{"id":"https://openalex.org/W7223704397","doi":"https://doi.org/10.64898/2026.10.20.760589","title":"Denoising single-cell ATAC-seq data with Shannon entropy","display_name":"Denoising single-cell ATAC-seq data with Shannon entropy","publication_year":2026,"publication_date":"2026-10-23","ids":{"openalex":"https://openalex.org/W7223704397","doi":"https://doi.org/10.64898/2026.10.20.760589","pmid":"https://pubmed.ncbi.nlm.nih.gov/42996021","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13738552"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.20.760589","doi":"https://doi.org/10.64898/2026.10.20.760589","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.20.760589","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/23/2026.10.20.760589.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/23/2026.10.20.760589.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084826131","display_name":"Shiyi Yang","orcid":"https://orcid.org/0000-0003-1827-3229","observed_orcids":["https://orcid.org/0000-0003-1827-3229"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyi Yang","raw_affiliation_strings":["UC Berkeley, Center for Computational Biology, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1827-3229","affiliations":[{"raw_affiliation_string":"UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113352900","display_name":"Kevin An","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin An","raw_affiliation_strings":["UC Berkeley, Department of Bioengineering, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Department of Bioengineering, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014463673","display_name":"Juliana J. Lee","orcid":"https://orcid.org/0000-0002-7393-9997","observed_orcids":["https://orcid.org/0000-0002-7393-9997"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana J. Lee","raw_affiliation_strings":["UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","UC Berkeley, Department of Molecular & Cell Biology, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, Department of Molecular & Cell Biology, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035120638","display_name":"Jase Gehring","orcid":"https://orcid.org/0000-0002-3894-9495","observed_orcids":["https://orcid.org/0000-0002-3894-9495"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jase Gehring","raw_affiliation_strings":["UC Berkeley, Department of Bioengineering, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Department of Bioengineering, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029305307","display_name":"A. Sina Booeshaghi","orcid":"https://orcid.org/0000-0002-6442-4502","observed_orcids":["https://orcid.org/0000-0002-6442-4502"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sina Booeshaghi","raw_affiliation_strings":["UC Berkeley, Department of Bioengineering, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6442-4502","affiliations":[{"raw_affiliation_string":"UC Berkeley, Department of Bioengineering, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143809848","display_name":"Haiyan Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyan Huang","raw_affiliation_strings":["UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","UC Berkeley, Department of Statistics, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, Department of Statistics, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064329611","display_name":"Aaron Streets","orcid":"https://orcid.org/0000-0002-3909-8389","observed_orcids":["https://orcid.org/0000-0002-3909-8389"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaron Streets","raw_affiliation_strings":["UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","UC Berkeley, Department of Bioengineering, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3909-8389","affiliations":[{"raw_affiliation_string":"UC Berkeley, Center for Computational Biology, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, Department of Bioengineering, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064329611"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9628999829292297,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9628999829292297,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.031300000846385956,"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/T12820","display_name":"Chromatin Remodeling and Cancer","score":0.0006000000284984708,"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/data-denoising","display_name":"data denoising","score":0.7940000295639038},{"id":"https://openalex.org/keywords/shannon-entropy","display_name":"Shannon entropy","score":0.9629999995231628},{"id":"https://openalex.org/keywords/chromatin-accessibility","display_name":"chromatin accessibility","score":0.9829999804496765},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"signal-to-noise ratio","score":0.8730000257492065}],"concepts":[{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.7706000208854675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5221999883651733},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43299999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42750000953674316},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.35260000824928284},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3224000036716461},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3125},{"id":"https://openalex.org/C172510086","wikidata":"https://www.wikidata.org/wiki/Q410629","display_name":"Transposase","level":5,"score":0.31130000948905945},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C2984485829","wikidata":"https://www.wikidata.org/wiki/Q100766421","display_name":"Noise level","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.10.20.760589","doi":"https://doi.org/10.64898/2026.10.20.760589","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.20.760589","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/23/2026.10.20.760589.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13738552","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13738552/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13738552/pdf/nihpp-2026.10.20.760589v1.pdf","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmid:42996021","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42996021","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.64898/2026.10.20.760589","doi":"https://doi.org/10.64898/2026.10.20.760589","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.20.760589","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/23/2026.10.20.760589.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223704397.pdf","grobid_xml":"https://content.openalex.org/works/W7223704397.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1602702667","https://openalex.org/W1978107331","https://openalex.org/W2013571070","https://openalex.org/W2014677321","https://openalex.org/W2068728923","https://openalex.org/W2102619694","https://openalex.org/W2171808845","https://openalex.org/W2553449527","https://openalex.org/W2953622121","https://openalex.org/W2971398276","https://openalex.org/W3013371767","https://openalex.org/W3013880401","https://openalex.org/W3101780755","https://openalex.org/W3131634425","https://openalex.org/W3133082627","https://openalex.org/W3160422429","https://openalex.org/W3196441678","https://openalex.org/W3210860076","https://openalex.org/W4210587306","https://openalex.org/W4385543702","https://openalex.org/W4385851326","https://openalex.org/W4387138272","https://openalex.org/W4392163844","https://openalex.org/W4396865956","https://openalex.org/W4414367365","https://openalex.org/W4416527380","https://openalex.org/W4416589927"],"related_works":["https://openalex.org/W6925393775","https://openalex.org/W4297425141","https://openalex.org/W4220680295","https://openalex.org/W4297425528","https://openalex.org/W4413108614","https://openalex.org/W4414625608","https://openalex.org/W3210657952","https://openalex.org/W4290672942","https://openalex.org/W3034491533","https://openalex.org/W4405183973"],"abstract_inverted_index":{"Single-cell":[0],"Assay":[1],"for":[2,96],"Transposase":[3],"Accessible":[4],"Chromatin":[5],"with":[6],"sequencing":[7],"(scATAC-seq)":[8],"is":[9,32],"widely":[10],"used":[11],"to":[12],"investigate":[13],"chromatin":[14,68],"accessibility":[15,69,87],"but":[16],"experiments":[17],"often":[18,51],"contain":[19],"empty":[20],"droplets,":[21],"droplets":[22,36],"containing":[23],"damaged":[24],"nuclei":[25,31,81],"or":[26,57],"cellular-debris.":[27],"Accurately":[28],"filtering":[29],"high-quality":[30,80],"important":[33],"as":[34,67],"noisy":[35],"contribute":[37],"reads":[38],"that":[39,61,78],"can":[40],"distort":[41],"downstream":[42,103],"analysis":[43],"and":[44,56,99],"obscure":[45],"rare":[46],"cell":[47],"population.":[48],"Current":[49],"approaches":[50],"rely":[52],"on":[53],"read":[54],"depth":[55],"predefined":[58],"genomic":[59],"features":[60],"are":[62],"not":[63],"exactly":[64],"the":[65],"same":[66],"landscape.":[70],"Here,":[71],"we":[72],"present":[73],"a":[74],"Shannon":[75],"entropy-based":[76],"method":[77],"filters":[79],"more":[82,101],"robustly":[83],"by":[84],"quantifying":[85],"genome-wide":[86],"complexity.":[88],"This":[89],"approach":[90],"improves":[91],"signal-to-noise":[92],"ratio,":[93],"increases":[94],"sensitivity":[95],"accessible-region":[97],"detection,":[98],"enables":[100],"reliable":[102],"inference":[104],"in":[105],"scATAC-seq":[106],"studies.":[107]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-27T00:00:00"}
