Identification of key genes and immune infiltration modulated by CPAP in obstructive sleep apnea by integrated bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34529670", "kind": "science-record", "revision": 7, "content_hash": "sha256:356089cf7f968cc87c4ea5bbbff88e958add9e49deb741ec82a068eca232f5d7", "created_at": "2026-11-01T15:41:52Z", "updated_at": "2026-11-01T22:04:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes and immune infiltration modulated by CPAP in obstructive sleep apnea by integrated bioinformatics analysis.", "doi": "10.1371/journal.pone.0255708", "pmid": "34529670", "authors": ["Cheng Fan", "Shiyuan Huang", "Chunhua Xiang", "Tianhui An", "Yi Song"], "journal": "PloS one", "year": 2021, "abstract": "Patients with obstructive sleep apnea (OSA) experience partial or complete upper airway collapses during sleep resulting in nocturnal hypoxia-normoxia cycling, and continuous positive airway pressure (CPAP) is the golden treatment for OSA. Nevertheless, the exact mechanisms of action, especially the transcriptome effect of CPAP on OSA patients, remain elusive. The goal of this study was to evaluate the longitudinal alterations in peripheral blood mononuclear cells transcriptome profiles of OSA patients in order to identify the hub gene and immune response. GSE133601 was downloaded from Gene Expression Omnibus (GEO). We identified black module via weighted gene co-expression network analysis (WGCNA), the genes in which were correlated significantly with the clinical trait of CPAP treatment. Finally, eleven hub genes (TRAV10, SNORA36A, RPL10, OBP2B, IGLV1-40, H2BC8, ESAM, DNASE1L3, CD22, ANK3, ACP3) were traced and used to construct a random forest model to predict therapeutic efficacy of CPAP in OSA with a good performance with AUC of 0.92. We further studied the immune cells infiltration in OSA patients with CIBERSORT, and monocytes were found to be related with the remission of OSA and partially correlated with the hub genes identified. In conclusion, these key genes and immune infiltration may be of great importance in the remission of OSA and related research of these genes may provide a new therapeutic target for OSA in the future.", "claims": [{"id": "claim-method", "statement": "Weighted co-expression network was constructed by WGCNA based on the GSE133601.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34529670", "locator": "sections[10] \"Construction of weighted co-expression network and identification of key modules\" paragraph 2", "quote": "Weighted co-expression network was constructed by WGCNA based on the GSE133601."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All relevant data are within the paper.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34529670", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "All relevant data are within the paper."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:34529670"], "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:GSE133601"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {"auc": "a good performance with AUC of 0"}, "inputs": ["data:geo:GSE133601"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34529670", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0255708", "sha256": "sha256:2fdeb69075221801cb57666eba98b5bb56636f64b891c0ef610291649218ad60", "bytes": 27320, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0255708", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8445487", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE133601", "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=GSE133601", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE133601", "version": null, "note": "All relevant data are within the paper.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the paper.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3912810", "GSM3912811", "GSM3912812", "GSM3912813", "GSM3912814", "GSM3912815", "GSM3912816", "GSM3912817", "GSM3912818", "GSM3912819", "GSM3912820", "GSM3912821", "GSM3912822", "GSM3912823", "GSM3912824", "GSM3912825", "GSM3912826", "GSM3912827", "GSM3912828", "GSM3912829", "GSM3912830", "GSM3912831", "GSM3912832", "GSM3912833", "GSM3912834", "GSM3912835", "GSM3912836", "GSM3912837", "GSM3912838", "GSM3912839"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "17244", "taxon": "Homo sapiens", "title": "Transcriptional survey of peripheral blood links lower oxygen saturation during sleep with reduced expressions of CD1D and RAB20 that is reversed by CPAP therapy", "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:34529670:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:01e5c9a758f87eaafcfb3cb5d53f9c70cc801815fe988de2aa7a8ba29951a7db", "bytes": 1103, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#pone.0255708.t001", "version": null, "note": "Top 15 GO enrichment terms associated with genes in black module.", "structure": {"pmcid": "PMC8445487", "section_index": 11, "section_title": "Functional enrichment analysis of genes in the black module", "row_count": 16, "column_count": 4}, "table": {"label": "Table 1", "caption": "Top 15 GO enrichment terms associated with genes in black module.", "rows": [["Categray", "Top 15 enriched GO terms.", "Count", "P-value"], ["BP", "GO:0043928~exonucleolytic nuclear-transcribed mRNA catabolic process involved in deadenylation-dependent decay", "7", "2.1E-3"], ["GO:0007595~lactation", "8", "3.4E-3"], ["GO:0051384~response to glucocorticoid", "10", "3.5E-3"], ["GO:0045124~regulation of bone resorption", "4", "7.3E-3"], ["GO:0001886~endothelial cell morphogenesis", "4", "1.3E-2"], ["CC", "GO:0005737~cytoplasm", "287", "2.4E-4"], ["GO:0005829~cytosol", "191", "4.7E-4"], ["GO:0016607~nuclear speck", "19", "5.4E-3"], ["GO:0043204~perikaryon", "12", "1.6E-2"], ["GO:0042383~sarcolemma", "10", "1.7E-2"], ["MF", "GO:0004842~ubiquitin-protein transferase activity", "26", "1.1E-2"], ["GO:0051213~dioxygenase activity", "5", "1.5E-2"], ["GO:0051920~peroxiredoxin activity", "3", "2.9E-2"], ["GO:0005179~hormone activity", "10", "3.0E-2"], ["GO:0005515~protein binding", "435", "3.1E-2"]], "row_count": 16, "column_count": 4, "numeric_cells": 46, "header_rows": 1, "locator": "section[11]/table-wrap[1]#pone.0255708.t001"}}, {"id": "asset:table:pmid:34529670:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cb3eadf74eaf34987268080f37a8666eece7fea0b404fe7ef4970df5f95ce38c", "bytes": 1268, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#pone.0255708.t002", "version": null, "note": "Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis of genes in black module.", "structure": {"pmcid": "PMC8445487", "section_index": 11, "section_title": "Functional enrichment analysis of genes in the black module", "row_count": 8, "column_count": 5}, "table": {"label": "Table 2", "caption": "Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis of genes in black module.", "rows": [["Pathway", "ID", "Gene count", "P-value", "Genes"], ["RNA degradation", "hsa03018", "10", "1.4E-2", "PAN2, EDC4, LSM6, CNOT7, DIS3, CNOT2, PABPC3, DCPS, PFKP, EDC3"], ["Neuroactive ligand-receptor interaction", "hsa04080", "21", "5.9E-2", "UTS2R, LHCGR, OXTR, CALCRL, NPY5R, PTGER1, CHRNA4, MLNR, SCTR, LPAR1, TACR2, GRIK2, HTR5A, SSTR4, HCRTR2, RXFP2, P2RY8, HRH1, HRH3, LPAR6, TSHB"], ["Sulfur metabolism", "hsa00920", "3", "7.0E-2", "MPST, ETHE1, SUOX"], ["Transcriptional misregulation in cancer", "hsa05202", "14", "7.2E-2", "NGFR, CSF1R, CDKN1B, ITGAM, FUS, IL1R2, JMJD1C, MLF1, FOXO1, PTK2, SPINT1, TLX1, ITGB7, MET"], ["Proteoglycans in cancer", "hsa05205", "16", "7.2E-2", "ARHGEF12, PDPK1, SRC, LUM, ANK3, HIF1A, PTK2, ACTB, VEGFA, SMO, CTSL, TIMP3, ITGAV, PPP1R12B, MET, WNT2"], ["Ubiquitin mediated proteolysis", "hsa04120", "12", "7.8E-2", "UBE2W, CUL5, UBA7, AIRE, FBXW11, UBE2D2, SYVN1, UBA2, ANAPC4, KEAP1, STUB1, SKP1"], ["Amino sugar and nucleotide sugar metabolism", "hsa00520", "6", "8.8E-2", "CYB5R2, NAGK, GFPT2, GMPPA, PGM3, HK2"]], "row_count": 8, "column_count": 5, "numeric_cells": 23, "header_rows": 1, "locator": "section[11]/table-wrap[2]#pone.0255708.t002"}}], "gaps": ["asset:data:geo:GSE133601 not downloaded", "asset:data:geo:GSE133601 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {"auc": "a good performance with AUC of 0"}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Weighted gene co-expression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Weighted co-expression network was constructed by WGCNA based on the GSE133601."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["GSE133601"], "resolved_accessions": ["GSE133601"], "statements": ["All relevant data are within the paper."], "basis": "The paper names GSE133601 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": [], "assets": ["source:pmid:34529670", "data:geo:GSE133601", "asset:table:pmid:34529670:1", "asset:table:pmid:34529670:2"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE133601"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:42Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 22099, "completion_tokens": 715, "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:34529670", "type": "paper", "label": "pmid:34529670"}, {"id": "source:pmid:34529670", "type": "manuscript", "label": "PMID 34529670 full text"}, {"id": "data:geo:GSE133601", "type": "dataset", "label": "GEO GSE133601"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34529670", "type": "paper", "label": "pmid:34529670"}, {"id": "source:pmid:34529670", "type": "manuscript", "label": "PMID 34529670 full text"}, {"id": "data:geo:GSE133601", "type": "dataset", "label": "GEO GSE133601"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34529670", "type": "extraction", "used": ["source:pmid:34529670"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE133601", "type": "accession_resolution", "used": ["data:geo:GSE133601"], "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:34529670", "parent_hash": "sha256:8e11035419b167fdaca5fe404687eb5d55a6ab5fde7edce5b645e2924e2e3fb1", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE133601 licence not read", "asset:data:geo:GSE133601 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["random forest"], "order_basis": "analysis_only", "id": "assay:1"}]}