Hub genes identification and association of key pathways with hypoxia in cancer cells: A bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37593462", "kind": "science-record", "revision": 4, "content_hash": "sha256:fef9e89e62a45618f1f824915faed617b5fae99e02db9758280fb9df7f26d8b3", "created_at": "2026-11-01T19:02:23Z", "updated_at": "2026-11-01T22:10:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Hub genes identification and association of key pathways with hypoxia in cancer cells: A bioinformatics analysis.", "doi": "10.1016/j.sjbs.2023.103752", "pmid": "37593462", "authors": ["Faiza Aziz", "Naila Shoaib", "Abdul Rehman"], "journal": "Saudi journal of biological sciences", "year": 2023, "abstract": "Three human cancer cell lines (A549, HCT116, and HeLa) were used to investigate the molecular mechanisms and potential prognostic biomarkers associated with hypoxia. We obtained gene expression data from Gene Expression Omnibus (GEO) datasets GSE11704, GSE147384, and GSE38061, which included 5 hypoxic and 8 control samples. Using the GEO2R tool and Venn diagram software, we identified common differentially expressed genes (cDEGs). The cDEGs were then subjected to Gene ontology (GO) and Kyoto Encyclopedia of Gene and Genome (KEGG) pathway analysis by employing DAVID. The hub genes were identified from critical PPI subnetworks through CytoHuba plugin and these genes' prognostic significance and expression were verified using Kaplan-Meier analysis and Gene Expression Profiling Interactive Analysis (GEPIA), respectively. The research showed 676 common DEGs (cDEGs), with 207 upregulated and 469 downregulated genes. The STRING analysis showed 673 nodes and 1446 edges in the PPI network. We identified 4 significant modules and 19 downregulated hub genes. GO analysis revealed all of them were majorly involved in ribosomal large subunit assembly and biogenesis, rRNA processing, ribosome biogenesis, translation, RNA & protein binding frequently at the sites of nucleolus and nucleoplasm while 11 were significantly associated with a better prognosis of hypoxic tumors. Our research sheds light on the molecular mechanisms that underpin hypoxia in human cancer cell lines and identifies potential prognostic biomarkers for hypoxic tumors.", "claims": [{"id": "claim-data-access", "statement": "The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37593462", "locator": "sections[3] \"Microarray data and GEO database\" paragraph 2", "quote": "The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The research showed 676 common DEGs (cDEGs), with 207 upregulated and 469 downregulated genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37593462", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The research showed 676 common DEGs (cDEGs), with 207 upregulated and 469 downregulated genes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The research showed 676 common DEGs (cDEGs), with 207 upregulated and 469 downregulated genes.", "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:37593462"], "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:GSE11704"], "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": {"p_value": "istical analysis with a p-value greater than 0"}, "inputs": ["data:geo:GSE11704"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37593462", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.sjbs.2023.103752", "sha256": "sha256:9384e1da1288d224fd4b2d1b49c2ecc2c0ba81bee6025bcb28d825ac2c15dd17", "bytes": 33538, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.sjbs.2023.103752", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10428120", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE11704", "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=GSE11704", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE11704", "version": null, "note": "The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM297326", "GSM297327", "GSM297328", "GSM297329", "GSM297330", "GSM297331", "GSM297332", "GSM297333", "GSM297334", "GSM297335", "GSM297336", "GSM297337", "GSM297338", "GSM297339", "GSM297340", "GSM297341", "GSM297342", "GSM297343", "GSM297344", "GSM297345", "GSM297346", "GSM297347", "GSM297348", "GSM297349", "GSM297350", "GSM297351", "GSM297352", "GSM297353", "GSM297354", "GSM297355", "GSM297356", "GSM297357", "GSM297358", "GSM297359", "GSM297360", "GSM297361", "GSM297362", "GSM297363"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "3738", "taxon": "Canis lupus familiaris; Mustela putorius furo", "title": "Absence of host innate immune responses in SARS-CoV-infected ferrets upon subsequent challenge", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE147384", "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=GSE147384", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE147384", "version": null, "note": "The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM4429815", "GSM4429816", "GSM4429817", "GSM4429818", "GSM4429819", "GSM4429820", "GSM4429821", "GSM4429822", "GSM4429823", "GSM4429824", "GSM4429825", "GSM4429826", "GSM4429827", "GSM4429828", "GSM4429829", "GSM4429830", "GSM4429831", "GSM4429832", "GSM4429833", "GSM4429834"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "MR Imaging Distinguishes Tumor Hypoxia Levels of Different Prognostic and Biological Significance in Cervical Cancer", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE11704 not downloaded", "asset:data:geo:GSE11704 licence not read", "asset:data:geo:GSE147384 not downloaded", "asset:data:geo:GSE147384 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {"p_value": "istical analysis with a p-value greater than 0"}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"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": 0.7, "band": "medium", "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": 0.7, "band": "medium", "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE11704", "GSE147384", "and GSE38061"], "resolved_accessions": ["GSE11704", "GSE147384"], "statements": ["The expression profiles of GSE11704, GSE147384, and GSE38061 were subsequently retrieved from the GEO database for investigation."], "basis": "The paper names GSE11704, GSE147384 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:37593462", "data:geo:GSE11704"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE11704"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:50:59Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 5, "usage": {"prompt_tokens": 10371, "completion_tokens": 1421, "cached_tokens": 264}}, "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:37593462", "type": "paper", "label": "pmid:37593462"}, {"id": "source:pmid:37593462", "type": "manuscript", "label": "PMID 37593462 full text"}, {"id": "data:geo:GSE11704", "type": "dataset", "label": "GEO GSE11704"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37593462", "type": "paper", "label": "pmid:37593462"}, {"id": "source:pmid:37593462", "type": "manuscript", "label": "PMID 37593462 full text"}, {"id": "data:geo:GSE11704", "type": "dataset", "label": "GEO GSE11704"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37593462", "type": "extraction", "used": ["source:pmid:37593462"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE11704", "type": "accession_resolution", "used": ["data:geo:GSE11704"], "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:37593462", "parent_hash": "sha256:09a45ee026d319abefc034723601a48d6858c7c2840e53acd1144f47803df691", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE11704 licence not read", "asset:data:geo:GSE11704 not downloaded", "asset:data:geo:GSE147384 licence not read", "asset:data:geo:GSE147384 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Three human cancer cell lines (A549, HCT116, and HeLa) were used to investigate", "e human cancer cell lines (A549, HCT116, and HeLa) were used to investigate the molecular mech"], "order_basis": "paper_text_order:114", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["ANOVA"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}