H19- and hsa-miR-338-3p-mediated NRP1 expression is an independent predictor of poor prognosis in glioblastoma.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34843522", "kind": "science-record", "revision": 4, "content_hash": "sha256:3780b699b3c6600fc8fdf538ab5bea061220838f4f6fd901c36a8b038fe29279", "created_at": "2026-11-01T17:36:32Z", "updated_at": "2026-11-01T22:05:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "H19- and hsa-miR-338-3p-mediated NRP1 expression is an independent predictor of poor prognosis in glioblastoma.", "doi": "10.1371/journal.pone.0260103", "pmid": "34843522", "authors": ["Yong Liu", "Yuelin Liu", "Yong Gao", "Lei Wang", "Hengliang Shi", "Chengmin Xuan"], "journal": "PloS one", "year": 2021, "abstract": "Glioblastoma multiforme (GBM) is the most common and also the most invasive brain cancer. GBM progression is rapid and its prognosis is poor. Therefore, finding molecular targets in GBM is a critical goal that could also play important roles in clinical diagnostics and treatments to improve patient prognosis. We jointly analyzed the GSE103227, GSE103229, and TCGA databases for differentially expressed RNA species, obtaining 52 long non-coding RNAs (lncRNAs), 31 microRNAs (miRNAs), and 186 mRNAs, which were used to build a competing endogenous RNA network. Kaplan-Meier and receiver operating characteristic (ROC) analyses revealed five survival-related lncRNAs: H19, LINC01574, LINC01614, RNF144A-AS1, and OSMR-AS1. With multiple optimization mRNAs, we found the H19-hsa-miR-338-3P-NRP1 regulatory pathway. Additionally, we noted high NRP1 expression in GBM patients, and Kaplan-Meier and ROC analyses showed that NRP1 expression was associated with GBM prognosis. Cox analysis indicated that NRP1 is an independent prognostic factor in GBM patients. In conclusion, H19 and hsa-miR-338-3P regulate NRP1 expression, and this pathway plays an important role in GBM.", "claims": [{"id": "claim-method", "statement": "Univariate and multivariate Cox analyses were performed using R software, with P<0.05 considered statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34843522", "locator": "sections[6] \"Statistical analysis\" paragraph 2", "quote": "Univariate and multivariate Cox analyses were performed using R software, with P<0.05 considered statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34843522", "locator": "sections[14] \"Data Availability\" paragraph 2", "quote": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Cox analysis indicated that NRP1 is an independent prognostic factor in GBM patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:34843522", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Cox analysis indicated that NRP1 is an independent prognostic factor in GBM patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Cox analysis indicated that NRP1 is an independent prognostic factor in GBM patients.", "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:34843522"], "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:GSE103227"], "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:GSE103227"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34843522", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0260103", "sha256": "sha256:5195596ce71b22d6789016b12d869db8e7fde672236d430da1bfde4730e51903", "bytes": 24088, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0260103", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8629300", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE103227", "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=GSE103227", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103227", "version": null, "note": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2758524", "GSM2758525", "GSM2758526", "GSM2758527", "GSM2758528", "GSM2758529", "GSM2758530", "GSM2758531", "GSM2758532", "GSM2758533"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "16956", "taxon": "Homo sapiens", "title": "mRNA and lncRNA expression profiling in human brain glioblastoma", "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:GSE103229", "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=GSE103229", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103229", "version": null, "note": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2758524", "GSM2758525", "GSM2758526", "GSM2758527", "GSM2758528", "GSM2758529", "GSM2758530", "GSM2758531", "GSM2758532", "GSM2758533", "GSM2758534", "GSM2758535", "GSM2758536", "GSM2758537", "GSM2758538", "GSM2758539", "GSM2758540", "GSM2758541", "GSM2758542", "GSM2758543"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "18058;16956", "taxon": "Homo sapiens; Mus musculus; Rattus norvegicus", "title": "mRNA, lncRNA and microRNA expression profiling in human brain glioblastoma", "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:GSE16011", "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=GSE16011", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16011", "version": null, "note": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM405200", "GSM405201", "GSM405202", "GSM405203", "GSM405204", "GSM405205", "GSM405206", "GSM405207", "GSM405208", "GSM405209", "GSM405210", "GSM405211", "GSM405212", "GSM405213", "GSM405214", "GSM405215", "GSM405216", "GSM405217", "GSM405218", "GSM405219", "GSM405220", "GSM405221", "GSM405222", "GSM405223", "GSM405224", "GSM405225", "GSM405226", "GSM405227", "GSM405228", "GSM405229", "GSM405230", "GSM405231", "GSM405232", "GSM405233", "GSM405234", "GSM405235", "GSM405236", "GSM405237", "GSM405238", "GSM405239", "GSM405240", "GSM405241", "GSM405242", "GSM405243", "GSM405244", "GSM405245", "GSM405246", "GSM405247", "GSM405248", "GSM405249", "GSM405250", "GSM405251", "GSM405252", "GSM405253", "GSM405254", "GSM405255", "GSM405256", "GSM405257", "GSM405258", "GSM405259", "GSM405260", "GSM405261", "GSM405262", "GSM405263", "GSM405264", "GSM405265", "GSM405266", "GSM405267", "GSM405268", "GSM405269", "GSM405270", "GSM405271", "GSM405272", "GSM405273", "GSM405274", "GSM405275", "GSM405276", "GSM405277", "GSM405278", "GSM405279", "GSM405280", "GSM405281", "GSM405282", "GSM405283", "GSM405284", "GSM405285", "GSM405286", "GSM405287", "GSM405288", "GSM405289", "GSM405290", "GSM405291", "GSM405292", "GSM405293", "GSM405294", "GSM405295", "GSM405296", "GSM405297", "GSM405298", "GSM405299", "GSM405300", "GSM405301", "GSM405302", "GSM405303", "GSM405304", "GSM405305", "GSM405306", "GSM405307", "GSM405308", "GSM405309", "GSM405310", "GSM405311", "GSM405312", "GSM405313", "GSM405314", "GSM405315", "GSM405316", "GSM405317", "GSM405318", "GSM405319", "GSM405320", "GSM405321", "GSM405322", "GSM405323", "GSM405324", "GSM405325", "GSM405326", "GSM405327", "GSM405328", "GSM405329", "GSM405330", "GSM405331", "GSM405332", "GSM405333", "GSM405334", "GSM405335", "GSM405336", "GSM405337", "GSM405338", "GSM405339", "GSM405340", "GSM405341", "GSM405342", "GSM405343", "GSM405344", "GSM405345", "GSM405346", "GSM405347", "GSM405348", "GSM405349", "GSM405350", "GSM405351", "GSM405352", "GSM405353", "GSM405354", "GSM405355", "GSM405356", "GSM405357", "GSM405358", "GSM405359", "GSM405360", "GSM405361", "GSM405362", "GSM405363", "GSM405364", "GSM405365", "GSM405366", "GSM405367", "GSM405368", "GSM405369", "GSM405370", "GSM405371", "GSM405372", "GSM405373", "GSM405374", "GSM405375", "GSM405376", "GSM405377", "GSM405378", "GSM405379", "GSM405380", "GSM405381", "GSM405382", "GSM405383", "GSM405384", "GSM405385", "GSM405386", "GSM405387", "GSM405388", "GSM405389", "GSM405390", "GSM405391", "GSM405392", "GSM405393", "GSM405394", "GSM405395", "GSM405396", "GSM405397", "GSM405398", "GSM405399", "GSM405400", "GSM405401", "GSM405402", "GSM405403", "GSM405404", "GSM405405", "GSM405406", "GSM405407", "GSM405408", "GSM405409", "GSM405410", "GSM405411", "GSM405412", "GSM405413", "GSM405414", "GSM405415", "GSM405416", "GSM405417", "GSM405418", "GSM405419", "GSM405420", "GSM405421", "GSM405422", "GSM405423", "GSM405424", "GSM405425", "GSM405426", "GSM405427", "GSM405428", "GSM405429", "GSM405430", "GSM405431", "GSM405432", "GSM405433", "GSM405434", "GSM405435", "GSM405436", "GSM405437", "GSM405438", "GSM405439", "GSM405440", "GSM405441", "GSM405442", "GSM405443", "GSM405444", "GSM405445", "GSM405446", "GSM405447", "GSM405448", "GSM405449", "GSM405450", "GSM405451", "GSM405452", "GSM405453", "GSM405454", "GSM405455", "GSM405456", "GSM405457", "GSM405458", "GSM405459", "GSM405460", "GSM405461", "GSM405462", "GSM405463", "GSM405464", "GSM405465", "GSM405466", "GSM405467", "GSM405468", "GSM405469", "GSM405470", "GSM405471", "GSM405472", "GSM405473", "GSM405474", "GSM405475", "GSM405476", "GSM405477", "GSM405478", "GSM405479", "GSM405480", "GSM405481", "GSM405482", "GSM405483"], "sample_count": 284, "group_sizes": null, "group_sizes_basis": null, "platform": "8542", "taxon": "Homo sapiens", "title": "Intrinsic Gene Expression Profiles of Gliomas are a Better Predictor of Survival than Histology", "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:GSE103227 not downloaded", "asset:data:geo:GSE103227 licence not read", "asset:data:geo:GSE103229 not downloaded", "asset:data:geo:GSE103229 licence not read", "asset:data:geo:GSE16011 not downloaded", "asset:data:geo:GSE16011 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}, {"id": "method-3", "family": null, "specific": null, "label": "Univariate and multivariate Cox analyses", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Univariate and multivariate Cox analyses were performed using R software, with P<0.05 considered statistically significant."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE103227", "GSE103229", "GSE16011"], "resolved_accessions": ["GSE103227", "GSE103229", "GSE16011"], "statements": ["The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and supporting information."], "basis": "The paper names GSE103227, GSE103229, GSE16011 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": ["survival_km"], "assets": ["source:pmid:34843522", "data:geo:GSE103227"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE103227"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:09:23Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8741, "completion_tokens": 2083, "cached_tokens": 256}}, "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:34843522", "type": "paper", "label": "pmid:34843522"}, {"id": "source:pmid:34843522", "type": "manuscript", "label": "PMID 34843522 full text"}, {"id": "data:geo:GSE103227", "type": "dataset", "label": "GEO GSE103227"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34843522", "type": "paper", "label": "pmid:34843522"}, {"id": "source:pmid:34843522", "type": "manuscript", "label": "PMID 34843522 full text"}, {"id": "data:geo:GSE103227", "type": "dataset", "label": "GEO GSE103227"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34843522", "type": "extraction", "used": ["source:pmid:34843522"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE103227", "type": "accession_resolution", "used": ["data:geo:GSE103227"], "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:34843522", "parent_hash": "sha256:3ea91dbe5e79c7e71f9a6fbd410c3e72760e35f3fc9c584d2d970aeba0921597", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE103227 licence not read", "asset:data:geo:GSE103227 not downloaded", "asset:data:geo:GSE103229 licence not read", "asset:data:geo:GSE103229 not downloaded", "asset:data:geo:GSE16011 licence not read", "asset:data:geo:GSE16011 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "analysis_only", "id": "assay:1"}]}