Bioinformatics analysis identifies hub genes and pathways in nasopharyngeal carcinoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31516577", "kind": "science-record", "revision": 7, "content_hash": "sha256:da73dbb803b2a88b96f2df5806699ccebc3c807130ca95cb5f7e329c96ee1261", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:00:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics analysis identifies hub genes and pathways in nasopharyngeal carcinoma.", "doi": "10.3892/ol.2019.10707", "pmid": "31516577", "authors": ["Kang Liu", "Min Kang", "Ziyan Zhou", "Wen Qin", "Rensheng Wang"], "journal": "Oncology letters", "year": 2019, "abstract": "The aim of the present study was to identify genes associated with and the underlying mechanisms in nasopharyngeal carcinoma (NPC) using microarray data. GSE12452 and GSE34573 gene expression profiles were obtained from the Gene Expression Omnibus (GEO) database. GEO2R was utilized to obtain differentially expressed genes (DEGs). In addition, the Database for Annotation, Visualization and Integrated Discovery was used to perform pathway enrichment analyses for DEGs using the Gene Ontology (GO) annotation along with the Kyoto Encyclopedia of Genes and Genomes (KEGG). Furthermore, Cytoscape was used to perform module analysis of the protein-protein interaction (PPI) network and pathways of the hub genes were studied. A total of 298 genes were ascertained as DEGs in the two datasets. To functionally categorize these DEGs, we obtained 82 supplemented GO terms along with 7 KEGG pathways. Subsequently, a PPI network consisting of 10 hub genes with high degrees of interaction was constructed. These hub genes included cyclin-dependent kinase (CDK) 1, structural maintenance of chromosomes (SMC) 4, kinetochore-associated (KNTC) 1, kinesin family member (KIF) 23, aurora kinase A (AURKA), ATAD (ATPase family AAA domain containing) 2, NDC80 kinetochore complex component, enhancer of zeste 2 polycomb repressive complex 2 subunit, BUB1 mitotic checkpoint serine/threonine kinase and protein regulator of cytokinesis 1. CDK1, SMC4, KNTC1, KIF23, AURKA and ATAD2 presented with high areas under the curve in receiver operator curves, suggesting that these genes may be diagnostic markers for nasopharyngeal carcinoma. In conclusion, it was proposed that CDK1, SMC4, KNTC1, KIF23, AURKA and ATAD2 may be involved in the tumorigenesis of NPC. Furthermore, they may be utilized as molecular biomarkers in early diagnosis of NPC.", "claims": [{"id": "claim-method", "statement": "The receiver operating characteristic (ROC) curve was constructed using SPSS 19.0 (IBM Corp., Armonk, NY, USA).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31516577", "locator": "sections[8] \"Statistical analysis\" paragraph 2", "quote": "The receiver operating characteristic (ROC) curve was constructed using SPSS 19.0 (IBM Corp., Armonk, NY, USA)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31516577", "locator": "sections[18] \"Availability of data and materials\" paragraph 2", "quote": "The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/)."}], "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:31516577"], "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:GSE12452"], "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:GSE12452"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31516577", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ol.2019.10707", "sha256": "sha256:1b2b15e4018291eddd95bbce37437998a67d915cb508d7b9006af7a4e172b41f", "bytes": 18892, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ol.2019.10707", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6732963", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12452", "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=GSE12452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12452", "version": null, "note": "The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM312896", "GSM312897", "GSM312898", "GSM312899", "GSM312900", "GSM312901", "GSM312902", "GSM312903", "GSM312904", "GSM312905", "GSM312906", "GSM312907", "GSM312908", "GSM312909", "GSM312910", "GSM312911", "GSM312912", "GSM312913", "GSM312914", "GSM312915", "GSM312916", "GSM312917", "GSM312918", "GSM312919", "GSM312920", "GSM312921", "GSM312922", "GSM312923", "GSM312924", "GSM312925", "GSM312926", "GSM312927", "GSM312928", "GSM312929", "GSM312930", "GSM312931", "GSM312932", "GSM312933", "GSM312934", "GSM312935", "GSM312936"], "sample_count": 41, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "mRNA expression profiling of nasopharyngeal 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:GSE34573", "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=GSE34573", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE34573", "version": null, "note": "The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM850481", "GSM850482", "GSM850483", "GSM850484", "GSM850485", "GSM850486", "GSM850487", "GSM850488", "GSM850489", "GSM850490", "GSM850491", "GSM850492", "GSM850493", "GSM850494", "GSM850495", "GSM850496", "GSM850497", "GSM850498", "GSM850499", "GSM850500", "GSM850523", "GSM850524", "GSM850525", "GSM850526", "GSM850537", "GSM850538", "GSM850539", "GSM850540", "GSM850541", "GSM850542", "GSM850543", "GSM850544", "GSM850545", "GSM850546", "GSM850562", "GSM850563", "GSM850564", "GSM850565", "GSM850566", "GSM850567", "GSM850568", "GSM850569", "GSM850570", "GSM850575", "GSM850576", "GSM850577", "GSM850578", "GSM850587", "GSM850588", "GSM850589", "GSM850590", "GSM850591", "GSM850592", "GSM850593", "GSM850640", "GSM850641", "GSM850642", "GSM850643", "GSM850672", "GSM850673", "GSM850674", "GSM850675", "GSM850676", "GSM850707"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "3720;3718;570", "taxon": "Homo sapiens", "title": "A Global View of the Oncogenic Landscape in Nasopharyngeal Carcinoma:An Integrated Analysis at the Genetic and Expression Levels", "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:GSE12452 not downloaded", "asset:data:geo:GSE12452 licence not read", "asset:data:geo:GSE34573 not downloaded", "asset:data:geo:GSE34573 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": "receiver operating characteristic (ROC) curve", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The receiver operating characteristic (ROC) curve was constructed using SPSS 19.0 (IBM Corp., Armonk, NY, USA)."}}], "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": ["GSE12452", "GSE34573"], "resolved_accessions": ["GSE12452", "GSE34573"], "statements": ["The datasets generated and/or analyzed during the present study are available in the GEO repository, (https://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE12452, GSE34573 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:31516577", "data:geo:GSE12452"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12452"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:04Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 15537, "completion_tokens": 1259, "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:31516577", "type": "paper", "label": "pmid:31516577"}, {"id": "source:pmid:31516577", "type": "manuscript", "label": "PMID 31516577 full text"}, {"id": "data:geo:GSE12452", "type": "dataset", "label": "GEO GSE12452"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31516577", "type": "paper", "label": "pmid:31516577"}, {"id": "source:pmid:31516577", "type": "manuscript", "label": "PMID 31516577 full text"}, {"id": "data:geo:GSE12452", "type": "dataset", "label": "GEO GSE12452"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31516577", "type": "extraction", "used": ["source:pmid:31516577"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12452", "type": "accession_resolution", "used": ["data:geo:GSE12452"], "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:31516577", "parent_hash": "sha256:1ecd6697a30e016b1b36327454acd9ed3add1d1e0d06770160f3ca4fcaa15ce5", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE12452 licence not read", "asset:data:geo:GSE12452 not downloaded", "asset:data:geo:GSE34573 licence not read", "asset:data:geo:GSE34573 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["isms in nasopharyngeal carcinoma (NPC) using microarray data. GSE12452 and GSE34573 gene expression"], "order_basis": "paper_text_order:179", "id": "assay:1"}, {"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": "consumes_earlier_output", "id": "assay:2"}]}