Identification and Validation of Hub Genes Associated With Hepatocellular Carcinoma Via Integrated Bioinformatics Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34277395", "kind": "science-record", "revision": 7, "content_hash": "sha256:500208a40d08e1c4bcb38548a64e8a0b7034510b51c7d702abdc76a76b830f4b", "created_at": "2026-11-01T15:41:44Z", "updated_at": "2026-11-01T22:04:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and Validation of Hub Genes Associated With Hepatocellular Carcinoma Via Integrated Bioinformatics Analysis.", "doi": "10.3389/fonc.2021.614531", "pmid": "34277395", "authors": ["Sumei Wang", "Zuoli Song", "Bing Tan", "Jinjuan Zhang", "Jiandong Zhang", "Shuye Liu"], "journal": "Frontiers in oncology", "year": 2021, "abstract": "Hepatocellular carcinoma (HCC) is the most common malignant tumor of the liver, with high morbidity and mortality, yet its molecular mechanisms of tumorigenesis are still unclear. In this study, gene expression profile of GSE62232 was downloaded from the Gene Expression Omnibus (GEO). The RNA-seq expression data and relative clinical information were retrieved from the Cancer Genome Atlas (TCGA) database. The datasets were analyzed by differential gene expression analysis and Weighted Gene Co-expression Network Analysis (WGCNA) to obtain the overlapping genes. Then, we performed a functional enrichment analysis to understand the potential biological functions of these co-expression genes. Finally, we constructed the protein-protein interaction (PPI) analysis combined with survival analysis. MARCO, CLEC4M, FCGR2B, LYVE1, TIMD4, STAB2, CFP, CLEC4G, CLEC1B, FCN2, FCN3 and FOXO1 were identified as the candidate hub genes using the CytoHubba plugin of Cytoscape. Based on survival analysis, the lower expression of FCN3 and FOXO1 were associated with worse overall survival (OS) in HCC patients. Furthermore, the expression levels of FCN3 and FOXO1 were validated by the Human Protein Atlas (HPA) database and the qRT-PCR. In summary, our findings contribute new ideas for the precise early diagnosis, clinical treatment and prognosis of HCC in the future.", "claims": [{"id": "claim-method", "statement": "For survival analysis, R package “survival” and “survminer” were used to implement log-rank tests, p-value <0.05 was considered as statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34277395", "locator": "sections[8] \"Hub Genes Validation and Survival Analysis\" paragraph 2", "quote": "For survival analysis, R package “survival” and “survminer” were used to implement log-rank tests, p-value <0.05 was considered as statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/supplementary material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34277395", "locator": "sections[18] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/supplementary material."}], "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:34277395"], "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:GSE62232"], "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:GSE62232"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34277395", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2021.614531", "sha256": "sha256:e17661aaca0e756c493d0b4068d7d31dc41e6e53e35420f42bb885136d7acf15", "bytes": 29644, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2021.614531", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8278315", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE62232", "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=GSE62232", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62232", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/supplementary material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/supplementary material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1523329", "GSM1523330", "GSM1523331", "GSM1523332", "GSM1523333", "GSM1523334", "GSM1523335", "GSM1523336", "GSM1523337", "GSM1523338", "GSM1523339", "GSM1523340", "GSM1523341", "GSM1523342", "GSM1523343", "GSM1523344", "GSM1523345", "GSM1523346", "GSM1523347", "GSM1523348", "GSM1523349", "GSM1523350", "GSM1523351", "GSM1523352", "GSM1523353", "GSM1523354", "GSM1523355", "GSM1523356", "GSM1523357", "GSM1523358", "GSM1523359", "GSM1523360", "GSM1523361", "GSM1523362", "GSM1523363", "GSM1523364", "GSM1523365", "GSM1523366", "GSM1523367", "GSM1523368", "GSM1523369", "GSM1523370", "GSM1523371", "GSM1523372", "GSM1523373", "GSM1523374", "GSM1523375", "GSM1523376", "GSM1523377", "GSM1523378", "GSM1523379", "GSM1523380", "GSM1523381", "GSM1523382", "GSM1523383", "GSM1523384", "GSM1523385", "GSM1523386", "GSM1523387", "GSM1523388", "GSM1523389", "GSM1523390", "GSM1523391", "GSM1523392", "GSM1523393", "GSM1523394", "GSM1523395", "GSM1523396", "GSM1523397", "GSM1523398", "GSM1523399", "GSM1523400", "GSM1523401", "GSM1523402", "GSM1523403", "GSM1523404", "GSM1523405", "GSM1523406", "GSM1523407", "GSM1523408", "GSM1523409", "GSM1523410", "GSM1523411", "GSM1523412", "GSM1523413", "GSM1523414", "GSM1523415", "GSM1523416", "GSM1523417", "GSM1523418", "GSM1523419"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Large-scale gene expression profiling  of 81 hepatocellular carcinomas", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE62232 not downloaded", "asset:data:geo:GSE62232 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For survival analysis, R package “survival” and “survminer” were used to implement log-rank tests, p-value <0.05 was considered as statistically significant."}}, {"id": "method-2", "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": "protein-protein interaction"}}, {"id": "method-3", "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"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE62232"], "resolved_accessions": ["GSE62232"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/supplementary material."], "basis": "The paper names GSE62232 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": ["logrank_test"], "assets": ["source:pmid:34277395", "data:geo:GSE62232"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE62232"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24906, "completion_tokens": 1332, "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:34277395", "type": "paper", "label": "pmid:34277395"}, {"id": "source:pmid:34277395", "type": "manuscript", "label": "PMID 34277395 full text"}, {"id": "data:geo:GSE62232", "type": "dataset", "label": "GEO GSE62232"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34277395", "type": "paper", "label": "pmid:34277395"}, {"id": "source:pmid:34277395", "type": "manuscript", "label": "PMID 34277395 full text"}, {"id": "data:geo:GSE62232", "type": "dataset", "label": "GEO GSE62232"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34277395", "type": "extraction", "used": ["source:pmid:34277395"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE62232", "type": "accession_resolution", "used": ["data:geo:GSE62232"], "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:34277395", "parent_hash": "sha256:b6b6a59fd76c7fe4b35b9fa4fa547fc795cb3902c9bced69f3dc0964d2561497", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE62232 licence not read", "asset:data:geo:GSE62232 not downloaded", "execution.not_run", "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": 0.99, "evidence": ["from the Gene Expression Omnibus (GEO). The RNA-seq expression data and relative clinical inform", "s were selected for subsequent analysis. The RNA-seq expression data and relative clinical inform"], "order_basis": "paper_text_order:370", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["d based on GPL570 platform ([HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array), including"], "order_basis": "paper_text_order:1837", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For survival analysis, R package “survival” and “survminer” were used to implement log-rank tests, p-value <0.05 was considered as statistically significant."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]}