{"id":"https://openalex.org/W7225269168","doi":"https://doi.org/10.64898/2026.11.02.763757","title":"NBDC Data Tools: Building Analysis-ready Datasets From ABCD and HBCD Releases in R and Python","display_name":"NBDC Data Tools: Building Analysis-ready Datasets From ABCD and HBCD Releases in R and Python","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225269168","doi":"https://doi.org/10.64898/2026.11.02.763757"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.02.763757","doi":"https://doi.org/10.64898/2026.11.02.763757","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.02.763757","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.02.763757.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.02.763757.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100350657","display_name":"Le Zhang","orcid":"https://orcid.org/0009-0008-0205-2150","observed_orcids":["https://orcid.org/0009-0008-0205-2150"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":"https://orcid.org/0009-0008-0205-2150","affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012503272","display_name":"Biplabendu Das","orcid":"https://orcid.org/0000-0003-0855-262X","observed_orcids":["https://orcid.org/0000-0003-0855-262X"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biplabendu Das","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":"https://orcid.org/0000-0003-0855-262X","affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058284418","display_name":"O. Celhay","orcid":"https://orcid.org/0000-0002-2971-9110","observed_orcids":["https://orcid.org/0000-0002-2971-9110"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Celhay","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":"https://orcid.org/0000-0002-2971-9110","affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012874498","display_name":"Calen J. Smith","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calen J Smith","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067347169","display_name":"Laura R. Ziemer","orcid":"https://orcid.org/0000-0003-0026-3823","observed_orcids":["https://orcid.org/0000-0003-0026-3823"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura R Ziemer","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":"https://orcid.org/0000-0003-0026-3823","affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087626511","display_name":"Anders Martin Dale","orcid":"https://orcid.org/0000-0002-6126-2966","observed_orcids":["https://orcid.org/0000-0002-6126-2966"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anders M Dale","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":"https://orcid.org/0000-0002-6126-2966","affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036285254","display_name":"Janosch Linkersd\u00f6rfer","orcid":"https://orcid.org/0000-0002-1577-1233","observed_orcids":["https://orcid.org/0000-0002-1577-1233"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Janosch Linkersd\u00f6rfer","raw_affiliation_strings":["J. Craig Venter Institute"],"raw_orcid":"https://orcid.org/0000-0002-1577-1233","affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute","institution_ids":["https://openalex.org/I1301553790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036285254"],"corresponding_institution_ids":["https://openalex.org/I1301553790"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11937","display_name":"Research Data Management Practices","score":0.8119999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.8119999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.17419999837875366,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adolescent-brain-cognitive-development-study","display_name":"Adolescent Brain Cognitive Development Study","score":0.9559999704360962},{"id":"https://openalex.org/keywords/data-preparation","display_name":"data preparation","score":0.5870000123977661},{"id":"https://openalex.org/keywords/open-source-r-package","display_name":"open-source R package","score":0.6079999804496765},{"id":"https://openalex.org/keywords/python-library","display_name":"Python library","score":0.7269999980926514},{"id":"https://openalex.org/keywords/reproducible-workflows","display_name":"reproducible workflows","score":0.6890000104904175},{"id":"https://openalex.org/keywords/metadata","display_name":"metadata","score":0.44999998807907104},{"id":"https://openalex.org/keywords/data-joining","display_name":"data joining","score":0.35899999737739563},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.41100001335144043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7825000286102295},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.652400016784668},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6179999709129333},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C11090531","wikidata":"https://www.wikidata.org/wiki/Q1361922","display_name":"NetCDF","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46320000290870667},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.44119998812675476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C98143201","wikidata":"https://www.wikidata.org/wiki/Q1147639","display_name":"Data dictionary","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C3102742","wikidata":"https://www.wikidata.org/wiki/Q6031177","display_name":"Information repository","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C91790935","wikidata":"https://www.wikidata.org/wiki/Q5358348","display_name":"Electronic data capture","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C61871575","wikidata":"https://www.wikidata.org/wiki/Q384093","display_name":"Master data","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.02.763757","doi":"https://doi.org/10.64898/2026.11.02.763757","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.02.763757","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.02.763757.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.02.763757","doi":"https://doi.org/10.64898/2026.11.02.763757","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.02.763757","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/04/2026.11.02.763757.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.4043000042438507,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338078","display_name":"National Bioscience Database Center","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225269168.pdf","grobid_xml":"https://content.openalex.org/works/W7225269168.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2302501749","https://openalex.org/W2507622755","https://openalex.org/W2765637225","https://openalex.org/W2790406046","https://openalex.org/W2951438521","https://openalex.org/W4280652567","https://openalex.org/W4399771647","https://openalex.org/W4402328390","https://openalex.org/W4410472313","https://openalex.org/W4414157899","https://openalex.org/W6949656255","https://openalex.org/W7163912493"],"related_works":["https://openalex.org/W3180060468","https://openalex.org/W6893252086","https://openalex.org/W4414157899","https://openalex.org/W3214973009","https://openalex.org/W2949454877","https://openalex.org/W4403164100","https://openalex.org/W2968308266","https://openalex.org/W175941868","https://openalex.org/W3150246466","https://openalex.org/W7166695175"],"abstract_inverted_index":{"act":[0],"The":[1,32,110,159],"NIH":[2],"Brain":[3,18,26],"Development":[4,20,29],"Cohorts":[5],"(NBDC)":[6],"Data":[7,81,223,233],"Hub":[8,234],"provides":[9,130],"access":[10,244],"to":[11,170,245],"large-scale":[12],"longitudinal":[13],"datasets,":[14],"including":[15],"the":[16,24,101,116,126,131,148,150,153,163,168,172,178,197,207,226,231],"Adolescent":[17],"Cognitive":[19],"(ABCD)":[21],"Study\u00ae":[22],"and":[23,27,66,72,108,125,138,152,180,188,218],"HEALthy":[25],"Child":[28],"(HBCD)":[30],"Study.":[31],"studies":[33,169],"release":[34,132,209],"their":[35],"tabulated":[36],"data":[37,64,91,184,228,243,247],"as":[38,193],"hundreds":[39],"of":[40,44,46,85,230],"tables":[41,156,176],"with":[42,216],"tens":[43],"thousands":[45],"variables.":[47],"Turning":[48],"these":[49],"files":[50],"into":[51],"a":[52,55,83,142,201,237],"dataset":[53,106,143,198],"for":[54,74,88,105,135,248],"particular":[56],"analysis":[57,67],"poses":[58],"substantial":[59],"informatics":[60],"challenges,":[61],"especially":[62],"when":[63],"preparation":[65],"workflows":[68],"must":[69],"be":[70,213],"reproducible":[71],"reusable":[73],"new":[75],"releases.":[76],"We":[77],"therefore":[78],"developed":[79],"NBDC":[80,90,222,232],"Tools,":[82],"suite":[84],"open-source":[86],"packages":[87],"preparing":[89],"in":[92,123,144,220],"local":[93],"or":[94,119,155],"other":[95],"approved":[96,242],"computing":[97],"environments.":[98],"NBDCtools":[99,137],"is":[100,200],"core":[102],"R":[103,117,127],"package":[104,112,128],"construction":[107],"processing.":[109],"Python":[111],"nbdctools":[113],"either":[114],"calls":[115],"workflow":[118],"assembles":[120],"datasets":[121],"natively":[122],"Python,":[124],"NBDCtoolsData":[129],"metadata":[133,165],"support":[134],"both":[136],"nbdctools.":[139],"Users":[140],"define":[141],"code":[145],"by":[146,167,235],"naming":[147],"study,":[149],"release,":[151],"variables":[154],"they":[157],"need.":[158],"software":[160],"then":[161],"uses":[162],"standardized":[164],"released":[166],"locate":[171],"relevant":[173],"files,":[174,210],"join":[175],"on":[177,206],"participant":[179],"session":[181],"identifiers,":[182],"convert":[183],"types,":[185],"attach":[186],"labels,":[187],"optionally":[189],"recode":[190],"non-response":[191],"codes":[192],"missing":[194],"values.":[195],"Because":[196],"definition":[199],"short":[202],"script":[203],"that":[204],"runs":[205],"original":[208],"it":[211],"can":[212],"rerun,":[214],"shared":[215],"collaborators,":[217],"reported":[219],"publications.":[221],"Tools":[224],"complements":[225],"web-based":[227],"platforms":[229],"providing":[236],"reproducible,":[238],"scriptable":[239],"path":[240],"from":[241],"analysis-ready":[246],"statistical":[249],"analysis.":[250]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}
