{"id":"https://openalex.org/W7020694598","doi":null,"title":"Leveraging Single-Cell ATAC-Seq for Genomic Language Models and Multimodal Foundation Models","display_name":"Leveraging Single-Cell ATAC-Seq for Genomic Language Models and Multimodal Foundation Models","publication_year":2025,"publication_date":"2025-02-01","ids":{"openalex":"https://openalex.org/W7020694598"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/159110","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/159110","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/159110/-1/kim-dyk0518-meng-eecs-2025-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/159110/-1/kim-dyk0518-meng-eecs-2025-thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kim, Dong Young","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kim, Dong Young","raw_affiliation_strings":["MASSACHUSETTS INSTITUTE OF TECHNOLOGY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MASSACHUSETTS INSTITUTE OF TECHNOLOGY","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"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":true,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.7383000254631042,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.7383000254631042,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.21119999885559082,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.00839999970048666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/single-cell-atac-seq","display_name":"single-cell ATAC-seq","score":0.9459999799728394},{"id":"https://openalex.org/keywords/chromatin-accessibility","display_name":"chromatin accessibility","score":0.9710000157356262},{"id":"https://openalex.org/keywords/genomic-language-models","display_name":"genomic language models","score":0.984000027179718},{"id":"https://openalex.org/keywords/nucleotide-transformer","display_name":"Nucleotide Transformer","score":0.9340000152587891},{"id":"https://openalex.org/keywords/multimodal-foundation-models","display_name":"multimodal foundation models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.7990000247955322},{"id":"https://openalex.org/keywords/cell-type-classification","display_name":"cell type classification","score":0.9200000166893005},{"id":"https://openalex.org/keywords/regulatory-elements","display_name":"regulatory elements","score":0.5730000138282776},{"id":"https://openalex.org/keywords/epigenomics","display_name":"epigenomics","score":0.5899999737739563},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.6517999768257141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029999852180481},{"id":"https://openalex.org/C121912465","wikidata":"https://www.wikidata.org/wiki/Q3589153","display_name":"Epigenomics","level":5,"score":0.5692999958992004},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5274999737739563},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.521399974822998},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38119998574256897},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.35839998722076416},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.296099990606308},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2840999960899353},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/159110","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/159110","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/159110/-1/kim-dyk0518-meng-eecs-2025-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/159110","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/159110","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/159110/-1/kim-dyk0518-meng-eecs-2025-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7020694598.pdf","grobid_xml":"https://content.openalex.org/works/W7020694598.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W2896457183","https://openalex.org/W3030163527","https://openalex.org/W3168867926","https://openalex.org/W4224308101","https://openalex.org/W4322718191","https://openalex.org/W4382490702"],"related_works":["https://openalex.org/W4415016592","https://openalex.org/W4415881950","https://openalex.org/W7138089501","https://openalex.org/W4322770903","https://openalex.org/W4409406144","https://openalex.org/W4290672942","https://openalex.org/W7108459752","https://openalex.org/W4411929701","https://openalex.org/W7130511508","https://openalex.org/W4406951674"],"abstract_inverted_index":{"Single-cell":[0],"Assay":[1],"for":[2,14,58,178,207],"Transposase-Accessible":[3],"Chromatin":[4],"using":[5],"sequencing":[6,47],"(scATAC-seq)":[7],"has":[8],"emerged":[9],"as":[10],"a":[11,113,144,171,205],"powerful":[12],"tool":[13],"profiling":[15],"chromatin":[16,104,168],"accessibility":[17],"at":[18,138],"single-cell":[19],"resolution.":[20,140],"By":[21],"capturing":[22],"epigenomic":[23],"landscapes,":[24],"scATAC-seq":[25,41,68,157,196],"provides":[26],"critical":[27],"insights":[28],"into":[29,76,198,214],"the":[30,38,51,65,92,119,192],"regulatory":[31,130,209],"elements":[32,131],"that":[33,117,149,174],"govern":[34],"gene":[35,165],"expression.":[36],"However,":[37],"sparsity":[39],"of":[40,67,94,127,194],"data,":[42],"resulting":[43],"from":[44,132],"its":[45,74],"low":[46],"depth":[48],"relative":[49],"to":[50,110,123,136],"genome\u2019s":[52],"potential":[53,193],"complexity,":[54],"poses":[55],"significant":[56],"challenges":[57],"effective":[59],"and":[60,129,167,186],"accurate":[61],"modeling.":[62,216],"To":[63],"advance":[64],"utility":[66],"in":[69],"modern":[70],"biology,":[71],"we":[72,85,107,142],"explore":[73],"integration":[75],"deep":[77,201],"learning":[78,202],"frameworks":[79],"through":[80],"two":[81],"innovative":[82],"applications.":[83],"First,":[84],"demonstrate":[86],"how":[87],"incorporating":[88,195],"scATAC":[89,109],"data":[90,197],"enhances":[91],"performance":[93],"existing":[95,151,199],"genomic":[96,128,215],"language":[97],"models":[98,154],"by":[99,155],"providing":[100,204],"complementary":[101],"context":[102],"about":[103],"accessibility.":[105],"Specifically,":[106],"introduce":[108,143],"improve":[111],"SegmentNT,":[112],"DNA":[114,133,210],"segmentation":[115],"model":[116,148,160],"leverages":[118],"Nucleotide":[120],"Transformer":[121],"(NT)":[122],"predict":[124],"14":[125],"types":[126],"sequences":[134],"up":[135],"30kb":[137],"single-nucleotide":[139],"Second,":[141],"novel":[145],"multimodal":[146],"foundation":[147,153],"extends":[150],"scRNA-seq":[152],"integrating":[156,208],"data.":[158],"This":[159],"captures":[161],"crossmodal":[162],"relationships":[163],"between":[164],"expression":[166],"accessibility,":[169],"establishing":[170],"unified":[172],"framework":[173,206],"can":[175],"be":[176],"fine-tuned":[177],"diverse":[179],"downstream":[180],"tasks,":[181],"including":[182],"cell":[183],"type":[184],"classification":[185],"cross-modal":[187],"imputation.":[188],"Our":[189],"work":[190],"highlights":[191],"genomics":[200],"strategies,":[203],"analysis":[211],"more":[212],"seamlessly":[213]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}