Global proteomic characterization of microdissected estrogen receptor positive breast tumors.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26958599", "kind": "science-record", "revision": 3, "content_hash": "sha256:5c1e6100d0eef67192cde21e52bf297797b8d7b56e08de75cd65e1c3c3be469b", "created_at": "2026-11-01T15:40:16Z", "updated_at": "2026-11-01T18:48:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Global proteomic characterization of microdissected estrogen receptor positive breast tumors.", "doi": "10.1016/j.dib.2015.09.034", "pmid": "26958599", "authors": ["Tommaso De Marchi", "Ning Qing Liu", "Christoph Sting", "Marcel Smid", "Mila Tjoa", "René B H Braakman", "Theo M Luider", "John A Foekens", "John W M Martens", "Arzu Umar"], "journal": "Data in brief", "year": 2015, "abstract": "We here describe two proteomic datasets deposited in ProteomeXchange via PRIDE partner repository [1] with dataset identifiers PXD000484 (defined as \"training\") and PXD000485 (defined as \"test\") that have been used for the development of a tamoxifen outcome predictive signature [2]. Both datasets comprised 56 fresh frozen estrogen receptor (ER) positive primary breast tumor specimens derived from patients who received tamoxifen as first line therapy for recurrent disease. Patient groups were defined based on time to progression (TTP) after start of tamoxifen therapy (6 months cutoff): 32 good and 24 poor treatment outcome patients were comprised in the training set, respectively. The test set included 41 good and 15 poor treatment outcome patients. All specimens were subjected to laser capture microdissection (LCM) to enrich for epithelial tumor cells prior to high resolution mass spectrometric (MS) analysis. Protein identification and label-free quantification (LFQ) were performed with MaxQuant software package [3]. A total of 3109 and 4061 proteins were identified and quantified in the training and test set, respectively. We here present the first public proteomic dataset analyzing ER positive recurrent breast cancer by LCM coupled to high resolution MS.", "claims": [{"id": "claim-data-access", "statement": "Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26958599", "locator": "sections[1] \"Specifications table\" paragraph 2", "quote": "Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485"}], "state": "complete"}, {"id": "claim-target-result", "statement": "We here present the first public proteomic dataset analyzing ER positive recurrent breast cancer by LCM coupled to high resolution MS.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26958599", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We here present the first public proteomic dataset analyzing ER positive recurrent breast cancer by LCM coupled to high resolution MS."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We here present the first public proteomic dataset analyzing ER positive recurrent breast cancer by LCM coupled to high resolution MS.", "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:26958599"], "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:PXD000484"], "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:PXD000484"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26958599", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2015.09.034", "sha256": "sha256:a0cb2f6a067e263a7384716a9535baefa397361880f8e48bc53c2db9ced1506c", "bytes": 8433, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2015.09.034", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4773412", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000484", "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=PXD000484", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000484", "version": null, "note": "Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Discovery dataset on tamoxifen treated Estrogen Receptor (ER) positive breast cancer patients", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD000485", "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=PXD000485", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000485", "version": null, "note": "Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Validation dataset on tamoxifen treated Estrogen Receptor (ER) positive breast cancer patients", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:26958599:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d4639db66b30ea9f72d4432165f99e775469f1dc0b6233eb341f235854c26adf", "bytes": 1264, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC4773412", "section_index": 1, "section_title": "Specifications table", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Clinical Proteomics"], ["Type of data", "1.RAW MS Orbitrap XL data2.MaxQuant “Protein groups.txt” output"], ["How data was acquired", "LTQ Orbitrap XL MS interfaced with a reverse phase column (PepMap C18, 75 µm ID x 50 cm, 3 µm particle size, 100 Å pore size)."], ["Data format", "RAW;.txt"], ["Experimental factors", "All ER positive fresh frozen breast cancer tissues were subjected to LCM to enrich for epithelial tumor cells prior to protein digestion, which enabled analysis of highly pure subpopulations of breast cancer cells."], ["Experimental features", "1.Cryo-sectioning of breast cancer tissues and collection on polyethylene–naphtalate coated slides2.Hematoxylin staining and LCM-enrichment3.Protein digestion (MS Grade Trypsin)4.LC–MS analysis5.Label-free quantitation (LFQ) by MaxQuant software"], ["Data source location", "Rotterdam, The Netherlands"], ["Data accessibility", "PXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484"], ["PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485"]], "row_count": 10, "column_count": 2, "numeric_cells": 5, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:PXD000484 not downloaded", "asset:data:geo:PXD000484 licence not read", "asset:data:geo:PXD000485 not downloaded", "asset:data:geo:PXD000485 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": ["PXD000484", "PXD000485"], "resolved_accessions": ["PXD000484", "PXD000485"], "statements": ["Data accessibilityPXD000484:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000484PXD000485:http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD000485"], "basis": "The paper names PXD000484, PXD000485 in ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26958599", "data:geo:PXD000484", "asset:table:pmid:26958599:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000484"]}, "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": "2026-10-31T18:27:26Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 22499, "completion_tokens": 3928, "cached_tokens": 2096}}, "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:26958599", "type": "paper", "label": "pmid:26958599"}, {"id": "source:pmid:26958599", "type": "manuscript", "label": "PMID 26958599 full text"}, {"id": "data:geo:PXD000484", "type": "dataset", "label": "GEO PXD000484"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26958599", "type": "paper", "label": "pmid:26958599"}, {"id": "source:pmid:26958599", "type": "manuscript", "label": "PMID 26958599 full text"}, {"id": "data:geo:PXD000484", "type": "dataset", "label": "GEO PXD000484"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26958599", "type": "extraction", "used": ["source:pmid:26958599"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000484", "type": "accession_resolution", "used": ["data:geo:PXD000484"], "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:26958599", "parent_hash": "sha256:c172c801b653baacd4adc4530edfb3fb076daeca36bb34ecd3b8bb5d644c1a8e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD000484 licence not read", "asset:data:geo:PXD000484 not downloaded", "asset:data:geo:PXD000485 licence not read", "asset:data:geo:PXD000485 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]}