Gene Expression Profiling of Type 2 Diabetes Mellitus by Bioinformatics Analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33149760", "kind": "science-record", "revision": 7, "content_hash": "sha256:f07dc374024fc1be9d3bc3ee938da6bf09af2539e827b0fd028adc9701d4d9d6", "created_at": "2026-11-01T15:41:15Z", "updated_at": "2026-11-01T22:02:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene Expression Profiling of Type 2 Diabetes Mellitus by Bioinformatics Analysis.", "doi": "10.1155/2020/9602016", "pmid": "33149760", "authors": ["Huijing Zhu", "Xin Zhu", "Yuhong Liu", "Fusong Jiang", "Miao Chen", "Lin Cheng", "Xingbo Cheng"], "journal": "Computational and mathematical methods in medicine", "year": 2020, "abstract": "OBJECTIVE: The aim of this study was to identify the candidate genes in type 2 diabetes mellitus (T2DM) and explore their potential mechanisms.\nMETHODS: The gene expression profile GSE26168 was downloaded from the Gene Expression Omnibus (GEO) database. The online tool GEO2R was used to obtain differentially expressed genes (DEGs). Gene Ontology (GO) term enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were performed by using Metascape for annotation, visualization, and comprehensive discovery. The protein-protein interaction (PPI) network of DEGs was constructed by using Cytoscape software to find the candidate genes and key pathways.\nRESULTS: A total of 981 DEGs were found in T2DM, including 301 upregulated genes and 680 downregulated genes. GO analyses from Metascape revealed that DEGs were significantly enriched in cell differentiation, cell adhesion, intracellular signal transduction, and regulation of protein kinase activity. KEGG pathway analysis revealed that DEGs were mainly enriched in the cAMP signaling pathway, Rap1 signaling pathway, regulation of lipolysis in adipocytes, PI3K-Akt signaling pathway, MAPK signaling pathway, and so on. On the basis of the PPI network of the DEGs, the following 6 candidate genes were identified: PIK3R1, RAC1, GNG3, GNAI1, CDC42, and ITGB1.\nCONCLUSION: Our data provide a comprehensive bioinformatics analysis of genes, functions, and pathways, which may be related to the pathogenesis of T2DM.", "claims": [{"id": "claim-method", "statement": "GEO2R was applied to explore DEGs between T2DM and normal blood samples. Statistically significant DEGs were defined with ∣logFC | ≥2, and the P value < 0.05 was the cut-off criterion.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33149760", "locator": "sections[4] \"2.2. Identification of DEGs\" paragraph 2", "quote": "GEO2R was applied to explore DEGs between T2DM and normal blood samples. Statistically significant DEGs were defined with ∣logFC | ≥2, and the P value < 0.05 was the cut-off criterion."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33149760", "locator": "sections[14] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are available from the corresponding author upon request."}], "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:33149760"], "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:GSE26168"], "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:GSE26168"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33149760", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/9602016", "sha256": "sha256:b68baed0feaeff0bb06d04241f0075cd8eb4e0ff4eaa268dcca8ef5fce43cbfc", "bytes": 28304, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/9602016", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7603564", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE26168", "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=GSE26168", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26168", "version": null, "note": "The data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM532819", "GSM532820", "GSM532821", "GSM532822", "GSM532823", "GSM532824", "GSM532825", "GSM532826", "GSM532827", "GSM532828", "GSM532829", "GSM532830", "GSM532831", "GSM532832", "GSM532833", "GSM532834", "GSM532835", "GSM532836", "GSM532837", "GSM532838", "GSM532839", "GSM532840", "GSM532841", "GSM532842", "GSM532843", "GSM532844", "GSM532845", "GSM532846", "GSM532847", "GSM532848", "GSM532849", "GSM532850", "GSM532851", "GSM532852", "GSM532853", "GSM532854", "GSM532855", "GSM532856", "GSM532857", "GSM532858", "GSM532859", "GSM532860", "GSM532861", "GSM532862", "GSM532863", "GSM532864", "GSM532865", "GSM532866", "GSM532867", "GSM532868", "GSM642434", "GSM642435", "GSM642436", "GSM642437", "GSM642438", "GSM642439", "GSM642440", "GSM642441", "GSM642442", "GSM642443"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "10322;6883", "taxon": "Homo sapiens; Human betaherpesvirus 5; Murid gammaherpesvirus 4; Betapolyomavirus hominis; Rattus norvegicus; Murid betaherpesvirus 1; JC polyomavirus; Human immunodeficiency virus 1; human gammaherpesvirus 4; Human gammaherpesvirus 8; Betapolyomavirus macacae; Mus musculus; Human alphaherpesvirus 1", "title": "Type 2 Diabetes mellitus: mRNA and miRNA profiling", "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:33149760:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:80a3576d9403eea8a99ba1aed31d59f01d946ff68ff10005a0d579d29cdbdb77", "bytes": 1169, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tab1", "version": null, "note": "The candidate genes selected from the protein-protein interaction network.", "structure": {"pmcid": "PMC7603564", "section_index": 10, "section_title": "3.3. PPI Network Construction and Analysis of Modules", "row_count": 13, "column_count": 4}, "table": {"label": "Table 1", "caption": "The candidate genes selected from the protein-protein interaction network.", "rows": [["Core genes", "Gene IDs"], ["Cluster", "Nodes", "Edges"], ["1", "15", "104", "AVPR1B CYSLTR2 EDN3 GHSR GNG3 GRM5 KALRN LTB4R2 MLN NMBR NPFFR2 PIK3R1 PTGFR SAA1 TBXA2R"], ["2", "13", "78", "ASB11 FBXL18 FBXL7 FBXO17 FBXO7 GLMN KLHL41 RNF7 UBE2H UBE2L6 UBE2V1 ZNF645 ZNRF1"], ["3", "8", "28", "CCL20 CXCL3 DRD2 GNAI1 HRH4 NPY2R PTGER3 TAS2R46"], ["4", "8", "28", "ARMC8 CYFIP1 DEFA4 DNASE1L1 HP LTF OLFM4 VCL"], ["5", "8", "28", "CEACAM5 GP2 LY6G6C LY6H LY6K LYPD4 LYPD5 PRSS21"], ["6", "6", "14", "COL19A1 COL25A1 COL4A6 COL9A1 PLOD2 PPIB"], ["7", "5", "10", "CGA FSHB GLP2R GPR45 HTR4"], ["8", "10", "22", "APOA2 BCAR1 BMP4 EVA1A ITGB1 ITGB3 MEN1 MET TMEM132A TNC"], ["9", "17", "35", "ARF6 BDNF CDC42 CFTR FZD4 GBP6 GNAZ HLA-C HLA-DRB1 HLA-DRB5 ITSN2 NGFR NTRK2 RAC1 SNX9 SYT9 TRIM62"], ["Hub genes", "AKT1 CDC42 CREBBP GNAI1 GNG3 GRM5 ITGB1 KALRN PIK3R1 RAC1 SAA1 TBXA2R"], ["Bottleneck genes", "AKT1 CDC42 CEACAM8 CREBBP GNAI1 GNG3 ITGB1 MAP2K3 PIK3R1 PSMB8 RAC1 RFC2 UBE2L6 UBE2V1"]], "row_count": 13, "column_count": 4, "numeric_cells": 36, "header_rows": 2, "locator": "section[10]/table-wrap[1]#tab1"}}], "gaps": ["asset:data:geo:GSE26168 not downloaded", "asset:data:geo:GSE26168 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": 0.8, "band": "high", "quote": "Pathway Enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R differential expression analysis with |logFC| ≥ 2 and P < 0.05", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GEO2R was applied to explore DEGs between T2DM and normal blood samples. Statistically significant DEGs were defined with ∣logFC | ≥2, and the P value < 0.05 was the cut-off criterion."}}], "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": ["GSE26168"], "resolved_accessions": ["GSE26168"], "statements": ["The data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names GSE26168 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33149760", "data:geo:GSE26168", "asset:table:pmid:33149760:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE26168"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24165, "completion_tokens": 1116, "cached_tokens": 792}}, "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:33149760", "type": "paper", "label": "pmid:33149760"}, {"id": "source:pmid:33149760", "type": "manuscript", "label": "PMID 33149760 full text"}, {"id": "data:geo:GSE26168", "type": "dataset", "label": "GEO GSE26168"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33149760", "type": "paper", "label": "pmid:33149760"}, {"id": "source:pmid:33149760", "type": "manuscript", "label": "PMID 33149760 full text"}, {"id": "data:geo:GSE26168", "type": "dataset", "label": "GEO GSE26168"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33149760", "type": "extraction", "used": ["source:pmid:33149760"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE26168", "type": "accession_resolution", "used": ["data:geo:GSE26168"], "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:33149760", "parent_hash": "sha256:db18eaf50165ce6f5ee0aaa5128aabb8495982c325d56e0e510dbf92b3e47b75", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE26168 licence not read", "asset:data:geo:GSE26168 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"}]}