{"id":"https://openalex.org/W7212418106","doi":"https://doi.org/10.64898/2026.09.05.749598","title":"Explainable Machine Learning and Epigenomic Profiling Decipher the Topological Determinants of Lentiviral Integration and Longitudinal Persistence in SCID-X1 Gene Therapy","display_name":"Explainable Machine Learning and Epigenomic Profiling Decipher the Topological Determinants of Lentiviral Integration and Longitudinal Persistence in SCID-X1 Gene Therapy","publication_year":2026,"publication_date":"2026-09-12","ids":{"openalex":"https://openalex.org/W7212418106","doi":"https://doi.org/10.64898/2026.09.05.749598"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.05.749598","doi":"https://doi.org/10.64898/2026.09.05.749598","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.05.749598","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/12/2026.09.05.749598.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":"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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/12/2026.09.05.749598.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136574976","display_name":"Zahra Mousavipour","orcid":"https://orcid.org/0009-0009-9840-7792","observed_orcids":["https://orcid.org/0009-0009-9840-7792"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zahra Mousavipour","raw_affiliation_strings":["Department of Genetics, Stanford Medicine School, Stanford University, Stanford, California 94305, USA"],"raw_orcid":"https://orcid.org/0009-0009-9840-7792","affiliations":[{"raw_affiliation_string":"Department of Genetics, Stanford Medicine School, Stanford University, Stanford, California 94305, USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091253838","display_name":"Hamidreza Saber","orcid":"https://orcid.org/0000-0001-7590-2023","observed_orcids":["https://orcid.org/0000-0001-7590-2023","https://orcid.org/0009-0007-7469-8068"]},"institutions":[{"id":"https://openalex.org/I4210161716","display_name":"Islamic Azad University Ardabil","ror":"https://ror.org/058np3c43","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I4210161716"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Hamidreza Saber","raw_affiliation_strings":["Department of Cellular and Molecular Biology, Faculty of Basic Sciences, Islamic Azad University, Ardabil Branch, Ardabil, 56131, Iran"],"raw_orcid":"https://orcid.org/0009-0007-7469-8068","affiliations":[{"raw_affiliation_string":"Department of Cellular and Molecular Biology, Faculty of Basic Sciences, Islamic Azad University, Ardabil Branch, Ardabil, 56131, Iran","institution_ids":["https://openalex.org/I4210161716"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091253838"],"corresponding_institution_ids":["https://openalex.org/I4210161716"],"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/T10613","display_name":"Virus-based gene therapy research","score":0.9980000257492065,"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/T10613","display_name":"Virus-based gene therapy research","score":0.9980000257492065,"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/T10878","display_name":"CRISPR and Genetic Engineering","score":0.0005000000237487257,"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/T11491","display_name":"CAR-T cell therapy research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lentiviral-integration","display_name":"lentiviral integration","score":0.7639999985694885},{"id":"https://openalex.org/keywords/x-linked-severe-combined-immunodeficiency","display_name":"X-linked severe combined immunodeficiency","score":0.781000018119812},{"id":"https://openalex.org/keywords/epigenomic-features","display_name":"epigenomic features","score":0.5740000009536743},{"id":"https://openalex.org/keywords/chromosome-topology","display_name":"chromosome topology","score":0.5370000004768372},{"id":"https://openalex.org/keywords/transcription-start-site","display_name":"transcription start sites","score":0.7450000047683716},{"id":"https://openalex.org/keywords/explainable-machine-learning","display_name":"explainable machine learning","score":0.8050000071525574}],"concepts":[{"id":"https://openalex.org/C121912465","wikidata":"https://www.wikidata.org/wiki/Q3589153","display_name":"Epigenomics","level":5,"score":0.8654000163078308},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6381000280380249},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.5976999998092651},{"id":"https://openalex.org/C2874115","wikidata":"https://www.wikidata.org/wiki/Q17099562","display_name":"Persistent homology","level":2,"score":0.5697000026702881},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5644999742507935},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C2781009140","wikidata":"https://www.wikidata.org/wiki/Q7170389","display_name":"Persistence (discontinuity)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4259999990463257},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.3977999985218048},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.38339999318122864},{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3391000032424927},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C120821319","wikidata":"https://www.wikidata.org/wiki/Q1501491","display_name":"Copy-number variation","level":4,"score":0.30329999327659607},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C41091548","wikidata":"https://www.wikidata.org/wiki/Q26939","display_name":"Epigenetics","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.27730000019073486},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C179463898","wikidata":"https://www.wikidata.org/wiki/Q10273301","display_name":"Epigenesis","level":5,"score":0.2635999917984009},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.05.749598","doi":"https://doi.org/10.64898/2026.09.05.749598","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.05.749598","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/12/2026.09.05.749598.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.05.749598","doi":"https://doi.org/10.64898/2026.09.05.749598","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.05.749598","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/12/2026.09.05.749598.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.9537000060081482}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212418106.pdf","grobid_xml":"https://content.openalex.org/works/W7212418106.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1902159756","https://openalex.org/W1976477813","https://openalex.org/W2006765654","https://openalex.org/W2008902252","https://openalex.org/W2046156611","https://openalex.org/W2057879405","https://openalex.org/W2082485360","https://openalex.org/W2085489729","https://openalex.org/W2094331955","https://openalex.org/W2130174662","https://openalex.org/W2137582063","https://openalex.org/W2167523976","https://openalex.org/W2295598076","https://openalex.org/W2560136348","https://openalex.org/W2792588868","https://openalex.org/W2915985519","https://openalex.org/W2999048613","https://openalex.org/W2999615587","https://openalex.org/W4387409872"],"related_works":["https://openalex.org/W4387409872","https://openalex.org/W1979262175","https://openalex.org/W2024556138","https://openalex.org/W1996466353","https://openalex.org/W2061361780","https://openalex.org/W1965255526","https://openalex.org/W4247628447","https://openalex.org/W1966991523","https://openalex.org/W2045995615","https://openalex.org/W6907525827"],"abstract_inverted_index":{"Abstract":[0],"Lentiviral":[1],"vectors":[2],"(LVs)":[3],"are":[4],"clinically":[5],"established":[6],"for":[7],"SCID-X1":[8,35],"gene":[9,164,244],"therapy,":[10],"yet":[11],"the":[12,128,238],"quantitative":[13],"epigenomic":[14,63,219],"and":[15,21,64,74,84,101,120,152,218,271,281],"spatial":[16,226],"determinants":[17],"governing":[18],"integration":[19,42,224,252,278],"targeting":[20],"long-term":[22,230],"clonal":[23,47],"persistence":[24],"across":[25,45],"chromosomes":[26,89],"remain":[27],"incompletely":[28],"characterized.":[29],"Using":[30],"clinical":[31,41,250],"multi-omics":[32],"datasets":[33],"from":[34,49,180],"trials,":[36],"we":[37],"curated":[38,254],"274,959":[39,249],"unique":[40],"sites":[43,253],"(VIS)":[44],"276,839":[46],"records":[48],"10":[50],"patients":[51],"(hg38).":[52],"Balanced":[53],"against":[54],"length-weighted":[55],"genomic":[56],"controls":[57],"(total":[58],"N":[59],"=":[60,146,156,168,186,189,211,214],"549,918),":[61],"five":[62],"topological":[65,217],"features":[66,220],"were":[67],"modeled.":[68],"We":[69],"evaluated":[70],"Logistic":[71],"Regression,":[72],"XGBoost,":[73],"a":[75,204],"Deep":[76,110],"Genomic":[77],"ResNet":[78,111],"using":[79],"inner":[80],"5-fold":[81],"chromosome-grouped":[82],"cross-validation":[83],"evaluation":[85],"on":[86],"held-out":[87,108],"test":[88],"(chr19-22,":[90],"chrX).":[91],"Statistical":[92],"uncertainty":[93],"was":[94],"quantified":[95],"via":[96],"1-Mb":[97,102,135,274],"block-bootstrap":[98],"(5,000":[99],"replicates)":[100],"block":[103,136,275],"permutations":[104,137,276],"(10,000":[105],"replicates).":[106],"On":[107],"chromosomes,":[109],"achieved":[112],"an":[113],"ROC-AUC":[114],"of":[115,122,174,232,241,248],"0.7857":[116,270],"[95%":[117,124],"CI:":[118,125],"0.7672-0.8029]":[119],"PR-AUC":[121,272],"0.8027":[123],"0.7640-0.8337]":[126],"over":[127],"0.5755":[129],"prevalence":[130],"baseline,":[131],"outperforming":[132],"linear":[133],"baselines.":[134],"confirmed":[138],"significant":[139,205],"proximity":[140],"to":[141],"scATAC-seq":[142,260],"peaks":[143],"(Cliff\u2019s":[144],"\u03b4":[145,155],"\u22120.3364,":[147],"P":[148,158,188,213],"perm":[149,159],"<":[150,160],"0.0001)":[151],"TSSs":[153],"(":[154],"\u22120.2446,":[157],"0.0001),":[161],"alongside":[162],"82.71%":[163],"body":[165],"overlap":[166],"(OR":[167,185,210],"3.47).":[169],"Targeted":[170],"analysis":[171],"showed":[172],"99.91%":[173],"VIS":[175],"reside":[176],"distal":[177],"(>100":[178],"kb)":[179],"proto-oncogenes":[181,209],"without":[182,225],"proximal":[183],"enrichment":[184],"1.05,":[187],"0.617).":[190],"Furthermore,":[191],"longitudinal":[192],"tracking":[193],"identified":[194],"79,587":[195],"persistent":[196,233,285],"clones":[197,234,286],"(\u2265":[198],"2":[199],"time":[200],"points),":[201],"which":[202],"exhibited":[203],"31%":[206,288],"depletion":[207,231,289],"near":[208,235,279,290],"0.69,":[212],"0.014).":[215],"Compact":[216],"robustly":[221],"predict":[222],"lentiviral":[223,243,251],"data":[227],"leakage.":[228],"The":[229],"oncogenes":[236],"confirms":[237],"insertional":[239],"safety":[240],"SIN":[242],"therapy.":[245],"Highlights":[246],"Atlas":[247],"in":[255],"hg38.":[256],"Non-redundant":[257],"bone":[258],"marrow":[259],"union":[261],"atlas":[262],"maps":[263],"chromatin":[264],"accessibility.":[265],"Chromosome-disjoint":[266],"validation":[267],"achieves":[268],"AUROC":[269],"0.8027.":[273],"confirm":[277],"TSS":[280],"open":[282],"chromatin.":[283],"Longitudinal":[284],"exhibit":[287],"proto-oncogene.":[291]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-14T00:00:00"}
