{"id":"https://openalex.org/W7203868091","doi":"https://doi.org/10.5281/zenodo.22030000","title":"Synthetic Genomes Benchmark","display_name":"Synthetic Genomes Benchmark","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203868091","doi":"https://doi.org/10.5281/zenodo.22030000"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22030000","doi":"https://doi.org/10.5281/zenodo.22030000","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22030000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"volume":null,"type":"software","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22030000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123039011","display_name":"Alexandros Tzanakakis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tzanakakis, Alexandros","raw_affiliation_strings":["Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute, Austin, TX 78723, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute, Austin, TX 78723, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091718368","display_name":"Ioannis Mouratidis","orcid":"https://orcid.org/0000-0002-1025-8780","observed_orcids":["https://orcid.org/0000-0002-1025-8780"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mouratidis, Ioannis","raw_affiliation_strings":["Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute, Austin, TX 78723, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute, Austin, TX 78723, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055883774","display_name":"Ilias Georgakopoulos\u2010Soares","orcid":"https://orcid.org/0000-0003-3641-1488","observed_orcids":["https://orcid.org/0000-0003-3641-1488"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgakopoulos-Soares, Ilias","raw_affiliation_strings":["Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute, Austin, TX 78723, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Pharmacology and Toxicology, College of Pharmacy, The University of Texas at Austin, Dell Pediatric Research Institute, Austin, TX 78723, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3082999885082245,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3082999885082245,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.27320000529289246,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.18330000340938568,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genomic-language-models","display_name":"genomic language models","score":0.7720000147819519},{"id":"https://openalex.org/keywords/jensen-shannon-divergence","display_name":"Jensen-Shannon divergence","score":0.7620000243186951},{"id":"https://openalex.org/keywords/chaos-game-representation","display_name":"chaos game representation","score":0.8029999732971191},{"id":"https://openalex.org/keywords/gc-content","display_name":"GC content","score":0.6660000085830688},{"id":"https://openalex.org/keywords/cpg-content","display_name":"CpG content","score":0.7540000081062317},{"id":"https://openalex.org/keywords/transcription-factor-binding-sites","display_name":"transcription factor binding sites","score":0.7929999828338623},{"id":"https://openalex.org/keywords/z-dna","display_name":"Z-DNA","score":0.7670000195503235},{"id":"https://openalex.org/keywords/g-quadruplex","display_name":"G-quadruplex","score":0.9929999709129333},{"id":"https://openalex.org/keywords/microsatellite-markers","display_name":"microsatellite markers","score":0.8700000047683716}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6248999834060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205999851226807},{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5224999785423279},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4693000018596649},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4311999976634979},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.41620001196861267},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.35199999809265137},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C140173407","wikidata":"https://www.wikidata.org/wiki/Q1138358","display_name":"CpG site","level":5,"score":0.3431999981403351},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.3427000045776367},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3019999861717224},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.28780001401901245},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.27959999442100525},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22030000","doi":"https://doi.org/10.5281/zenodo.22030000","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22030000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.22030001","doi":"https://doi.org/10.5281/zenodo.22030001","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22030001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22030000","doi":"https://doi.org/10.5281/zenodo.22030000","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22030000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214726783","https://openalex.org/W7124713317","https://openalex.org/W7126067746","https://openalex.org/W7123286964","https://openalex.org/W6979241630","https://openalex.org/W4407424297","https://openalex.org/W7106138964","https://openalex.org/W4400151950","https://openalex.org/W6893984688","https://openalex.org/W4388962805"],"abstract_inverted_index":{"Benchmarks":[0],"for":[1,15,141],"evaluating":[2],"generated":[3,36],"DNA":[4,124],"against":[5],"matched":[6,23,85],"natural":[7,29,90],"sequence,":[8],"accompanying":[9],"Limitations":[10],"of":[11,25],"genomic":[12,71],"language":[13],"models":[14,97],"realistic":[16],"sequence":[17,35],"generation.":[18],"The":[19],"suite":[20],"works":[21],"on":[22],"pairs":[24],"windows,":[26],"with":[27,109],"each":[28,84],"locus":[30],"paired":[31],"to":[32,94,99],"the":[33,68,80,112,157,161],"synthetic":[34,92],"from":[37,111],"it,":[38],"and":[39,42,58,91,98,122,130,150,156,164],"measures:":[40],"Composition":[41],"divergence:":[43],"GC,":[44],"CpG":[45],"observed/expected,":[46],"homopolymer":[47],"content,":[48],"low":[49],"complexity,":[50],"entropy,":[51],"canonical":[52],"nullomer":[53],"fraction,":[54],"k-mer":[55,96],"Jensen-Shannon":[56],"divergence":[57,66],"chaos":[59],"game":[60],"representation":[61],"distance.":[62],"Calibration:":[63],"whether":[64],"that":[65],"exceeds":[67],"variation":[69],"real":[70],"windows":[72],"already":[73],"show":[74],"among":[75],"themselves,":[76],"tested":[77],"by":[78],"permuting":[79],"natural/synthetic":[81],"label":[82],"within":[83],"pair.":[86],"Detectability:":[87],"how":[88,106],"separable":[89],"are":[93,138],"shallow":[95],"a":[100],"dilated":[101],"1D":[102],"ResNet.":[103],"Context":[104],"decay:":[105],"detectability":[107],"grows":[108],"distance":[110],"conditioning":[113],"prompt.":[114],"Biological":[115],"structure:":[116],"transcription":[117],"factor":[118],"binding":[119],"site":[120],"abundance":[121],"non-B":[123],"motifs":[125],"(Z-DNA,":[126],"G-quadruplexes,":[127],"inverted,":[128],"direct":[129],"mirror":[131],"repeats,":[132],"short":[133],"tandem":[134],"repeats).":[135],"Also":[136],"included":[137],"reusable":[139],"interventions":[140],"constraining":[142],"generation":[143],"at":[144,151],"training":[145],"time":[146,153],"(structural":[147],"auxiliary":[148],"losses)":[149],"sampling":[152],"(logit":[154],"constraints),":[155],"archival":[158],"scripts":[159],"behind":[160],"paper's":[162],"figures":[163],"statistics.":[165]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-22T00:00:00"}