{"id":"https://openalex.org/W7225460644","doi":"https://doi.org/10.5281/zenodo.24042980","title":"A practical and reproducible workflow for validation and characterization of animal mitochondrial genomes: from raw sequencing reads and GenBank records to publication-ready mitogenomic analyses","display_name":"A practical and reproducible workflow for validation and characterization of animal mitochondrial genomes: from raw sequencing reads and GenBank records to publication-ready mitogenomic analyses","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225460644","doi":"https://doi.org/10.5281/zenodo.24042980"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24042980","doi":"https://doi.org/10.5281/zenodo.24042980","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042980","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24042980","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121119540","display_name":"Matheus Arthur L\u00facio da Rocha","orcid":"https://orcid.org/0000-0003-3742-5101","observed_orcids":["https://orcid.org/0000-0003-3742-5101"]},"institutions":[{"id":"https://openalex.org/I35046152","display_name":"Universidade Federal do Rio Grande do Norte","ror":"https://ror.org/04wn09761","country_code":"BR","type":"education","lineage":["https://openalex.org/I35046152"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"DA ROCHA, MATHEUS","raw_affiliation_strings":["Universidade Federal do Rio Grande do Norte"],"raw_orcid":"https://orcid.org/0000-0003-3742-5101","affiliations":[{"raw_affiliation_string":"Universidade Federal do Rio Grande do Norte","institution_ids":["https://openalex.org/I35046152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5121119540"],"corresponding_institution_ids":["https://openalex.org/I35046152"],"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":1.0,"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":1.0,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10012","display_name":"Genetic diversity and population structure","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/mitogenome-annotation","display_name":"mitogenome annotation","score":0.7919999957084656},{"id":"https://openalex.org/keywords/circularization","display_name":"circularization","score":0.37599998712539673},{"id":"https://openalex.org/keywords/open-reading-frames","display_name":"open reading frames","score":0.7179999947547913},{"id":"https://openalex.org/keywords/gene-order","display_name":"gene order","score":0.5979999899864197},{"id":"https://openalex.org/keywords/intergenic-spacer","display_name":"intergenic spacer","score":0.8299999833106995},{"id":"https://openalex.org/keywords/codon-usage","display_name":"codon usage","score":0.7860000133514404},{"id":"https://openalex.org/keywords/relative-synonymous-codon-usage","display_name":"relative synonymous codon usage","score":0.9110000133514404},{"id":"https://openalex.org/keywords/nucleotide-composition","display_name":"nucleotide composition","score":0.6119999885559082},{"id":"https://openalex.org/keywords/reproducible-workflows","display_name":"reproducible workflows","score":0.4440000057220459},{"id":"https://openalex.org/keywords/genbank-records","display_name":"GenBank records","score":0.6790000200271606}],"concepts":[{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.8034999966621399},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.734499990940094},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6071000099182129},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5354999899864197},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4708000123500824},{"id":"https://openalex.org/C24586158","wikidata":"https://www.wikidata.org/wiki/Q27075","display_name":"Mitochondrial DNA","level":3,"score":0.4296000003814697},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.4268999993801117},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4189999997615814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3977999985218048},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.38589999079704285},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.3528999984264374},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C87253356","wikidata":"https://www.wikidata.org/wiki/Q1106472","display_name":"Codon usage bias","level":4,"score":0.3328999876976013},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.3244999945163727},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.3147999942302704},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.30869999527931213},{"id":"https://openalex.org/C195139083","wikidata":"https://www.wikidata.org/wiki/Q3463539","display_name":"Intergenic region","level":4,"score":0.30230000615119934},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.2980000078678131},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.29739999771118164},{"id":"https://openalex.org/C170748874","wikidata":"https://www.wikidata.org/wiki/Q21117977","display_name":"Proofreading","level":4,"score":0.29089999198913574},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C20580545","wikidata":"https://www.wikidata.org/wiki/Q28354","display_name":"Stop codon","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C153957851","wikidata":"https://www.wikidata.org/wiki/Q201448","display_name":"Transfer RNA","level":4,"score":0.28200000524520874},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.27959999442100525},{"id":"https://openalex.org/C67905577","wikidata":"https://www.wikidata.org/wiki/Q215980","display_name":"Ribosomal RNA","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.27459999918937683},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.2563000023365021},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C2779462738","wikidata":"https://www.wikidata.org/wiki/Q17146409","display_name":"Realisation","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24042980","doi":"https://doi.org/10.5281/zenodo.24042980","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042980","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24042981","doi":"https://doi.org/10.5281/zenodo.24042981","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042981","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24042980","doi":"https://doi.org/10.5281/zenodo.24042980","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042980","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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/W2888282377","https://openalex.org/W1989083100","https://openalex.org/W2950509696","https://openalex.org/W2901560297","https://openalex.org/W7223455650","https://openalex.org/W1495148515","https://openalex.org/W4407891887","https://openalex.org/W4388541926","https://openalex.org/W3130782122","https://openalex.org/W2051890517"],"abstract_inverted_index":{"Mitochondrial":[0],"genomes":[1],"are":[2,25,275],"widely":[3],"used":[4],"in":[5,219,277],"zoology":[6],"for":[7,37,71,183,251,261],"taxonomy,":[8],"systematics,":[9],"phylogeography,":[10],"biodiversity":[11],"assessment":[12],"and":[13,22,29,45,115,134,155,177,216,231,238,256,271],"comparative":[14],"genomics,":[15],"yet":[16],"the":[17,220,272],"steps":[18],"required":[19],"to":[20,80,93],"validate":[21],"characterize":[23],"them":[24],"scattered":[26],"across":[27],"programs":[28],"methodological":[30],"traditions.":[31],"This":[32],"is":[33,69,210,244],"a":[34,65,189,196,232,258],"particular":[35],"problem":[36],"researchers":[38,252],"beginning":[39,253],"mitogenomic":[40,254],"studies,":[41],"because":[42],"automated":[43],"assemblies":[44],"annotations":[46],"may":[47],"contain":[48],"incomplete":[49],"genes,":[50],"incorrect":[51],"gene":[52,138,150,190,197],"boundaries,":[53],"undetected":[54],"tRNAs,":[55],"unresolved":[56],"repetitive":[57],"regions":[58],"or":[59,92,201,240],"unsupported":[60],"claims":[61],"of":[62,122,130,206,228,265],"circularization.":[63,207],"Here,":[64],"practical,":[66],"step-by-step":[67],"workflow":[68,107],"presented":[70],"animal":[72,266],"mitochondrial":[73,267],"genomes.":[74,268],"It":[75,158,243],"can":[76,170],"be":[77,171],"applied":[78],"either":[79],"raw":[81],"paired-end":[82],"sequencing":[83,165],"reads":[84,166],"together":[85],"with":[86,173],"an":[87,247],"assembled":[88,95],"mitogenome":[89],"(Workflow":[90,104],"A)":[91],"previously":[94],"mitogenomes":[96],"obtained":[97],"from":[98,167],"public":[99],"databases":[100],"such":[101,186],"as":[102,187,195,204,246,257],"GenBank":[103],"B).":[105],"The":[106,223],"integrates":[108],"read":[109,112],"quality":[110],"control,":[111],"mapping,":[113],"genome-wide":[114],"gene-level":[116],"coverage":[117],"assessment,":[118],"annotation":[119,239],"auditing,":[120],"validation":[121],"open":[123],"reading":[124],"frames,":[125],"tRNA":[126],"reassessment,":[127],"direct":[128],"testing":[129],"circularization,":[131],"nucleotide":[132],"composition":[133],"compositional":[135],"skews,":[136],"protein-coding":[137],"characterization,":[139,149],"codon":[140,144],"usage,":[141,145],"relative":[142],"synonymous":[143],"amino-acid":[146],"composition,":[147],"rRNA":[148],"order,":[151],"intergenic":[152],"spacers,":[153],"overlaps":[154],"non-coding":[156],"regions.":[157],"explicitly":[159],"separates":[160],"analyses":[161],"that":[162,169,191,198],"require":[163],"original":[164],"those":[168],"performed":[172],"annotated":[174],"sequences":[175],"alone,":[176],"it":[178],"provides":[179],"conservative":[180],"interpretation":[181],"rules":[182],"common":[184],"pitfalls,":[185],"treating":[188],"was":[192,199],"not":[193],"detected":[194],"lost,":[200],"coding":[202],"completeness":[203],"proof":[205],"Every":[208],"step":[209],"accompanied":[211],"by":[212],"generalized,":[213],"commented":[214],"command-line":[215],"Python":[217],"examples":[218],"Supplementary":[221],"Material.":[222],"framework":[224,260],"emphasizes":[225],"traceability,":[226],"preservation":[227],"intermediate":[229],"outputs":[230],"clear":[233],"distinction":[234],"between":[235],"biological":[236],"variation":[237],"assembly":[241],"artifacts.":[242],"intended":[245],"accessible":[248],"entry":[249],"point":[250],"studies":[255],"reproducible":[259],"producing":[262],"publication-ready":[263],"descriptions":[264],"\u201cSupplementary":[269],"Material":[270],"script":[273],"06b_junction_spanning_reads.py":[274],"included":[276],"this":[278],"record.\u201d":[279]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}