Identification of potential hub genes related to the progression and prognosis of hepatocellular carcinoma through integrated bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31746405", "kind": "science-record", "revision": 7, "content_hash": "sha256:1d23488b04fb2a919368d108ed799c557e0029f3b2f4939fc697ee419f30581d", "created_at": "2026-11-01T15:40:52Z", "updated_at": "2026-11-01T22:01:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential hub genes related to the progression and prognosis of hepatocellular carcinoma through integrated bioinformatics analysis.", "doi": "10.3892/or.2019.7400", "pmid": "31746405", "authors": ["Xiudao Song", "Rao Du", "Huan Gui", "Mi Zhou", "Wen Zhong", "Chenmei Mao", "Jin Ma"], "journal": "Oncology reports", "year": 2020, "abstract": "Hepatocellular carcinoma (HCC) is the fourth leading cause of cancer‑related deaths among cancer patients. Genes correlated with the progression and prognosis of HCC are critically needed to be identified. In the present study, 3 Gene Expression Omnibus (GEO) datasets (GSE46408, GSE65372 and GSE84402) were used to analyze the differentially expressed genes (DEGs) between HCC and non‑tumor liver tissues. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were conducted to clarify the functional roles of DEGs. A protein‑protein interaction network was established to screen the hub genes associated with HCC. The prognostic values of hub genes in HCC patients were analyzed using The Cancer Genome Atlas (TCGA) database. The expression levels of hub genes were validated based on ONCOMINE, TCGA and Human Protein Atlas (HPA) databases. Notably, 56 upregulated and 33 downregulated DEGs were markedly enriched under various GO terms and four KEGG terms. Among these DEGs, 10 hub genes with high connectivity degree were identified, including cyclin B1, cyclin A2, cyclin B2, condensin complex subunit 3, PDZ binding kinase, nucleolar and spindle‑associated protein 1, aurora kinase A, ZW10 interacting kinetochore protein, protein regulator of cytokinesis 1 and kinesin family member 4A. The upregulated expression levels of these hub genes in HCC tissues were further confirmed by ONCOMINE, TCGA, and HPA databases. Additionally, the increased mRNA expression of each hub gene was related to the unfavorable disease‑free survival and overall survival of HCC patients. The present study identified ten genes associated with HCC, which may help to provide candidate targets for the diagnosis and treatment of HCC.", "claims": [{"id": "claim-method", "statement": "Log-rank test results with P<0.01 were regarded as statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31746405", "locator": "sections[10] \"Survival analyses for hub genes\" paragraph 2", "quote": "Log-rank test results with P<0.01 were regarded as statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during this study are included in this published article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31746405", "locator": "sections[22] \"Availability of data and materials\" paragraph 2", "quote": "All data generated or analyzed during this study are included in this published article."}], "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:31746405"], "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:GSE46408"], "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:GSE46408"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31746405", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/or.2019.7400", "sha256": "sha256:87f570279ce15d750f4c4e9052197e2e41c50b7820e036dc43da4fd5047b5109", "bytes": 28274, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/or.2019.7400", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6908929", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE46408", "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=GSE46408", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46408", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1129834", "GSM1129835", "GSM1129836", "GSM1129837", "GSM1129838", "GSM1129839", "GSM1129840", "GSM1129841", "GSM1129842", "GSM1129843", "GSM1129844", "GSM1129845"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Analysis of genes overexpressed in hepatocellular carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE65372", "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=GSE65372", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65372", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1594003", "GSM1594004", "GSM1594005", "GSM1594006", "GSM1594007", "GSM1594008", "GSM1594009", "GSM1594010", "GSM1594011", "GSM1594012", "GSM1594013", "GSM1594014", "GSM1594015", "GSM1594016", "GSM1594017", "GSM1594018", "GSM1594019", "GSM1594020", "GSM1594021", "GSM1594022", "GSM1594023", "GSM1594024", "GSM1594025", "GSM1594026", "GSM1594027", "GSM1594028", "GSM1594029", "GSM1594030", "GSM1594031", "GSM1594032", "GSM1594033", "GSM1594034", "GSM1594035", "GSM1594036", "GSM1594037", "GSM1594038", "GSM1594039", "GSM1594040", "GSM1594041", "GSM1594042", "GSM1594043", "GSM1594044", "GSM1594045", "GSM1594046", "GSM1594047", "GSM1594048", "GSM1594049", "GSM1594050", "GSM1594051", "GSM1594052", "GSM1594053", "GSM1594054", "GSM1594055", "GSM1594056"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Molecular heterogeneity of multinodular hepatocellular carcinoma [gene expression]", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE84402", "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=GSE84402", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE84402", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2233086", "GSM2233087", "GSM2233088", "GSM2233089", "GSM2233090", "GSM2233091", "GSM2233092", "GSM2233093", "GSM2233094", "GSM2233095", "GSM2233096", "GSM2233097", "GSM2233098", "GSM2233099", "GSM2233100", "GSM2233101", "GSM2233102", "GSM2233103", "GSM2233104", "GSM2233105", "GSM2233106", "GSM2233107", "GSM2233108", "GSM2233109", "GSM2233110", "GSM2233111", "GSM2233112", "GSM2233113"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from human hepatocellular carcinoma tissues and the correponding non-cancerous tissues", "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:GSE46408 not downloaded", "asset:data:geo:GSE46408 licence not read", "asset:data:geo:GSE65372 not downloaded", "asset:data:geo:GSE65372 licence not read", "asset:data:geo:GSE84402 not downloaded", "asset:data:geo:GSE84402 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": "Log-rank test results with P<0.01 were regarded as statistically significant."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"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": 0.8, "band": "high", "quote": "PPI"}}], "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": ["GSE46408", "GSE65372", "GSE84402"], "resolved_accessions": ["GSE46408", "GSE65372", "GSE84402"], "statements": ["All data generated or analyzed during this study are included in this published article."], "basis": "The paper names GSE46408, GSE65372, GSE84402 in Gene Expression Omnibus (GEO) database 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:31746405", "data:geo:GSE46408"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE46408"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 21822, "completion_tokens": 2894, "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:31746405", "type": "paper", "label": "pmid:31746405"}, {"id": "source:pmid:31746405", "type": "manuscript", "label": "PMID 31746405 full text"}, {"id": "data:geo:GSE46408", "type": "dataset", "label": "GEO GSE46408"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31746405", "type": "paper", "label": "pmid:31746405"}, {"id": "source:pmid:31746405", "type": "manuscript", "label": "PMID 31746405 full text"}, {"id": "data:geo:GSE46408", "type": "dataset", "label": "GEO GSE46408"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31746405", "type": "extraction", "used": ["source:pmid:31746405"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE46408", "type": "accession_resolution", "used": ["data:geo:GSE46408"], "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:31746405", "parent_hash": "sha256:7ecd5625539723d813789636a41382e61ecbac95d6fa6519bd3bc89ed3dbccf9", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE46408 licence not read", "asset:data:geo:GSE46408 not downloaded", "asset:data:geo:GSE65372 licence not read", "asset:data:geo:GSE65372 not downloaded", "asset:data:geo:GSE84402 licence not read", "asset:data:geo:GSE84402 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": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Log-rank test results with P<0.01 were regarded as statistically significant."], "order_basis": "analysis_only", "id": "assay:1"}]}