Identify the co-expressed genes of hypertensive nephropathy and diabetic nephropathy.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40461634", "kind": "science-record", "revision": 4, "content_hash": "sha256:74b4d7ea5c13c033beb85520e06c03d4581024fc5c3fb08ee68869020ad64e4e", "created_at": "2026-11-01T20:30:35Z", "updated_at": "2026-11-01T22:56:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identify the co-expressed genes of hypertensive nephropathy and diabetic nephropathy.", "doi": "10.1038/s41598-025-04679-w", "pmid": "40461634", "authors": ["Yanmin Wang", "Yiming Wang", "Jing Jin", "Bing Ma"], "journal": "Scientific reports", "year": 2025, "abstract": "This study focused on the intricate connections between hypertension nephropathy (HN) and diabetic nephropathy (DN) in terms of molecular and pathological mechanisms. The samples were from the Gene Expression Omnibus (GEO) database. GSE37460 and GSE142153 are training sets, and GSE37455 and GSE30529 are validation sets. We found 42 shared differentially expressed genes (DEGs) by means of the differential analysis. The GO/KEGG and GSEA analysis mainly highlights the signal transduction pathways related to the proteasome and cytokines. The eight hub genes identified through the Protein-Protein Interaction (PPI) network analysis include NR4A1, TNFSF10, CX3CR1, EGF, THBD, CXCR4, CCL5, and ATF3. Single-cell sequencing analysis revealed that TNFSF10 and NR4A1 were the most highly expressed in the cells of both HN and DN. Furthermore, five significant microRNAs identified include hsa-miR-1248, hsa-miR-200b-5p, hsa-miR-23b-5p, hsa-miR-3059-5p, and hsa-miR-3065-3p. Six essential transcription factors (TFs) (NFIL3, STAT3, NFKB1, USF1, USF2, and EGR1), 11 important drug chemicals (Cisplatin, Cyclosporine, perfluorooctanoic acid, Quercetin, Tretinoin, bisphenol A, Curcumin, Valproic Acid, Particulate Matter, Simvastatin, and Cadmium), seven related diseases (Atherosclerosis, Glioblastoma, Pulmonary Fibrosis, Asthma, Hepatitis B, Hepatitis C, and Diabetes Mellitus), and ten important RNA-binding proteins (RBPs) (CHTOP, EIF4E, HNRNPK, IGF2BP3, YTHDF3, HNRNPA2B1, RBM47, YBX1, RBFOX2, and RBM10). Finally, molecular docking simulations suggest that Tretinoin and Curcumin may have potential therapeutic value for both HN and DN. This study provides novel therapeutic targets for the combined diagnosis and treatment of HN and DN.", "claims": [{"id": "claim-method", "statement": "For the DN and HN datasets, the limma package (version 3.62.2) in R is used for differential analysis to determine DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40461634", "locator": "sections[4] \"Shared DEGs between HN and DN\" paragraph 2", "quote": "For the DN and HN datasets, the limma package (version 3.62.2) in R is used for differential analysis to determine DEGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40461634", "locator": "sections[26] \"notes\" paragraph 1", "quote": "All data generated or analyzed during this study will be available upon request to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We found 42 shared differentially expressed genes (DEGs) by means of the differential analysis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40461634", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We found 42 shared differentially expressed genes (DEGs) by means of the differential analysis."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We found 42 shared differentially expressed genes (DEGs) by means of the differential analysis.", "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:40461634"], "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:GSE131882"], "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:GSE131882"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40461634", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-04679-w", "sha256": "sha256:f2f44da4bc74dfe65f685b00c1a49ffee4f4d797600dfea6cd3a39780c4d82c6", "bytes": 40425, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-04679-w", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12134351", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE131882", "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=GSE131882", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE131882", "version": null, "note": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3823939", "GSM3823940", "GSM3823941", "GSM3823942", "GSM3823943", "GSM3823944"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "The Single Cell Transcriptomic Landscape of Early Human Diabetic Nephropathy", "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:GSE142153", "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=GSE142153", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE142153", "version": null, "note": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4221568", "GSM4221569", "GSM4221570", "GSM4221571", "GSM4221572", "GSM4221573", "GSM4221574", "GSM4221575", "GSM4221576", "GSM4221577", "GSM4221578", "GSM4221579", "GSM4221580", "GSM4221581", "GSM4221582", "GSM4221583", "GSM4221584", "GSM4221585", "GSM4221586", "GSM4221587", "GSM4221588", "GSM4221589", "GSM4221590", "GSM4221591", "GSM4221592", "GSM4221593", "GSM4221594", "GSM4221595", "GSM4221596", "GSM4221597", "GSM4221598", "GSM4221599", "GSM4221600", "GSM4221601", "GSM4221602", "GSM4221603", "GSM4221604", "GSM4221605", "GSM4221606", "GSM4221607"], "sample_count": 40, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Human PBMCs: Healthy vs Diabetic nephropathy vs ESRD", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE174219", "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=GSE174219", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE174219", "version": null, "note": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5289541", "GSM5289542", "GSM5289543"], "sample_count": 3, "group_sizes": null, "group_sizes_basis": null, "platform": "20795", "taxon": "Homo sapiens", "title": "Single-cell RNA Sequencing Reveals Transcriptional Signatures and Cell-cell crosstalk in Patients with Hypertensive Nephropathy", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE30529", "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=GSE30529", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30529", "version": null, "note": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM757014", "GSM757015", "GSM757016", "GSM757017", "GSM757018", "GSM757019", "GSM757020", "GSM757021", "GSM757022", "GSM757023", "GSM757024", "GSM757025", "GSM757026", "GSM757027", "GSM757028", "GSM757029", "GSM757030", "GSM757031", "GSM757032", "GSM757033", "GSM757034", "GSM757035"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Transcriptome Analysis of Human Diabetic Kidney Disease (DKD Tubuli vs. Control Tubuli)", "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:GSE37455", "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=GSE37455", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37455", "version": null, "note": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM920034", "GSM920035", "GSM920036", "GSM920052", "GSM920053", "GSM920054", "GSM920055", "GSM920056", "GSM920057", "GSM920058", "GSM920059", "GSM920060", "GSM920061", "GSM920062", "GSM920063", "GSM920064", "GSM920065", "GSM920066", "GSM920067", "GSM920068", "GSM920069", "GSM920070", "GSM920071", "GSM920072", "GSM920073", "GSM920074", "GSM920075", "GSM920076", "GSM920077", "GSM920078", "GSM920079", "GSM920080", "GSM920081", "GSM920082", "GSM920083", "GSM920084", "GSM920085", "GSM920086", "GSM920087", "GSM920088", "GSM920089"], "sample_count": 41, "group_sizes": null, "group_sizes_basis": null, "platform": "14663;11670", "taxon": "Homo sapiens", "title": "Cross-species transcriptional network analysis defines shared inflammatory responses in murine and human lupus nephritis[Tubulointerstitial]", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE37460", "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=GSE37460", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37460", "version": null, "note": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study will be available upon request to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1046922", "GSM1046923", "GSM1046924", "GSM1046925", "GSM1046926", "GSM920350", "GSM920351", "GSM920352", "GSM920353", "GSM920368", "GSM920369", "GSM920370", "GSM920371", "GSM920372", "GSM920373", "GSM920374", "GSM920375", "GSM920376", "GSM920377", "GSM920378", "GSM920379", "GSM920380", "GSM920381", "GSM920382", "GSM920383", "GSM920384", "GSM920385", "GSM920386", "GSM920387", "GSM920388", "GSM920389", "GSM920390", "GSM920391", "GSM920392", "GSM920393", "GSM920394", "GSM920395", "GSM920396", "GSM920397", "GSM920398", "GSM920399", "GSM920400", "GSM920401", "GSM920402", "GSM920403", "GSM920404", "GSM920405", "GSM920406", "GSM920407", "GSM920408", "GSM920409", "GSM920410", "GSM920411", "GSM920412", "GSM920413", "GSM920414", "GSM920415", "GSM920416", "GSM920417", "GSM920418", "GSM920419", "GSM920420", "GSM920421", "GSM920422", "GSM920423", "GSM920424", "GSM920425", "GSM920426", "GSM920427"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "14663;11670", "taxon": "Homo sapiens", "title": "Cross-species transcriptional network analysis defines shared inflammatory responses in murine and human lupus nephritis [Glomeruli]", "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:GSE131882 not downloaded", "asset:data:geo:GSE131882 licence not read", "asset:data:geo:GSE142153 not downloaded", "asset:data:geo:GSE142153 licence not read", "asset:data:geo:GSE174219 not downloaded", "asset:data:geo:GSE174219 licence not read", "asset:data:geo:GSE30529 not downloaded", "asset:data:geo:GSE30529 licence not read", "asset:data:geo:GSE37455 not downloaded", "asset:data:geo:GSE37455 licence not read", "asset:data:geo:GSE37460 not downloaded", "asset:data:geo:GSE37460 licence not read"]}, "analysis": {"state": "partial", "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": "verbatim", "quote": "For the DN and HN datasets, the limma package (version 3.62.2) in R is used for differential analysis to determine DEGs."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"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": "Protein-Protein Interaction"}}, {"id": "method-4", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["GSE37460", "GSE37455", "GSE142153", "GSE30529", "GSE174219", "GSE131882"], "resolved_accessions": ["GSE37460", "GSE37455", "GSE142153", "GSE30529", "GSE174219", "GSE131882"], "statements": ["All data generated or analyzed during this study will be available upon request to the corresponding author."], "basis": "The paper names GSE37460, GSE37455, GSE142153, GSE30529, GSE174219, GSE131882 in Gene Expression Omnibus 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:40461634", "data:geo:GSE131882"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE131882"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:53:42Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11625, "completion_tokens": 2037, "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:40461634", "type": "paper", "label": "pmid:40461634"}, {"id": "source:pmid:40461634", "type": "manuscript", "label": "PMID 40461634 full text"}, {"id": "data:geo:GSE131882", "type": "dataset", "label": "GEO GSE131882"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40461634", "type": "paper", "label": "pmid:40461634"}, {"id": "source:pmid:40461634", "type": "manuscript", "label": "PMID 40461634 full text"}, {"id": "data:geo:GSE131882", "type": "dataset", "label": "GEO GSE131882"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40461634", "type": "extraction", "used": ["source:pmid:40461634"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE131882", "type": "accession_resolution", "used": ["data:geo:GSE131882"], "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:40461634", "parent_hash": "sha256:c4eb5d1595229a5002848ebed7cceeff8348b3b800277ff8df50eec6b39e80e0", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE131882 licence not read", "asset:data:geo:GSE131882 not downloaded", "asset:data:geo:GSE142153 licence not read", "asset:data:geo:GSE142153 not downloaded", "asset:data:geo:GSE174219 licence not read", "asset:data:geo:GSE174219 not downloaded", "asset:data:geo:GSE30529 licence not read", "asset:data:geo:GSE30529 not downloaded", "asset:data:geo:GSE37455 licence not read", "asset:data:geo:GSE37455 not downloaded", "asset:data:geo:GSE37460 licence not read", "asset:data:geo:GSE37460 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Materials and methods Samples collection The RNA-Seq data are available in the Gene Expression Om"], "order_basis": "paper_text_order:1825", "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": ["For the DN and HN datasets, the limma package (version 3.62.2) in R is used for differential analysis to determine DEGs."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}