Unfolded protein response pathways in stroke patients: a comprehensive landscape assessed through machine learning algorithms and experimental verification.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37891634", "kind": "science-record", "revision": 4, "content_hash": "sha256:c5bc0879ba1d94cd9cd9f441a94ec1efc3b12ac7eea563be95bced7e1119d2f1", "created_at": "2026-11-01T19:02:45Z", "updated_at": "2026-11-01T22:52:57Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Unfolded protein response pathways in stroke patients: a comprehensive landscape assessed through machine learning algorithms and experimental verification.", "doi": "10.1186/s12967-023-04567-9", "pmid": "37891634", "authors": ["Haiyang Yu", "Xiaoyu Ji", "Yang Ouyang"], "journal": "Journal of translational medicine", "year": 2023, "abstract": "BACKGROUND: The unfolding protein response is a critical biological process implicated in a variety of physiological functions and disease states across eukaryotes. Despite its significance, the role and underlying mechanisms of the response in the context of ischemic stroke remain elusive. Hence, this study endeavors to shed light on the mechanisms and role of the unfolding protein response in the context of ischemic stroke.\nMETHODS: In this study, mRNA expression patterns were extracted from the GSE58294 and GSE16561 datasets in the GEO database. The screening and validation of protein response-related biomarkers in stroke patients, as well as the analysis of the immune effects of the pathway, were carried out. To identify the key genes in the unfolded protein response, we constructed diagnostic models using both random forest and support vector machine-recursive feature elimination methods. The internal validation was performed using a bootstrapping approach based on a random sample of 1,000 iterations. Lastly, the target gene was validated by RT-PCR using clinical samples. We utilized two algorithms, CIBERSORT and MCPcounter, to investigate the relationship between the model genes and immune cells. Additionally, we performed uniform clustering of ischemic stroke samples based on expression of genes related to the UPR pathway and analyzed the relationship between different clusters and clinical traits. The weighted gene co-expression network analysis was conducted to identify the core genes in various clusters, followed by enrichment analysis and protein profiling for the hub genes from different clusters.\nRESULTS: Our differential analysis revealed 44 genes related to the UPR pathway to be statistically significant. The integration of both machine learning algorithms resulted in the identification of 7 key genes, namely ATF6, EXOSC5, EEF2, LSM4, NOLC1, BANF1, and DNAJC3. These genes served as the foundation for a diagnostic model, with an area under the curve of 0.972. Following 1000 rounds of internal validation via randomized sampling, the model was confirmed to exhibit high levels of both specificity and sensitivity. Furthermore, the expression of these genes was found to be linked with the infiltration of immune cells such as neutrophils and CD8 T cells. The cluster analysis of ischemic stroke samples revealed three distinct groups, each with differential expression of most genes related to the UPR pathway, immune cell infiltration, and inflammatory factor secretion. The weighted gene co-expression network analysis showed that all three clusters were associated with the unfolded protein response, as evidenced by gene enrichment analysis and the protein landscape of each cluster. The results showed that the expression of the target gene in blood was consistent with the previous analysis.\nCONCLUSION: The study of the relationship between UPR and ischemic stroke can help to better understand the underlying mechanisms of the disease and provide new targets for therapeutic intervention. For example, targeting the UPR pathway by blocking excessive autophagy or inducing moderate UPR could potentially reduce tissue injury and promote cell survival after ischemic stroke. In addition, the results of this study suggest that the use of UPR gene expression levels as biomarkers could improve the accuracy of early diagnosis and prognosis of ischemic stroke, leading to more personalized treatment strategies. Overall, this study highlights the importance of the UPR pathway in the pathology of ischemic stroke and provides a foundation for future studies in this field.", "claims": [{"id": "claim-method", "statement": "To identify the key genes in the unfolded protein response, we constructed diagnostic models using both random forest and support vector machine-recursive feature elimination methods.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37891634", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "To identify the key genes in the unfolded protein response, we constructed diagnostic models using both random forest and support vector machine-recursive feature elimination methods."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the fndings of this study are included within the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37891634", "locator": "sections[26] \"notes\" paragraph 1", "quote": "The data used to support the fndings of this study are included within the article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The seven-gene diagnostic model achieved an area under the curve of 0.972.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37891634", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "These genes served as the foundation for a diagnostic model, with an area under the curve of 0.972."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The seven-gene diagnostic model achieved an area under the curve of 0.972.", "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:37891634"], "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:GSE16561"], "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": {}, "inputs": ["data:geo:GSE16561"], "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:37891634", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-023-04567-9", "sha256": "sha256:afa02e0621f52b3c0eece46fa5d658378719512b539fe80d265e0901ae6b4db2", "bytes": 36469, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-023-04567-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10605787", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE16561", "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=GSE16561", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16561", "version": null, "note": "The data used to support the fndings of this study are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the fndings of this study are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM416528", "GSM416529", "GSM416530", "GSM416531", "GSM416532", "GSM416533", "GSM416534", "GSM416535", "GSM416536", "GSM416537", "GSM416538", "GSM416539", "GSM416540", "GSM416541", "GSM416542", "GSM416543", "GSM416544", "GSM416545", "GSM416546", "GSM416547", "GSM416548", "GSM416549", "GSM416550", "GSM416551", "GSM416552", "GSM416553", "GSM416554", "GSM416555", "GSM416556", "GSM416557", "GSM416558", "GSM416559", "GSM416560", "GSM416561", "GSM416562", "GSM416563", "GSM416564", "GSM416565", "GSM416566", "GSM416567", "GSM416568", "GSM416569", "GSM416570", "GSM416571", "GSM416572", "GSM416573", "GSM416574", "GSM416575", "GSM416576", "GSM416577", "GSM416578", "GSM416579", "GSM416580", "GSM416581", "GSM416582", "GSM416583", "GSM416584", "GSM416585", "GSM416586", "GSM416587", "GSM416588", "GSM416589", "GSM416590"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "6883", "taxon": "Homo sapiens", "title": "Gene expression analysis of peripheral whole blood RNA following ischemic stroke", "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:GSE58294", "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=GSE58294", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58294", "version": null, "note": "The data used to support the fndings of this study are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the fndings of this study are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1406033", "GSM1406034", "GSM1406035", "GSM1406036", "GSM1406037", "GSM1406038", "GSM1406039", "GSM1406040", "GSM1406041", "GSM1406042", "GSM1406043", "GSM1406044", "GSM1406045", "GSM1406046", "GSM1406047", "GSM1406048", "GSM1406049", "GSM1406050", "GSM1406051", "GSM1406052", "GSM1406053", "GSM1406054", "GSM1406055", "GSM1406056", "GSM1406057", "GSM1406058", "GSM1406059", "GSM1406060", "GSM1406061", "GSM1406062", "GSM1406063", "GSM1406064", "GSM1406065", "GSM1406066", "GSM1406067", "GSM1406068", "GSM1406069", "GSM1406070", "GSM1406071", "GSM1406072", "GSM1406073", "GSM1406074", "GSM1406075", "GSM1406076", "GSM1406077", "GSM1406078", "GSM1406079", "GSM1406080", "GSM1406081", "GSM1406082", "GSM1406083", "GSM1406084", "GSM1406085", "GSM1406086", "GSM1406087", "GSM1406088", "GSM1406089", "GSM1406090", "GSM1406091", "GSM1406092", "GSM1406093", "GSM1406094", "GSM1406095", "GSM1406096", "GSM1406097", "GSM1406098", "GSM1406099", "GSM1406100", "GSM1406101", "GSM1406102", "GSM1406103", "GSM1406104", "GSM1406105", "GSM1406106", "GSM1406107", "GSM1406108", "GSM1406109", "GSM1406110", "GSM1406111", "GSM1406112", "GSM1406113", "GSM1406114", "GSM1406115", "GSM1406116", "GSM1406117", "GSM1406118", "GSM1406119", "GSM1406120", "GSM1406121", "GSM1406122", "GSM1406123", "GSM1406124"], "sample_count": 92, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene Expression Following Cardioembolic Stroke", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE16561 not downloaded", "asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE58294 not downloaded", "asset:data:geo:GSE58294 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": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify the key genes in the unfolded protein response, we constructed diagnostic models using both random forest and support vector machine-recursive feature elimination methods."}}, {"id": "method-2", "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"}}, {"id": "method-3", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "logistic regression"}}], "targets": [], "gaps": ["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": ["GSE58294", "GSE16561"], "resolved_accessions": ["GSE58294", "GSE16561"], "statements": ["The data used to support the fndings of this study are included within the article."], "basis": "The paper names GSE58294, GSE16561 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:37891634", "data:geo:GSE16561"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE16561"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:57:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9619, "completion_tokens": 1145, "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:37891634", "type": "paper", "label": "pmid:37891634"}, {"id": "source:pmid:37891634", "type": "manuscript", "label": "PMID 37891634 full text"}, {"id": "data:geo:GSE16561", "type": "dataset", "label": "GEO GSE16561"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37891634", "type": "paper", "label": "pmid:37891634"}, {"id": "source:pmid:37891634", "type": "manuscript", "label": "PMID 37891634 full text"}, {"id": "data:geo:GSE16561", "type": "dataset", "label": "GEO GSE16561"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37891634", "type": "extraction", "used": ["source:pmid:37891634"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE16561", "type": "accession_resolution", "used": ["data:geo:GSE16561"], "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:37891634", "parent_hash": "sha256:54bda5f75b39b4464db2244fdc41c2e3325937cf12fe3c66909d2756448ba6cf", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE16561 licence not read", "asset:data:geo:GSE16561 not downloaded", "asset:data:geo:GSE58294 licence not read", "asset:data:geo:GSE58294 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "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": 1.0, "evidence": ["To identify the key genes in the unfolded protein response, we constructed diagnostic models using both random forest and support vector machine-recursive feature elimination methods."], "order_basis": "analysis_only", "id": "assay:1"}]}