Transcriptional profiling of differentially expressed long non-coding RNAs in breast cancer.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26697378", "kind": "science-record", "revision": 7, "content_hash": "sha256:0e9b4d81fe3a1855bb2227434f9714ceab990b7a4234ac61565ba81b3dff073b", "created_at": "2026-11-01T15:40:15Z", "updated_at": "2026-11-01T21:20:21Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptional profiling of differentially expressed long non-coding RNAs in breast cancer.", "doi": "10.1016/j.gdata.2015.09.020", "pmid": "26697378", "authors": ["Lizhen Wang", "Xiaokun Shen", "Bojian Xie", "Zhaosheng Ma", "Xiaobing Chen", "Feilin Cao"], "journal": "Genomics data", "year": 2015, "abstract": "Long non-coding RNAs (lncRNAs) are subclass of noncoding RNAs that have been recently shown to play critical roles in cancer biology. However, little is known about their mechanistic role in breast cancer pathogenesis, especially in triple-negative breast carcinomas (TNBC) that have particular poor outcomes. This study was specifically designed to identify the signatures relevant lncRNAs in breast cancer and characterize lncRNAs that modulate the phenotype. Here we provide detailed methods and analysis of microarray data, which is deposited in the Gene Expression Omnibus (GEO) with the accession number GSE64790. The basic analysis as contained in the manuscript published in Oncotarget with the PMID 26078338. These data can be used to further elucidate the mechanisms of breast cancer.", "claims": [{"id": "claim-method", "statement": "For comparisons, paired t-tests and unpaired t-tests were performed where appropriate.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697378", "locator": "sections[11] \"Statistical analysis\" paragraph 2", "quote": "For comparisons, paired t-tests and unpaired t-tests were performed where appropriate."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Here we provide detailed methods and analysis of microarray data, which is deposited in the Gene Expression Omnibus (GEO) with the accession number GSE64790.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697378", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Here we provide detailed methods and analysis of microarray data, which is deposited in the Gene Expression Omnibus (GEO) with the accession number GSE64790."}], "state": "complete"}], "gaps": []}, "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:26697378"], "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:GSE64790"], "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:GSE64790"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26697378", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.09.020", "sha256": "sha256:23bce97ae16aa3bb3a622c8041ccd4d97e2c4f23fb23599f2dd5841ec9c08b53", "bytes": 7715, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.09.020", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4664755", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE64790", "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=GSE64790", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE64790", "version": null, "note": "Here we provide detailed methods and analysis of microarray data, which is deposited in the Gene Expression Omnibus (GEO) with the accession number GSE64790.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Here we provide detailed methods and analysis of microarray data, which is deposited in the Gene Expression Omnibus (GEO) with the accession number GSE64790.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1580581", "GSM1580582", "GSM1580583", "GSM1580584", "GSM1580585", "GSM1580586"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "19612", "taxon": "Homo sapiens", "title": "Identifying long non-coding RNAs in triple-negative breast cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:26697378:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dc83834c9f798f0d88aa65bbf395ca38fabebcec49687ff8195f76aa52f6520f", "bytes": 777, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC4664755", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Specifications [standardized info for the reader] Where applicable, please follow the Ontology for Biomedical Investigations: http://obi-ontology.org/page/Main_Page"], ["Organism/cell line/tissue", "Homo sapiens/breast"], ["Sex", "Female"], ["Sequencer or array type", "Agilent Human lncRNA Microarray V4.0 028,004 (GPL19612)"], ["Data format", "Raw and processed"], ["Experimental factors", "tumor vs. normal"], ["Experimental features", "Triple-negative breast carcinomas"], ["Consent", "Informed consent and ethical approval obtained from patients and ethical committee, respectively"], ["Sample source location", "Taizhou, Zhejiang, China"]], "row_count": 9, "column_count": 2, "numeric_cells": 1, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0010"}}], "gaps": ["asset:data:geo:GSE64790 not downloaded", "asset:data:geo:GSE64790 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "paired t-tests and unpaired t-tests", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For comparisons, paired t-tests and unpaired t-tests were performed where appropriate."}}], "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 (paired t-tests and unpaired t-tests), 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": ["GSE64790"], "resolved_accessions": ["GSE64790"], "statements": ["Here we provide detailed methods and analysis of microarray data, which is deposited in the Gene Expression Omnibus (GEO) with the accession number GSE64790."], "basis": "The paper names GSE64790 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:26697378", "data:geo:GSE64790", "asset:table:pmid:26697378:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE64790"]}, "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": "2026-10-31T18:26:53Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 18353, "completion_tokens": 2006, "cached_tokens": 5656}}, "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:26697378", "type": "paper", "label": "pmid:26697378"}, {"id": "source:pmid:26697378", "type": "manuscript", "label": "PMID 26697378 full text"}, {"id": "data:geo:GSE64790", "type": "dataset", "label": "GEO GSE64790"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26697378", "type": "paper", "label": "pmid:26697378"}, {"id": "source:pmid:26697378", "type": "manuscript", "label": "PMID 26697378 full text"}, {"id": "data:geo:GSE64790", "type": "dataset", "label": "GEO GSE64790"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26697378", "type": "extraction", "used": ["source:pmid:26697378"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE64790", "type": "accession_resolution", "used": ["data:geo:GSE64790"], "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:26697378", "parent_hash": "sha256:00aafe89f005769ed4b53b84599d11c655ce752d34776a6e01ac17f3d3d8a53a", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE64790 licence not read", "asset:data:geo:GSE64790 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["we provide detailed methods and analysis of microarray data, which is deposited in the Gene Express", "r to surgery. 3 paired samples were used for microarray analysis of lncRNAs. Demographic and clinica"], "order_basis": "paper_text_order:560", "id": "assay:1"}]}