{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:33:57Z","timestamp":1772138037466,"version":"3.50.1"},"reference-count":12,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2020,4,24]],"date-time":"2020-04-24T00:00:00Z","timestamp":1587686400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U24-AG041689"],"award-info":[{"award-number":["U24-AG041689"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U54-AG052427"],"award-info":[{"award-number":["U54-AG052427"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U01-AG032984"],"award-info":[{"award-number":["U01-AG032984"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["T32-AG00255"],"award-info":[{"award-number":["T32-AG00255"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Biomarkers Across Neurodegenerative Diseases","award":["18062"],"award-info":[{"award-number":["18062"]}]},{"name":"Michael J Fox Foundation"},{"DOI":"10.13039\/100000957","name":"Alzheimer's Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000957","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alzheimer's Research UK"},{"DOI":"10.13039\/100012479","name":"Weston Brain institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>We report Spark-based INFERence of the molecular mechanisms of NOn-coding genetic variants (SparkINFERNO), a scalable bioinformatics pipeline characterizing non-coding genome-wide association study (GWAS) association findings. SparkINFERNO prioritizes causal variants underlying GWAS association signals and reports relevant regulatory elements, tissue contexts and plausible target genes they affect. To achieve this, the SparkINFERNO algorithm integrates GWAS summary statistics with large-scale collection of functional genomics datasets spanning enhancer activity, transcription factor binding, expression quantitative trait loci and other functional datasets across more than 400 tissues and cell types. Scalability is achieved by an underlying API implemented using Apache Spark and Giggle-based genomic indexing. We evaluated SparkINFERNO on large GWASs and show that SparkINFERNO is more than 60 times efficient and scales with data size and amount of computational resources.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>SparkINFERNO runs on clusters or a single server with Apache Spark environment, and is available at https:\/\/bitbucket.org\/wanglab-upenn\/SparkINFERNO or https:\/\/hub.docker.com\/r\/wanglab\/spark-inferno.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Contact<\/jats:title>\n                    <jats:p>lswang@pennmedicine.upenn.edu<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data\u00a0are available at\u00a0Bioinformatics\u00a0online<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa246","type":"journal-article","created":{"date-parts":[[2020,4,17]],"date-time":"2020-04-17T15:11:49Z","timestamp":1587136309000},"page":"3879-3881","source":"Crossref","is-referenced-by-count":15,"title":["SparkINFERNO: a scalable high-throughput pipeline for inferring molecular mechanisms of non-coding genetic variants"],"prefix":"10.1093","volume":"36","author":[{"given":"Pavel P","family":"Kuksa","sequence":"first","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chien-Yueh","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre","family":"Amlie-Wolf","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"},{"name":"Genomics and Computational Biology Graduate Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prabhakaran","family":"Gangadharan","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6560-2876","authenticated-orcid":false,"given":"Elizabeth E","family":"Mlynarski","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Fan","family":"Chou","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han-Jen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heather","family":"Issen","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily","family":"Greenfest-Allen","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"},{"name":"Department of Genetics , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Otto","family":"Valladares","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuk Yee","family":"Leung","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-San","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine , Penn Neurodegeneration Genomics Center"},{"name":"Department of Genetics , Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,4,24]]},"reference":[{"key":"2023063011300405600_btaa246-B1","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1038\/nature24277","article-title":"Genetic effects on gene expression across human tissues","volume":"550","author":"Aguet","year":"2017","journal-title":"Nature"},{"key":"2023063011300405600_btaa246-B2","doi-asserted-by":"crossref","first-page":"8740","DOI":"10.1093\/nar\/gky686","article-title":"INFERNO: inferring the molecular mechanisms of noncoding genetic variants","volume":"46","author":"Amlie-Wolf","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023063011300405600_btaa246-B3","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1038\/nature12787","article-title":"An atlas of active enhancers across human cell types and tissues","volume":"507","author":"Andersson","year":"2014","journal-title":"Nature"},{"key":"2023063011300405600_btaa246-B4","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Bernstein","year":"2012","journal-title":"Nature"},{"key":"2023063011300405600_btaa246-B5","doi-asserted-by":"crossref","first-page":"D1005","DOI":"10.1093\/nar\/gky1120","article-title":"The NHGRI-EBI GWAS Catalog of published genome-wide association studies, targeted arrays and summary statistics 2019","volume":"47","author":"Buniello","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023063011300405600_btaa246-B6","doi-asserted-by":"crossref","first-page":"e1004383","DOI":"10.1371\/journal.pgen.1004383","article-title":"Bayesian test for colocalisation between pairs of genetic association studies using summary statistics","volume":"10","author":"Giambartolomei","year":"2014","journal-title":"PLoS Genet"},{"key":"2023063011300405600_btaa246-B7","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/nature14248","article-title":"Integrative analysis of 111 reference human epigenomes","volume":"518","author":"Kundaje","year":"2015","journal-title":"Nature"},{"key":"2023063011300405600_btaa246-B8","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1038\/ng.2802","article-title":"Meta-analysis of 74,046 individuals identifies 11 new susceptibility loci for Alzheimer\u2019s disease","volume":"45","author":"Lambert","year":"2013","journal-title":"Nat. Genet"},{"key":"2023063011300405600_btaa246-B9","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1038\/nmeth.4556","article-title":"GIGGLE: a search engine for large-scale integrated genome analysis","volume":"15","author":"Layer","year":"2018","journal-title":"Nat. Methods"},{"key":"2023063011300405600_btaa246-B10","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1038\/ng.3359","article-title":"Association analyses identify 38 susceptibility loci for inflammatory bowel disease and highlight shared genetic risk across populations","volume":"47","author":"Liu","year":"2015","journal-title":"Nat. Genet"},{"key":"2023063011300405600_btaa246-B11","doi-asserted-by":"crossref","first-page":"1826","DOI":"10.1038\/s41467-017-01261-5","article-title":"Functional mapping and annotation of genetic associations with FUMA","volume":"8","author":"Watanabe","year":"2017","journal-title":"Nat. Commun"},{"key":"2023063011300405600_btaa246-B12","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2934664","article-title":"Apache Spark: a unified engine for big data processing","volume":"59","author":"Zaharia","year":"2016","journal-title":"Commun. ACM"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa246\/33124787\/btaa246.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/12\/3879\/50747769\/bioinformatics_36_12_3879.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/12\/3879\/50747769\/bioinformatics_36_12_3879.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T07:30:43Z","timestamp":1688110243000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/12\/3879\/5824793"}},"subtitle":[],"editor":[{"given":"Peter","family":"Robinson","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,4,24]]},"references-count":12,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa246","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.737817574.793574820","asserted-by":"object"}],"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.01.07.897579","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,6,15]]},"published":{"date-parts":[[2020,4,24]]}}}