Candidate Genes Identified in Systemic Sclerosis-Related Pulmonary Arterial Hypertension Were Associated with Immunity, Inflammation, and Cytokines.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33680092", "kind": "science-record", "revision": 5, "content_hash": "sha256:baaa0a27474e764f93de3ebdad2f9eff3f18799321f918c1ec814a1a9201b16d", "created_at": "2026-11-01T15:41:27Z", "updated_at": "2026-11-01T22:03:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Candidate Genes Identified in Systemic Sclerosis-Related Pulmonary Arterial Hypertension Were Associated with Immunity, Inflammation, and Cytokines.", "doi": "10.1155/2021/6651009", "pmid": "33680092", "authors": ["Zhixiao Xu", "Jiaxing Ruan", "Lingyun Pan", "Chengshui Chen"], "journal": "Cardiovascular therapeutics", "year": 2021, "abstract": "BACKGROUND: Pulmonary complications of systemic sclerosis (SSc), including pulmonary arterial hypertension (PAH), are the leading causes of patient death. However, the precise molecular mechanisms of its etiology are unclear. This study's objective was to identify the candidate genes involved in the progression of SSc-PAH and investigate the genes' function.\nMETHODS: The gene expression profiles of GSE33463 were obtained from the Gene Expression Omnibus (GEO) database. A free-scale gene coexpression network was constructed using the weighted gene coexpression network analysis (WGCNA) to explore the association between gene sets and clinical features and identify candidate biomarkers. Then, gene ontology analysis was performed. A second dataset was used, GSE19617, to validate the hub genes. The verified hub genes' potential function was further explored using gene set enrichment analysis (GSEA).\nRESULTS: Through average link-level clustering, a total of seven modules were classified. A total of 938 hub genes were identified in the key module, and the key module's function mainly enriched was related to chemokine activities. Subsequently, four candidate genes, BTG3, CCR2, RAB10, and TMEM60, were filtered. The expression levels of these four hub genes were consistent in the GSE19617 and GSE33463 datasets. We plotted the ROC curve of the hub genes (all AUC > 0.70). Furthermore, the results of the GSEA for hub genes were correlated with complement and inflammatory responses.\nCONCLUSIONS: The hub genes (BTG3, CCR2, RAB10, and TMEM60) performed well in distinguishing the SSc-PAH patients from controls, and some biological functions, related to immunity, inflammation, and cytokines, might pave the way for follow-up studies on the diagnosis and treatment of SSc-PAH.", "claims": [{"id": "claim-method", "statement": "The gene expression profiles of GSE33463 were obtained from the Gene Expression Omnibus (GEO) database. A free-scale gene coexpression network was constructed using the weighted gene coexpression network analysis (WGCNA) to explore the association between gene sets and clinical features and identify candidate biomarkers.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33680092", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The gene expression profiles of GSE33463 were obtained from the Gene Expression Omnibus (GEO) database. A free-scale gene coexpression network was constructed using the weighted gene coexpression network analysis (WGCNA) to explore the association between gene sets and clinical features and identify candidate biomarkers."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33680092", "locator": "sections[20] \"Data Availability\" paragraph 2", "quote": "The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset."}], "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:33680092"], "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:GSE19617"], "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:GSE19617"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33680092", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/6651009", "sha256": "sha256:094a71f57fe9286cb9b49ab96ad7c2ce1406b91e881ea80749b05725db66e35b", "bytes": 29307, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/6651009", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7906811", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19617", "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=GSE19617", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19617", "version": null, "note": "The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM489194", "GSM489195", "GSM489196", "GSM489197", "GSM489198", "GSM489199", "GSM489200", "GSM489201", "GSM489202", "GSM489203", "GSM489204", "GSM489205", "GSM489206", "GSM489207", "GSM489208", "GSM489209", "GSM489210", "GSM489211", "GSM489212", "GSM489213", "GSM489214", "GSM489215", "GSM489216", "GSM489217", "GSM489218", "GSM489219", "GSM489220", "GSM489221", "GSM489222", "GSM489223", "GSM489224", "GSM489225", "GSM489226", "GSM489227", "GSM489228", "GSM489229", "GSM489230", "GSM489231", "GSM489232", "GSM489233", "GSM489234", "GSM489235", "GSM489236", "GSM489237", "GSM489238", "GSM489239", "GSM489240", "GSM489241", "GSM489242", "GSM489243", "GSM489244", "GSM489245", "GSM489246", "GSM489247"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Limited systemic sclerosis patients with PAH show biomarkers of inflammation and vascular injury", "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:GSE33463", "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=GSE33463", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33463", "version": null, "note": "The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM827665", "GSM827666", "GSM827667", "GSM827668", "GSM827669", "GSM827670", "GSM827671", "GSM827672", "GSM827673", "GSM827674", "GSM827675", "GSM827676", "GSM827677", "GSM827678", "GSM827679", "GSM827680", "GSM827681", "GSM827682", "GSM827683", "GSM827684", "GSM827685", "GSM827686", "GSM827687", "GSM827688", "GSM827689", "GSM827690", "GSM827691", "GSM827692", "GSM827693", "GSM827694", "GSM827695", "GSM827696", "GSM827697", "GSM827698", "GSM827699", "GSM827700", "GSM827701", "GSM827702", "GSM827703", "GSM827704", "GSM827705", "GSM827706", "GSM827707", "GSM827708", "GSM827709", "GSM827710", "GSM827711", "GSM827712", "GSM827713", "GSM827714", "GSM827715", "GSM827716", "GSM827717", "GSM827718", "GSM827719", "GSM827720", "GSM827721", "GSM827722", "GSM827723", "GSM827724", "GSM827725", "GSM827726", "GSM827727", "GSM827728", "GSM827729", "GSM827730", "GSM827731", "GSM827732", "GSM827733", "GSM827734", "GSM827735", "GSM827736", "GSM827737", "GSM827738", "GSM827739", "GSM827740", "GSM827741", "GSM827742", "GSM827743", "GSM827744", "GSM827745", "GSM827746", "GSM827747", "GSM827748", "GSM827749", "GSM827750", "GSM827751", "GSM827752", "GSM827753", "GSM827754", "GSM827755", "GSM827756", "GSM827757", "GSM827758", "GSM827759", "GSM827760", "GSM827761", "GSM827762", "GSM827763", "GSM827764", "GSM827765", "GSM827766", "GSM827767", "GSM827768", "GSM827769", "GSM827770", "GSM827771", "GSM827772", "GSM827773", "GSM827774", "GSM827775", "GSM827776", "GSM827777", "GSM827778", "GSM827779", "GSM827780", "GSM827781", "GSM827782", "GSM827783", "GSM827784", "GSM827785", "GSM827786", "GSM827787", "GSM827788", "GSM827789", "GSM827790", "GSM827791", "GSM827792", "GSM827793", "GSM827794", "GSM827795", "GSM827796", "GSM827797", "GSM827798", "GSM827799", "GSM827800", "GSM827801", "GSM827802", "GSM827803", "GSM827804"], "sample_count": 140, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Erythroid-Specific Transcriptional Changes in PBMCs from Pulmonary Hypertension Patients", "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:33680092:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:03e7d12839c70e48a5e36c368649f92bd9751d62060c7221ed565fb7c4890169", "bytes": 1672, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab1", "version": null, "note": "The top 15 up-regulated genes and 15 down-regulated genes identified in the microarray dataset GSE33463.", "structure": {"pmcid": "PMC7906811", "section_index": 11, "section_title": "3.1. Differentially Expressed Genes between SSc-PAH and Normal Controls", "row_count": 30, "column_count": 4}, "table": {"label": "Table 1", "caption": "The top 15 up-regulated genes and 15 down-regulated genes identified in the microarray dataset GSE33463.", "rows": [["Gene symbol", "logFC", "P value", "Adj. P value"], ["MOAP1", "1.051413956", "1.25E-21", "2.01E-17"], ["MED10", "0.757768783", "1.77E-21", "2.01E-17"], ["EIF1", "0.949347975", "9.48E-21", "4.91E-17"], ["DNAJB1", "1.235358669", "9.76E-21", "4.91E-17"], ["MYLIP", "1.145187023", "1.42E-20", "5.36E-17"], ["DYNLL2", "1.300670563", "2.45E-20", "7.69E-17"], ["SBDS", "1.160211817", "5.46E-20", "1.18E-16"], ["CCDC59", "0.943865194", "5.61E-20", "1.18E-16"], ["PITPNC1", "0.729721186", "7.93E-20", "1.53E-16"], ["LOC652773", "0.833258361", "2.19E-19", "3.07E-16"], ["LOC388275", "0.765982809", "3.01E-19", "3.79E-16"], ["MGAT4A", "1.340399036", "6.79E-19", "7.77E-16"], ["TOMM20", "0.627208790", "7.46E-19", "8.16E-16"], ["TIGA1", "0.820889344", "8.78E-19", "9.20E-16"], ["IRF2BP2", "0.974930681", "1.42E-18", "1.38E-15"], ["TMEM60", "-1.131294044", "2.40E-21", "2.01E-17"], ["EXOSC3", "-0.835661131", "1.49E-20", "5.36E-17"], ["ASH2L", "-0.588897110", "3.02E-20", "8.44E-17"], ["GIMAP4", "-1.639178038", "4.24E-20", "1.07E-16"], ["FPR2", "-1.495763022", "1.10E-19", "1.85E-16"], ["TNFAIP8L2", "-0.909455924", "1.51E-19", "2.37E-16"], ["SCO1", "-0.615800262", "1.67E-19", "2.48E-16"], ["CRIPT", "-0.737821571", "2.59E-19", "3.43E-16"], ["NFE2", "-1.595721981", "5.07E-19", "6.07E-16"], ["RNF149", "-1.090753168", "9.18E-19", "9.24E-16"], ["COPB2", "-0.823346942", "1.97E-18", "1.77E-15"], ["APEX2", "-0.546065608", "2.34E-18", "2.03E-15"], ["SAMD9L", "-1.095950962", "2.65E-18", "2.17E-15"], ["LFNG", "-1.479067449", "2.84E-18", "2.23E-15"]], "row_count": 30, "column_count": 4, "numeric_cells": 94, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:33680092:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:957e1f77ac0cfb80e80f4f4f24bcd6426f81c57974687fba804bb3bff2713e97", "bytes": 940, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#tab2", "version": null, "note": "Gene ontology enrichment analysis of turquoise module genes.", "structure": {"pmcid": "PMC7906811", "section_index": 14, "section_title": "3.4. Functional Annotation of the Key Module", "row_count": 12, "column_count": 4}, "table": {"label": "Table 2", "caption": "Gene ontology enrichment analysis of turquoise module genes.", "rows": [["Term", "Description", "Count", "P adjust"], ["GO:0016493", "C-C chemokine receptor activity", "4", "0.029688"], ["GO:0019957", "C-C chemokine binding", "4", "0.029688"], ["GO:0001637", "G protein-coupled chemoattractant receptor activity", "4", "0.029688"], ["GO:0004950", "Chemokine receptor activity", "4", "0.029688"], ["GO:0019956", "Chemokine binding", "4", "0.045889"], ["GO:0004519", "Endonuclease activity", "7", "0.045889"], ["GO:0004518", "Nuclease activity", "9", "0.045889"], ["GO:0005159", "Insulin-like growth factor receptor binding", "3", "0.045889"], ["GO:0061630", "Ubiquitin protein ligase activity", "9", "0.045889"], ["GO:0004521", "Endoribonuclease activity", "5", "0.045889"], ["GO:0061659", "Ubiquitin-like protein ligase activity", "9", "0.048451"]], "row_count": 12, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[14]/table-wrap[1]#tab2"}}], "gaps": ["asset:data:geo:GSE19617 not downloaded", "asset:data:geo:GSE19617 licence not read", "asset:data:geo:GSE33463 not downloaded", "asset:data:geo:GSE33463 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 0.7, "band": "medium", "quote": "ROC curve"}}, {"id": "method-2", "family": null, "specific": null, "label": "Weighted gene coexpression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The gene expression profiles of GSE33463 were obtained from the Gene Expression Omnibus (GEO) database. A free-scale gene coexpression network was constructed using the weighted gene coexpression network analysis (WGCNA) to explore the association between gene sets and clinical features and identify candidate biomarkers."}}], "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": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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": ["GSE33463", "GSE19617"], "resolved_accessions": ["GSE33463", "GSE19617"], "statements": ["The datasets analyzed during this study were publicly available databases, such as the Gene Expression Omnibus (GEO) dataset."], "basis": "The paper names GSE33463, GSE19617 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": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:33680092", "data:geo:GSE19617", "asset:table:pmid:33680092:1", "asset:table:pmid:33680092:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19617"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:36Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24632, "completion_tokens": 1166, "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:33680092", "type": "paper", "label": "pmid:33680092"}, {"id": "source:pmid:33680092", "type": "manuscript", "label": "PMID 33680092 full text"}, {"id": "data:geo:GSE19617", "type": "dataset", "label": "GEO GSE19617"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33680092", "type": "paper", "label": "pmid:33680092"}, {"id": "source:pmid:33680092", "type": "manuscript", "label": "PMID 33680092 full text"}, {"id": "data:geo:GSE19617", "type": "dataset", "label": "GEO GSE19617"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33680092", "type": "extraction", "used": ["source:pmid:33680092"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19617", "type": "accession_resolution", "used": ["data:geo:GSE19617"], "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:33680092", "parent_hash": "sha256:623e8adf7ef9c72162ff72b13a4ca2ec617181effdd06ea183645923ab16a5bf", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE19617 licence not read", "asset:data:geo:GSE19617 not downloaded", "asset:data:geo:GSE33463 licence not read", "asset:data:geo:GSE33463 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["ROC curve"], "order_basis": "analysis_only", "id": "assay:1"}]}