Identification and validation of oxidative stress-related genes in primary open-angle glaucoma by weighted gene co-expression network analysis and machine learning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39560561", "kind": "science-record", "revision": 4, "content_hash": "sha256:ec9a8021a398e419c743c7cd7f63461f2c17b42f2ea9b431d4312a4fbfc55ee9", "created_at": "2026-11-01T20:29:49Z", "updated_at": "2026-11-01T22:55:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and validation of oxidative stress-related genes in primary open-angle glaucoma by weighted gene co-expression network analysis and machine learning.", "doi": "10.1097/MD.0000000000040389", "pmid": "39560561", "authors": ["Lu-Qian Yang", "Yue Song", "Feng Huang", "Wei Wu", "Hong-Pei Ji"], "journal": "Medicine", "year": 2024, "abstract": "Primary open-angle glaucoma (POAG) is a common ocular disease, and there is currently no effective treatment for POAG therapy. Thus, identifying some effective diagnostic markers is beneficial to the treatment of patients. The expression profile was obtained from Gene Expression Omnibus (GEO) database. The functional enrichment was analyzed using Gene Ontology, Kyoto Encyclopedia of Genes and Genomes and gene set enrichment analysis. Co-expressed genes were identified using weighted gene co-expression network analysis (WGCNA). Hub genes were screened through Lasso regression, support vector machine-recursive feature elimination (SVM-RFE) and Random Forest, and receiver operating characteristic curve was used to assess diagnostic value. Immune cell infiltration was calculated using IOBR package. The regulatory network was constructed through STRING, miRactDB and Cytoscape. The oncoPredict package was employed to predict the candidate chemotherapy agents. According to GSE27276 database, 541 differentially expressed genes were identified. Five oxidative stress-related genes with high area under the curve value, namely HBB, MAOA, ACOX2, ALDH7A1 and TYMP, were determined using WGCNA and machine learning. Infiltration level of NK cells, CD4 T cells and dendritic cells were significantly increased in POAG group compared with normal group, while CD8 T cells and Tregs cells were significantly decreased. HBB was closely related to most immune cells. Hub genes were all targeted by 16 miRNAs. Drug sensitivity analysis exhibited that some drugs were more sensitivity for POAG, such as Acetalax_1804, Ibrutinib_1799 and OSI_027_1594. We identified 5 oxidative stress-related genes with high diagnostic value for POAG.", "claims": [{"id": "claim-method", "statement": "The differentially expressed genes (DEGs) from GSE27276 were identified using the limma R package after the raw data were log-transformed.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39560561", "locator": "sections[4] \"2.2. The analysis of differentially expressed genes\" paragraph 2", "quote": "The differentially expressed genes (DEGs) from GSE27276 were identified using the limma R package after the raw data were log-transformed."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated during and/or analyzed during the current study are publicly available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39560561", "locator": "sections[27] \"fn-group\" paragraph 1", "quote": "The datasets generated during and/or analyzed during the current study are publicly available."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We identified 5 oxidative stress-related genes with high diagnostic value for POAG.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39560561", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We identified 5 oxidative stress-related genes with high diagnostic value for POAG."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We identified 5 oxidative stress-related genes with high diagnostic value for POAG.", "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:39560561"], "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:GSE27276"], "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:GSE27276"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39560561", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000040389", "sha256": "sha256:15719a0c0fc0ecbe47984d57dc2f9bebe976fd85de3ee06c39d9a145b74975cd", "bytes": 25574, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000040389", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11576032", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE27276", "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=GSE27276", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27276", "version": null, "note": "The datasets generated during and/or analyzed during the current study are publicly available.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated during and/or analyzed during the current study are publicly available.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM674408", "GSM674409", "GSM674410", "GSM674411", "GSM674412", "GSM674413", "GSM674414", "GSM674415", "GSM674416", "GSM674417", "GSM674418", "GSM674419", "GSM674420", "GSM674421", "GSM674422", "GSM674423", "GSM674424", "GSM674425", "GSM674426", "GSM674427", "GSM674428", "GSM674429", "GSM674430", "GSM674431", "GSM674432", "GSM674433", "GSM674434", "GSM674435", "GSM674436", "GSM674437", "GSM674438", "GSM674439", "GSM674440", "GSM674441", "GSM674442", "GSM674443"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "2507", "taxon": "Homo sapiens", "title": "Genome-wide Expression of Trabecular Meshwork in POAG", "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:GSE27276 not downloaded", "asset:data:geo:GSE27276 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": "The differentially expressed genes (DEGs) from GSE27276 were identified using the limma R package after the raw data were log-transformed."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"id": "method-3", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}], "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": ["GSE27276"], "resolved_accessions": ["GSE27276"], "statements": ["The datasets generated during and/or analyzed during the current study are publicly available."], "basis": "The paper names GSE27276 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:39560561", "data:geo:GSE27276"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE27276"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:39:00Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8039, "completion_tokens": 2366, "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:39560561", "type": "paper", "label": "pmid:39560561"}, {"id": "source:pmid:39560561", "type": "manuscript", "label": "PMID 39560561 full text"}, {"id": "data:geo:GSE27276", "type": "dataset", "label": "GEO GSE27276"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39560561", "type": "paper", "label": "pmid:39560561"}, {"id": "source:pmid:39560561", "type": "manuscript", "label": "PMID 39560561 full text"}, {"id": "data:geo:GSE27276", "type": "dataset", "label": "GEO GSE27276"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39560561", "type": "extraction", "used": ["source:pmid:39560561"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE27276", "type": "accession_resolution", "used": ["data:geo:GSE27276"], "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:39560561", "parent_hash": "sha256:1179dc7549df46214ca2bb4c2f0d38004c7a49b383cdfffa19d18771c44e82d6", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE27276 licence not read", "asset:data:geo:GSE27276 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": ["The differentially expressed genes (DEGs) from GSE27276 were identified using the limma R package after the raw data were log-transformed."], "order_basis": "analysis_only", "id": "assay:1"}]}