Identification of Key Pathways and Genes of Acute Respiratory Distress Syndrome Specific Neutrophil Phenotype.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31531373", "kind": "science-record", "revision": 8, "content_hash": "sha256:b98bcf330cfe7472f3abde4f3123f1b66f2ef315a57a5a56d69abad5d5c196eb", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:44:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Key Pathways and Genes of Acute Respiratory Distress Syndrome Specific Neutrophil Phenotype.", "doi": "10.1155/2019/9528584", "pmid": "31531373", "authors": ["Dong Wang", "Yajuan Li", "Changping Gu", "Mengjie Liu", "Yuelan Wang"], "journal": "BioMed research international", "year": 2019, "abstract": "Despite over 50 years of clinical and basic studies, acute respiratory distress syndrome (ARDS) is still a critical challenge with high mortality worldwide. The severity of neutrophil activation was associated with disease severity. However, the detailed pathophysiology of the circulating polymorphonuclear neutrophil activation in ARDS remains unclear. To identify key pathways and genes in the ARDS-specific neutrophil phenotype distinct from sepsis, the datasets of blood polymorphonuclear neutrophils (PMNs) from patients with ARDS (GSE76293) and from sepsis patients (GSE49757) were chosen from the Gene Expression Omnibus (GEO) and analyzed using bioinformatics methods. A total of 220 differential expressed genes (DEGs) were overlapped between GSE49757 and GSE76293 in a Venn diagram. Pathway enrichment analysis results showed that DEGs in GSE76293 were mainly enriched in the MAPK signaling pathway, FoxO signaling pathway, and AMPK signaling pathway relative to GSE49757. We identified 30 hub genes in the protein-protein interaction network. By comparing with GSE49757, we speculated that GAPDH, MAPK8, PIK3CB, and MMP9 may play important roles in the progression of ARDS-specific circulating neutrophil activation. The findings may provide novel insights into the development of promising targets for the diagnosis and treatment of ARDS in the future.", "claims": [{"id": "claim-method", "statement": "DEGs were identified using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), which is an online tool based on the GEOquery and Limma R packages [12].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31531373", "locator": "sections[4] \"2.2. Identification of DEGs\" paragraph 2", "quote": "DEGs were identified using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), which is an online tool based on the GEOquery and Limma R packages [12]."}], "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:31531373", "locator": "sections[19] \"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:31531373"], "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:GSE49757"], "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:GSE49757"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31531373", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2019/9528584", "sha256": "sha256:620e6c23268c4cd7684215035a8ca3dccf97b15ec0a966e4a590d064798452e4", "bytes": 27548, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2019/9528584", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6720049", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE49757", "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=GSE49757", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE49757", "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": ["GSM1206587", "GSM1206588", "GSM1206589", "GSM1206590", "GSM1206591", "GSM1206592", "GSM1206593", "GSM1206594", "GSM1206595", "GSM1206596", "GSM1206597", "GSM1206598", "GSM1206599", "GSM1206600", "GSM1206601", "GSM1206602", "GSM1206603", "GSM1206604", "GSM1206605", "GSM1206606", "GSM1206607", "GSM1206608", "GSM1206609", "GSM1206610", "GSM1206611", "GSM1206612", "GSM1206613", "GSM1206614", "GSM1206615", "GSM1206616", "GSM1206617", "GSM1206618", "GSM1206619", "GSM1206620", "GSM1206621", "GSM1206622", "GSM1206623", "GSM1206624", "GSM1206625", "GSM1206626", "GSM1206627", "GSM1206628", "GSM1206629", "GSM1206630", "GSM1206631", "GSM1206632", "GSM1206633", "GSM1206634", "GSM1206635", "GSM1206636", "GSM1206637", "GSM1206638", "GSM1206639", "GSM1206640", "GSM1206641", "GSM1206642"], "sample_count": 56, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "A Transcriptomic Reporter Assay Employing Neutrophils to Measure Immunogenic Activity of Septic Patients' Plasma (Expt. 3)", "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:GSE76293", "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=GSE76293", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76293", "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": ["GSM1979240", "GSM1979241", "GSM1979242", "GSM1979243", "GSM1979244", "GSM1979245", "GSM1979246", "GSM1979247", "GSM1979248", "GSM1979249", "GSM1979250", "GSM1979251", "GSM1979252", "GSM1979253", "GSM1979254", "GSM1979255", "GSM1979256", "GSM1979257", "GSM1979258", "GSM1979259", "GSM1979260", "GSM1979261", "GSM1979262", "GSM1979263", "GSM1979264", "GSM1979265", "GSM1979266", "GSM1979267", "GSM1979268", "GSM1979269", "GSM1979270", "GSM1979271", "GSM1979272", "GSM1979273", "GSM1979274", "GSM1979275", "GSM1979276", "GSM1979277", "GSM1979278", "GSM1979279", "GSM1979280", "GSM1979281", "GSM1979282", "GSM1979283", "GSM1979284", "GSM1979285", "GSM1979286", "GSM1979287", "GSM1979288", "GSM1979289", "GSM1979290", "GSM1979291", "GSM1979292", "GSM1979293", "GSM1979294", "GSM1979295", "GSM1979296", "GSM1979297", "GSM1979298", "GSM1979299", "GSM1979300", "GSM1979301", "GSM1979302", "GSM1979303", "GSM1979304", "GSM1979305", "GSM1979306", "GSM1979307", "GSM1979308", "GSM1979309", "GSM1979310", "GSM1979311", "GSM1979312", "GSM1979313", "GSM1979314", "GSM1979315", "GSM1979316", "GSM1979317", "GSM1979318", "GSM1979319", "GSM1979320", "GSM1979321", "GSM1979322", "GSM1979323", "GSM1979324", "GSM1979325", "GSM1979326", "GSM1979327", "GSM1979328", "GSM1979329", "GSM1979330", "GSM1979331", "GSM1979332", "GSM1979333"], "sample_count": 94, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Neutrophils from ARDS patients and healthy volunteers, and healthy volunteer samples treated with PI3K inhibitors", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31531373:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f3a81c99dca9218672e9de849d1fe04c5d9d85c63831813056401b70e93cd328", "bytes": 1345, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tab1", "version": null, "note": "The top 30 hub genes of the PPI network in GSE76293. logFC: log2 fold change between two experimental conditions. adj.P.Val: p value after adjustment for multiple testing.", "structure": {"pmcid": "PMC6720049", "section_index": 13, "section_title": "3.3. PPI Network Analysis", "row_count": 30, "column_count": 4}, "table": {"label": "Table 1", "caption": "The top 30 hub genes of the PPI network in GSE76293. logFC: log2 fold change between two experimental conditions. adj.P.Val: p value after adjustment for multiple testing.", "rows": [["Gene symbol", "Degree", "logFC", "adj.P.Val"], ["GAPDH", "106", "1.28", "2.69E-06"], ["AKT1", "105", "-1.23", "6.93E-05"], ["RIPK4", "102", "-1.62", "3.42E-04"], ["TOP2A", "87", "0.97", "3.44E-03"], ["MAPK14", "69", "1.50", "1.74E-07"], ["MAPK8", "68", "-0.97", "2.15E-03"], ["CXCL8", "67", "-2.12", "1.97E-03"], ["SMARCA4", "66", "-0.62", "7.63E-03"], ["PIK3CB", "60", "0.65", "3.56E-03"], ["APP", "55", "1.37", "4.14E-03"], ["CREB1", "51", "-0.68", "6.18E-03"], ["JAK2", "47", "0.95", "5.29E-05"], ["CD44", "43", "1.82", "2.85E-06"], ["HDAC4", "42", "0.97", "1.66E-05"], ["PTGS2", "39", "-1.47", "5.15E-03"], ["H2AFV", "39", "-0.68", "2.36E-03"], ["MMP9", "37", "0.69", "2.75E-04"], ["BCL2L1", "37", "0.84", "3.26E-03"], ["SKP2", "36", "-0.69", "5.53E-03"], ["POLR2I", "35", "-0.69", "2.77E-03"], ["NDE1", "35", "-0.72", "8.75E-04"], ["ITGAM", "34", "0.79", "5.92E-05"], ["SNU13", "34", "-0.78", "3.66E-03"], ["CSF1R", "33", "-2.10", "1.08E-05"], ["HIST1H2BK", "32", "0.60", "1.05E-04"], ["MIB2", "31", "-0.73", "5.11E-04"], ["CDKN3", "30", "0.89", "6.48E-04"], ["UBE2D4", "29", "-0.59", "1.51E-03"], ["NDC80", "29", "-1.13", "6.52E-04"]], "row_count": 30, "column_count": 4, "numeric_cells": 91, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tab1"}}], "gaps": ["asset:data:geo:GSE49757 not downloaded", "asset:data:geo:GSE49757 licence not read", "asset:data:geo:GSE76293 not downloaded", "asset:data:geo:GSE76293 licence not read"]}, "analysis": {"state": "complete", "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": "DEGs were identified using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), which is an online tool based on the GEOquery and Limma R packages [12]."}}, {"id": "method-2", "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-3", "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": "Pathway enrichment"}}], "targets": [], "gaps": []}, "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": ["GSE76293", "GSE49757"], "resolved_accessions": ["GSE76293", "GSE49757"], "statements": ["The data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names GSE76293, GSE49757 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:31531373", "data:geo:GSE49757", "asset:table:pmid:31531373:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE49757"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 23511, "completion_tokens": 1239, "cached_tokens": 776}}, "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:31531373", "type": "paper", "label": "pmid:31531373"}, {"id": "source:pmid:31531373", "type": "manuscript", "label": "PMID 31531373 full text"}, {"id": "data:geo:GSE49757", "type": "dataset", "label": "GEO GSE49757"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31531373", "type": "paper", "label": "pmid:31531373"}, {"id": "source:pmid:31531373", "type": "manuscript", "label": "PMID 31531373 full text"}, {"id": "data:geo:GSE49757", "type": "dataset", "label": "GEO GSE49757"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31531373", "type": "extraction", "used": ["source:pmid:31531373"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE49757", "type": "accession_resolution", "used": ["data:geo:GSE49757"], "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:31531373", "parent_hash": "sha256:9af2f8e69dd117a49273d60698d40072ded0855bbb03fa5c48e322384e5d92e5", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE49757 licence not read", "asset:data:geo:GSE49757 not downloaded", "asset:data:geo:GSE76293 licence not read", "asset:data:geo:GSE76293 not downloaded", "execution.not_run", "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": ["DEGs were identified using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), which is an online tool based on the GEOquery and Limma R packages [12]."], "order_basis": "analysis_only", "id": "assay:1"}]}