Identification of Hub Genes Associated With Development and Microenvironment of Hepatocellular Carcinoma by Weighted Gene Co-expression Network Analysis and Differential Gene Expression Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33414813", "kind": "science-record", "revision": 8, "content_hash": "sha256:fcbe6fa4a99e3fa9d61a97e7ba5ee0db056ec1593dc2c0e78966c5cd9deb0150", "created_at": "2026-11-01T15:41:22Z", "updated_at": "2026-11-01T22:45:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Hub Genes Associated With Development and Microenvironment of Hepatocellular Carcinoma by Weighted Gene Co-expression Network Analysis and Differential Gene Expression Analysis.", "doi": "10.3389/fgene.2020.615308", "pmid": "33414813", "authors": ["Qingquan Bai", "Haoling Liu", "Hongyu Guo", "Han Lin", "Xuan Song", "Ye Jin", "Yao Liu", "Hongrui Guo", "Shuhang Liang", "Ruipeng Song", "Jiabei Wang", "Zhibo Qu", "Huaxin Guo", "Hongchi Jiang", "Lianxin Liu", "Haiyan Yang"], "journal": "Frontiers in genetics", "year": 2020, "abstract": "A further understanding of the molecular mechanism of hepatocellular carcinoma (HCC) is necessary to predict a patient's prognosis and develop new targeted gene drugs. This study aims to identify essential genes related to HCC. We used the Weighted Gene Co-expression Network Analysis (WGCNA) and differential gene expression analysis to analyze the gene expression profile of GSE45114 in the Gene Expression Omnibus (GEO) database and The Cancer Genome Atlas database (TCGA). A total of 37 overlapping genes were extracted from four groups of results. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway and Gene Ontology (GO) enrichment analyses were performed on the 37 overlapping genes. Then, we used the STRING database to map the protein interaction (PPI) network of 37 overlapping genes. Ten hub genes were screened according to the Maximal Clique Centrality (MCC) score using the Cytohubba plugin of Cytoscape (including FOS, EGR1, EPHA2, DUSP1, IGFBP3, SOCS2, ID1, DUSP6, MT1G, and MT1H). Most hub genes show a significant association with immune infiltration types and tumor stemness of microenvironment in HCC. According to Univariate Cox regression analysis and Kaplan-Meier survival estimation, SOCS2 was positively correlated with overall survival (OS), and IGFBP3 was negatively correlated with OS. Moreover, the expression of IGFBP3 increased with the increase of the clinical stage, while the expression of SOCS2 decreased with the increase of the clinical stage. In conclusion, our findings suggest that SOCS2 and IGFBP3 may play an essential role in the development of HCC and may serve as a potential biomarker for future diagnosis and treatment.", "claims": [{"id": "claim-method", "statement": "All hub genes were evaluated by Univariate Cox regression analysis and Kaplan-Meier survival estimation to study the relationship between gene expression and overall survival.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33414813", "locator": "sections[14] \"Expression and Prognostic Values of Hub Genes in HCC\" paragraph 2", "quote": "All hub genes were evaluated by Univariate Cox regression analysis and Kaplan-Meier survival estimation to study the relationship between gene expression and overall survival."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA and GSE45114. The data that support the findings of this study are available from the corresponding authors upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33414813", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA and GSE45114. The data that support the findings of this study are available from the corresponding authors upon reasonable request."}], "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:33414813"], "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:GSE45114"], "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:GSE45114"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33414813", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2020.615308", "sha256": "sha256:dfa5e265b2d1a88c55c29d6182bcb532545c4c64b3f8234e8eb2e0af1fd76474", "bytes": 35951, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2020.615308", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7783465", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE45114", "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=GSE45114", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45114", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA and GSE45114. The data that support the findings of this study are available from the corresponding authors upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA and GSE45114. The data that support the findings of this study are available from the corresponding authors upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1097015", "GSM1097016", "GSM1097017", "GSM1097018", "GSM1097019", "GSM1097020", "GSM1097021", "GSM1097022", "GSM1097023", "GSM1097024", "GSM1097025", "GSM1097026", "GSM1097027", "GSM1097028", "GSM1097029", "GSM1097030", "GSM1097031", "GSM1097032", "GSM1097033", "GSM1097034", "GSM1097035", "GSM1097036", "GSM1097037", "GSM1097038", "GSM1097039", "GSM1097040", "GSM1097041", "GSM1097042", "GSM1097043", "GSM1097044", "GSM1097045", "GSM1097046", "GSM1097047", "GSM1097048", "GSM1097049", "GSM1097050", "GSM1097051", "GSM1097052", "GSM1097054", "GSM1097055", "GSM1097056", "GSM1097057", "GSM1097058", "GSM1097059", "GSM1097060", "GSM1097061", "GSM1097062", "GSM1097063", "GSM1097064"], "sample_count": 49, "group_sizes": null, "group_sizes_basis": null, "platform": "5918", "taxon": "Homo sapiens", "title": "Transcriptional profiling of HCC vs. Normal liver and Pericancer vs. Normal liver.", "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:GSE45114 not downloaded", "asset:data:geo:GSE45114 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "All hub genes were evaluated by Univariate Cox regression analysis and Kaplan-Meier survival estimation to study the relationship between gene expression and overall survival."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO Enrichment"}}, {"id": "method-5", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Centrality"}}], "targets": [], "gaps": []}, "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE45114"], "resolved_accessions": ["GSE45114"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: TCGA and GSE45114. The data that support the findings of this study are available from the corresponding authors upon reasonable request."], "basis": "The paper names GSE45114 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": ["survival_km"], "assets": ["source:pmid:33414813", "data:geo:GSE45114"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE45114"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29668, "completion_tokens": 1396, "cached_tokens": 784}}, "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:33414813", "type": "paper", "label": "pmid:33414813"}, {"id": "source:pmid:33414813", "type": "manuscript", "label": "PMID 33414813 full text"}, {"id": "data:geo:GSE45114", "type": "dataset", "label": "GEO GSE45114"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33414813", "type": "paper", "label": "pmid:33414813"}, {"id": "source:pmid:33414813", "type": "manuscript", "label": "PMID 33414813 full text"}, {"id": "data:geo:GSE45114", "type": "dataset", "label": "GEO GSE45114"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33414813", "type": "extraction", "used": ["source:pmid:33414813"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE45114", "type": "accession_resolution", "used": ["data:geo:GSE45114"], "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:33414813", "parent_hash": "sha256:f2f416b966d7dacb90fcb18774899520e80f586d1cdbf4a7b16bdc5a44163f66", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE45114 licence not read", "asset:data:geo:GSE45114 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["All hub genes were evaluated by Univariate Cox regression analysis and Kaplan-Meier survival estimation to study the relationship between gene expression and overall survival."], "order_basis": "analysis_only", "id": "assay:1"}]}