{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38585981", "kind": "science-record", "revision": 3, "content_hash": "sha256:9a25e1a4bda6f672f4398c5f704a92431ccbbd0041c2ef4813dd490a4201bcc8", "created_at": "2026-11-01T19:20:33Z", "updated_at": "2026-11-01T22:54:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "CD133 expression is associated with less DNA repair, better response to chemotherapy and survival in ER-positive/HER2-negative breast cancer.", "doi": "10.21203/rs.3.rs-4148608/v1", "pmid": "38585981", "authors": ["Takumi Sato", "Masanori Oshi", "Jing Li Huang", "Kohei Chida", "Arya Mariam Roy", "Itaru Endo", "Kazuaki Takabe"], "journal": "Research square", "year": 2024, "abstract": "Purpose: CD133, a cancer stem cells (CSC) marker, has been reported to be associated with treatment resistance and worse survival in triple-negative breast cancer (BC). However, the clinical relevance of CD133 expression in ER-positive/HER2-negative (ER+/HER2-) BC, the most abundant subtype, remains unknown.\nMethods: The BC cohorts from the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC, n = 1904) and The Cancer Genome Atlas (TCGA, n = 1065) were used to obtain biological variables and gene expression data.\nResults: Epithelial cells were the exclusive source of CD133 gene expression in a bulk BC. CD133-high ER+/HER2- BC was associated with CD24, NOTCH1, DLL1, and ALDH1A1 gene expressions, as well as with WNT/β-Catenin, Hedgehog, and Notchsignaling pathways, all characteristic for CSC. Consistent with a CSC phenotype, CD133-low BC was enriched with gene sets related to cell proliferation, such as G2M Checkpoint, MYC Targets V1, E2F Targets, and Ki67 gene expression. CD133-low BC was also linked with enrichment of genes related to DNA repair, such as BRCA1, E2F1, E2F4, CDK1/2. On the other hand, CD133-high tumors had proinflammatory microenvironment, higher activity of immune cells, and higher expression of genes related to inflammation and immune response. Finally, CD133-high tumors had better pathological complete response after neoadjuvant chemotherapy in GSE25066 cohort and better disease-free survival and overall survival in both TCGA and METABRIC cohorts.\nConclusion: CD133-high ER+/HER2- BC was associated with CSC phenotype such as less cell proliferation and DNA repair, but also with enhanced inflammation, better response to neoadjuvant chemotherapy and better prognosis.", "claims": [{"id": "claim-method", "statement": "Survival analyses were performed using Kaplan-Meier plots with log-rank tests.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38585981", "locator": "sections[6] \"Statistical Analysis\" paragraph 2", "quote": "Survival analyses were performed using Kaplan-Meier plots with log-rank tests."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38585981", "locator": "sections[20] \"Data Availability:\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271]."}], "state": "complete"}, {"id": "claim-target-result", "statement": "CD133-high ER+/HER2− BC was associated with CSC phenotype such as less cell proliferation and DNA repair, but also with enhanced inflammation, better response to neoadjuvant chemotherapy and better prognosis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38585981", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "CD133-high ER+/HER2− BC was associated with CSC phenotype such as less cell proliferation and DNA repair, but also with enhanced inflammation, better response to neoadjuvant chemotherapy and better prognosis."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "CD133-high ER+/HER2− BC was associated with CSC phenotype such as less cell proliferation and DNA repair, but also with enhanced inflammation, better response to neoadjuvant chemotherapy and better prognosis.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:38585981"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE20194"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE20194"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38585981", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21203/rs.3.rs-4148608/v1", "sha256": "sha256:3899be6053bcbb32ad9bb73ae0258ef09d06207b47e676ed8f2da73de7dec97d", "bytes": 48497, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21203/rs.3.rs-4148608/v1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10996805", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20194", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE20194", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20194", "version": null, "note": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM505327", "GSM505328", "GSM505329", "GSM505330", "GSM505331", "GSM505333", "GSM505334", "GSM505335", "GSM505336", "GSM505337", "GSM505338", "GSM505339", "GSM505340", "GSM505341", "GSM505342", "GSM505343", "GSM505344", "GSM505345", "GSM505346", "GSM505347", "GSM505348", "GSM505349", "GSM505350", "GSM505351", "GSM505352", "GSM505353", "GSM505354", "GSM505355", "GSM505356", "GSM505357", "GSM505358", "GSM505359", "GSM505360", "GSM505361", "GSM505362", "GSM505363", "GSM505364", "GSM505365", "GSM505366", "GSM505367", "GSM505368", "GSM505369", "GSM505370", "GSM505371", "GSM505372", "GSM505373", "GSM505374", "GSM505375", "GSM505376", "GSM505377", "GSM505378", "GSM505379", "GSM505380", "GSM505381", "GSM505382", "GSM505383", "GSM505384", "GSM505385", "GSM505386", "GSM505387", "GSM505388", "GSM505389", "GSM505390", "GSM505391", "GSM505392", "GSM505393", "GSM505394", "GSM505395", "GSM505396", "GSM505397", "GSM505398", "GSM505399", "GSM505400", "GSM505401", "GSM505402", "GSM505403", "GSM505404", "GSM505405", "GSM505406", "GSM505407", "GSM505408", "GSM505409", "GSM505410", "GSM505411", "GSM505412", "GSM505413", "GSM505414", "GSM505415", "GSM505416", "GSM505417", "GSM505418", "GSM505419", "GSM505420", "GSM505421", "GSM505422", "GSM505423", "GSM505424", "GSM505425", "GSM505426", "GSM505427", "GSM505428", "GSM505429", "GSM505430", "GSM505431", "GSM505432", "GSM505433", "GSM505434", "GSM505435", "GSM505436", "GSM505437", "GSM505438", "GSM505439", "GSM505440", "GSM505441", "GSM505442", "GSM505443", "GSM505444", "GSM505445", "GSM505446", "GSM505447", "GSM505448", "GSM505449", "GSM505450", "GSM505451", "GSM505452", "GSM505453", "GSM505454", "GSM505455", "GSM505456", "GSM505457", "GSM505458", "GSM505459", "GSM505460", "GSM505461", "GSM505462", "GSM505463", "GSM505464", "GSM505465", "GSM505466", "GSM505467", "GSM505468", "GSM505469", "GSM505470", "GSM505471", "GSM505472", "GSM505473", "GSM505474", "GSM505475", "GSM505476", "GSM505477", "GSM505478", "GSM505479", "GSM505480", "GSM505481", "GSM505482", "GSM505483", "GSM505484", "GSM505485", "GSM505486", "GSM505487", "GSM505488", "GSM505489", "GSM505490", "GSM505491", "GSM505492", "GSM505493", "GSM505494", "GSM505495", "GSM505496", "GSM505497", "GSM505498", "GSM505499", "GSM505500", "GSM505501", "GSM505502", "GSM505503", "GSM505504", "GSM505505", "GSM505506", "GSM505507", "GSM505508", "GSM505509", "GSM505510", "GSM505511", "GSM505512", "GSM505513", "GSM505514", "GSM505515", "GSM505516", "GSM505517", "GSM505518", "GSM505519", "GSM505520", "GSM505521", "GSM505522", "GSM505523", "GSM505524", "GSM505525", "GSM505526", "GSM505527", "GSM505528", "GSM505529", "GSM505530", "GSM505531", "GSM505532", "GSM505533", "GSM505534", "GSM505535", "GSM505536", "GSM505537", "GSM505538", "GSM505539", "GSM505540", "GSM505541", "GSM505542", "GSM505543", "GSM505544", "GSM505545", "GSM505546", "GSM505547", "GSM505548", "GSM505549", "GSM505550", "GSM505551", "GSM505552", "GSM505553", "GSM505554", "GSM505555", "GSM505556", "GSM505557", "GSM505558", "GSM505559", "GSM505560", "GSM505561", "GSM505562", "GSM505563", "GSM505564", "GSM505565", "GSM505566", "GSM505567", "GSM505568", "GSM505569", "GSM505570", "GSM505571", "GSM505572", "GSM505573", "GSM505574", "GSM505575", "GSM505576", "GSM505577", "GSM505578", "GSM505579", "GSM505580", "GSM505581", "GSM505582", "GSM505583", "GSM505584", "GSM505585", "GSM505586", "GSM505587", "GSM505588", "GSM505589", "GSM505590", "GSM505591", "GSM505592", "GSM505593", "GSM505594", "GSM505595", "GSM505596", "GSM505597", "GSM505598", "GSM505599", "GSM505600", "GSM505601", "GSM505602", "GSM505603", "GSM505604", "GSM505605"], "sample_count": 278, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "MAQC-II Project: human breast cancer (BR) data set", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE25066", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE25066", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25066", "version": null, "note": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM615096", "GSM615097", "GSM615098", "GSM615099", "GSM615100", "GSM615101", "GSM615102", "GSM615103", "GSM615104", "GSM615105", "GSM615106", "GSM615107", "GSM615108", "GSM615109", "GSM615110", "GSM615111", "GSM615112", "GSM615113", "GSM615114", "GSM615115", "GSM615116", "GSM615117", "GSM615118", "GSM615119", "GSM615120", "GSM615121", "GSM615122", "GSM615123", "GSM615124", "GSM615125", "GSM615126", "GSM615127", "GSM615128", "GSM615129", "GSM615130", "GSM615131", "GSM615132", "GSM615133", "GSM615134", "GSM615135", "GSM615136", "GSM615137", "GSM615138", "GSM615139", "GSM615140", "GSM615141", "GSM615142", "GSM615143", "GSM615144", "GSM615145", "GSM615146", "GSM615147", "GSM615148", "GSM615149", "GSM615150", "GSM615151", "GSM615152", "GSM615153", "GSM615154", "GSM615155", "GSM615156", "GSM615157", "GSM615158", "GSM615159", "GSM615160", "GSM615161", "GSM615162", "GSM615163", "GSM615164", "GSM615165", "GSM615166", "GSM615167", "GSM615168", "GSM615169", "GSM615170", "GSM615171", "GSM615172", "GSM615173", "GSM615174", "GSM615175", "GSM615176", "GSM615177", "GSM615178", "GSM615179", "GSM615180", "GSM615181", "GSM615182", "GSM615183", "GSM615184", "GSM615185", "GSM615186", "GSM615187", "GSM615188", "GSM615189", "GSM615190", "GSM615191", "GSM615192", "GSM615193", "GSM615194", "GSM615195", "GSM615196", "GSM615197", "GSM615198", "GSM615199", "GSM615200", "GSM615201", "GSM615202", "GSM615203", "GSM615204", "GSM615205", "GSM615206", "GSM615207", "GSM615208", "GSM615209", "GSM615210", "GSM615211", "GSM615212", "GSM615213", "GSM615214", "GSM615215", "GSM615216", "GSM615217", "GSM615218", "GSM615219", "GSM615220", "GSM615221", "GSM615222", "GSM615223", "GSM615224", "GSM615225", "GSM615226", "GSM615227", "GSM615228", "GSM615229", "GSM615230", "GSM615231", "GSM615232", "GSM615233", "GSM615234", "GSM615235", "GSM615236", "GSM615237", "GSM615238", "GSM615239", "GSM615240", "GSM615241", "GSM615242", "GSM615243", "GSM615244", "GSM615245", "GSM615246", "GSM615247", "GSM615248", "GSM615249", "GSM615250", "GSM615251", "GSM615252", "GSM615253", "GSM615254", "GSM615255", "GSM615256", "GSM615257", "GSM615258", "GSM615259", "GSM615260", "GSM615261", "GSM615262", "GSM615263", "GSM615264", "GSM615265", "GSM615266", "GSM615267", "GSM615268", "GSM615269", "GSM615270", "GSM615271", "GSM615272", "GSM615273", "GSM615274", "GSM615275", "GSM615276", "GSM615277", "GSM615278", "GSM615279", "GSM615280", "GSM615281", "GSM615282", "GSM615283", "GSM615284", "GSM615285", "GSM615286", "GSM615287", "GSM615288", "GSM615289", "GSM615290", "GSM615291", "GSM615292", "GSM615293", "GSM615294", "GSM615295", "GSM615296", "GSM615297", "GSM615298", "GSM615299", "GSM615300", "GSM615301", "GSM615302", "GSM615303", "GSM615304", "GSM615305", "GSM615306", "GSM615307", "GSM615308", "GSM615309", "GSM615310", "GSM615311", "GSM615312", "GSM615313", "GSM615314", "GSM615315", "GSM615316", "GSM615317", "GSM615318", "GSM615319", "GSM615320", "GSM615321", "GSM615322", "GSM615323", "GSM615324", "GSM615325", "GSM615326", "GSM615327", "GSM615328", "GSM615329", "GSM615330", "GSM615331", "GSM615332", "GSM615333", "GSM615334", "GSM615335", "GSM615336", "GSM615337", "GSM615338", "GSM615339", "GSM615340", "GSM615341", "GSM615342", "GSM615343", "GSM615344", "GSM615345", "GSM615346", "GSM615347", "GSM615348", "GSM615349", "GSM615350", "GSM615351", "GSM615352", "GSM615353", "GSM615354", "GSM615355", "GSM615356", "GSM615357", "GSM615358", "GSM615359", "GSM615360", "GSM615361", "GSM615362", "GSM615363", "GSM615364", "GSM615365", "GSM615366", "GSM615367", "GSM615368", "GSM615369", "GSM615370", "GSM615371", "GSM615372", "GSM615373", "GSM615374", "GSM615375", "GSM615376", "GSM615377", "GSM615378", "GSM615379", "GSM615380", "GSM615381", "GSM615382", "GSM615383", "GSM615384", "GSM615385", "GSM615386", "GSM615387", "GSM615388", "GSM615389", "GSM615390", "GSM615391", "GSM615392", "GSM615393", "GSM615394", "GSM615395", "GSM615396", "GSM615397", "GSM615398", "GSM615399", "GSM615400", "GSM615401", "GSM615402", "GSM615403", "GSM615404", "GSM615405", "GSM615631", "GSM615632", "GSM615633", "GSM615634", "GSM615635", "GSM615636", "GSM615637", "GSM615638", "GSM615639", "GSM615640", "GSM615641", "GSM615642", "GSM615643", "GSM615644", "GSM615645", "GSM615646", "GSM615647", "GSM615648", "GSM615649", "GSM615650", "GSM615651", "GSM615652", "GSM615653", "GSM615654", "GSM615655", "GSM615656", "GSM615657", "GSM615658", "GSM615659", "GSM615660", "GSM615661", "GSM615662", "GSM615663", "GSM615664", "GSM615665", "GSM615666", "GSM615667", "GSM615668", "GSM615669", "GSM615670", "GSM615671", "GSM615672", "GSM615673", "GSM615674", "GSM615675", "GSM615676", "GSM615677", "GSM615678", "GSM615679", "GSM615680", "GSM615681", "GSM615682", "GSM615683", "GSM615684", "GSM615685", "GSM615686", "GSM615687", "GSM615688", "GSM615689", "GSM615690", "GSM615691", "GSM615692", "GSM615693", "GSM615694", "GSM615695", "GSM615696", "GSM615697", "GSM615698", "GSM615699", "GSM615700", "GSM615701", "GSM615702", "GSM615703", "GSM615704", "GSM615705", "GSM615706", "GSM615707", "GSM615708", "GSM615709", "GSM615710", "GSM615711", "GSM615712", "GSM615713", "GSM615714", "GSM615715", "GSM615716", "GSM615717", "GSM615718", "GSM615719", "GSM615720", "GSM615721", "GSM615722", "GSM615723", "GSM615724", "GSM615725", "GSM615726", "GSM615727", "GSM615728", "GSM615729", "GSM615730", "GSM615731", "GSM615732", "GSM615733", "GSM615734", "GSM615735", "GSM615736", "GSM615737", "GSM615738", "GSM615739", "GSM615740", "GSM615741", "GSM615742", "GSM615743", "GSM615744", "GSM615745", "GSM615746", "GSM615747", "GSM615748", "GSM615749", "GSM615750", "GSM615751", "GSM615752", "GSM615753", "GSM615754", "GSM615755", "GSM615756", "GSM615757", "GSM615758", "GSM615759", "GSM615760", "GSM615761", "GSM615762", "GSM615763", "GSM615764", "GSM615765", "GSM615766", "GSM615767", "GSM615768", "GSM615769", "GSM615770", "GSM615771", "GSM615772", "GSM615773", "GSM615774", "GSM615775", "GSM615776", "GSM615777", "GSM615778", "GSM615779", "GSM615780", "GSM615781", "GSM615782", "GSM615783", "GSM615784", "GSM615785", "GSM615786", "GSM615787", "GSM615788", "GSM615789", "GSM615790", "GSM615791", "GSM615792", "GSM615793", "GSM615794", "GSM615795", "GSM615796", "GSM615797", "GSM615798", "GSM615799", "GSM615800", "GSM615801", "GSM615802", "GSM615803", "GSM615804", "GSM615805", "GSM615806", "GSM615807", "GSM615808", "GSM615809", "GSM615810", "GSM615811", "GSM615812", "GSM615813", "GSM615814", "GSM615815", "GSM615816", "GSM615817", "GSM615818", "GSM615819", "GSM615820", "GSM615821", "GSM615822", "GSM615823", "GSM615824", "GSM615825", "GSM615826", "GSM615827", "GSM615828"], "sample_count": 508, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Genomic predictor of response and survival following neoadjuvant taxane-anthracycline chemotherapy in breast cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE32646", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32646", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32646", "version": null, "note": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM809184", "GSM809185", "GSM809186", "GSM809187", "GSM809188", "GSM809189", "GSM809190", "GSM809191", "GSM809192", "GSM809193", "GSM809194", "GSM809195", "GSM809196", "GSM809197", "GSM809198", "GSM809199", "GSM809200", "GSM809201", "GSM809202", "GSM809203", "GSM809204", "GSM809205", "GSM809206", "GSM809207", "GSM809208", "GSM809209", "GSM809210", "GSM809211", "GSM809212", "GSM809213", "GSM809214", "GSM809215", "GSM809216", "GSM809217", "GSM809218", "GSM809219", "GSM809220", "GSM809221", "GSM809222", "GSM809223", "GSM809224", "GSM809225", "GSM809226", "GSM809227", "GSM809228", "GSM809229", "GSM809230", "GSM809231", "GSM809232", "GSM809233", "GSM809234", "GSM809235", "GSM809236", "GSM809237", "GSM809238", "GSM809239", "GSM809240", "GSM809241", "GSM809242", "GSM809243", "GSM809244", "GSM809245", "GSM809246", "GSM809247", "GSM809248", "GSM809249", "GSM809250", "GSM809251", "GSM809252", "GSM809253", "GSM809254", "GSM809255", "GSM809256", "GSM809257", "GSM809258", "GSM809259", "GSM809260", "GSM809261", "GSM809262", "GSM809263", "GSM809264", "GSM809265", "GSM809266", "GSM809267", "GSM809268", "GSM809269", "GSM809270", "GSM809271", "GSM809272", "GSM809273", "GSM809274", "GSM809275", "GSM809276", "GSM809277", "GSM809278", "GSM809279", "GSM809280", "GSM809281", "GSM809282", "GSM809283", "GSM809284", "GSM809285", "GSM809286", "GSM809287", "GSM809288", "GSM809289", "GSM809290", "GSM809291", "GSM809292", "GSM809293", "GSM809294", "GSM809295", "GSM809296", "GSM809297", "GSM809298"], "sample_count": 115, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "GSTP1 expression predicts poor pathological complete response to neoadjuvant chemotherapy in ER-negative breast cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE20194 not downloaded", "asset:data:geo:GSE20194 licence not read", "asset:data:geo:GSE25066 not downloaded", "asset:data:geo:GSE25066 licence not read", "asset:data:geo:GSE32646 not downloaded", "asset:data:geo:GSE32646 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Survival analyses were performed using Kaplan-Meier plots with log-rank tests."}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE25066", "GSE20194", "GSE32646"], "resolved_accessions": ["GSE25066", "GSE20194", "GSE32646"], "statements": ["Publicly available datasets were analyzed in this study. TCGA data can be found here: [https://www.cbioportal.org. /Breast Invasive Carcinoma (TCGA, PanCancer Atlas)]. METABRIC data can be found here: [https://www.cbioportal.org. / Breast Cancer (METABRIC, Nature 2012 & Nat Commun 2016)]. Data sets from each of the GEO databases can be downloaded from the following sites and access numbers: [https://www.ncbi.nlm.nih.gov/geo./GSE96058/GSE2034/GSE124647/GSE159956/GSE12276/GSE110590/GSE20194/GSE25066/GSE163882/ GSE20271]."], "basis": "The paper names GSE25066, GSE20194, GSE32646 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:38585981", "data:geo:GSE20194"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20194"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:15:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14884, "completion_tokens": 2638, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:38585981", "type": "paper", "label": "pmid:38585981"}, {"id": "source:pmid:38585981", "type": "manuscript", "label": "PMID 38585981 full text"}, {"id": "data:geo:GSE20194", "type": "dataset", "label": "GEO GSE20194"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38585981", "type": "paper", "label": "pmid:38585981"}, {"id": "source:pmid:38585981", "type": "manuscript", "label": "PMID 38585981 full text"}, {"id": "data:geo:GSE20194", "type": "dataset", "label": "GEO GSE20194"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38585981", "type": "extraction", "used": ["source:pmid:38585981"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20194", "type": "accession_resolution", "used": ["data:geo:GSE20194"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:38585981", "parent_hash": "sha256:f94ff6d78b8b4e7a7955b2ed639a5a0dcd36c15280172f4321d782201adb366f", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE20194 licence not read", "asset:data:geo:GSE20194 not downloaded", "asset:data:geo:GSE25066 licence not read", "asset:data:geo:GSE25066 not downloaded", "asset:data:geo:GSE32646 licence not read", "asset:data:geo:GSE32646 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["Checkpoint, MYC Targets V1, E2F Targets, and Ki67 gene expression. CD133-low BC was also linke"], "order_basis": "paper_text_order:1079", "id": "assay:1"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["ts analyzed in this study include cohorts of patients who received neoadjuvant chemotherapy (NAC); GSE"], "order_basis": "paper_text_order:2440", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Survival analyses were performed using Kaplan-Meier plots with log-rank tests."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:52:35+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}