Identification of Differentially Expressed Genes and Prediction of Expression Regulation Networks in Dysfunctional Endothelium.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36140731", "kind": "science-record", "revision": 5, "content_hash": "sha256:e69f6274b4910921d04004a9a7ada2636235a01be550eb4d1de105b8e5eb84f0", "created_at": "2026-11-01T18:15:24Z", "updated_at": "2026-11-01T22:50:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Differentially Expressed Genes and Prediction of Expression Regulation Networks in Dysfunctional Endothelium.", "doi": "10.3390/genes13091563", "pmid": "36140731", "authors": ["Fang Cheng", "Yujie Zeng", "Minzhu Zhao", "Ying Zhu", "Jianbo Li", "Renkuan Tang"], "journal": "Genes", "year": 2022, "abstract": "The detection of early coronary atherosclerosis (ECA) is still a challenge and the mechanism of endothelial dysfunction remains unclear. In the present study, we aimed to identify differentially expressed genes (DEGs) and the regulatory network of miRNAs as well as TFs in dysfunctional endothelium to elucidate the possible pathogenesis of ECA and find new potential markers. The GSE132651 data set of the GEO database was used for the bioinformatic analysis. Principal component analysis (PCA), the identification of DEGs, correlation analysis between significant DEGs, the prediction of regulatory networks of miRNA and transcription factors (TFs), the validation of the selected significant DEGs, and the receiver operating characteristic (ROC) curve analysis as well as area under the curve (AUC) values were performed. We identified ten genes with significantly upregulated signatures and thirteen genes with significantly downregulated signals. Following this, we found twenty-two miRNAs regulating two or more DEGs based on the miRNA-target gene regulatory network. TFs with targets ≥ 10 were E2F1, RBPJ, SSX3, MMS19, POU3F3, HOXB5, and KLF4. Finally, three significant DEGs (TOX, RasGRP3, TSPAN13) were selected to perform validation experiments. Our study identified TOX, RasGRP3, and TSPAN13 in dysfunctional endothelium and provided potential biomarkers as well as new insights into the possible molecular mechanisms of ECA.", "claims": [{"id": "claim-method", "statement": "Differentially expressed genes (DEGs) were obtained and identified from samples with abnormal coronary artery endothelial function and normal samples by the limma package in R software", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36140731", "locator": "sections[4] \"2.2. Differential Gene Screening and Data Processing\" paragraph 2", "quote": "Differentially expressed genes (DEGs) were obtained and identified from samples with abnormal coronary artery endothelial function and normal samples by the limma package in R software"}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE132651 dataset is openly available in the Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132651 accessed on 5 July 2022.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36140731", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "The GSE132651 dataset is openly available in the Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132651 accessed on 5 July 2022."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 10 significantly upregulated genes and 13 significantly downregulated genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36140731", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We identified ten genes with significantly upregulated signatures and thirteen genes with significantly downregulated signals."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified 10 significantly upregulated genes and 13 significantly downregulated genes.", "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:36140731"], "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:GSE132651"], "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:GSE132651"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36140731", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/genes13091563", "sha256": "sha256:e944574adaf4325831d8a6f2ea5bc4aa40fdf4c3cd98fed31e73795179aa005b", "bytes": 38680, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/genes13091563", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9498925", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE132651", "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=GSE132651", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE132651", "version": null, "note": "The GSE132651 dataset is openly available in the Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132651 accessed on 5 July 2022.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE132651 dataset is openly available in the Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132651 accessed on 5 July 2022.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3884865", "GSM3884866", "GSM3884867", "GSM3884868", "GSM3884869", "GSM3884870", "GSM3884871", "GSM3884872", "GSM3884873", "GSM3884874", "GSM3884875", "GSM3884876", "GSM3884877", "GSM3884878", "GSM3884879", "GSM3884880", "GSM3884881", "GSM3884882", "GSM3884883"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Endothelial Gene Expression Associated With Early Coronary Atherosclerosis ", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE132651 not downloaded", "asset:data:geo:GSE132651 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": "Differentially expressed genes (DEGs) were obtained and identified from samples with abnormal coronary artery endothelial function and normal samples by the limma package in R software"}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal component 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": ["GSE132651"], "resolved_accessions": ["GSE132651"], "statements": ["The GSE132651 dataset is openly available in the Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132651 accessed on 5 July 2022."], "basis": "The paper names GSE132651 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:36140731", "data:geo:GSE132651"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE132651"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:06:24Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12526, "completion_tokens": 1181, "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:36140731", "type": "paper", "label": "pmid:36140731"}, {"id": "source:pmid:36140731", "type": "manuscript", "label": "PMID 36140731 full text"}, {"id": "data:geo:GSE132651", "type": "dataset", "label": "GEO GSE132651"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36140731", "type": "paper", "label": "pmid:36140731"}, {"id": "source:pmid:36140731", "type": "manuscript", "label": "PMID 36140731 full text"}, {"id": "data:geo:GSE132651", "type": "dataset", "label": "GEO GSE132651"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36140731", "type": "extraction", "used": ["source:pmid:36140731"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE132651", "type": "accession_resolution", "used": ["data:geo:GSE132651"], "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:36140731", "parent_hash": "sha256:372fa260b01283155984c24898a3ffb2453797600f5bbafe880c06370ee314b2", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE132651 licence not read", "asset:data:geo:GSE132651 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["Differentially expressed genes (DEGs) were obtained and identified from samples with abnormal coronary artery endothelial function and normal samples by the limma package in R software"], "order_basis": "analysis_only", "id": "assay:1"}]}