{"id":"https://openalex.org/W4411455815","doi":"https://doi.org/10.1186/s13040-025-00459-4","title":"A compact encoding of the genome suitable for machine learning prediction of traits and genetic risk scores","display_name":"A compact encoding of the genome suitable for machine learning prediction of traits and genetic risk scores","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411455815","doi":"https://doi.org/10.1186/s13040-025-00459-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/40537821"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-025-00459-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00459-4","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00459-4","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00459-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033306060","display_name":"Yasaman Fatapour","orcid":"https://orcid.org/0000-0001-8660-1621"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]},{"id":"https://openalex.org/I4210140791","display_name":"Irvine University","ror":"https://ror.org/04ysmca02","country_code":"US","type":"education","lineage":["https://openalex.org/I4210140791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasaman Fatapour","raw_affiliation_strings":["Department of Biomedical Engineering, University of California, Irvine, CA, 2714, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, University of California, Irvine, CA, 2714, USA","institution_ids":["https://openalex.org/I204250578","https://openalex.org/I4210140791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022307884","display_name":"James P. Brody","orcid":"https://orcid.org/0000-0002-7995-5197"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James P. Brody","raw_affiliation_strings":["Department of Biomedical Engineering, University of California, Irvine, CA, 2714, USA. jpbrody@uci.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, University of California, Irvine, CA, 2714, USA. jpbrody@uci.edu","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022307884"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":1.7159,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8418698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"18","issue":"1","first_page":"44","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9991000294685364,"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/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.9965000152587891,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.9962000250816345,"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/white","display_name":"White (mutation)","score":0.6029639840126038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765135288238525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5391090512275696},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.5220986604690552},{"id":"https://openalex.org/keywords/chromosome","display_name":"Chromosome","score":0.4891336262226105},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4837179481983185},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.43535593152046204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39086222648620605},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.38993123173713684},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3202742040157318},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3125074803829193},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28703659772872925},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.25438830256462097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21605819463729858}],"concepts":[{"id":"https://openalex.org/C56273599","wikidata":"https://www.wikidata.org/wiki/Q3122841","display_name":"White (mutation)","level":3,"score":0.6029639840126038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765135288238525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5391090512275696},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.5220986604690552},{"id":"https://openalex.org/C30481170","wikidata":"https://www.wikidata.org/wiki/Q37748","display_name":"Chromosome","level":3,"score":0.4891336262226105},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4837179481983185},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.43535593152046204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39086222648620605},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38993123173713684},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3202742040157318},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3125074803829193},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28703659772872925},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25438830256462097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21605819463729858}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13040-025-00459-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00459-4","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00459-4","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:40537821","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40537821","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":"BioData mining","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12180147","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12180147","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":"BioData Min","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:4d62c71423b24488a1e22cfa3472a26b","is_oa":true,"landing_page_url":"https://doaj.org/article/4d62c71423b24488a1e22cfa3472a26b","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 18, Iss 1, Pp 1-14 (2025)","raw_type":"article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt3xz4v5j3","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3xz4v5j3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"BioData Mining, vol 18, iss 1","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13040-025-00459-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00459-4","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00459-4","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411455815.pdf","grobid_xml":"https://content.openalex.org/works/W4411455815.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1528782506","https://openalex.org/W2061008984","https://openalex.org/W2076469310","https://openalex.org/W2104549677","https://openalex.org/W2107256939","https://openalex.org/W2112430946","https://openalex.org/W2127230663","https://openalex.org/W2130395838","https://openalex.org/W2139852278","https://openalex.org/W2145307001","https://openalex.org/W2146948473","https://openalex.org/W2155496693","https://openalex.org/W2161998322","https://openalex.org/W2163924952","https://openalex.org/W2167254204","https://openalex.org/W2168909179","https://openalex.org/W2209106767","https://openalex.org/W2725988230","https://openalex.org/W2759066107","https://openalex.org/W2803332630","https://openalex.org/W2886752110","https://openalex.org/W2934861239","https://openalex.org/W2952883732","https://openalex.org/W2963897438","https://openalex.org/W2980086570","https://openalex.org/W3012141744","https://openalex.org/W3028329270","https://openalex.org/W3039570821","https://openalex.org/W3090495773","https://openalex.org/W3092519965","https://openalex.org/W3100732120","https://openalex.org/W3138565406","https://openalex.org/W3199247546","https://openalex.org/W4292622945","https://openalex.org/W4293785792","https://openalex.org/W4304698823","https://openalex.org/W4315644439","https://openalex.org/W4318026217","https://openalex.org/W4380988593","https://openalex.org/W4386385034","https://openalex.org/W4391925485"],"related_works":["https://openalex.org/W2134373856","https://openalex.org/W2385665726","https://openalex.org/W2347271704","https://openalex.org/W4233030723","https://openalex.org/W2391157579","https://openalex.org/W3029453589","https://openalex.org/W2325793530","https://openalex.org/W2036624756","https://openalex.org/W2372977423","https://openalex.org/W2387402244"],"abstract_inverted_index":{"Genotype":[0],"to":[1,18,70,150,155,172],"phenotype":[2,90],"prediction":[3],"is":[4,14,26,69,109],"a":[5,15,23,30,40,75,81,88,99,106,121,124,192,242,252],"central":[6],"problem":[7,46],"in":[8,86,146,169],"biology":[9],"and":[10,35,161,182,219],"medicine.":[11],"Machine":[12],"learning":[13],"natural":[16],"tool":[17],"address":[19],"this":[20,45,67,238],"problem.":[21],"However,":[22],"person's":[24,89,100,243,253],"genotype":[25,77,101],"usually":[27],"represented":[28],"by":[29,133],"few":[31,41],"million":[32],"single-nucleotide":[33],"polymorphisms":[34],"most":[36],"datasets":[37],"only":[38,195],"have":[39,235],"thousand":[42],"patients.":[43],"Thus,":[44],"typically":[47],"has":[48],"many":[49],"more":[50],"predictors":[51],"than":[52],"the":[53,72,92,112,134,142,152,166,174],"number":[54,83],"of":[55,66,74,84,94,115,123,137,176,241],"samples":[56],"(patients),":[57],"making":[58],"it":[59],"unsuitable":[60],"for":[61],"machine":[62,95,247],"learning.":[63,96],"The":[64],"objective":[65],"paper":[68],"examine":[71],"efficacy":[73],"compact":[76,239],"representation,":[78],"which":[79],"employs":[80],"limited":[82],"predictors,":[85],"predicting":[87],"through":[91],"application":[93],"We":[97,126,140,163],"characterized":[98],"using":[102,194],"chromosome-scale":[103],"length":[104],"variation,":[105],"measure":[107],"that":[108,187,237],"computed":[110,127],"as":[111,200],"average":[113],"value":[114],"reported":[116],"log":[117],"R":[118],"ratios":[119],"across":[120],"portion":[122],"chromosome.":[125],"these":[128],"numbers":[129],"from":[130,197],"data":[131],"collected":[132],"NIH":[135],"All":[136],"Us":[138],"program.":[139],"used":[141,165],"AutoML":[143,167],"function":[144,168],"(h2o.ai)":[145],"binary":[147],"classification":[148],"mode":[149,171],"identify":[151],"best":[153],"models":[154],"differentiate":[156],"between":[157],"male/female,":[158],"Black/white,":[159],"white/Asian,":[160],"Black/Asian.":[162],"also":[164,228],"regression":[170],"predict":[173,251],"height":[175],"people":[177],"based":[178],"on":[179],"their":[180],"age":[181],"genotype.":[183],"Our":[184],"results":[185],"showed":[186],"we":[188,234],"could":[189],"effectively":[190,229,250],"classify":[191],"person,":[193],"information":[196],"chromosomes":[198],"1-22,":[199],"Male/Female":[201],"(AUC":[202,208,214,221],"=":[203,209,215,222],"0.9988":[204],"\u00b1":[205,211,217,224],"0.0001),":[206],"White/Black":[207],"0.970":[210],"0.002),":[212,218],"Asian/White":[213],"0.877":[216],"Black/Asian":[220],"0.966":[223],"0.002).":[225],"This":[226],"approach":[227],"predicted":[230],"height.":[231],"In":[232],"conclusion,":[233],"shown":[236],"representation":[240],"genotype,":[244],"along":[245],"with":[246],"learning,":[248],"can":[249],"phenotype.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}