Screening Key Genes and Biological Pathways in Nasopharyngeal Carcinoma by Integrated Bioinformatics Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36555343", "kind": "science-record", "revision": 3, "content_hash": "sha256:ba00ea31ad01f5cf78dc2b1cd2282de92d9248b8596917e6f602c179dfaa642a", "created_at": "2026-11-01T19:01:05Z", "updated_at": "2026-11-01T22:08:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening Key Genes and Biological Pathways in Nasopharyngeal Carcinoma by Integrated Bioinformatics Analysis.", "doi": "10.3390/ijms232415701", "pmid": "36555343", "authors": ["Junhu Tai", "Jaehyung Park", "Munsoo Han", "Tae Hoon Kim"], "journal": "International journal of molecular sciences", "year": 2022, "abstract": "The purpose of this study was to identify the hub genes and biological pathways of nasopharyngeal carcinoma (NPC) through bioinformatics analysis and potential new therapeutic targets. In this study, three datasets were downloaded from the Gene Expression Omnibus (GEO), and differentially expressed genes (DEGs) between NPC and normal tissues were analyzed using the GEO2R online tool. Volcano and heat maps of the DEGs were visualized using the hiplot database. Gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses of the upregulated and downregulated DEGs were performed using the DAVID database. Finally, we established a protein-protein interaction (PPI) network using the STRING database and showed the differential expression of hub genes between the normal and tumor tissues. In all, 109,371,221 upregulated DEGs and 139,226,520 downregulated DEGs were obtained in datasets GSE40290, GSE61218, and GSE53819, respectively, and 18 common differential genes, named co-DEGs, were screened in the three datasets. The most abundant biological GO terms of the co-DEGs were inflammatory response et al. The KEGG pathway enrichment analysis showed that co-DEGs mainly participated in the interleukin (IL)-17 signaling pathway et al. Finally, we identified four hub genes using PPI analysis and observed that three of them were highly expressed in tumor tissues. In this study, the hub genes of NPC, such as PTGS2, and pathways such as IL-17 signaling, were identified through bioinformatics analysis, which may be potential new therapeutic targets for NPC.", "claims": [{"id": "claim-method", "statement": "We analyzed DEGs between NPC and normal tissues in the GSE40290, GSE61218, and GSE53819 datasets using the GEO2R tool.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36555343", "locator": "sections[11] \"4.2. Identification of DEGs and Data Visualization\" paragraph 2", "quote": "We analyzed DEGs between NPC and normal tissues in the GSE40290, GSE61218, and GSE53819 datasets using the GEO2R tool."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data presented in this study are openly available in GEO datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36555343", "locator": "sections[20] \"notes\" paragraph 1", "quote": "The data presented in this study are openly available in GEO datasets."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In all, 109,371,221 upregulated DEGs and 139,226,520 downregulated DEGs were obtained in datasets GSE40290, GSE61218, and GSE53819, respectively, and 18 common differential genes, named co-DEGs, were screened in the three datasets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36555343", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In all, 109,371,221 upregulated DEGs and 139,226,520 downregulated DEGs were obtained in datasets GSE40290, GSE61218, and GSE53819, respectively, and 18 common differential genes, named co-DEGs, were screened in the three datasets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "In all, 109,371,221 upregulated DEGs and 139,226,520 downregulated DEGs were obtained in datasets GSE40290, GSE61218, and GSE53819, respectively, and 18 common differential genes, named co-DEGs, were screened in the three datasets.", "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:36555343"], "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:GSE40290"], "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:GSE40290"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36555343", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms232415701", "sha256": "sha256:4dba35efae6de9bc6849ecedc5ea2569993c826f497687921586e19ce1ffe34e", "bytes": 20638, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms232415701", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9779079", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE40290", "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=GSE40290", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40290", "version": null, "note": "The data presented in this study are openly available in GEO datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data presented in this study are openly available in GEO datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM990732", "GSM990733", "GSM990734", "GSM990735", "GSM990736", "GSM990737", "GSM990738", "GSM990739", "GSM990740", "GSM990741", "GSM990742", "GSM990743", "GSM990744", "GSM990745", "GSM990746", "GSM990747", "GSM990748", "GSM990749", "GSM990750", "GSM990751", "GSM990752", "GSM990753", "GSM990754", "GSM990755", "GSM990756", "GSM990757", "GSM990758", "GSM990759", "GSM990760", "GSM990761", "GSM990762", "GSM990763", "GSM990764"], "sample_count": 33, "group_sizes": null, "group_sizes_basis": null, "platform": "8380", "taxon": "Homo sapiens", "title": "Molecular classification of non-keratinizing nasopharyngeal carcinoma using mRNA expression profiling", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE53819", "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=GSE53819", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53819", "version": null, "note": "The data presented in this study are openly available in GEO datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data presented in this study are openly available in GEO datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1301444", "GSM1301445", "GSM1301446", "GSM1301447", "GSM1301448", "GSM1301449", "GSM1301450", "GSM1301451", "GSM1301452", "GSM1301453", "GSM1301454", "GSM1301455", "GSM1301456", "GSM1301457", "GSM1301458", "GSM1301459", "GSM1301460", "GSM1301461", "GSM1301462", "GSM1301463", "GSM1301464", "GSM1301465", "GSM1301466", "GSM1301467", "GSM1301468", "GSM1301469", "GSM1301470", "GSM1301471", "GSM1301472", "GSM1301473", "GSM1301474", "GSM1301475", "GSM1301476", "GSM1301477", "GSM1301478", "GSM1301479"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Genome-wide expressing profiling of nasopharyngeal carcinoma primary tumors versus non-cancerous nasopharyngeal tissues.", "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:GSE61218", "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=GSE61218", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE61218", "version": null, "note": "The data presented in this study are openly available in GEO datasets.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data presented in this study are openly available in GEO datasets.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1499764", "GSM1499765", "GSM1499766", "GSM1499767", "GSM1499768", "GSM1499769", "GSM1499770", "GSM1499771", "GSM1499772", "GSM1499773", "GSM1499774", "GSM1499775", "GSM1499776", "GSM1499777", "GSM1499778", "GSM1499779"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "19061", "taxon": "Homo sapiens", "title": "mRNA and lncRNA gene expression profile of nasopharyngeal carcinoma", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE40290 not downloaded", "asset:data:geo:GSE40290 licence not read", "asset:data:geo:GSE53819 not downloaded", "asset:data:geo:GSE53819 licence not read", "asset:data:geo:GSE61218 not downloaded", "asset:data:geo:GSE61218 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We analyzed DEGs between NPC and normal tissues in the GSE40290, GSE61218, and GSE53819 datasets using the GEO2R tool."}}], "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE40290", "GSE61218", "GSE53819"], "resolved_accessions": ["GSE40290", "GSE61218", "GSE53819"], "statements": ["The data presented in this study are openly available in GEO datasets."], "basis": "The paper names GSE40290, GSE61218, GSE53819 in NCBI-GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:36555343", "data:geo:GSE40290"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE40290"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:21:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6920, "completion_tokens": 1319, "cached_tokens": 128}}, "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:36555343", "type": "paper", "label": "pmid:36555343"}, {"id": "source:pmid:36555343", "type": "manuscript", "label": "PMID 36555343 full text"}, {"id": "data:geo:GSE40290", "type": "dataset", "label": "GEO GSE40290"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36555343", "type": "paper", "label": "pmid:36555343"}, {"id": "source:pmid:36555343", "type": "manuscript", "label": "PMID 36555343 full text"}, {"id": "data:geo:GSE40290", "type": "dataset", "label": "GEO GSE40290"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36555343", "type": "extraction", "used": ["source:pmid:36555343"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE40290", "type": "accession_resolution", "used": ["data:geo:GSE40290"], "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:36555343", "parent_hash": "sha256:06fde5e3c05d2b925ec21bb6349ec816bbd764a0076f9b09902d2846c0a7ee38", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE40290 licence not read", "asset:data:geo:GSE40290 not downloaded", "asset:data:geo:GSE53819 licence not read", "asset:data:geo:GSE53819 not downloaded", "asset:data:geo:GSE61218 licence not read", "asset:data:geo:GSE61218 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]}