Identification of key genes predicting the efficacy of mepolizumab in the treatment of severe eosinophilic asthma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41225087", "kind": "science-record", "revision": 4, "content_hash": "sha256:b807a90ceaa860084f5c1b54b68f126f425efd2b337278e2d3c11b5c5bc5a63b", "created_at": "2026-11-01T20:31:15Z", "updated_at": "2026-11-01T22:57:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes predicting the efficacy of mepolizumab in the treatment of severe eosinophilic asthma.", "doi": "10.1038/s41598-025-23443-8", "pmid": "41225087", "authors": ["Peng Xinmin", "Cheng Jinxia", "Li Fengyuan"], "journal": "Scientific reports", "year": 2025, "abstract": "Severe eosinophilic asthma is a treatment-resistant subtype that remains poorly controlled with conventional therapies. According to the latest European Respiratory Society (ERS) guidelines, anti-interleukin-5 (anti-IL-5) biologics such as mepolizumab are recommended for these patients. However, not all individuals respond favorably to mepolizumab. This study aimed to identify gene expression biomarkers predictive of therapeutic response to mepolizumab, facilitating early identification of likely responders. Transcriptomic data (GSE274410) were obtained from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) between responder and non-responder groups were identified. Functional enrichment was conducted using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) gene sets via gene set enrichment analysis (GSEA). Protein-protein interaction (PPI) networks were constructed using the STRING database, and hub genes were identified with the cytoHubba plugin in Cytoscape. Box plots were used to visualize gene expression patterns. FOS and CXCL3 were significantly downregulated in the responder group. Their predictive value was further assessed using receiver operating characteristic (ROC) curve analysis. These findings suggest that FOS and CXCL3 may serve as promising biomarkers for predicting response to mepolizumab and may aid in stratifying patients with severe eosinophilic asthma for individualized biologic therapy.", "claims": [{"id": "claim-method", "statement": "Differential expression analysis was conducted on the filtered dataset using the ‘DESeq2’ package (version 1.44.0)10 in R software (version 4.4.2).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41225087", "locator": "sections[5] \"Screening of differentially expressed genes\" paragraph 2", "quote": "Differential expression analysis was conducted on the filtered dataset using the ‘DESeq2’ package (version 1.44.0)10 in R software (version 4.4.2)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The R code used for analysis is available in the Supplementary Material 1. The datasets analyzed in this study are publicly available in the Gene Expression Omnibus (GEO) database under accession number GSE274410 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274410).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41225087", "locator": "sections[18] \"Data availability\" paragraph 2", "quote": "The R code used for analysis is available in the Supplementary Material 1. The datasets analyzed in this study are publicly available in the Gene Expression Omnibus (GEO) database under accession number GSE274410 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274410)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "FOS and CXCL3 showed AUCs of 0.818 (95% CI: 0.65–0.99) and 0.75 (95% CI: 0.56–0.94), respectively.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "(a) FOS shows an AUC of 0.818 with 95% CI: 0.65–0.99."}, "evidence": [{"asset": "source:pmid:41225087", "locator": "sections[14] \"Validation of core genes and evaluation of their diagnostic value\" paragraph 4", "quote": "(a) FOS shows an AUC of 0.818 with 95% CI: 0.65–0.99."}, {"asset": "source:pmid:41225087", "locator": "sections[14] \"Validation of core genes and evaluation of their diagnostic value\" paragraph 4", "quote": "(b) CXCL3 shows an AUC of 0.75 with 95% CI: 0.56–0.94."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "FOS and CXCL3 showed AUCs of 0.818 (95% CI: 0.65–0.99) and 0.75 (95% CI: 0.56–0.94), respectively.", "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:41225087"], "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:GSE274410"], "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:GSE274410"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41225087", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-23443-8", "sha256": "sha256:cdbe304d9bbb44d933b662ec9127bc340887569f3810eaadb13543bbd75c1c52", "bytes": 32189, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-23443-8", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12612187", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE274410", "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=GSE274410", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE274410", "version": null, "note": "The R code used for analysis is available in the Supplementary Material 1. The datasets analyzed in this study are publicly available in the Gene Expression Omnibus (GEO) database under accession number GSE274410 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274410).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The R code used for analysis is available in the Supplementary Material 1. The datasets analyzed in this study are publicly available in the Gene Expression Omnibus (GEO) database under accession number GSE274410 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274410).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM8448599", "GSM8448600", "GSM8448601", "GSM8448602", "GSM8448603", "GSM8448604", "GSM8448605", "GSM8448606", "GSM8448607", "GSM8448608", "GSM8448609", "GSM8448610", "GSM8448611", "GSM8448612", "GSM8448613", "GSM8448614", "GSM8448615", "GSM8448616", "GSM8448617", "GSM8448618", "GSM8448619", "GSM8448620", "GSM8448621", "GSM8448622", "GSM8448623", "GSM8448624", "GSM8448625", "GSM8448626", "GSM8448627", "GSM8448628", "GSM8448629", "GSM8448630", "GSM8448631", "GSM8448632", "GSM8448633", "GSM8448634", "GSM8448635", "GSM8448636", "GSM8448637", "GSM8448638", "GSM8448639", "GSM8448640", "GSM8448641", "GSM8448642", "GSM8448643", "GSM8448644", "GSM8448645", "GSM8448646", "GSM8448647", "GSM8448648", "GSM8448649", "GSM8448650", "GSM8448651", "GSM8448652"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Mepolizumab-induced Changes in Nasal Methylome and Transcriptome to Predict Response in Asthma", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE274410 not downloaded", "asset:data:geo:GSE274410 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": "Differential expression analysis was conducted on the filtered dataset using the ‘DESeq2’ package (version 1.44.0)10 in R software (version 4.4.2)."}}, {"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"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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: deseq2."}, "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": ["GSE274410"], "resolved_accessions": ["GSE274410"], "statements": ["The R code used for analysis is available in the Supplementary Material 1. The datasets analyzed in this study are publicly available in the Gene Expression Omnibus (GEO) database under accession number GSE274410 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE274410)."], "basis": "The paper names GSE274410 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:41225087", "data:geo:GSE274410"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE274410"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:05:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9186, "completion_tokens": 1781, "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:41225087", "type": "paper", "label": "pmid:41225087"}, {"id": "source:pmid:41225087", "type": "manuscript", "label": "PMID 41225087 full text"}, {"id": "data:geo:GSE274410", "type": "dataset", "label": "GEO GSE274410"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41225087", "type": "paper", "label": "pmid:41225087"}, {"id": "source:pmid:41225087", "type": "manuscript", "label": "PMID 41225087 full text"}, {"id": "data:geo:GSE274410", "type": "dataset", "label": "GEO GSE274410"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41225087", "type": "extraction", "used": ["source:pmid:41225087"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE274410", "type": "accession_resolution", "used": ["data:geo:GSE274410"], "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:41225087", "parent_hash": "sha256:3e12fec2b4238ca0f4eb5f6f879a6c8b00e1f78218a0b7dc88e72980d3b6e03c", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE274410 licence not read", "asset:data:geo:GSE274410 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": ["Differential expression analysis was conducted on the filtered dataset using the ‘DESeq2’ package (version 1.44.0)10 in R software (version 4.4.2)."], "order_basis": "analysis_only", "id": "assay:1"}]}