Integrated bioinformatic analysis reveals the underlying molecular mechanism of and potential drugs for pulmonary arterial hypertension.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34016786", "kind": "science-record", "revision": 9, "content_hash": "sha256:cb37eb1b26ec31beb8ddad595a688aeced82e5fea6d8b5ac40bcca90ef3ef6af", "created_at": "2026-11-01T15:41:36Z", "updated_at": "2026-11-01T22:46:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrated bioinformatic analysis reveals the underlying molecular mechanism of and potential drugs for pulmonary arterial hypertension.", "doi": "10.18632/aging.203040", "pmid": "34016786", "authors": ["Haoru Dong", "Xiuchun Li", "Mengsi Cai", "Chi Zhang", "Weiqi Mao", "Ying Wang", "Qian Xu", "Mayun Chen", "Liangxing Wang", "Xiaoying Huang"], "journal": "Aging", "year": 2021, "abstract": "Pulmonary arterial hypertension (PAH) is a devastating cardiovascular disease without a clear mechanism or drugs for treatment. Therefore, it is crucial to reveal the underlying molecular mechanism and identify potential drugs for PAH. In this study, we first integrated three human lung tissue datasets (GSE113439, GSE53408, GSE117261) from GEO. A total of 151 differentially expressed genes (DEGs) were screened, followed by KEGG and GO enrichment analyses and PPI network construction. Five hub genes (CSF3R, NT5E, ANGPT2, FGF7, and CXCL9) were identified by Cytoscape (Cytohubba). GSEA and GSVA were performed for each hub gene to uncover the potential mechanism. Moreover, to repurpose known and therapeutic drugs, the CMap database was retrieved, and nine candidate compounds (lypressin, ruxolitinib, triclabendazole, L-BSO, tiaprofenic acid, AT-9283, QL-X-138, huperzine-a, and L-741742) with a high level of confidence were obtained. Then ruxolitinib was selected to perform molecular docking simulations with ANGPT2, FGF7, NT5E, CSF3R, JAK1, JAK2, JAK3, TYK2. A certain concentration of ruxolitinib could inhibit the proliferation and migration of rat pulmonary artery smooth muscle cells (rPASMCs) in vitro. Together, these analyses principally identified CSF3R, NT5E, ANGPT2, FGF7 and CXCL9 as candidate biomarkers of PAH, and ruxolitinib might exert promising therapeutic action for PAH.", "claims": [{"id": "claim-method", "statement": "To select the DEGs, “Limma” package was utilized with cut-offs of adjusted P value < 0.05 and fold change (FC) > 1.5.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34016786", "locator": "sections[11] \"Identification of DEGs\" paragraph 2", "quote": "To select the DEGs, “Limma” package was utilized with cut-offs of adjusted P value < 0.05 and fold change (FC) > 1.5."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34016786", "locator": "sections[11] \"Identification of DEGs\" paragraph 2", "quote": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database."}], "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:34016786"], "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:GSE113439"], "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:GSE113439"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34016786", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.203040", "sha256": "sha256:6ba621be674ed868cfc896c89be2f8f0a35309d472558a9817806ec386a331b0", "bytes": 50657, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.203040", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8202883", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE113439", "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=GSE113439", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE113439", "version": null, "note": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3106326", "GSM3106327", "GSM3106328", "GSM3106329", "GSM3106330", "GSM3106331", "GSM3106332", "GSM3106333", "GSM3106334", "GSM3106335", "GSM3106336", "GSM3106337", "GSM3106338", "GSM3106339", "GSM3106340", "GSM3106341", "GSM3106342", "GSM3106343", "GSM3106344", "GSM3106345", "GSM3106346", "GSM3106347", "GSM3106348", "GSM3106349", "GSM3106350", "GSM3106351"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling of pulmonary arterial hypertension", "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:GSE117261", "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=GSE117261", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE117261", "version": null, "note": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3290067", "GSM3290068", "GSM3290069", "GSM3290070", "GSM3290071", "GSM3290072", "GSM3290073", "GSM3290074", "GSM3290075", "GSM3290076", "GSM3290077", "GSM3290078", "GSM3290079", "GSM3290080", "GSM3290081", "GSM3290082", "GSM3290083", "GSM3290084", "GSM3290085", "GSM3290086", "GSM3290087", "GSM3290088", "GSM3290089", "GSM3290090", "GSM3290091", "GSM3290092", "GSM3290093", "GSM3290094", "GSM3290095", "GSM3290096", "GSM3290097", "GSM3290098", "GSM3290099", "GSM3290100", "GSM3290101", "GSM3290102", "GSM3290103", "GSM3290104", "GSM3290105", "GSM3290106", "GSM3290107", "GSM3290108", "GSM3290109", "GSM3290110", "GSM3290111", "GSM3290112", "GSM3290113", "GSM3290114", "GSM3290115", "GSM3290116", "GSM3290117", "GSM3290118", "GSM3290119", "GSM3290120", "GSM3290121", "GSM3290122", "GSM3290123", "GSM3290124", "GSM3290125", "GSM3290126", "GSM3290127", "GSM3290128", "GSM3290129", "GSM3290130", "GSM3290131", "GSM3290132", "GSM3290133", "GSM3290134", "GSM3290135", "GSM3290136", "GSM3290137", "GSM3290138", "GSM3290139", "GSM3290140", "GSM3290141", "GSM3290142", "GSM3290143", "GSM3290144", "GSM3290145", "GSM3290146", "GSM3290147", "GSM3290148", "GSM3290149"], "sample_count": 83, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Systems Analysis of the Human Pulmonary Arterial Hypertension Lung Transcriptome", "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:GSE53408", "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=GSE53408", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53408", "version": null, "note": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1290988", "GSM1290989", "GSM1290990", "GSM1290991", "GSM1290992", "GSM1290993", "GSM1290994", "GSM1290995", "GSM1290996", "GSM1290997", "GSM1290998", "GSM1290999", "GSM1291000", "GSM1291001", "GSM1291002", "GSM1291003", "GSM1291004", "GSM1291005", "GSM1291006", "GSM1291007", "GSM1291008", "GSM1291009", "GSM1291010"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Metabolomic heterogeneity of severe pulmonary arterial hypertension", "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:34016786:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a4feb26dc3b3e27a89393a50ea39f93b2a3dbea5c568ec942243107777720076", "bytes": 858, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t1", "version": null, "note": "The result of CMap.", "structure": {"pmcid": "PMC8202883", "section_index": 7, "section_title": "CMap analysis and molecular docking simulation", "row_count": 10, "column_count": 4}, "table": {"label": "Table 1", "caption": "The result of CMap.", "rows": [["Drug name", "Score", "Description", "Target"], ["lypressin", "98.84", "Vasopressin receptor agonist", "AVPR1A, AVPR1B, AVPR2"], ["ruxolitinib", "97.86", "JAK inhibitor", "JAK1, JAK2, TYK2, JAK3"], ["triclabendazole", "94.73", "Microtubule inhibitor", "DNMT1"], ["L-BSO", "94.66", "Glutathione transferase inhibitor", "GCLM"], ["tiaprofenic-acid", "93.96", "Cyclooxygenase inhibitor", "PTGS2, PTGS1"], ["AT-9283", "91.00", "JAK inhibitor", "AURKA, AURKB, ABL1, BCR, FLT3, JAK2, JAK3, RPS6KA6, STK17A"], ["QL-X-138", "90.35", "MTOR inhibitor", "BTK, JAK3, MKNK2, MTOR, PRKDC"], ["L-741742", "-90.13", "Dopamine receptor antagonist", "DRD4, DRD3, SCN1A, SCN3A"], ["huperzine-a", "-90.46", "Acetylcholinesterase inhibitor", "ACHE"]], "row_count": 10, "column_count": 4, "numeric_cells": 13, "header_rows": 0, "locator": "section[7]/table-wrap[1]#t1"}}], "gaps": ["asset:data:geo:GSE113439 not downloaded", "asset:data:geo:GSE113439 licence not read", "asset:data:geo:GSE117261 not downloaded", "asset:data:geo:GSE117261 licence not read", "asset:data:geo:GSE53408 not downloaded", "asset:data:geo:GSE53408 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": "To select the DEGs, “Limma” package was utilized with cut-offs of adjusted P value < 0.05 and fold change (FC) > 1.5."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "analysis of variance"}}, {"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": "PPI"}}, {"id": "method-4", "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": 0.7, "band": "medium", "quote": "GO enrichment"}}], "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": ["GSE113439", "GSE53408", "GSE117261"], "resolved_accessions": ["GSE113439", "GSE53408", "GSE117261"], "statements": ["The raw data of three eligible microarray datasets (GSE113439, GSE53408, GSE117261) based on platform GPL6244 (Affymetrix Human Gene 1.0 ST Array) were downloaded from GEO database."], "basis": "The paper names GSE113439, GSE53408, GSE117261 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:34016786", "data:geo:GSE113439", "asset:table:pmid:34016786:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE113439"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:11Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 42554, "completion_tokens": 1316, "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:34016786", "type": "paper", "label": "pmid:34016786"}, {"id": "source:pmid:34016786", "type": "manuscript", "label": "PMID 34016786 full text"}, {"id": "data:geo:GSE113439", "type": "dataset", "label": "GEO GSE113439"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34016786", "type": "paper", "label": "pmid:34016786"}, {"id": "source:pmid:34016786", "type": "manuscript", "label": "PMID 34016786 full text"}, {"id": "data:geo:GSE113439", "type": "dataset", "label": "GEO GSE113439"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34016786", "type": "extraction", "used": ["source:pmid:34016786"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE113439", "type": "accession_resolution", "used": ["data:geo:GSE113439"], "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:34016786", "parent_hash": "sha256:28e9358a49b018f2f9ef3134424bfb1d6308cf3aafee09f2f6168237280f6979", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE113439 licence not read", "asset:data:geo:GSE113439 not downloaded", "asset:data:geo:GSE117261 licence not read", "asset:data:geo:GSE117261 not downloaded", "asset:data:geo:GSE53408 licence not read", "asset:data:geo:GSE53408 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": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.642, "evidence": ["d inhibit the proliferation and migration of rat pulmonary artery smooth muscle cells (rPASMC"], "order_basis": "paper_text_order:1249", "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": ["To select the DEGs, “Limma” package was utilized with cut-offs of adjusted P value < 0.05 and fold change (FC) > 1.5."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}