Prognostic Genes of Breast Cancer Identified by Gene Co-expression Network Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30254986", "kind": "science-record", "revision": 4, "content_hash": "sha256:54074c730457b78f18c7ee6e522df3c3600230cc36616d6bf70dc4b624b20268", "created_at": "2026-11-01T15:40:37Z", "updated_at": "2026-11-01T21:21:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prognostic Genes of Breast Cancer Identified by Gene Co-expression Network Analysis.", "doi": "10.3389/fonc.2018.00374", "pmid": "30254986", "authors": ["Jianing Tang", "Deguang Kong", "Qiuxia Cui", "Kun Wang", "Dan Zhang", "Yan Gong", "Gaosong Wu"], "journal": "Frontiers in oncology", "year": 2018, "abstract": "Breast cancer is one of the most common malignancies. The molecular mechanisms of its pathogenesis are still to be investigated. The aim of this study was to identify the potential genes associated with the progression of breast cancer. Weighted gene co-expression network analysis (WGCNA) was used to construct free-scale gene co-expression networks to explore the associations between gene sets and clinical features, and to identify candidate biomarkers. The gene expression profiles of GSE1561 were selected from the Gene Expression Omnibus (GEO) database. RNA-seq data and clinical information of breast cancer from TCGA were used for validation. A total of 18 modules were identified via the average linkage hierarchical clustering. In the significant module (R2 = 0.48), 42 network hub genes were identified. Based on the Cancer Genome Atlas (TCGA) data, 5 hub genes (CCNB2, FBXO5, KIF4A, MCM10, and TPX2) were correlated with poor prognosis. Receiver operating characteristic (ROC) curve validated that the mRNA levels of these 5 genes exhibited excellent diagnostic efficiency for normal and tumor tissues. In addition, the protein levels of these 5 genes were also significantly higher in tumor tissues compared with normal tissues. Among them, CCNB2, KIF4A, and TPX2 were further upregulated in advanced tumor stage. In conclusion, 5 candidate biomarkers were identified for further basic and clinical research on breast cancer with co-expression network analysis.", "claims": [{"id": "claim-method", "statement": "Weighted gene co-expression network analysis (WGCNA) was used to construct free-scale gene co-expression networks to explore the associations between gene sets and clinical features, and to identify candidate biomarkers.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30254986", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Weighted gene co-expression network analysis (WGCNA) was used to construct free-scale gene co-expression networks to explore the associations between gene sets and clinical features, and to identify candidate biomarkers."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The gene expression profiles of GSE1561 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1561) submitted by Richard Iggo et al. was downloaded from the Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30254986", "locator": "sections[3] \"Data procession\" paragraph 2", "quote": "The gene expression profiles of GSE1561 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1561) submitted by Richard Iggo et al. was downloaded from the Gene Expression Omnibus (GEO) database."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:30254986"], "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:GSE1561"], "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:GSE1561"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30254986", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2018.00374", "sha256": "sha256:2478c89dfdd18888cb737b6333a7babf838202ec7e1599fd5f90293bb8d053c4", "bytes": 25975, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2018.00374", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6141856", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE1561", "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=GSE1561", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE1561", "version": null, "note": "The gene expression profiles of GSE1561 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1561) submitted by Richard Iggo et al. was downloaded from the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression profiles of GSE1561 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1561) submitted by Richard Iggo et al. was downloaded from the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM26804", "GSM26867", "GSM26868", "GSM26869", "GSM26870", "GSM26871", "GSM26872", "GSM26873", "GSM26874", "GSM26875", "GSM26876", "GSM26877", "GSM26878", "GSM26879", "GSM26880", "GSM26881", "GSM26882", "GSM26883", "GSM26884", "GSM26885", "GSM26886", "GSM26887", "GSM26888", "GSM26889", "GSM26890", "GSM26891", "GSM26892", "GSM26893", "GSM26894", "GSM26895", "GSM26896", "GSM26897", "GSM26898", "GSM26899", "GSM26900", "GSM26901", "GSM26902", "GSM26903", "GSM26904", "GSM26905", "GSM26906", "GSM26907", "GSM26908", "GSM26909", "GSM26910", "GSM26911", "GSM26912", "GSM26913", "GSM26914"], "sample_count": 49, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "EORTC 10994 clinical trial", "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:GSE1561 not downloaded", "asset:data:geo:GSE1561 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "hierarchical clustering"}}, {"id": "method-2", "family": null, "specific": null, "label": "Weighted gene co-expression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Weighted gene co-expression network analysis (WGCNA) was used to construct free-scale gene co-expression networks to explore the associations between gene sets and clinical features, and to identify candidate biomarkers."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["hierarchical_cluster"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: hierarchical."}, "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": ["GSE1561"], "resolved_accessions": ["GSE1561"], "statements": ["The gene expression profiles of GSE1561 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1561) submitted by Richard Iggo et al. was downloaded from the Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE1561 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": ["hierarchical_cluster"], "assets": ["source:pmid:30254986", "data:geo:GSE1561"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE1561"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 19142, "completion_tokens": 3799, "cached_tokens": 656}}, "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:30254986", "type": "paper", "label": "pmid:30254986"}, {"id": "source:pmid:30254986", "type": "manuscript", "label": "PMID 30254986 full text"}, {"id": "data:geo:GSE1561", "type": "dataset", "label": "GEO GSE1561"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30254986", "type": "paper", "label": "pmid:30254986"}, {"id": "source:pmid:30254986", "type": "manuscript", "label": "PMID 30254986 full text"}, {"id": "data:geo:GSE1561", "type": "dataset", "label": "GEO GSE1561"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30254986", "type": "extraction", "used": ["source:pmid:30254986"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE1561", "type": "accession_resolution", "used": ["data:geo:GSE1561"], "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:30254986", "parent_hash": "sha256:f376f22bfc6405e630cfc526c65244d9e1b2c95d1eb8334b25ef4f555d0d05ff", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE1561 licence not read", "asset:data:geo:GSE1561 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["the Gene Expression Omnibus (GEO) database. RNA-seq data and clinical information of breast canc"], "order_basis": "paper_text_order:602", "id": "assay:1"}, {"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["hierarchical_cluster"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["hierarchical clustering"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}