119286,0.00003066909,0.0001315952,0.000003552621,0.0140123,0.2078397,0.002134272,0.7752858],"study_design_scores_gemma":[0.003240959,0.001695218,0.001416097,0.00003315489,0.0001341092,0.001099599,0.00007866615,0.2677464,0.0779603,0.08859631,0.5559506,0.002048647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006464815,0.001226355,0.9941287,0.001044079,0.001673306,0.0004630539,0.00009092841,0.0002142037,0.0005128845],"genre_scores_gemma":[0.02175312,0.00003961734,0.9757945,0.001382699,0.0005919621,0.0001819108,0.0001580138,0.00003363105,0.00006453508],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7732371,"threshold_uncertainty_score":0.9999653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165398449","doi":"10.1186/1748-7188-5-38","title":"Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization (EM) training and Viterbi training","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Viterbi algorithm; Computer science; Hidden Markov model; Iterative Viterbi decoding; Forward algorithm; Markov model; Markov chain; Soft output Viterbi algorithm; Expectation–maximization algorithm; Training (meteorology); Machine learning; Algorithm; Maximum-entropy Markov model; Artificial intelligence; Variable-order Markov model; Maximum likelihood; Decoding methods; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07937526116788873,"gpt":0.3143771748915459,"spread":0.2350019137236571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007773076,0.0002496256,0.0003658791,0.0001713434,0.0002517985,0.00009132604,0.0004746495,0.0002037065,9.070944e-7],"category_scores_gemma":[0.0001883825,0.0002101343,0.0001397553,0.0002347176,0.0001861803,0.0001104641,0.00008868791,0.0002009705,1.199514e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002002684,"about_ca_system_score_gemma":0.0001430368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002202593,"about_ca_topic_score_gemma":0.000004461321,"domain_scores_codex":[0.9982051,0.00009709285,0.000450339,0.0005988691,0.0001490132,0.000499624],"domain_scores_gemma":[0.9986522,0.0004289897,0.000268188,0.0003494026,0.0002030992,0.00009813903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002853083,0.00003673795,0.000001548105,0.00002644828,0.00009125689,0.000001879538,0.02759005,0.09988469,0.07233888,0.02001729,0.000001411906,0.7799813],"study_design_scores_gemma":[0.0006370533,0.0002591891,0.000005494009,0.00003014408,0.00004641131,0.00004913033,0.001479246,0.9663659,0.001978411,0.02890578,0.000002707964,0.0002405407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1824783,0.0001020858,0.8162019,0.0001436714,0.0004206325,0.0005645189,0.00002815018,0.00005296434,0.000007788253],"genre_scores_gemma":[0.5290615,0.000001148718,0.4706912,0.00008581219,0.00003811783,0.00008665861,0.00001697803,0.00001683274,0.000001735376],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8664812,"threshold_uncertainty_score":0.8569027,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392343346","doi":"10.1186/s13015-024-00256-4","title":"SparseRNAfolD: optimized sparse RNA pseudoknot-free folding with dangle consideration","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudoknot; Computer science; Algorithm; Computation; Recursion (computer science); Folding (DSP implementation); Theoretical computer science; Mathematical optimization; Mathematics; RNA","retraction":null,"screen_n_in":null,"score":{"opus":0.01835453689503884,"gpt":0.2802774089962778,"spread":0.261922872101239,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003506754,0.0003264296,0.0003026015,0.0001094693,0.0001341309,0.00009321771,0.000343288,0.0003473642,0.00004018048],"category_scores_gemma":[0.00017186,0.0002751059,0.0002075071,0.0001277911,0.0001179288,0.000009827811,0.0001417697,0.0001058396,0.00001663331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002240032,"about_ca_system_score_gemma":0.0001402617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002694693,"about_ca_topic_score_gemma":0.00001151124,"domain_scores_codex":[0.9982114,0.000118769,0.000297339,0.0007788484,0.000118322,0.0004753307],"domain_scores_gemma":[0.9989593,0.00006266317,0.00008451993,0.0006637,0.0001152297,0.0001145793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001801126,0.00002957824,0.00001088841,0.00003370727,0.0002886342,0.00005005748,0.00002226077,0.0001582066,0.9745099,0.01067889,0.0008386996,0.01319907],"study_design_scores_gemma":[0.001250187,0.001075017,0.000004830651,0.00005192344,0.0001115851,0.0001396073,0.00003103011,0.001941352,0.9530879,0.008967196,0.03290322,0.0004361993],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1106862,0.004461508,0.8815222,0.000777122,0.0006583693,0.000900807,0.0001316558,0.0001034533,0.0007586135],"genre_scores_gemma":[0.6994084,0.0002717393,0.2968285,0.0007898516,0.0006161418,0.0005784667,0.0006439723,0.0001505303,0.0007123757],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5887222,"threshold_uncertainty_score":0.9999701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392885478","doi":"10.1186/s13015-024-00258-2","title":"Infrared: a declarative tree decomposition-powered framework for bioinformatics","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; Universität Wien; Austrian Science Fund; Agence Nationale de la Recherche","keywords":"Computer science; Theoretical computer science; Feature (linguistics); Tree (set theory); Data mining; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01613810383166685,"gpt":0.3277411422206731,"spread":0.3116030383890062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001718096,0.0002711116,0.000261178,0.00009085367,0.0001453727,0.00005430118,0.0002331255,0.000352002,0.000005473286],"category_scores_gemma":[0.0001345313,0.0002502456,0.0003145923,0.000113522,0.0001277713,0.000001831826,0.0001132107,0.00009044462,0.000007854422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002008607,"about_ca_system_score_gemma":0.0001075193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002824763,"about_ca_topic_score_gemma":0.000004582479,"domain_scores_codex":[0.9986916,0.00003249015,0.0003351075,0.0004667566,0.00005519409,0.0004189036],"domain_scores_gemma":[0.9992397,0.000127803,0.00007290827,0.0003206935,0.0001544265,0.00008451136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002544591,0.0001009657,0.00008107974,0.0002034981,0.001632239,0.000006972597,0.0004537695,0.00008405713,0.7707276,0.1435243,0.003968384,0.07896277],"study_design_scores_gemma":[0.001295848,0.003043545,0.00008551469,0.00006464915,0.0002159359,0.00005227053,0.0002651827,0.007697652,0.3248693,0.3161973,0.3453552,0.0008575593],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02260119,0.008439335,0.9654055,0.0003453976,0.0008564592,0.000942582,0.0006996578,0.00002342023,0.0006865091],"genre_scores_gemma":[0.2263244,0.0006025255,0.7680565,0.001210505,0.0006833581,0.001060139,0.001565603,0.0001003481,0.0003966017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4458583,"threshold_uncertainty_score":0.999995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394688386","doi":"10.1186/s13015-024-00260-8","title":"Pfp-fm: an accelerated FM-index","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; Japan Society for the Promotion of Science; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; National Institutes of Health; National Science Foundation","keywords":"Computer science; Parsing; Suffix; Word (group theory); Sorting; Search engine indexing; Prefix; Character (mathematics); Suffix array; Index (typography); Algorithm; Artificial intelligence; Natural language processing; Data structure; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03292274683587503,"gpt":0.3461846779970787,"spread":0.3132619311612037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002998787,0.0002633124,0.0002581444,0.0001980014,0.000160997,0.0003177271,0.001196043,0.0002407309,0.00003027151],"category_scores_gemma":[0.00002860847,0.0002188283,0.0001403865,0.0004549777,0.00007733663,0.0005114854,0.000421973,0.0002039774,0.00006972239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003627774,"about_ca_system_score_gemma":0.00009874009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008096312,"about_ca_topic_score_gemma":0.000004188752,"domain_scores_codex":[0.9979634,0.0001040902,0.0002941134,0.0009536455,0.0001444934,0.0005403075],"domain_scores_gemma":[0.9987318,0.00008426166,0.0000518121,0.0008329992,0.0001216507,0.0001774636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001375033,0.00009527356,0.00002825383,0.00002783705,0.00009939959,0.0001585695,0.0001171763,0.00006926236,0.05079982,0.110462,0.001380804,0.8367479],"study_design_scores_gemma":[0.0004175065,0.000551815,0.00007233661,0.00001981662,0.00001653129,0.00008594305,0.0000106398,0.8494522,0.01959071,0.05195629,0.07741966,0.0004065693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00401137,0.001380998,0.9911991,0.0006012869,0.001621322,0.0003349026,0.00008475711,0.0005311192,0.0002350847],"genre_scores_gemma":[0.573393,0.00006755796,0.4230097,0.001529299,0.0006609395,0.0001206377,0.0008620291,0.00008601262,0.0002707244],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8493829,"threshold_uncertainty_score":0.8923558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147043108","doi":"10.1186/1748-7188-8-5","title":"Protein Structure Idealization: How accurately is it possible to model protein structures with dihedral angles?","year":2013,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; Killam Trusts; City University of Hong Kong","keywords":"Dihedral angle; Protein structure prediction; Protein structure; Algorithm; Computer science; Gaussian; Idealization; Ideal (ethics); Physics; Computational chemistry; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.0163310326278924,"gpt":0.2876081307289795,"spread":0.2712770981010871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007773154,0.0005159625,0.0003835424,0.0001175191,0.0001874297,0.0001392106,0.0005389457,0.0005732273,0.00004189467],"category_scores_gemma":[0.00008957604,0.0004054238,0.0001505254,0.0002473708,0.0001638551,0.00002248794,0.0002120022,0.0001776923,0.000005255458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000310775,"about_ca_system_score_gemma":0.0002107222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007124923,"about_ca_topic_score_gemma":0.00006380388,"domain_scores_codex":[0.9977501,0.00007590496,0.0003017663,0.0009631297,0.0001876993,0.0007213705],"domain_scores_gemma":[0.9983663,0.000006312118,0.0001892521,0.0007291992,0.0004633815,0.000245529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001458643,0.00001911838,0.00006185415,0.00004569028,0.0001543874,0.000003524245,0.00006842543,0.001127916,0.9865697,0.00487875,0.00141002,0.005514741],"study_design_scores_gemma":[0.001260601,0.00166811,0.00007911341,0.0000275784,0.00004343174,0.00004377234,0.00007158493,0.009021794,0.9450987,0.03630137,0.005572095,0.0008118275],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4820853,0.0001617837,0.5121605,0.002152564,0.0000631239,0.002872726,0.0003721986,0.00003251529,0.00009926079],"genre_scores_gemma":[0.8222823,0.000004456607,0.171838,0.002597208,0.0002156165,0.0009143203,0.00100261,0.00009018912,0.001055346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3403225,"threshold_uncertainty_score":0.9998398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3021210550","doi":"10.1186/s13015-020-00169-y","title":"The distance and median problems in the single-cut-or-join model with single-gene duplications","year":2020,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Join (topology); Computer science; Gene duplication; Algorithm; Gene; Data mining; Genetics; Biology; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.0360477283324637,"gpt":0.2649155196467826,"spread":0.2288677913143189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002708469,0.0002478381,0.0001964727,0.00003117519,0.0001963112,0.00005651344,0.0004751017,0.0001585936,0.000001241635],"category_scores_gemma":[0.0001249508,0.0001427216,0.00007026335,0.0002261271,0.0003382386,0.000005368247,0.0001159148,0.0001312859,0.000001821459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001796226,"about_ca_system_score_gemma":0.00007201234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009739445,"about_ca_topic_score_gemma":0.0002258115,"domain_scores_codex":[0.9984596,0.000106054,0.000280624,0.0005835151,0.0001188752,0.000451357],"domain_scores_gemma":[0.9991637,0.00006582122,0.000115735,0.0004579803,0.00009477088,0.0001019666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001893254,0.000162297,0.0003141513,0.00003764236,0.000163499,0.000009244377,0.0005669069,0.001360601,0.9762977,0.001519014,0.0002952068,0.01908441],"study_design_scores_gemma":[0.01177407,0.01680516,0.0006847589,0.00008661173,0.0004695391,0.0004064011,0.002335441,0.1499993,0.4535613,0.01683393,0.3439086,0.003134846],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0756222,0.003487768,0.9011319,0.01713858,0.00007531593,0.002076131,0.0001681935,0.00003119381,0.0002687061],"genre_scores_gemma":[0.9655007,0.0004275286,0.03015217,0.002173199,0.000193766,0.0008132875,0.0005333999,0.00006874539,0.0001371662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8898786,"threshold_uncertainty_score":0.5820019,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964468345","doi":"10.1186/s13015-019-0153-8","title":"A branching process for homology distribution-based inference of polyploidy, speciation and loss","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Genome; Biology; Gene; Branching process; Computational biology; Divergence (linguistics); Evolutionary biology; Genetics; Mathematics; Computer science; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01048060292094039,"gpt":0.3043564349767752,"spread":0.2938758320558348,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002420889,0.0002046385,0.0002997818,0.00006934174,0.00005710179,0.00001018872,0.0001964925,0.0002679384,0.000007741454],"category_scores_gemma":[0.0001898531,0.0002062703,0.0001338779,0.00009949029,0.0001394985,0.000004994067,0.00005868919,0.00006221517,0.000001937652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001662629,"about_ca_system_score_gemma":0.0001106597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001484625,"about_ca_topic_score_gemma":0.000006121787,"domain_scores_codex":[0.9987095,0.00005051799,0.0002988921,0.0005120881,0.00007201343,0.0003569702],"domain_scores_gemma":[0.9991274,0.00006703746,0.0001971016,0.0002877356,0.0002589023,0.00006176394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002704872,0.0001379931,0.01903816,0.0002900008,0.0002074544,0.000001046267,0.00004471116,0.0003167595,0.9666096,0.003299814,0.00003315112,0.009750791],"study_design_scores_gemma":[0.006724248,0.004636963,0.004499838,0.00004855981,0.000146433,0.00002340568,0.00008940699,0.01154832,0.9496986,0.01011034,0.01164261,0.0008313233],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5632573,0.0004722037,0.4347259,0.0001282155,0.0001643115,0.0008415817,0.0003791552,0.00000953638,0.00002189161],"genre_scores_gemma":[0.9888265,0.00003231594,0.008127507,0.00013512,0.0001055055,0.0002133739,0.002475225,0.0000310989,0.00005341128],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4265983,"threshold_uncertainty_score":0.8411459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130654549","doi":"10.1186/1748-7188-8-20","title":"Fast half-sibling population reconstruction: theory and algorithms","year":2013,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Kinship; Computer science; Heuristic; Population; Inference; Inheritance (genetic algorithm); Cluster analysis; Integer (computer science); Theoretical computer science; Data mining; Machine learning; Artificial intelligence; Biology; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.00999279403419891,"gpt":0.266749084789505,"spread":0.2567562907553061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005171353,0.0003305934,0.0003128301,0.0001692177,0.0001884741,0.00006718929,0.000223492,0.0003790761,0.00006849908],"category_scores_gemma":[0.0001521316,0.0003230177,0.0001656175,0.0001547043,0.0001945081,0.00001719133,0.0001630711,0.0001262511,0.00002476147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002493228,"about_ca_system_score_gemma":0.00003290236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001186317,"about_ca_topic_score_gemma":0.000008980289,"domain_scores_codex":[0.9979895,0.0002024885,0.0003880019,0.0007818367,0.0001030152,0.0005351047],"domain_scores_gemma":[0.998984,0.00005146137,0.0001610706,0.0004334776,0.0002109994,0.0001589946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005510568,0.00005411202,0.003069086,0.00003608563,0.0002963767,0.00000272659,0.00004312048,0.00003437902,0.5428882,0.004776669,0.0002293308,0.4485148],"study_design_scores_gemma":[0.01546735,0.007293237,0.0299427,0.0001762923,0.0007424832,0.00203783,0.002148576,0.0199335,0.5591962,0.2631418,0.09350741,0.006412616],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5255697,0.002673988,0.4683041,0.0005599441,0.0007998255,0.001448579,0.00005691278,0.00007147722,0.0005154723],"genre_scores_gemma":[0.7946932,0.0005288451,0.1984966,0.001061714,0.00100859,0.0009168734,0.001872418,0.000166457,0.001255219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4421021,"threshold_uncertainty_score":0.9999222,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115843315","doi":"10.1186/1748-7188-6-8","title":"An FPT haplotyping algorithm on pedigrees with a small number of sites","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pedigree chart; Computer science; Algorithm; Haplotype; Data mining; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03441372841316802,"gpt":0.3044060543597645,"spread":0.2699923259465964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000316184,0.0002585691,0.0003556072,0.00006719536,0.00008337975,0.000005422429,0.000302492,0.000353101,0.00002713327],"category_scores_gemma":[0.0001026124,0.0002179698,0.000152232,0.00009911186,0.0002033834,0.000003185402,0.00006130178,0.00009344156,0.000008047684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000109325,"about_ca_system_score_gemma":0.00006993676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001095268,"about_ca_topic_score_gemma":0.0000467459,"domain_scores_codex":[0.9984187,0.0001565397,0.0003390144,0.0005774988,0.00006127138,0.0004469378],"domain_scores_gemma":[0.9988909,0.00004062137,0.0002275373,0.0005052509,0.0002248004,0.0001108891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006656965,0.001040165,0.08999366,0.00005118831,0.001098949,0.00001828169,0.0004354039,0.0001404946,0.7826245,0.00557798,0.0002824794,0.1180711],"study_design_scores_gemma":[0.005710718,0.02255971,0.05096478,0.00006176414,0.0004467122,0.0002427624,0.0008007392,0.004086131,0.8878351,0.0174257,0.007763918,0.002102006],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7275723,0.0001551623,0.2711081,0.00004452309,0.00009785052,0.0003158884,0.0001022511,0.00002053469,0.000583443],"genre_scores_gemma":[0.6536825,0.0000455018,0.3449479,0.000408529,0.0001431758,0.000110436,0.0005394326,0.00004884192,0.00007366436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1159691,"threshold_uncertainty_score":0.8888552,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2789974803","doi":"10.1186/s13015-018-0123-6","title":"Derivative-free neural network for optimizing the scoring functions associated with dynamic programming of pairwise-profile alignment","year":2018,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Genetics","keywords":"Computer science; Pairwise comparison; Cosine similarity; Artificial neural network; Similarity (geometry); Multiple sequence alignment; Artificial intelligence; Data mining; Smith–Waterman algorithm; Function (biology); Solver; Sequence alignment; Pattern recognition (psychology); Sequence (biology); Algorithm; Machine learning; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0158604832505475,"gpt":0.2656652575393171,"spread":0.2498047742887696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002900475,0.0002040736,0.000231275,0.00002577229,0.000313105,0.00001333662,0.0002885294,0.0001290756,0.000001700596],"category_scores_gemma":[0.0001490903,0.0001488117,0.000152228,0.0001173771,0.0003459024,0.000001030599,0.0001777291,0.0000526951,2.926232e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001908543,"about_ca_system_score_gemma":0.00004958017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000160273,"about_ca_topic_score_gemma":0.00007005491,"domain_scores_codex":[0.9987766,0.00006577962,0.0002461607,0.0003967013,0.00006149655,0.0004532957],"domain_scores_gemma":[0.999012,0.00007676947,0.000193008,0.0003975333,0.000279303,0.00004140211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004319809,0.0001386266,0.003141158,0.00003750655,0.001923157,0.000001188354,0.0001998584,0.003045202,0.9547591,0.0009621209,0.0007806342,0.03457943],"study_design_scores_gemma":[0.0139525,0.03740048,0.01166021,0.0002272346,0.001562961,0.00006282108,0.00210475,0.06366935,0.7913462,0.009065318,0.06619002,0.002758165],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5897421,0.001259166,0.4068106,0.0002611019,0.000375617,0.001262391,0.0002198743,0.00001126776,0.00005786049],"genre_scores_gemma":[0.9077614,0.00002415562,0.09071238,0.0001850358,0.0002531498,0.000596898,0.0003401601,0.00004452132,0.00008230442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3180193,"threshold_uncertainty_score":0.6068363,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391565229","doi":"10.1186/s13015-023-00242-2","title":"Predicting horizontal gene transfers with perfect transfer networks","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Phylogenetic tree; Character (mathematics); Horizontal gene transfer; Inference; Phylogenetic network; Biology; Set (abstract data type); Similarity (geometry); Phylogenetics; Evolutionary biology; Gene; Genetics; Computational biology; Computer science; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.007755730313516916,"gpt":0.2434699862928719,"spread":0.2357142559793549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001787905,0.0003011115,0.0002477396,0.00005994118,0.0001281369,0.00003569893,0.0001866166,0.0002558583,0.000004846279],"category_scores_gemma":[0.00001064266,0.0002475304,0.0002369037,0.0001154064,0.0001600374,0.000001222841,0.00003954334,0.0001280798,0.000001830996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001515106,"about_ca_system_score_gemma":0.00007766436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002714229,"about_ca_topic_score_gemma":0.00003838236,"domain_scores_codex":[0.9984717,0.00005207712,0.0002220618,0.0006913369,0.00006729252,0.000495522],"domain_scores_gemma":[0.99954,0.00002984589,0.00001450396,0.0002536023,0.00006836328,0.00009368207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001629313,0.00003132948,0.0007902434,0.00003184954,0.000644095,0.0000228172,0.0000756064,0.0009868686,0.9743982,0.00104063,0.00006201187,0.02175344],"study_design_scores_gemma":[0.002864771,0.01242861,0.0007248492,0.00006324564,0.0005839138,0.000425618,0.0001751837,0.02304442,0.9064635,0.0007441531,0.05103351,0.001448211],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5305285,0.007378761,0.4609399,0.0001038458,0.0003667561,0.0003880154,0.0001384567,0.0000200043,0.0001358437],"genre_scores_gemma":[0.9920989,0.0005059999,0.006000704,0.0001786489,0.000524401,0.0002113822,0.0003373679,0.0000800237,0.00006253525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4615705,"threshold_uncertainty_score":0.9999977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2544103171","doi":"10.1186/s13015-017-0101-4","title":"Aligning coding sequences with frameshift extension penalties","year":2017,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Canada Research Chairs; Université de Sherbrooke","keywords":"Frameshift mutation; Coding (social sciences); Extension (predicate logic); Gene; Homologous chromosome; Encoding (memory); Efficient algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02500415426522971,"gpt":0.3100925058355515,"spread":0.2850883515703218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003400692,0.0002410494,0.0002529379,0.00004522956,0.0005704989,0.00009313627,0.0004981319,0.000275209,0.00001083349],"category_scores_gemma":[0.0002359898,0.0001919806,0.0001285749,0.00002318912,0.0002741901,0.000008891769,0.0001584188,0.0000754634,0.000006035633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008233796,"about_ca_system_score_gemma":0.00006627128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006286472,"about_ca_topic_score_gemma":0.0000166978,"domain_scores_codex":[0.9986429,0.00007262327,0.0001901323,0.0005873843,0.00009526136,0.000411654],"domain_scores_gemma":[0.9987628,0.00002614485,0.0002325144,0.0007527787,0.00013805,0.00008765213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001023909,0.000016169,0.0003290407,0.00001421682,0.00009779232,0.00001505739,0.00001889295,0.000008940064,0.9806019,0.00444213,0.00006238452,0.01429108],"study_design_scores_gemma":[0.0005940526,0.001044914,0.0001859231,0.00004063016,0.00004080885,0.00005434044,0.00006375302,0.000125581,0.9821503,0.00512851,0.01022599,0.0003451512],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3778615,0.001205536,0.6181946,0.0006881144,0.0004075794,0.0006375565,0.0000494199,0.00003542798,0.0009202267],"genre_scores_gemma":[0.9339694,0.0001216957,0.06477245,0.0003929305,0.0002257544,0.0001448999,0.0001122914,0.00004235195,0.0002182276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5561079,"threshold_uncertainty_score":0.7828741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039803514","doi":"10.1186/1748-7188-6-11","title":"Listing all sorting reversals in quadratic time","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Permutation (music); Sorting; Listing (finance); Computer science; Identity (music); Sorting algorithm; Quadratic equation; Algorithm; Time complexity; Combinatorics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03749375139985743,"gpt":0.3000611005173297,"spread":0.2625673491174723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005722814,0.0002852079,0.0003237187,0.0001416096,0.00005886151,0.00001393818,0.0003611676,0.0003102781,0.00005572144],"category_scores_gemma":[0.0002900996,0.0002962628,0.0001801904,0.0001510493,0.0001054933,0.000005708117,0.0001781247,0.0001224946,0.00004809351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000295633,"about_ca_system_score_gemma":0.00006215872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009833416,"about_ca_topic_score_gemma":0.00002436498,"domain_scores_codex":[0.9979625,0.0001303331,0.0004828038,0.0006722751,0.00008481641,0.0006673133],"domain_scores_gemma":[0.9991326,0.00002771272,0.0001914961,0.0004454037,0.00009804574,0.0001047279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005727706,0.0001070436,0.001614371,0.00002926087,0.0001574134,0.00002375173,0.0001946536,0.00001446825,0.9875121,0.000543794,0.0001782287,0.009567711],"study_design_scores_gemma":[0.005678697,0.003466829,0.002467119,0.00008990552,0.0002295757,0.0001336066,0.0003563949,0.006232706,0.933174,0.01693478,0.02899489,0.002241479],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8131464,0.002437595,0.1754096,0.000252748,0.0005673012,0.002072029,0.00008594605,0.000101385,0.005927047],"genre_scores_gemma":[0.8204606,0.00009269677,0.1755308,0.001052723,0.0003535624,0.0003903267,0.0009889002,0.0001508456,0.0009795499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.054338,"threshold_uncertainty_score":0.999949,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965995818","doi":"10.1186/s13015-019-0150-y","title":"A cubic algorithm for the generalized rank median of three genomes","year":2019,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; Alfred P. Sloan Foundation","keywords":"Genome; Linear subspace; Heuristics; Time complexity; Combinatorics; Rank (graph theory); Matrix (chemical analysis); Computer science; Algorithm; Omega; Polynomial; Upper and lower bounds; Mathematics; Mathematical optimization; Biology; Pure mathematics; Physics; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01477803924146979,"gpt":0.2761304000805498,"spread":0.26135236083908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005758139,0.0003719539,0.0005051466,0.0001170839,0.0001155005,0.00001957383,0.0007392116,0.0003660994,0.00005098421],"category_scores_gemma":[0.00007570915,0.0002863806,0.0005582494,0.000174122,0.0002351862,0.000004951353,0.0001989249,0.0001038174,0.00001586482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002264659,"about_ca_system_score_gemma":0.0001287728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000454667,"about_ca_topic_score_gemma":0.00002509428,"domain_scores_codex":[0.9978553,0.00008040982,0.0004971022,0.0007323525,0.0001606949,0.0006741312],"domain_scores_gemma":[0.9983023,0.0001279852,0.0002560092,0.0008899378,0.000318916,0.0001048827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001202136,0.00007871547,0.000460221,0.00005613135,0.0008902061,0.000001220868,0.00003883112,0.00009206147,0.7562488,0.001344295,0.0003870651,0.2402822],"study_design_scores_gemma":[0.01164908,0.00419854,0.0004582509,0.00002438661,0.0005364532,0.00005011141,0.0001704859,0.04924093,0.6271867,0.01142326,0.2937835,0.001278333],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06969948,0.01139989,0.9127471,0.0006622706,0.001108091,0.003696999,0.000533474,0.00002846536,0.00012417],"genre_scores_gemma":[0.2516938,0.002223606,0.7307538,0.001899308,0.002121702,0.00375417,0.004693109,0.0004484293,0.002412109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2933964,"threshold_uncertainty_score":0.9999588,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1909028472","doi":"10.1186/s13015-015-0055-3","title":"Erratum to: Inferring interaction type in gene regulatory networks using co-expression data","year":2015,"lang":"en","type":"erratum","venue":"Algorithms for Molecular Biology","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Computer science; Expression (computer science); Type (biology); Data type; Computational biology; Data mining; Gene regulatory network; Data science; Gene expression; Gene; Biology; Genetics; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.04794319886971091,"gpt":0.3569521048979705,"spread":0.3090089060282596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009035511,0.0006998125,0.0008775831,0.0004386485,0.0001185099,0.00005322598,0.001266748,0.001982932,0.00001043269],"category_scores_gemma":[0.0002858274,0.0007489143,0.0002473837,0.0004738786,0.0001212117,0.00001417951,0.001232987,0.0006814605,0.000008447663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001940371,"about_ca_system_score_gemma":0.000559842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008157782,"about_ca_topic_score_gemma":0.0001138965,"domain_scores_codex":[0.9958953,0.000350412,0.0007864344,0.001840974,0.0002415661,0.0008853647],"domain_scores_gemma":[0.9963458,0.0000218189,0.0004513653,0.002482699,0.000400374,0.0002978973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002554507,0.00009333362,0.0001943926,0.0000450673,0.0004652923,0.00002791713,0.00002143358,0.02738879,0.4806405,0.000008978358,0.4861784,0.00468044],"study_design_scores_gemma":[0.001597412,0.001124469,0.0001462808,0.0003792811,0.000528989,0.0001163069,0.00007269802,0.1747432,0.09553177,0.0003438461,0.7231777,0.002238029],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1240641,0.05552137,0.745464,0.0002951068,0.06488354,0.00493339,0.001377501,0.0002067247,0.003254351],"genre_scores_gemma":[0.4120759,0.003976649,0.1609794,0.003592955,0.03395932,0.0006826756,0.354405,0.002092943,0.02823512],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5844846,"threshold_uncertainty_score":0.9994962,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116920786","doi":"10.1186/1748-7188-8-24","title":"Asymptotic structural properties of quasi-random saturated structures of RNA","year":2013,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"National Science Foundation","keywords":"Pseudoknot; Combinatorics; Mathematics; Distribution (mathematics); Loop (graph theory); Statistical physics; Discrete mathematics; Physics; RNA; Mathematical analysis; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01265192242207659,"gpt":0.2524425439793396,"spread":0.239790621557263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001365323,0.0002360816,0.000408833,0.00007195929,0.00004990804,0.00001009637,0.0003127388,0.0003108879,0.00004219378],"category_scores_gemma":[0.0001921707,0.0001783873,0.0002203143,0.00008268726,0.0002297998,0.000005436313,0.00008491053,0.00006058166,0.000002134114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006182359,"about_ca_system_score_gemma":0.00006312025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001321892,"about_ca_topic_score_gemma":0.000003583921,"domain_scores_codex":[0.9986668,0.0001387519,0.0004255209,0.0003614509,0.00009524013,0.0003122989],"domain_scores_gemma":[0.9989763,0.00002233498,0.0002495265,0.0003842564,0.0003032422,0.00006435623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001520082,0.0000215025,0.00006766961,0.00006177701,0.0001944064,3.989211e-7,0.00002865993,0.00002088454,0.9836279,0.001441097,0.00002890823,0.01435475],"study_design_scores_gemma":[0.0009874478,0.0009722673,0.0001799101,0.00001839087,0.00004144266,0.00001197819,0.00004963202,0.0002955356,0.9897203,0.007284558,0.0002243505,0.0002141541],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9509392,0.002440753,0.045298,0.00007327108,0.0002388207,0.0008831868,0.00005503299,0.00001160564,0.00006015271],"genre_scores_gemma":[0.9846121,0.00004129605,0.01484823,0.0000832622,0.00007844514,0.0001182469,0.0001251145,0.0000324903,0.00006079654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03367294,"threshold_uncertainty_score":0.7274421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017156855","doi":"10.1186/1748-7188-5-35","title":"Estimating the evidence of selection and the reliability of inference in unigenic evolution","year":2010,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Inference; Computer science; Selection (genetic algorithm); Reliability (semiconductor); Data mining; Data science; Econometrics; Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.007156918695487575,"gpt":0.2929834438655729,"spread":0.2858265251700853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006778728,0.00008105321,0.0001365794,0.00002381429,0.00004525295,0.000003294213,0.0001714853,0.0001533732,8.780461e-7],"category_scores_gemma":[0.001564076,0.0000486163,0.00005853989,0.0001027392,0.0004141261,0.000003236705,0.00008319147,0.0001254477,5.030278e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000561392,"about_ca_system_score_gemma":0.00006936695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002127859,"about_ca_topic_score_gemma":0.0001990128,"domain_scores_codex":[0.9992982,0.0001206911,0.0002228061,0.0001957999,0.00004200226,0.0001205723],"domain_scores_gemma":[0.9992887,0.000164712,0.0001381331,0.0002578385,0.0001369581,0.0000136006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001457527,0.00001007766,0.005130161,0.00002632588,0.00001434463,5.91956e-8,0.00004133278,0.0009167774,0.9805453,0.00787735,7.324045e-7,0.005291812],"study_design_scores_gemma":[0.001956511,0.0009991596,0.01232442,0.00005487327,0.00007577444,0.00002705919,0.00005411017,0.2110004,0.6538403,0.1193131,0.0001052628,0.0002490103],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7007478,0.0004885953,0.2982519,0.0001198376,0.00008299688,0.0002949512,0.000005247068,0.000001831931,0.000006845204],"genre_scores_gemma":[0.9764062,0.00002530806,0.02343383,0.00003187061,0.00003648313,0.00004727455,0.00001091172,0.000005199267,0.000002882862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.326705,"threshold_uncertainty_score":0.1982515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414725606","doi":"10.1186/s13015-025-00283-9","title":"Finding maximum common contractions between phylogenetic networks","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Phylogenetic tree; Generalization; Contraction (grammar); Set (abstract data type); Computation; Space (punctuation); Upper and lower bounds","retraction":null,"screen_n_in":null,"score":{"opus":0.01606171810145554,"gpt":0.307544356855016,"spread":0.2914826387535605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001961697,0.0002621241,0.0003431652,0.00009590396,0.0002479857,0.00002297889,0.000302017,0.0003454965,0.000003625848],"category_scores_gemma":[0.00006460033,0.0002682913,0.0002246495,0.0001458217,0.0001644557,6.12256e-7,0.0001985321,0.000121058,0.000002752554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002011375,"about_ca_system_score_gemma":0.00006282303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003013747,"about_ca_topic_score_gemma":0.0000229276,"domain_scores_codex":[0.9984948,0.00008311067,0.0003342884,0.0005470833,0.00004393387,0.0004968042],"domain_scores_gemma":[0.999223,0.00006309067,0.0001041254,0.0004252026,0.0001113455,0.00007322809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007672521,0.00007980689,0.03276018,0.00002480252,0.001080162,0.00000332999,0.00001578987,0.001041275,0.8907186,0.004063753,0.00105846,0.06907711],"study_design_scores_gemma":[0.005567741,0.002312491,0.05760223,0.00005621793,0.0008604285,0.00003360676,0.0001614838,0.002965059,0.4384622,0.0488451,0.4413112,0.001822302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4828696,0.006436759,0.5075736,0.0004567372,0.00075727,0.0006948644,0.000163965,0.00001474267,0.001032456],"genre_scores_gemma":[0.9913281,0.0002876027,0.006495638,0.0006793395,0.0003234111,0.0001946511,0.0004074322,0.00003243485,0.0002513622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5084586,"threshold_uncertainty_score":0.9999769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413110219","doi":"10.1186/s13015-025-00281-x","title":"b-move: faster lossless approximate pattern matching in a run-length compressed index","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Institutes of Health; National Human Genome Research Institute; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Computer science; Search engine indexing; Lossless compression; Index (typography); RefSeq; Memory footprint; Pattern matching; Scalability; Matching (statistics); Overhead (engineering); Theoretical computer science; Data mining; Genome; Algorithm; Data compression; Information retrieval; Mathematics; Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.01169109429062735,"gpt":0.2933725954004427,"spread":0.2816815011098153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003410973,0.0003065774,0.0004346793,0.0003348143,0.0001317546,0.0001362453,0.001382478,0.0002470367,0.000006241036],"category_scores_gemma":[0.00002521777,0.0002763464,0.0001303417,0.0004290625,0.00008400528,0.000247281,0.0009954813,0.0002764137,0.000008537359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000052616,"about_ca_system_score_gemma":0.00007818412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002742516,"about_ca_topic_score_gemma":0.0000176527,"domain_scores_codex":[0.9977434,0.0001523656,0.0004660756,0.0008649936,0.0001407543,0.0006324051],"domain_scores_gemma":[0.9986802,0.0001467182,0.0001327214,0.0008682613,0.00008966406,0.00008245144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000603039,0.0004292211,0.002707984,0.0001725552,0.0001653884,0.0001295507,0.000471504,0.0007825762,0.01983031,0.06669345,0.0004152675,0.9081419],"study_design_scores_gemma":[0.003324723,0.0001633112,0.003180438,0.000183751,0.00001877577,0.00002300291,0.00006689037,0.8855392,0.0103363,0.08923618,0.007263219,0.0006642254],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01212475,0.0004305852,0.9850541,0.0006373432,0.0007179197,0.0005822739,0.00005941793,0.000123756,0.0002698963],"genre_scores_gemma":[0.8565545,0.00003164659,0.1402106,0.002471876,0.00008137805,0.0003016635,0.0001926424,0.00003489555,0.0001208013],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9074777,"threshold_uncertainty_score":0.9999689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403127906","doi":"10.1186/s13015-024-00267-1","title":"New generalized metric based on branch length distance to compare B cell lineage trees","year":2024,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Chronic Lymphocytic Leukemia Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Université de Sherbrooke","keywords":"Metric (unit); Computer science; Lineage (genetic); Combinatorics; Mathematics; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02388740729964758,"gpt":0.3531649598430179,"spread":0.3292775525433703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002677064,0.0002840509,0.0005067508,0.0004804539,0.00005831883,0.00004007458,0.0002570598,0.0001443833,0.0001366066],"category_scores_gemma":[0.000204086,0.0002307049,0.0002851397,0.0009239712,0.00006575566,0.00002118638,0.00006622593,0.0002222078,0.0001431616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002033634,"about_ca_system_score_gemma":0.002454268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004770571,"about_ca_topic_score_gemma":0.00004219258,"domain_scores_codex":[0.9979219,0.00008948984,0.0003305154,0.0007466302,0.0002818936,0.0006296035],"domain_scores_gemma":[0.9985077,0.0003786387,0.00003430361,0.0005893447,0.0001071733,0.0003828607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005404469,0.001222878,0.0002964691,0.002484004,0.00142668,0.003119164,0.0006117457,0.008526041,0.4147099,0.02650542,0.1176803,0.4180129],"study_design_scores_gemma":[0.01656383,0.002065543,0.00006355219,0.0001708768,0.0001780473,0.00005366309,0.00001389652,0.4244219,0.2428478,0.0003907685,0.3127909,0.0004392403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03055422,0.005550264,0.9578426,0.002213422,0.0006388261,0.00152907,0.0001714455,0.0002083892,0.001291706],"genre_scores_gemma":[0.9234837,0.00006860625,0.0684811,0.002409552,0.0005935203,0.000203516,0.0005608419,0.0001087334,0.004090481],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8929294,"threshold_uncertainty_score":0.9407872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982419655","doi":"10.1186/s13015-020-00175-0","title":"Reconstruction of time-consistent species trees","year":2020,"lang":"en","type":"preprint","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Gene duplication; Event (particle physics); Horizontal gene transfer; Tree (set theory); Gene; Biology; Tree of life (biology); Evolutionary biology; Genetic algorithm; Construct (python library); Phylogenetics; Gene family; Phylogenetic tree; Computational biology; Genetics; Mathematics; Genome; Combinatorics; Computer science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02409890680831704,"gpt":0.2661840530394918,"spread":0.2420851462311747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001361536,0.0003585734,0.0005892924,0.00007180036,0.00005693002,0.00001292803,0.0003505377,0.0005356172,0.00001278041],"category_scores_gemma":[0.0001289271,0.0003595303,0.0005018903,0.00005145714,0.0003056821,3.213727e-7,0.0006899995,0.0001495974,0.000004455711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001592546,"about_ca_system_score_gemma":0.0001450197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000262373,"about_ca_topic_score_gemma":0.00001095731,"domain_scores_codex":[0.9982958,0.00008423754,0.000478513,0.0007756104,0.00007137271,0.0002945046],"domain_scores_gemma":[0.9988101,0.00002089699,0.0003454114,0.000513387,0.0002310734,0.00007919392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000641927,0.00003374521,0.0003311212,0.00007044486,0.0007199514,0.000001486503,0.00003045272,0.0001434392,0.9874586,0.0004706552,0.0004410356,0.01023488],"study_design_scores_gemma":[0.001064115,0.001532744,0.001333629,0.00004942183,0.0003402405,0.00003776843,0.00008208515,0.0007576519,0.9475589,0.01548837,0.03095133,0.0008037516],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8797195,0.01219051,0.09852935,0.001137428,0.002150351,0.001796729,0.002518954,0.0000235478,0.001933628],"genre_scores_gemma":[0.9233871,0.001949158,0.07045604,0.0003797099,0.0009407984,0.0002979673,0.001997783,0.0001078784,0.0004835949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04366757,"threshold_uncertainty_score":0.9998857,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388490419","doi":"10.1186/s13015-023-00240-4","title":"Relative timing information and orthology in evolutionary scenarios","year":2023,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Stockholms Universitet; Deutsche Forschungsgemeinschaft","keywords":"Extant taxon; Combinatorics; Vertex (graph theory); Graph; Time complexity; Computer science; Biology; Mathematics; Theoretical computer science; Discrete mathematics; Evolutionary biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01593339747570286,"gpt":0.2869197491809849,"spread":0.270986351705282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003234621,0.0001740971,0.0001838937,0.0002808891,0.00007894129,0.00001158979,0.000133416,0.0002889537,0.000005286301],"category_scores_gemma":[0.0001859717,0.0001822948,0.00007231886,0.0002718244,0.0001315779,0.00001630655,0.0001861652,0.0001022757,0.00003210838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002390541,"about_ca_system_score_gemma":0.00006339372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002750144,"about_ca_topic_score_gemma":0.00001299127,"domain_scores_codex":[0.998805,0.00008135899,0.0002926102,0.0003491092,0.00006410106,0.0004077752],"domain_scores_gemma":[0.999518,0.00003228022,0.00008863577,0.0002121421,0.00008841758,0.00006056775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003674256,0.0001460597,0.03314611,0.0001649308,0.0005223102,0.00006424625,0.0009610136,0.001682649,0.782557,0.01520867,0.002347388,0.1628322],"study_design_scores_gemma":[0.02165796,0.00818051,0.1393276,0.000145477,0.0002976772,0.0006244197,0.002494238,0.08174808,0.08400148,0.07040077,0.5866662,0.004455674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8690407,0.001339854,0.1262583,0.001058175,0.0003945296,0.001182485,0.0001349602,0.00007914993,0.000511809],"genre_scores_gemma":[0.9533151,0.0006451978,0.04038489,0.0006632029,0.0001653633,0.0004951426,0.003970257,0.00005294961,0.0003078724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6985555,"threshold_uncertainty_score":0.7433764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385397331","doi":"10.1186/s13015-023-00231-5","title":"On the complexity of non-binary tree reconciliation with endosymbiotic gene transfer","year":2023,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Legume Nitrogen Fixing Symbiosis","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Binary number; Tree (set theory); Genome; Gene; Gene duplication; Binary tree; Biology; Genetics; Computational biology; Computer science; Algorithm; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.04071512233507958,"gpt":0.253661973143377,"spread":0.2129468508082974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000262356,0.0001434741,0.0002022017,0.0000218974,0.0001267955,0.000008574276,0.0002602795,0.0001154403,0.00005058567],"category_scores_gemma":[0.00004974638,0.00004804333,0.0001381301,0.0004058878,0.0002550492,0.00002039266,0.00002767609,0.0000820659,0.00002287275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001785927,"about_ca_system_score_gemma":0.00001095486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001159818,"about_ca_topic_score_gemma":0.0000830461,"domain_scores_codex":[0.9990228,0.000100532,0.0001872489,0.0002987582,0.0001052477,0.0002853921],"domain_scores_gemma":[0.9993807,0.0003423062,0.00005162977,0.0001030337,0.00008260367,0.00003974347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006438886,0.00004341475,0.0002393885,0.000004678665,0.00006082371,0.000003298503,0.00003604634,0.000002187922,0.9855954,0.004294415,0.0001026595,0.0095533],"study_design_scores_gemma":[0.0004771861,0.002537924,0.01871366,0.00001503184,0.00004362388,0.000007035255,0.00007945777,0.001036928,0.9655238,0.01114801,0.0002118377,0.0002055454],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951038,0.00002468651,0.0004721853,0.003422954,0.00008822572,0.0005134789,0.0002016163,0.00005632808,0.0001166947],"genre_scores_gemma":[0.9983745,0.000004885998,0.0007124404,0.0003605402,0.00005094841,0.00007712017,0.0003746531,0.000002641187,0.00004225451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02007164,"threshold_uncertainty_score":0.195915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413308490","doi":"10.1186/s13015-025-00284-8","title":"The path-label reconciliation (PLR) dissimilarity measure for gene trees","year":2025,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Ciencia y Tecnología; Université de Sherbrooke","keywords":"Metric (unit); Computer science; Measure (data warehouse); Normalization (sociology); Tree (set theory); Path (computing); Set (abstract data type); Data mining; Artificial intelligence; Algorithm; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01841881038842055,"gpt":0.2945175570745436,"spread":0.2760987466861231,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004300634,0.0002143396,0.0002156659,0.00003265615,0.0004221765,0.00002802725,0.0003062524,0.0002572694,6.614154e-7],"category_scores_gemma":[0.0003579843,0.0001661081,0.0002021656,0.0000798931,0.0001480097,6.971364e-7,0.0001206963,0.00006210869,6.949689e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002133204,"about_ca_system_score_gemma":0.0001190362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001512578,"about_ca_topic_score_gemma":0.00009092964,"domain_scores_codex":[0.9987087,0.0000734186,0.0002863141,0.0004897491,0.00005118767,0.0003906499],"domain_scores_gemma":[0.9990457,0.00009828805,0.0001019844,0.0004206504,0.0002875933,0.00004576962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001684578,0.0000480676,0.0005996453,0.00001454833,0.0003933374,3.213998e-7,0.00001779712,0.00001671026,0.9231614,0.004747306,0.0016353,0.06919708],"study_design_scores_gemma":[0.002906386,0.001149152,0.002147966,0.00001255357,0.000190194,0.000005092665,0.00008755674,0.001465076,0.6043875,0.02929522,0.3578766,0.0004766708],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2960238,0.02323178,0.6716818,0.00384703,0.00173316,0.002227118,0.0007765973,0.00001917866,0.0004596079],"genre_scores_gemma":[0.9573615,0.001245302,0.03602419,0.001413755,0.0004684817,0.001472643,0.0007915961,0.00005569034,0.001166902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6613376,"threshold_uncertainty_score":0.6773692,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}