{"id":"https://openalex.org/W4412765348","doi":"https://doi.org/10.1101/2025.07.24.666637","title":"Impact of integration on persistent homology clustering and biological signal detection in scRNA-seq data","display_name":"Impact of integration on persistent homology clustering and biological signal detection in scRNA-seq data","publication_year":2025,"publication_date":"2025-07-29","ids":{"openalex":"https://openalex.org/W4412765348","doi":"https://doi.org/10.1101/2025.07.24.666637","pmid":"https://pubmed.ncbi.nlm.nih.gov/40766507","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/12324225"},"language":"en","primary_location":{"id":"doi:10.1101/2025.07.24.666637","doi":"https://doi.org/10.1101/2025.07.24.666637","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.07.24.666637","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/07/29/2025.07.24.666637.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2025/07/29/2025.07.24.666637.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030940832","display_name":"Jonah C. Daneshmand","orcid":"https://orcid.org/0000-0002-7101-7542","observed_orcids":["https://orcid.org/0000-0002-7101-7542"]},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonah Daneshmand","raw_affiliation_strings":["Department of Graduate and Interdisciplinary Studies, University of Louisville, Louisville, Kentucky 40202, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Graduate and Interdisciplinary Studies, University of Louisville, Louisville, Kentucky 40202, United States of America","institution_ids":["https://openalex.org/I142740786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017324963","display_name":"Julia H. Chariker","orcid":"https://orcid.org/0000-0001-6805-7220","observed_orcids":["https://orcid.org/0000-0001-6805-7220"]},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia H. Chariker","raw_affiliation_strings":["Department of Neuroscience Training, University of Louisville, Louisville, Kentucky 40202, United States of America","Kentucky IDeA Network of Biomedical Research Excellence Data Science Core, University of Louisville, Louisville, Kentucky 40202, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6805-7220","affiliations":[{"raw_affiliation_string":"Department of Neuroscience Training, University of Louisville, Louisville, Kentucky 40202, United States of America","institution_ids":["https://openalex.org/I142740786"]},{"raw_affiliation_string":"Kentucky IDeA Network of Biomedical Research Excellence Data Science Core, University of Louisville, Louisville, Kentucky 40202, United States of America","institution_ids":["https://openalex.org/I142740786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070114395","display_name":"Akshitkumar M. Mistry","orcid":"https://orcid.org/0000-0002-7918-5153","observed_orcids":["https://orcid.org/0000-0002-7918-5153"]},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshitkumar Mistry","raw_affiliation_strings":["Department of Neurological Surgery, University of Louisville School of Medicine, University of Louisville, Louisville, Kentucky 40202, United States of America","Department of Neurological Surgery, University of Louisville School of Medicine, University of Louisville, Louisville, Kentucky 0202, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-7918-5153","affiliations":[{"raw_affiliation_string":"Department of Neurological Surgery, University of Louisville School of Medicine, University of Louisville, Louisville, Kentucky 40202, United States of America","institution_ids":["https://openalex.org/I142740786"]},{"raw_affiliation_string":"Department of Neurological Surgery, University of Louisville School of Medicine, University of Louisville, Louisville, Kentucky 0202, United States of America","institution_ids":["https://openalex.org/I142740786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034707578","display_name":"Eric Christian Rouchka","orcid":"https://orcid.org/0000-0003-3487-6572","observed_orcids":["https://orcid.org/0000-0003-3487-6572"]},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eric C. Rouchka","raw_affiliation_strings":["Department of Biochemistry and Molecular Genetics, University of Louisville, Louisville, Kentucky 40202, United States of America","Kentucky IDeA Network of Biomedical Research Excellence Data Science Core, University of Louisville, Louisville, Kentucky 40202, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3487-6572","affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Genetics, University of Louisville, Louisville, Kentucky 40202, United States of America","institution_ids":["https://openalex.org/I142740786"]},{"raw_affiliation_string":"Kentucky IDeA Network of Biomedical Research Excellence Data Science Core, University of Louisville, Louisville, Kentucky 40202, United States of America","institution_ids":["https://openalex.org/I142740786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034707578"],"corresponding_institution_ids":["https://openalex.org/I142740786"],"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.04349999874830246,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.0,"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/persistent-homology","display_name":"persistent homology","score":0.875},{"id":"https://openalex.org/keywords/single-cell-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.8159999847412109},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.7570000290870667},{"id":"https://openalex.org/keywords/topological-data-analysis","display_name":"topological data analysis","score":0.9639999866485596},{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.6309999823570251},{"id":"https://openalex.org/keywords/betti-curves","display_name":"Betti curves","score":0.8199999928474426},{"id":"https://openalex.org/keywords/persistence-landscapes","display_name":"persistence landscapes","score":0.9509999752044678},{"id":"https://openalex.org/keywords/batch-effects","display_name":"batch effects","score":0.8159999847412109},{"id":"https://openalex.org/keywords/biological-signal-detection","display_name":"biological signal detection","score":0.6970000267028809},{"id":"https://openalex.org/keywords/transcriptomic-landscape","display_name":"transcriptional landscape","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C2874115","wikidata":"https://www.wikidata.org/wiki/Q17099562","display_name":"Persistent homology","level":2,"score":0.7772059440612793},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.767633318901062},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5608620643615723},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.536405622959137},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4732285737991333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4091046154499054},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3648124933242798},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3563705384731293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2752450108528137},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23540112376213074},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16600912809371948},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.08329352736473083},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.058083683252334595}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1101/2025.07.24.666637","doi":"https://doi.org/10.1101/2025.07.24.666637","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.07.24.666637","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/07/29/2025.07.24.666637.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:40766507","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40766507","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"},{"id":"pmh:oai:pubmedcentral.nih.gov:12324225","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12324225","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,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1101/2025.07.24.666637","doi":"https://doi.org/10.1101/2025.07.24.666637","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.07.24.666637","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/07/29/2025.07.24.666637.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000896909","display_name":"IDeA Networks of Biomedical Research Excellence in Kentucky","funder_award_id":"P20GM103436","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412765348.pdf","grobid_xml":"https://content.openalex.org/works/W4412765348.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1976191845","https://openalex.org/W2107385756","https://openalex.org/W2527487499","https://openalex.org/W2603797465","https://openalex.org/W2610774430","https://openalex.org/W2763959081","https://openalex.org/W2794521141","https://openalex.org/W2886347923","https://openalex.org/W2890558008","https://openalex.org/W2912390237","https://openalex.org/W2917576966","https://openalex.org/W2931036699","https://openalex.org/W2949177718","https://openalex.org/W2951638683","https://openalex.org/W2971064792","https://openalex.org/W2984472267","https://openalex.org/W2997280954","https://openalex.org/W2999304916","https://openalex.org/W3005127469","https://openalex.org/W3007172120","https://openalex.org/W3014671498","https://openalex.org/W3045861332","https://openalex.org/W3092493138","https://openalex.org/W3098455240","https://openalex.org/W3111450319","https://openalex.org/W3122570763","https://openalex.org/W3165512555","https://openalex.org/W3183719453","https://openalex.org/W4317254710","https://openalex.org/W4378212544","https://openalex.org/W4394917959","https://openalex.org/W4396770137","https://openalex.org/W4399389044","https://openalex.org/W4405279452"],"related_works":["https://openalex.org/W7135711551","https://openalex.org/W3009302866","https://openalex.org/W4403705875","https://openalex.org/W4380357928","https://openalex.org/W2902566705","https://openalex.org/W4402253508","https://openalex.org/W4392878947","https://openalex.org/W4408565368","https://openalex.org/W3182487177","https://openalex.org/W4416660085"],"abstract_inverted_index":{"Background:":[0],"As":[1],"the":[2,76,83,123,149],"availability":[3],"of":[4,63,82,125,151],"single-cell":[5,167],"RNA":[6],"sequencing":[7],"(scRNA-seq)":[8],"data":[9,38,73],"expands,":[10],"there":[11],"is":[12],"a":[13,34,42,60,143,172],"growing":[14],"need":[15],"for":[16,45,147,174,186],"robust":[17],"methods":[18,177],"that":[19,138],"enable":[20],"integration":[21,74,121,152,180],"and":[22,28,79,94,105,115,153,182],"comparison":[23],"across":[24,112],"diverse":[25,61],"biological":[26,80,161],"conditions":[27],"experimental":[29],"protocols.":[30],"Persistent":[31],"homology":[32],"(PH),":[33],"technique":[35],"from":[36,163],"topological":[37,77,96,156,176],"analysis":[39],"(TDA),":[40],"provides":[41],"deformation-invariant":[43],"framework":[44,173],"capturing":[46],"structural":[47],"patterns":[48],"in":[49,166],"high-dimensional":[50],"data.":[51,168],"Methods:":[52],"In":[53],"this":[54],"study,":[55],"PH":[56,139],"was":[57,87,98],"applied":[58],"to":[59,70,178],"collection":[62],"scRNA-seq":[64],"datasets":[65],"spanning":[66],"eight":[67],"tissue":[68],"types":[69],"investigate":[71],"how":[72,155],"affects":[75],"features":[78],"interpretability":[81],"resulting":[84],"representations.":[85],"Clustering":[86],"performed":[88],"based":[89],"on":[90],"PH-derived":[91],"pairwise":[92],"distances":[93],"global":[95],"structure":[97],"assessed":[99],"through":[100],"Betti":[101],"curves,":[102],"Euler":[103],"characteristics,":[104],"persistence":[106],"landscapes.":[107],"By":[108],"comparing":[109],"these":[110],"summaries":[111,157],"raw,":[113],"normalized,":[114],"integrated":[116],"datasets,":[117],"we":[118],"examined":[119],"whether":[120],"enhances":[122],"detection":[124],"biologically":[126],"meaningful":[127],"patterns,":[128],"or,":[129],"conversely,":[130],"obscures":[131],"fine-scale":[132],"structure.":[133],"Results:":[134],"This":[135,169],"approach":[136],"demonstrates":[137],"can":[140,158],"serve":[141],"as":[142],"powerful":[144],"complementary":[145],"strategy":[146],"evaluating":[148],"impact":[150],"reveals":[154],"help":[159],"disentangle":[160],"signal":[162],"batch-related":[164],"noise":[165],"work":[170],"establishes":[171],"using":[175],"assess":[179],"quality":[181],"highlights":[183],"new":[184],"avenues":[185],"interpreting":[187],"complex":[188],"transcriptomic":[189],"landscapes":[190],"beyond":[191],"conventional":[192],"clustering.":[193]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}