{"id":"https://openalex.org/W2952156265","doi":"https://doi.org/10.1371/journal.pcbi.1005755","title":"Unmet needs for analyzing biological big data: A survey of 704 NSF principal investigators","display_name":"Unmet needs for analyzing biological big data: A survey of 704 NSF principal investigators","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2952156265","doi":"https://doi.org/10.1371/journal.pcbi.1005755","mag":"2952156265","pmid":"https://pubmed.ncbi.nlm.nih.gov/29049281"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1005755","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005755","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005755&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005755&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061740051","display_name":"Lindsay Barone","orcid":"https://orcid.org/0000-0002-6976-918X"},"institutions":[{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lindsay Barone","raw_affiliation_strings":["DNA Learning Center, Cold Spring Harbor Laboratory, Cold Spring Harbor, New York, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6976-918X","affiliations":[{"raw_affiliation_string":"DNA Learning Center, Cold Spring Harbor Laboratory, Cold Spring Harbor, New York, United States of America","institution_ids":["https://openalex.org/I2750212522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034832191","display_name":"Jason Williams","orcid":"https://orcid.org/0000-0003-3049-2010"},"institutions":[{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Williams","raw_affiliation_strings":["DNA Learning Center, Cold Spring Harbor Laboratory, Cold Spring Harbor, New York, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DNA Learning Center, Cold Spring Harbor Laboratory, Cold Spring Harbor, New York, United States of America","institution_ids":["https://openalex.org/I2750212522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054384273","display_name":"David Micklos","orcid":null},"institutions":[{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Micklos","raw_affiliation_strings":["DNA Learning Center, Cold Spring Harbor Laboratory, Cold Spring Harbor, New York, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DNA Learning Center, Cold Spring Harbor Laboratory, Cold Spring Harbor, New York, United States of America","institution_ids":["https://openalex.org/I2750212522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061740051"],"corresponding_institution_ids":["https://openalex.org/I2750212522"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":7.0939,"has_fulltext":true,"cited_by_count":158,"citation_normalized_percentile":{"value":0.9800689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"13","issue":"10","first_page":"e1005755","last_page":"e1005755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9976999759674072,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9976999759674072,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9904999732971191,"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/T13280","display_name":"Biomedical and Engineering Education","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.7158612012863159},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.612205982208252},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5803220868110657},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.5601593852043152},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5546106100082397},{"id":"https://openalex.org/keywords/data-archive","display_name":"Data archive","score":0.5266606211662292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4940686523914337},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.48781779408454895},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4157702922821045},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.19136309623718262},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1783079206943512},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16060656309127808},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15852311253547668}],"concepts":[{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.7158612012863159},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.612205982208252},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5803220868110657},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.5601593852043152},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5546106100082397},{"id":"https://openalex.org/C2778315783","wikidata":"https://www.wikidata.org/wiki/Q5227240","display_name":"Data archive","level":2,"score":0.5266606211662292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4940686523914337},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.48781779408454895},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4157702922821045},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.19136309623718262},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1783079206943512},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16060656309127808},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15852311253547668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012108","descriptor_name":"Research Personnel","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012108","descriptor_name":"Research Personnel","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012108","descriptor_name":"Research Personnel","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012108","descriptor_name":"Research Personnel","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1005755","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005755","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005755&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:29049281","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29049281","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:repository.cshl.edu:35574","is_oa":false,"landing_page_url":"https://repository.cshl.edu/id/eprint/35574/1/Barone%202017.pdf","pdf_url":"https://repository.cshl.edu/id/eprint/35574/1/Barone%202017.pdf","source":{"id":"https://openalex.org/S4306402288","display_name":"Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Paper"},{"id":"pmh:oai:pubmedcentral.nih.gov:5654259","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5654259","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:1ab703ddfc5142b9a343b2ca121b52b2","is_oa":false,"landing_page_url":"https://doaj.org/article/1ab703ddfc5142b9a343b2ca121b52b2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 13, Iss 10, p e1005755 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1005755","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1005755","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005755&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1515058201","display_name":"The iPlant Collaborative: Cyberinfrastructure for the Life Sciences","funder_award_id":"1265383","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6124298671","display_name":"PSCIC Full Proposal: The iPlant Collaborative: A Cyberinfrastructure-Centered Community for a New Plant Biology","funder_award_id":"0735191","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952156265.pdf","grobid_xml":"https://content.openalex.org/works/W2952156265.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1481355349","https://openalex.org/W1972581523","https://openalex.org/W2104846587","https://openalex.org/W2113142830","https://openalex.org/W2123179625","https://openalex.org/W2260181531","https://openalex.org/W2355436342","https://openalex.org/W2381276009","https://openalex.org/W2412625133","https://openalex.org/W2514664437","https://openalex.org/W2993222596","https://openalex.org/W4240500267","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W4283380322","https://openalex.org/W3124683630","https://openalex.org/W2782967896","https://openalex.org/W3011463519","https://openalex.org/W1906169760"],"abstract_inverted_index":{"In":[0],"a":[1,34,105,112],"2016":[2],"survey":[3],"of":[4,36,108],"704":[5],"National":[6],"Science":[7],"Foundation":[8],"(NSF)":[9],"Biological":[10],"Sciences":[11],"Directorate":[12],"principal":[13],"investigators":[14],"(BIO":[15],"PIs),":[16],"nearly":[17],"90%":[18],"indicated":[19],"they":[20],"are":[21,84],"currently":[22],"or":[23],"will":[24,100],"soon":[25],"be":[26,101],"analyzing":[27],"large":[28],"data":[29,87,89,97,114],"sets.":[30],"BIO":[31,76],"PIs":[32,77],"considered":[33],"range":[35],"computational":[37,130],"needs":[38,83],"important":[39],"to":[40,58,103,125],"their":[41,127],"work,":[42],"including":[43],"high":[44],"performance":[45],"computing":[46],"(HPC),":[47],"bioinformatics":[48],"support,":[49],"multistep":[50],"workflows,":[51],"updated":[52],"analysis":[53],"software,":[54],"and":[55,61,70,91,119,122],"the":[56,67,79],"ability":[57],"store,":[59],"share,":[60],"publish":[62],"data.":[63],"Previous":[64],"studies":[65],"in":[66,86,117,132],"United":[68],"States":[69],"Canada":[71],"emphasized":[72],"infrastructure":[73],"needs.":[74],"However,":[75],"said":[78],"most":[80],"pressing":[81],"unmet":[82],"training":[85,131],"integration,":[88],"management,":[90],"scaling":[92],"analyses":[93],"for":[94,129],"HPC-acknowledging":[95],"that":[96],"science":[98],"skills":[99],"required":[102],"build":[104],"deeper":[106],"understanding":[107],"life.":[109],"This":[110],"portends":[111],"growing":[113],"knowledge":[115],"gap":[116],"biology":[118],"challenges":[120],"institutions":[121],"funding":[123],"agencies":[124],"redouble":[126],"support":[128],"biology.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":7}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}
