Genome-wide epigenetic profiling of breast cancer tumors treated with aromatase inhibitors.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26484094", "kind": "science-record", "revision": 3, "content_hash": "sha256:d6cde5935ccdb5313a115aa137b9a49a67c26a681c6fee5a50a9ddd6ffcfda1e", "created_at": "2026-11-01T15:40:11Z", "updated_at": "2026-11-01T18:47:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Genome-wide epigenetic profiling of breast cancer tumors treated with aromatase inhibitors.", "doi": "10.1016/j.gdata.2014.06.023", "pmid": "26484094", "authors": ["Ekaterina Nevedomskaya", "Lodewyk Wessels", "Wilbert Zwart"], "journal": "Genomics data", "year": 2014, "abstract": "Aromatase inhibitors (AI) are extensively used in the treatment of estrogen receptor-positive breast cancers, however resistance to AI treatment is commonly observed. Apart from Estrogen receptor (ERα) expression, no predictive biomarkers for response to AI treatment are clinically applied. Yet, since other therapeutic options exist in the clinic, such as tamoxifen, there is an urgent medical need for the development of treatment-selective biomarkers, enabling personalized endocrine treatment selection in breast cancer. In the described dataset, ERα chromatin binding and histone marks H3K4me3 and H3K27me3 were assessed in a genome-wide manner by Chromatin Immunoprecipitation (ChIP) combined with massive parallel sequencing (ChIP-seq). These datasets were used to develop a classifier to stratify breast cancer patients on outcome after AI treatment in the metastatic setting. Here we describe in detail the data and quality control metrics, as well as the clinical information associated with the study, published by Jansen et al. [1]. The data is publicly available through the GEO database with accession number GSE40867.", "claims": [{"id": "claim-data-access", "statement": "The data is publicly available through the GEO database with accession number GSE40867.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484094", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The data is publicly available through the GEO database with accession number GSE40867."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used the MACS peak caller to identify enriched genomic regions, and its ChIP-seq and clinical source data are publicly available through GEO under accession number GSE40867.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26484094", "locator": "sections[5] \"Chromatin immunoprecipitations and sequencing\" paragraph 3", "quote": "Enriched regions of the genome were identified by comparing the ChIP samples to input using the MACS peak caller [5] version 1.3.7.1 with default parameters, except for the p-value cutoff that was set at 10− 7."}, {"asset": "source:pmid:26484094", "locator": "sections[5] \"Chromatin immunoprecipitations and sequencing\" paragraph 3", "quote": "ChIP-seq data and sample annotations were deposited in GEO under accession number GSE40867."}, {"asset": "source:pmid:26484094", "locator": "sections[4] \"Study population and clinical data\" paragraph 3", "quote": "The anonymized clinical data were deposited in the Gene Expression Omnibus database (GEO; [3]) under accession number GSE40867."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used the MACS peak caller to identify enriched genomic regions, and its ChIP-seq and clinical source data are publicly available through GEO under accession number GSE40867.", "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:26484094"], "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:GSE40867"], "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:GSE40867"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26484094", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2014.06.023", "sha256": "sha256:eb15941e6bf121aee1a041a30e5c1fbf6e81667fadd56f352d29b9000c7418ae", "bytes": 10637, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2014.06.023", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4536071", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE40867", "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=GSE40867", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40867", "version": null, "note": "The data is publicly available through the GEO database with accession number GSE40867.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data is publicly available through the GEO database with accession number GSE40867.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1003708", "GSM1003709", "GSM1003710", "GSM1003711", "GSM1003712", "GSM1003713", "GSM1003714", "GSM1003715", "GSM1003716", "GSM1003717", "GSM1003718", "GSM1003719", "GSM1003720", "GSM1003721", "GSM1003722", "GSM1003723", "GSM1003724", "GSM1003725", "GSM1003726", "GSM1003727", "GSM1003728", "GSM1003729", "GSM1003730", "GSM1003731", "GSM1003732", "GSM1003733", "GSM1003734", "GSM1003735", "GSM1003736", "GSM1003737", "GSM1003738", "GSM1003739", "GSM1003740", "GSM1003741", "GSM1003742", "GSM1003743"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Global mapping of estrogen receptor and histone modifications in breast tumor samples uncovers distinct patterns for aromatase inhibitor resistance", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:26484094:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dc7bb543e10502257fb12528f93482cc367d853169ae045bc1909cf2ada43829", "bytes": 1073, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0015", "version": null, "note": null, "structure": {"pmcid": "PMC4536071", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Specifications"], ["Organism/cell line/tissue", "Homo sapiens"], ["Sex", "Female"], ["Sequencer or array type", "Illumina Hiseq 2000 genome analyzer"], ["Data format", "Raw: SRA study; processed: BED"], ["Experimental factors", "Poor vs. good outcome tumors"], ["Experimental features", "Genome-wide binding of Estrogen Receptor α (ERα), as well as histone marks H3K4me3 and H3K27me3, were assessed in tumors from breast cancer patients with good or poor survival outcome after aromatase inhibitors therapy."], ["Consent", "All patients gave their written informed consent before study entry."], ["Sample source location", "Samples were from breast cancer patients, treated at the Erasmus University Medical Center (EMC; Rotterdam, the Netherlands), the Netherlands Cancer Institute/Antoni van Leeuwenhoek hospital (Amsterdam, the Netherlands), and the Translational Cancer Research Unit (Saint Augustinus Hospital, Antwerpen, Belgium)."]], "row_count": 9, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0015"}}], "gaps": ["asset:data:geo:GSE40867 not downloaded", "asset:data:geo:GSE40867 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["GSE40867"], "resolved_accessions": ["GSE40867"], "statements": ["The data is publicly available through the GEO database with accession number GSE40867."], "basis": "The paper names GSE40867 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26484094", "data:geo:GSE40867", "asset:table:pmid:26484094:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE40867"]}, "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": "2026-10-31T18:25:04Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 23426, "completion_tokens": 2716, "cached_tokens": 1816}}, "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:26484094", "type": "paper", "label": "pmid:26484094"}, {"id": "source:pmid:26484094", "type": "manuscript", "label": "PMID 26484094 full text"}, {"id": "data:geo:GSE40867", "type": "dataset", "label": "GEO GSE40867"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26484094", "type": "paper", "label": "pmid:26484094"}, {"id": "source:pmid:26484094", "type": "manuscript", "label": "PMID 26484094 full text"}, {"id": "data:geo:GSE40867", "type": "dataset", "label": "GEO GSE40867"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26484094", "type": "extraction", "used": ["source:pmid:26484094"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE40867", "type": "accession_resolution", "used": ["data:geo:GSE40867"], "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:26484094", "parent_hash": "sha256:1afd58e132f45899d0d00ee36cdc60cd76672750e8da7d06a4f9f7352d65c58d", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE40867 licence not read", "asset:data:geo:GSE40867 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "chip_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": [") combined with massive parallel sequencing (ChIP-seq). These datasets were used to develop a clas"], "order_basis": "paper_text_order:781", "id": "assay:1"}]}