A novel five-gene score to predict complete pathological response to neoadjuvant chemotherapy in ER-positive/HER2-negative breast cancer.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34354863", "kind": "science-record", "revision": 3, "content_hash": "sha256:fd50f73501b1ea9c7e86fef36a0bdfd2aa592cfeb7f430e0b197968943775617", "created_at": "2026-11-01T17:35:53Z", "updated_at": "2026-11-01T21:25:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "partial", "title": "A novel five-gene score to predict complete pathological response to neoadjuvant chemotherapy in ER-positive/HER2-negative breast cancer.", "doi": null, "pmid": "34354863", "authors": ["Masanori Oshi", "Shipra Gandhi", "Fernando A Angarita", "Tae Hee Kim", "Yoshihisa Tokumaru", "Li Yan", "Ryusei Matsuyama", "Itaru Endo", "Kazuaki Takabe"], "journal": "American journal of cancer research", "year": 2021, "abstract": "Neoadjuvant Chemotherapy (NAC) is not frequently used in ER-positive/HER2-negative breast cancer (BC) because around 10% patients achieve pathological complete response (pCR). Since NAC can result in cancer downstaging both in the breast and axilla and prevent a morbid surgery, thus a score to predict pCR in this population will be crucial to identify patients who can benefit from this approach. A total of 4038 patients from cohorts; GSE25066, GSE20194, Hess, GSE20181, TCGA-BRCA and METBRIC were analyzed. The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR. The area under the curve was significantly higher in the score than that for the E2F targets score. High score ER-positive/HER2-negative BCs were significantly associated with higher Nottingham pathological grade, AJCC cancer stage, MKI67 expression levels, intratumor heterogeneity, homologous recombination defects, mutation burden, neoantigen load, and infiltration of anti-cancer immune cells (CD4+, T helper type1, plasmacytoid dendritic cells, M1 macrophages). They also expressed lower abundance of stromal cells including fibroblasts, lymphatic endothelial cells, pericytes and adipocytes consistently in GSE25066, TCGA and METABRIC cohorts. All cell proliferation-related gene sets, G2M checkpoint, E2F targets, MYC targets v1 and v2, Mitotic Spindle, were strongly enriched in high score BCs consistently in 3 cohorts. The gene score was significantly associated with high pCR rate consistently in the GSE25066 (38%, P < 0.001), GSE20194 (16%, P = 0.006), and Hess cohort (23%, P = 0.037). In conclusion, the 5-gene score reflects cancer cell proliferation and immune cell infiltration, and predicts pCR after NAC in ER-positive/HER2-negative breast cancer.", "claims": [{"id": "claim-method", "statement": "The area under the curve was significantly higher in the score than that for the E2F targets score.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34354863", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The area under the curve was significantly higher in the score than that for the E2F targets score."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34354863", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR."}], "state": "complete"}], "gaps": ["doi"]}, "experiment": {"state": "complete", "objective": "", "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:34354863"], "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:GSE20181"], "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:GSE20181"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34354863", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": null, "sha256": "sha256:df464a6bc4c01b6c85cbcc3b035ad9d13117473b5d12394e6a4246f29ba5d534", "bytes": 1881, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "34354863", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8332850", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20181", "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=GSE20181", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20181", "version": null, "note": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM125123", "GSM125124", "GSM125125", "GSM125126", "GSM125127", "GSM125128", "GSM125129", "GSM125130", "GSM125131", "GSM125132", "GSM125133", "GSM125134", "GSM125135", "GSM125136", "GSM125137", "GSM125138", "GSM125139", "GSM125140", "GSM125141", "GSM125142", "GSM125143", "GSM125144", "GSM125145", "GSM125146", "GSM125147", "GSM125148", "GSM125149", "GSM125150", "GSM125151", "GSM125152", "GSM125153", "GSM125154", "GSM125155", "GSM125156", "GSM125157", "GSM125158", "GSM125159", "GSM125160", "GSM125161", "GSM125162", "GSM125163", "GSM125164", "GSM125165", "GSM125166", "GSM125167", "GSM125168", "GSM125169", "GSM125170", "GSM125171", "GSM125172", "GSM125173", "GSM125174", "GSM125175", "GSM125176", "GSM125177", "GSM125178", "GSM125179", "GSM125180", "GSM125181", "GSM125182", "GSM125183", "GSM125184", "GSM125185", "GSM125186", "GSM125187", "GSM125188", "GSM125189", "GSM125190", "GSM125191", "GSM125192", "GSM125193", "GSM125194", "GSM125195", "GSM125196", "GSM125197", "GSM125198", "GSM125199", "GSM125200", "GSM125201", "GSM125202", "GSM125203", "GSM125204", "GSM125205", "GSM125206", "GSM125207", "GSM125208", "GSM125209", "GSM125210", "GSM125211", "GSM125212", "GSM125213", "GSM125214", "GSM125215", "GSM125216", "GSM125217", "GSM125218", "GSM125219", "GSM125220", "GSM125221", "GSM125222", "GSM125223", "GSM125224", "GSM125225", "GSM125226", "GSM125227", "GSM125228", "GSM125229", "GSM125230", "GSM125231", "GSM125232", "GSM125233", "GSM125234", "GSM125235", "GSM125236", "GSM125237", "GSM125238", "GSM506267", "GSM506268", "GSM506269", "GSM506270", "GSM506271", "GSM506272", "GSM506273", "GSM506274", "GSM506275", "GSM506276", "GSM506277", "GSM506278", "GSM506279", "GSM506280", "GSM506281", "GSM506282", "GSM506283", "GSM506284", "GSM506285", "GSM506286", "GSM506287", "GSM506288", "GSM506289", "GSM506290", "GSM506291", "GSM506292", "GSM506293", "GSM506294", "GSM506295", "GSM506296", "GSM506297", "GSM506298", "GSM506299", "GSM506300", "GSM506301", "GSM506302", "GSM506303", "GSM506304", "GSM506305", "GSM506306", "GSM506307", "GSM506308", "GSM506309", "GSM506310", "GSM506311", "GSM506312", "GSM506313", "GSM506314", "GSM506315", "GSM506316", "GSM506317", "GSM506318", "GSM506319", "GSM506320", "GSM506321", "GSM506322", "GSM506323", "GSM506324", "GSM506325", "GSM506326"], "sample_count": 176, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Letrozole (Femara) early and late responses to treatment", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"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": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "access_statement_kind": "repository_route_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": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR.", "access_statement_kind": "repository_route_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}}], "gaps": ["asset:data:geo:GSE20181 not downloaded", "asset:data:geo:GSE20181 licence not read", "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"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "area under the curve", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The area under the curve was significantly higher in the score than that for the E2F targets score."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (area under the curve), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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", "GSE20181"], "resolved_accessions": ["GSE25066", "GSE20194", "GSE20181"], "statements": ["The score was generated by the 5 most highly expressed genes in the Hallmark E2F targets gene set amongst patients in the GSE25066 cohort with ER-positive/HER2-negative BC who achieved pCR."], "basis": "The paper names GSE25066, GSE20194, GSE20181 in GSE25066 and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34354863", "data:geo:GSE20181"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20181"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:02:36Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 2067, "completion_tokens": 1339, "cached_tokens": 128}}, "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:34354863", "type": "paper", "label": "pmid:34354863"}, {"id": "source:pmid:34354863", "type": "manuscript", "label": "PMID 34354863 full text"}, {"id": "data:geo:GSE20181", "type": "dataset", "label": "GEO GSE20181"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34354863", "type": "paper", "label": "pmid:34354863"}, {"id": "source:pmid:34354863", "type": "manuscript", "label": "PMID 34354863 full text"}, {"id": "data:geo:GSE20181", "type": "dataset", "label": "GEO GSE20181"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34354863", "type": "extraction", "used": ["source:pmid:34354863"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20181", "type": "accession_resolution", "used": ["data:geo:GSE20181"], "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:34354863", "parent_hash": "sha256:7012bb6251c3feca0220be7081acb694067bfb199f2c1d14b7e11c02e340941b", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE20181 licence not read", "asset:data:geo:GSE20181 not downloaded", "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", "doi", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}