{"id":"https://openalex.org/W7223346954","doi":"https://doi.org/10.64898/2026.10.18.759962","title":"An Interpretable Machine Learning Framework for Early- versus Late-Stage Classification of Breast Cancer from Gene Expression, with Co-expression Network Analysis","display_name":"An Interpretable Machine Learning Framework for Early- versus Late-Stage Classification of Breast Cancer from Gene Expression, with Co-expression Network Analysis","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223346954","doi":"https://doi.org/10.64898/2026.10.18.759962"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.18.759962","doi":"https://doi.org/10.64898/2026.10.18.759962","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.18.759962","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.18.759962.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","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.18.759962.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159017118","display_name":"Sriporna Biswas","orcid":"https://orcid.org/0009-0009-6683-5477","observed_orcids":["https://orcid.org/0009-0009-6683-5477"]},"institutions":[{"id":"https://openalex.org/I101407740","display_name":"Chandigarh University","ror":"https://ror.org/05t4pvx35","country_code":"IN","type":"education","lineage":["https://openalex.org/I101407740"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sriporna Biswas","raw_affiliation_strings":["Department of Computer Science & Engineering, Chandigarh University, Punjab, India 140413"],"raw_orcid":"https://orcid.org/0009-0009-6683-5477","affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Chandigarh University, Punjab, India 140413","institution_ids":["https://openalex.org/I101407740"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159001853","display_name":"Tanjidul Huda","orcid":"https://orcid.org/0009-0001-9522-1492","observed_orcids":["https://orcid.org/0009-0001-9522-1492"]},"institutions":[{"id":"https://openalex.org/I110166357","display_name":"University of Delhi","ror":"https://ror.org/04gzb2213","country_code":"IN","type":"education","lineage":["https://openalex.org/I110166357"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanjidul Huda","raw_affiliation_strings":["Department of Biomedical Science, BCAS, University of Delhi, Delhi, India 110007"],"raw_orcid":"https://orcid.org/0009-0001-9522-1492","affiliations":[{"raw_affiliation_string":"Department of Biomedical Science, BCAS, University of Delhi, Delhi, India 110007","institution_ids":["https://openalex.org/I110166357"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5159017118"],"corresponding_institution_ids":["https://openalex.org/I101407740"],"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/T10183","display_name":"Breast Cancer Treatment Studies","score":0.5619999766349792,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T10183","display_name":"Breast Cancer Treatment Studies","score":0.5619999766349792,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.4336000084877014,"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/T10862","display_name":"AI in cancer detection","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/breast-cancer","display_name":"breast cancer","score":0.9729999899864197},{"id":"https://openalex.org/keywords/early-breast-cancer","display_name":"early breast cancer","score":0.7770000100135803},{"id":"https://openalex.org/keywords/late-stage-breast-cancer","display_name":"late-stage breast cancer","score":0.8809999823570251},{"id":"https://openalex.org/keywords/gene-expression","display_name":"gene expression","score":0.6380000114440918},{"id":"https://openalex.org/keywords/transcriptome","display_name":"transcriptome","score":0.7419999837875366},{"id":"https://openalex.org/keywords/coexpression-network","display_name":"co-expression network","score":0.7269999980926514},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.8560000061988831},{"id":"https://openalex.org/keywords/gene-panel","display_name":"gene panel","score":0.4819999933242798},{"id":"https://openalex.org/keywords/oct4","display_name":"Oct4","score":0.8450000286102295},{"id":"https://openalex.org/keywords/flt3","display_name":"FLT3","score":0.984000027179718},{"id":"https://openalex.org/keywords/notch1","display_name":"Notch1","score":1.0},{"id":"https://openalex.org/keywords/rel","display_name":"REL","score":0.6430000066757202},{"id":"https://openalex.org/keywords/ep300","display_name":"EP300","score":0.9860000014305115},{"id":"https://openalex.org/keywords/esr1","display_name":"ESR1","score":0.9919999837875366},{"id":"https://openalex.org/keywords/cd44","display_name":"CD44","score":0.7089999914169312},{"id":"https://openalex.org/keywords/tcga-brca","display_name":"TCGA-BRCA","score":0.7670000195503235},{"id":"https://openalex.org/keywords/primary-tumor","display_name":"primary tumor","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6110000014305115},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.6085000038146973},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.5579000115394592},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.4812000095844269},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C143998085","wikidata":"https://www.wikidata.org/wiki/Q162555","display_name":"Oncology","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.32199999690055847},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.31869998574256897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3140000104904175},{"id":"https://openalex.org/C69991583","wikidata":"https://www.wikidata.org/wiki/Q1423575","display_name":"Candidate gene","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.30320000648498535},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C156957248","wikidata":"https://www.wikidata.org/wiki/Q1862216","display_name":"Odds ratio","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C3020225094","wikidata":"https://www.wikidata.org/wiki/Q80091","display_name":"Area under curve","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.18.759962","doi":"https://doi.org/10.64898/2026.10.18.759962","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.18.759962","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.18.759962.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:10.64898/2026.10.18.759962","doi":"https://doi.org/10.64898/2026.10.18.759962","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.18.759962","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/22/2026.10.18.759962.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":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.9476000070571899}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223346954.pdf","grobid_xml":"https://content.openalex.org/works/W7223346954.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4206165702","https://openalex.org/W4407390690","https://openalex.org/W4410361725"],"related_works":["https://openalex.org/W4289653821","https://openalex.org/W7101172605","https://openalex.org/W7163279656","https://openalex.org/W3009174700","https://openalex.org/W4392975215","https://openalex.org/W2253528542","https://openalex.org/W3088977911","https://openalex.org/W6958471654","https://openalex.org/W4414306340","https://openalex.org/W4417310060"],"abstract_inverted_index":{"ABSTRACT":[0],"Anatomical":[1],"stage":[2,22,66,224,299],"is":[3,16,23,216,316],"a":[4,36,92,120,254,268,278],"principal":[5],"determinant":[6],"of":[7,28,39,281,286],"treatment":[8],"and":[9,55,64,103,111,126,139,147,175,202,247,277,307],"prognosis":[10],"in":[11,179,193,309],"breast":[12,53,72],"cancer,":[13,54],"yet":[14],"it":[15],"unclear":[17],"how":[18],"much":[19],"information":[20,294],"about":[21,295],"carried":[24],"by":[25,131],"the":[26,29,80,86,156,162,194,214,250],"transcriptome":[27],"primary":[30,89],"tumour.":[31],"We":[32],"asked":[33],"whether":[34],"an":[35],"priori":[37],"panel":[38,289],"65":[40],"cancer-related":[41],"genes":[42,57],"can":[43],"distinguish":[44],"early-stage":[45],"(AJCC":[46],"Stage":[47],"I\u2013II)":[48],"from":[49,79,240],"late-stage":[50,282],"(Stage":[51],"III\u2013IV)":[52],"which":[56],"contribute":[58],"to":[59,88],"any":[60,313],"signal.":[61],"RNA-seq":[62],"expression":[63],"pathologic":[65],"for":[67],"The":[68],"Cancer":[69],"Genome":[70],"Atlas":[71],"invasive":[73],"carcinoma":[74],"cohort":[75],"(TCGA-BRCA)":[76],"were":[77,97,129,183],"obtained":[78],"UCSC":[81],"Xena":[82],"platform.":[83],"After":[84],"restricting":[85],"data":[87,145],"tumours":[90,96,242],"with":[91,135,169,264,304],"known":[93],"stage,":[94],"1,075":[95],"analysed":[98],"(805":[99],"early,":[100],"270":[101],"late)":[102],"split":[104],"into":[105],"stratified":[106,132],"training":[107,144,153,241],"(n":[108,114],"=":[109,115,189,232],"860)":[110],"held-out":[112],"test":[113,157,283],"215)":[116],"sets.":[117],"Logistic":[118,159],"regression,":[119],"support":[121],"vector":[122],"machine,":[123],"random":[124],"forest":[125],"gradient":[127],"boosting":[128],"tuned":[130],"five-fold":[133],"cross-validation,":[134],"median":[136],"imputation,":[137],"standardisation":[138],"SMOTE":[140],"oversampling":[141],"fitted":[142],"on":[143,151],"only":[146],"classification":[148],"thresholds":[149],"chosen":[150],"out-of-fold":[152],"predictions.":[154],"On":[155],"set,":[158],"Regression":[160],"had":[161],"highest":[163],"ROC-AUC,":[164],"0.618":[165],"(95%":[166],"CI":[167],"0.530\u20130.704),":[168],"balanced":[170],"accuracy":[171],"0.578,":[172],"sensitivity":[173],"0.741":[174],"specificity":[176],"0.416;":[177],"differences":[178],"AUC":[180,208],"between":[181,223],"models":[182,300],"not":[184],"statistically":[185],"significant":[186],"(DeLong":[187],"p":[188],"0.199\u20130.585).":[190],"Permutation":[191],"importance":[192],"Gradient":[195],"Boosting":[196],"model":[197],"ranked":[198],"POU5F1":[199],",":[200,245],"FLT3":[201],"NOTCH1":[203],"highest,":[204],"but":[205,292],"this":[206,287],"model\u2019s":[207],"confidence":[209],"interval":[210],"included":[211],"0.5,":[212],"so":[213],"ranking":[215],"exploratory.":[217],"No":[218],"gene":[219,288],"was":[220],"differentially":[221],"expressed":[222],"groups":[225],"after":[226],"false-discovery-rate":[227],"(FDR)":[228],"correction":[229],"(smallest":[230],"FDR":[231],"0.057,":[233],"CD44":[234],").":[235],"A":[236],"co-expression":[237,258],"network":[238],"built":[239],"identified":[243],"REL":[244],"EP300":[246],"ESR1":[248],"as":[249],"most":[251],"connected":[252],"genes,":[253],"property":[255],"that":[256],"reflects":[257],"rather":[259],"than":[260],"regulation":[261],"or":[262],"association":[263],"stage.":[265],"Limitations":[266],"include":[267],"single":[269],"cohort,":[270],"no":[271,274],"external":[272],"validation,":[273],"clinical":[275,314],"covariates":[276],"small":[279],"number":[280],"tumours.":[284],"Expression":[285],"carries":[290],"limited":[291],"measurable":[293],"anatomical":[296],"stage;":[297],"expression-based":[298],"should":[301],"be":[302],"combined":[303],"clinicopathological":[305],"variables":[306],"validated":[308],"independent":[310],"cohorts":[311],"before":[312],"application":[315],"considered.":[317]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-24T00:00:00"}