{"id":"https://openalex.org/W7225168091","doi":"https://doi.org/10.64898/2026.10.28.762524","title":"ssGSEA3.0: Feature-Level Bootstrap Resampling for Robust Assessment of Statistical Significance","display_name":"ssGSEA3.0: Feature-Level Bootstrap Resampling for Robust Assessment of Statistical Significance","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225168091","doi":"https://doi.org/10.64898/2026.10.28.762524"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.28.762524","doi":"https://doi.org/10.64898/2026.10.28.762524","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762524","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.28.762524.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.28.762524.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040624110","display_name":"Natalie M. Clark","orcid":"https://orcid.org/0000-0003-0988-321X","observed_orcids":["https://orcid.org/0000-0003-0988-321X"]},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalie M Clark","raw_affiliation_strings":["Broad Institute of MIT and Harvard"],"raw_orcid":"https://orcid.org/0000-0003-0988-321X","affiliations":[{"raw_affiliation_string":"Broad Institute of MIT and Harvard","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015184631","display_name":"D.R. Mani","orcid":"https://orcid.org/0000-0003-3914-133X","observed_orcids":["https://orcid.org/0000-0003-3914-133X"]},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. R. Mani","raw_affiliation_strings":["Broad Institute of MIT and Harvard"],"raw_orcid":"https://orcid.org/0000-0003-3914-133X","affiliations":[{"raw_affiliation_string":"Broad Institute of MIT and Harvard","institution_ids":["https://openalex.org/I107606265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015184631"],"corresponding_institution_ids":["https://openalex.org/I107606265"],"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9990000128746033,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9990000128746033,"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":0.0003000000142492354,"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/T10885","display_name":"Gene expression and cancer classification","score":0.00019999999494757503,"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/ssgsea","display_name":"single-sample gene set enrichment analysis","score":0.8289999961853027},{"id":"https://openalex.org/keywords/pathway-enrichment-analysis","display_name":"pathway enrichment","score":0.7310000061988831},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.9139999747276306},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"false positive rate","score":0.5770000219345093},{"id":"https://openalex.org/keywords/phosphoproteomics","display_name":"phosphoproteomics","score":0.847000002861023},{"id":"https://openalex.org/keywords/lung-adenocarcinoma","display_name":"lung adenocarcinoma","score":0.9760000109672546},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8108999729156494},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5257999897003174},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44190001487731934},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42590001225471497},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.40939998626708984},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C137668524","wikidata":"https://www.wikidata.org/wiki/Q189813","display_name":"Censoring (clinical trials)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C81790035","wikidata":"https://www.wikidata.org/wiki/Q847158","display_name":"Jackknife resampling","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.28.762524","doi":"https://doi.org/10.64898/2026.10.28.762524","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762524","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.28.762524.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.28.762524","doi":"https://doi.org/10.64898/2026.10.28.762524","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762524","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.28.762524.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.46810001134872437,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"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/W7225168091.pdf","grobid_xml":"https://content.openalex.org/works/W7225168091.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2904372598","https://openalex.org/W7224117068"],"related_works":["https://openalex.org/W4393866771","https://openalex.org/W7163702325","https://openalex.org/W4210522554","https://openalex.org/W2103209361","https://openalex.org/W2521164301","https://openalex.org/W4396949834","https://openalex.org/W2555986520","https://openalex.org/W3099862724","https://openalex.org/W2134582937","https://openalex.org/W4405005376"],"abstract_inverted_index":{"Motivation":[0],"Single-sample":[1],"Gene/Post-Translational":[2],"Modification":[3],"Set":[4],"Enrichment":[5],"Analysis":[6],"(ssGSEA/PTM-SEA)":[7],"methods":[8],"assess":[9],"pathway":[10],"or":[11,54],"signature":[12],"activity":[13],"per":[14],"sample":[15],"using":[16],"permutation-based":[17],"significance":[18],"testing.":[19],"ssGSEA2.0's":[20],"weighted":[21],"scoring":[22],"(ssGSEA2.0-orig)":[23],"uses":[24],"a":[25,103],"correlation-vector":[26],"reordering":[27],"that":[28],"inflates":[29],"false":[30],"positives":[31],"at":[32,46,98],"nonzero":[33,47,99],"weight;":[34],"directly":[35],"fixing":[36],"this":[37],"(ssGSEA2.0-fixed)":[38],"restores":[39],"null-distribution":[40],"calibration":[41],"but":[42],"sacrifices":[43],"detection":[44,78],"power":[45,79],"weight.":[48,100],"Results":[49],"ssGSEA3.0":[50,75,112],"replaces":[51],"feature-label":[52],"(gene-":[53],"site-level)":[55],"permutation":[56],"with":[57,82],"feature-level":[58],"bootstrap":[59],"resampling,":[60],"which":[61],"remains":[62],"calibrated":[63],"across":[64,95],"weighting":[65],"schemes.":[66],"On":[67],"published":[68,91],"lung":[69],"adenocarcinoma":[70],"and":[71,110,123],"phosphoproteomic":[72],"perturbation":[73],"datasets,":[74],"shows":[76],"greater":[77],"than":[80],"ssGSEA2.0-fixed,":[81],"an":[83,116],"additional":[84],"gain":[85],"for":[86],"directional":[87],"(PTM-SEA)":[88],"scoring.":[89],"Previously":[90],"findings":[92],"remain":[93],"robust":[94],"methods,":[96],"including":[97],"Bootstrapping":[101],"adds":[102],"~1.5-":[104],"to":[105],"2-fold":[106],"computational":[107],"cost.":[108],"Availability":[109],"Implementation":[111],"is":[113],"implemented":[114],"as":[115],"open-source":[117],"R":[118],"package":[119],"(github.com/broadinstitute/ssGSEA3.0,":[120],"DOI:":[121],"10.5281/zenodo.23734262)":[122],"includes":[124],"the":[125],"worked":[126],"examples":[127],"on":[128],"biological":[129],"data":[130],"presented":[131],"here.":[132]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}