Integrated Bioinformatics Analysis of Hub Genes and Pathways in Anaplastic Thyroid Carcinomas.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30774662", "kind": "science-record", "revision": 8, "content_hash": "sha256:12f71cb226b7a0db47407f2dcbcca965cfabae756e0f5cc0fc5e5d3293e4d8f1", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T22:43:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrated Bioinformatics Analysis of Hub Genes and Pathways in Anaplastic Thyroid Carcinomas.", "doi": "10.1155/2019/9651380", "pmid": "30774662", "authors": ["Xueren Gao", "Jianguo Wang", "Shulong Zhang"], "journal": "International journal of endocrinology", "year": 2019, "abstract": "Anaplastic thyroid carcinoma (ATC) is a very rare malignancy; the pathogenesis of which is still not fully understood. The aim of the present study was to identify hub genes and pathways in ATC by microarray expression profiling. Two independent datasets (GSE27155 and GSE53072) were downloaded from GEO database. The differentially expressed genes (DEGs) between ATC tissues and normal thyroid tissues were screened out by the limma package and then enriched by gene ontology (GO) and KEGG pathway analysis. The hub genes were selected by protein-protein interaction (PPI) analysis. A total of 141 common upregulated and 87 common downregulated genes were screened out. These DEGs were significantly enriched in the phagosome and NF-kappa B signaling pathway. Through PPI analysis, TOP2A, TYMS, CCNB1, RACGAP1, FEN1, PRC1, and UBE2C were selected as hub genes, which were highly expressed in ATC tissues. TCGA data suggested that the expression levels of TOP2A, TYMS, FEN1, and PRC1 genes were also upregulated in other histological subtypes of thyroid carcinoma. High expression of TOP2A, TYMS, FEN1, PRC1, or UBE2C gene significantly decreased disease-free survival of patients with other thyroid carcinomas. In conclusion, the present study identified several hub genes and pathways, which will contribute to elucidating the pathogenesis of ATC and providing therapeutic targets for ATC.", "claims": [{"id": "claim-data-access", "statement": "The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30774662", "locator": "sections[13] \"Data Availability\" paragraph 2", "quote": "The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072)."}], "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:30774662"], "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:GSE27155"], "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:GSE27155"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30774662", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2019/9651380", "sha256": "sha256:dd69434bcf5ccfb6c337b2e20c0aa7720c83993b05ac34151d8ec4df19d4ec91", "bytes": 27120, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2019/9651380", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6350566", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE27155", "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=GSE27155", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27155", "version": null, "note": "The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM671255", "GSM671256", "GSM671257", "GSM671258", "GSM671259", "GSM671260", "GSM671261", "GSM671262", "GSM671263", "GSM671264", "GSM671265", "GSM671266", "GSM671267", "GSM671268", "GSM671269", "GSM671270", "GSM671271", "GSM671272", "GSM671273", "GSM671274", "GSM671275", "GSM671276", "GSM671277", "GSM671278", "GSM671279", "GSM671280", "GSM671281", "GSM671282", "GSM671283", "GSM671284", "GSM671285", "GSM671286", "GSM671287", "GSM671288", "GSM671289", "GSM671290", "GSM671291", "GSM671292", "GSM671293", "GSM671294", "GSM671295", "GSM671296", "GSM671297", "GSM671298", "GSM671299", "GSM671300", "GSM671301", "GSM671302", "GSM671303", "GSM671304", "GSM671305", "GSM671306", "GSM671307", "GSM671308", "GSM671309", "GSM671310", "GSM671311", "GSM671312", "GSM671313", "GSM671314", "GSM671315", "GSM671316", "GSM671317", "GSM671318", "GSM671319", "GSM671320", "GSM671321", "GSM671322", "GSM671323", "GSM671324", "GSM671325", "GSM671326", "GSM671327", "GSM671328", "GSM671329", "GSM671330", "GSM671331", "GSM671332", "GSM671333", "GSM671334", "GSM671335", "GSM671336", "GSM671337", "GSM671338", "GSM671339", "GSM671340", "GSM671341", "GSM671342", "GSM671343", "GSM671344", "GSM671345", "GSM671346", "GSM671347", "GSM671348", "GSM671349", "GSM671350", "GSM671351", "GSM671352", "GSM671353"], "sample_count": 99, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Human thyroid adenomas, carcinomas, and normals", "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:GSE53072", "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=GSE53072", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53072", "version": null, "note": "The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1281636", "GSM1281637", "GSM1281638", "GSM1281639", "GSM1281640", "GSM1281641", "GSM1281642", "GSM1281643", "GSM1281644"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profilling of anaplastic thyroid carcinomas (ATC) and normal thyroid 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": "asset:table:pmid:30774662:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4ce0f6685b0d7b1d19afc27a188185c18b5782720ac90795798d27b294fad6e9", "bytes": 2462, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tab1", "version": null, "note": "The common differentially expressed genes in GSE27155 and GSE53072 datasets. Note: bold and italic data indicate genes in the phagosome and NF-kappa B signaling pathway, respectively. Bold-italic data indicates the common gene in the phagosome and NF-kappa B signaling pathway.", "structure": {"pmcid": "PMC6350566", "section_index": 10, "section_title": "3.1. Identification of DEGs", "row_count": 24, "column_count": 11}, "table": {"label": "Table 1", "caption": "The common differentially expressed genes in GSE27155 and GSE53072 datasets. Note: bold and italic data indicate genes in the phagosome and NF-kappa B signaling pathway, respectively. Bold-italic data indicates the common gene in the phagosome and NF-kappa B signaling pathway.", "rows": [["Common differentially expressed genes"], ["Downregulated genes", "Upregulated genes"], ["MAN1C1", "CA4", "WASF3", "HSD17B4", "C1QA", "NCF2", "CLEC7A", "RAB31", "COL5A2", "CCNB1", "RAP2C"], ["PBX1", "KCNJ16", "CLN5", "MYLIP", "CLIC4", "ASPM", "RECQL", "PMAIP1", "COL6A3", "VCAN", "IRAKI"], ["Clorfll5", "PTPRM", "RCBTB1", "HSD17B8", "CDC20", "KIF14", "TUBA1A", "ADGRE5", "CDC25B", "LMNB1", "FLNA"], ["MARC2", "TXNL1", "TSHR", "MTCH1", "VCAM1", "LBR", "RACGAP1", "TPM4", "TPX2", "TGFBI", "TAGLN2"], ["MARC1", "CIRBP", "SAV1", "KHDRBS2", "GPSM2", "ARID5B", "CORO1C", "COLGALT1", "UBE2C", "SLC36A1", "C3AR1"], ["RAP1GAP", "BCAM", "DI02", "LMBRD1", "GNAI3", "PLAU", "CIT", "VASP", "CTSA", "LHFPL2", "TYMS"], ["ECHDC2", "TLE2", "CKB", "SLC26A4", "CD53", "ZWINT", "ALOX5AP", "EMP3", "ADRM1", "CD14", "WIPF1"], ["PLPP3", "PAX8", "PPP1R13B", "EPHB6", "IFI16", "MICAL2", "PNP", "PLIN3", "B4GALT5", "TTK", "OSMR"], ["SELENBP1", "LRP2", "SORD", "ATP6V0E2", "FCER1G", "MS4A4A", "RNASE6", "DDX39A", "ITGB2", "RAB32", "KIF4A"], ["RGS5", "ACADL", "DUOX1", "TMEM243", "FCGR2A", "FEN1", "BAZ1A", "BST2", "YWHAH", "TUBB2A", ""], ["ALDH9A1", "RAB17", "CRABP1", "EPHX2", "FCGR2B", "NNMT", "SEC23A", "TYROBP", "LGALS1", "CLIC1", ""], ["RGS16", "SNTA1", "DUOX2", "TG", "PTPRC", "RHOG", "NUSAP1", "AP2S1", "RAC2", "HLA-DPA1", ""], ["HHEX", "INPP5J", "GATM", "TJP2", "TRAF5", "LPXN", "ANXA2", "RRM2", "GNL3", "TNFRSF21", ""], ["PRKCQ", "CBX7", "MY05C", "NTRK2", "DTL", "MS4A6A", "PKM", "MTHFD2", "CD86", "THBS2", ""], ["NEBL", "ACOX2", "DAPK2", "FOXE1", "ENOl", "PPP1R14B", "PRC1", "TMSB10", "SMC4", "UPP1", ""], ["OGDHL", "ZBED2", "ABAT", "BSPRY", "LAPTM5", "Cl lorf24", "CHSY1", "SLC20A1", "HCLS1", "TMEM176B", ""], ["ABLIM1", "HGD", "SALL1", "CCL21", "YARS", "CTSC", "CCL13", "ACTR3", "TOPBP1", "EIF4EBP1", ""], ["FGFR2", "LIMCH1", "CDH16", "ALDH1A1", "DPYD", "TUBA1C", "KPNA2", "COL3A1", "TFRC", "MCM4", ""], ["GLB1L2", "PPARGC1A", "ALDH3A2", "CLIC3", "MTMR11", "LYZ", "SLC16A3", "PXDN", "TLR2", "LY96", ""], ["METTL7A", "HOPX", "DUSP14", "RGN", "S100A10", "FOXM1", "EVI2A", "MCM6", "H2AFZ", "ANXA2P2", ""], ["PEBP1", "SORBS2", "HLF", "GPRASP1", "S100A11", "TNFRSF1A", "TOP2A", "RND3", "BASP1", "TNC", ""], ["IFT88", "PDE8B", "NAP1L2", "", "AIM2", "CD163", "COL1A1", "FAP", "SLC1A3", "PLP2", ""]], "row_count": 24, "column_count": 11, "numeric_cells": 39, "header_rows": 2, "locator": "section[10]/table-wrap[1]#tab1"}}], "gaps": ["asset:data:geo:GSE27155 not downloaded", "asset:data:geo:GSE27155 licence not read", "asset:data:geo:GSE53072 not downloaded", "asset:data:geo:GSE53072 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "reordered", "quote": "“The Benjamini-Hochberg (BH) method was introduced to adjust the raw p values.”"}}, {"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": "Pathway 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE27155", "GSE53072"], "resolved_accessions": ["GSE27155", "GSE53072"], "statements": ["The microarray data used to support the findings of this study have been deposited in the Gene Expression Omnibus (GEO) repository (accession numbers: GSE27155 and GSE53072)."], "basis": "The paper names GSE27155, GSE53072 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:30774662", "data:geo:GSE27155", "asset:table:pmid:30774662:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE27155"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:57Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 23452, "completion_tokens": 2275, "cached_tokens": 648}}, "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:30774662", "type": "paper", "label": "pmid:30774662"}, {"id": "source:pmid:30774662", "type": "manuscript", "label": "PMID 30774662 full text"}, {"id": "data:geo:GSE27155", "type": "dataset", "label": "GEO GSE27155"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30774662", "type": "paper", "label": "pmid:30774662"}, {"id": "source:pmid:30774662", "type": "manuscript", "label": "PMID 30774662 full text"}, {"id": "data:geo:GSE27155", "type": "dataset", "label": "GEO GSE27155"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30774662", "type": "extraction", "used": ["source:pmid:30774662"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE27155", "type": "accession_resolution", "used": ["data:geo:GSE27155"], "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:30774662", "parent_hash": "sha256:508916b8a6f3964df5124a42d3019bc30309bc8e6b36b84373c69ca940e782ed", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE27155 licence not read", "asset:data:geo:GSE27155 not downloaded", "asset:data:geo:GSE53072 licence not read", "asset:data:geo:GSE53072 not downloaded", "execution.not_run", "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": ["to identify hub genes and pathways in ATC by microarray expression profiling. Two independent datase"], "order_basis": "paper_text_order:247", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["“The Benjamini-Hochberg (BH) method was introduced to adjust the raw p values.”"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}