Prediction and analysis of hub genes between glioblastoma and low-grade glioma using bioinformatics analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33545929", "kind": "science-record", "revision": 7, "content_hash": "sha256:587b593b7d792b0c70a31357896d15ae48e02decfbc1ffba3e4d27015a41925c", "created_at": "2026-11-01T15:41:24Z", "updated_at": "2026-11-01T22:03:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prediction and analysis of hub genes between glioblastoma and low-grade glioma using bioinformatics analysis.", "doi": "10.1097/MD.0000000000023513", "pmid": "33545929", "authors": ["Baowei Xu"], "journal": "Medicine", "year": 2021, "abstract": "ABSTRACT: Gliomas are an intractable tumor in the central nervous system. The present study aimed to identify the differentially expressed genes (DEGs) between glioblastoma multiforme (GBM) and low-grade gliomas (LGG) in order to investigate the mechanisms of different grades of gliomas. The Cancer Genome Atlas (TCGA) database was used to identify DEGs between GBM and LGG, and 2641 genes have been found differentially expressed. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were used to determine the related functions and pathways of DEGs. Protein-protein interaction (PPI) network extracted a total of 444 nodes and 1953 interactions, and identified the top 6 hub genes in gliomas. The microarray data of the datasets GSE52009 and GSE4412, which were obtained from Gene Expression Omnibus (GEO) database, were used to externally validate DEGs expression levels. Gene Expression Profiling Interactive Analysis (GEPIA) database which was based on TCGA was used to explore the survival of hub genes in LGG and GBM. Additionally, the Oncomine database and Chinese Glioma Genome Atlas (CGGA) database were used to validate the mRNA expression level and prognostic value of hub genes. Gene Set Enrichment Analysis (GSEA) identified further hub genes-related pathways. In summary, through biological information and survival analysis, 6 hub genes may be new biomarkers for diagnosis and for guiding the choice of treatment strategies for different grades of gliomas.", "claims": [{"id": "claim-method", "statement": "To clarify the DEGs between LGG and GBM, the fold change (FC) >2 (|log2FC| ≥1) and false discovery rate (FDR) < 0.05 were used as the threshold to identify DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33545929", "locator": "sections[3] \"Datasets and identification of DEGs\" paragraph 2", "quote": "To clarify the DEGs between LGG and GBM, the fold change (FC) >2 (|log2FC| ≥1) and false discovery rate (FDR) < 0.05 were used as the threshold to identify DEGs."}], "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:33545929", "locator": "sections[22] \"Footnotes\" paragraph 2", "quote": "The datasets generated during and/or analyzed during the current study are publicly available."}], "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:33545929"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33545929", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000023513", "sha256": "sha256:3c4b72126c5b66361634fc7ee0e7bdd951471bbf5062ff45252f08078bd0c05f", "bytes": 35620, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000023513", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7837950", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33545929:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:72f66c4bc17873db254805080449bedb44f82a003e40005c95840a46cee06cbb", "bytes": 3699, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "Gene Ontology functional enrichment analyses of DEGs associated with LGG and GBM.", "structure": {"pmcid": "PMC7837950", "section_index": 12, "section_title": "Functional and pathway enrichment analysis of DEGs", "row_count": 49, "column_count": 6}, "table": {"label": "Table 1", "caption": "Gene Ontology functional enrichment analyses of DEGs associated with LGG and GBM.", "rows": [["Category", "Description", "Count", "%", "P value"], ["Total DEGs"], ["BP", "GO:0099177", "Regulation of trans-synaptic signaling", "147", "6.11", "4.98E-26"], ["BP", "GO:0050804", "Modulation of chemical synaptic transmission", "146", "6.07", "6.77E-26"], ["BP", "GO:0050808", "Synapse organization", "134", "5.57", "8.23E-23"], ["BP", "GO:0042391", "Regulation of membrane potential", "132", "5.48", "2.76E-19"], ["BP", "GO:0043062", "Extracellular structure organization", "131", "5.44", "6.19E-20"], ["CC", "GO:0097060", "Synaptic membrane", "163", "6.46", "1.50E-37"], ["CC", "GO:0062023", "Collagen-containing extracellular matrix", "143", "5.67", "2.25E-29"], ["CC", "GO:0043025", "Neuronal cell body", "140", "5.55", "1.53E-18"], ["CC", "GO:0045211", "Postsynaptic membrane", "125", "4.95", "6.90E-30"], ["CC", "GO:0098978", "Glutamatergic synapse", "123", "4.88", "3.15E-25"], ["MF", "GO:0015267", "Channel activity", "131", "5.49", "9.84E-16"], ["MF", "GO:0022803", "Passive transmembrane transporter activity", "131", "5.49", "1.00E-15"], ["MF", "GO:0022838", "Substrate-specific channel activity", "126", "5.28", "9.84E-16"], ["MF", "GO:0005216", "Ion channel activity", "123", "5.15", "9.84E-16"], ["MF", "GO:0046873", "Metal ion transmembrane transporter activity", "116", "4.86", "2.48E-11"], ["Up regulated DEGs"], ["BP", "GO:0043062", "Extracellular structure organization", "111", "8.38", "1.23E-31"], ["BP", "GO:0030198", "Extracellular matrix organization", "106", "8.01", "1.25E-33"], ["BP", "GO:0042119", "Neutrophil activation", "101", "7.63", "3.85E-19"], ["BP", "GO:0002446", "Neutrophil mediated immunity", "100", "7.55", "1.19E-18"], ["BP", "GO:0043312", "Neutrophil degranulation", "98", "7.40", "1.33E-18"], ["CC", "GO:0062023", "Collagen-containing extracellular matrix", "121", "8.75", "6.04E-42"], ["CC", "GO:0005788", "Endoplasmic reticulum lumen", "78", "5.64", "1.86E-21"], ["CC", "GO:0031983", "Vesicle lumen", "74", "5.35", "1.63E-16"], ["CC", "GO:0060205", "Cytoplasmic vesicle lumen", "73", "5.28", "3.16E-16"], ["CC", "GO:0034774", "Secretory granule lumen", "71", "5.13", "2.94E-16"], ["MF", "GO:0005201", "Extracellular matrix structural constituent", "61", "4.64", "8.74E-25"], ["MF", "GO:0030246", "Carbohydrate binding", "46", "3.50", "1.09E-05"], ["MF", "GO:0005539", "Glycosaminoglycan binding", "45", "3.42", "3.37E-07"], ["MF", "GO:0061134", "Peptidase regulator activity", "43", "3.27", "6.38E-07"], ["MF", "GO:0019838", "Growth factor binding", "40", "3.04", "6.69E-12"], ["Down regulated DEGs"], ["BP", "GO:0050804", "Modulation of chemical synaptic transmission", "126", "11.62", "9.72E-51"], ["BP", "GO:0099177", "Regulation of trans-synaptic signaling", "126", "11.62", "9.72E-51"], ["BP", "GO:0042391", "Regulation of membrane potential", "111", "10.24", "7.42E-39"], ["BP", "GO:0050808", "Synapse organization", "105", "9.69", "5.55E-37"], ["BP", "GO:0050890", "Cognition", "78", "7.20", "7.79E-28"], ["CC", "GO:0097060", "Synaptic membrane", "147", "12.88", "1.69E-71"], ["CC", "GO:0098793", "Presynapse", "126", "11.04", "5.85E-46"], ["CC", "GO:0045211", "Postsynaptic membrane", "115", "10.08", "6.77E-58"], ["CC", "GO:0098978", "Glutamatergic synapse", "110", "9.64", "2.65E-49"], ["CC", "GO:0099572", "Postsynaptic specialization", "107", "9.38", "7.56E-47"], ["MF", "GO:0015267", "Channel activity", "108", "10.06", "1.05E-33"], ["MF", "GO:0022803", "Passive transmembrane transporter activity", "108", "10.06", "1.08E-33"], ["MF", "GO:0022838", "Substrate-specific channel activity", "106", "9.88", "1.09E-34"], ["MF", "GO:0005216", "Ion channel activity", "105", "9.79", "5.81E-35"], ["MF", "GO:0046873", "Metal ion transmembrane transporter activity", "98", "9.13", "1.81E-28"]], "row_count": 49, "column_count": 6, "numeric_cells": 180, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33545929:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1a034585359b904f8f69e77c0aa3b8f01b53349c98e2c3e4623b08145d6480b0", "bytes": 2191, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T2", "version": null, "note": "Top 10 most KEGG of total, up regulated and down regulated DEGs.", "structure": {"pmcid": "PMC7837950", "section_index": 12, "section_title": "Functional and pathway enrichment analysis of DEGs", "row_count": 34, "column_count": 5}, "table": {"label": "Table 2", "caption": "Top 10 most KEGG of total, up regulated and down regulated DEGs.", "rows": [["Description", "", "Count", "%", "P value"], ["Total DEGs"], ["hsa04080", "Neuroactive ligand-receptor interaction", "86", "7.51", "8.47E-07"], ["hsa04010", "MAPK signaling pathway", "68", "5.94", "0.000258"], ["hsa05205", "Proteoglycans in cancer", "59", "5.15", "8.47E-07"], ["hsa04510", "Focal adhesion", "58", "5.07", "8.47E-07"], ["hsa04360", "Axon guidance", "51", "4.45", "1.64E-05"], ["hsa04145", "Phagosome", "50", "4.37", "1.85E-07"], ["hsa04020", "Calcium signaling pathway", "50", "4.37", ".000157"], ["hsa04514", "Cell adhesion molecules (CAMs)", "47", "4.10", "8.47E-07"], ["hsa04724", "Glutamatergic synapse", "44", "3.84", "1.49E-08"], ["hsa05322", "Systemic lupus erythematosus", "44", "3.84", "8.47E-07"], ["Up regulated DEGs"], ["hsa05165", "Human papillomavirus infection", "32", "8.24", "3.63E-11"], ["hsa04060", "Cytokine-cytokine receptor interaction", "30", "7.06", "7.45E-09"], ["hsa04145", "Phagosome", "28", "6.62", "7.45E-09"], ["hsa04510", "Focal adhesion", "45", "6.62", "2.81E-08"], ["hsa05205", "Proteoglycans in cancer", "22", "6.47", "5.05E-08"], ["hsa05166", "Human T-cell leukemia virus 1 infection", "29", "6.47", "5.05E-08"], ["hsa05169", "Epstein-Barr virus infection", "33", "6.32", "5.11E-08"], ["hsa05322", "Systemic lupus erythematosus", "25", "5.88", "5.24E-08"], ["hsa05152", "Tuberculosis", "44", "5.88", "1.16E-07"], ["hsa04110", "Cell cycle", "43", "4.85", "2.06E-07"], ["Down regulated DEGs"], ["hsa04080", "Neuroactive ligand-receptor interaction", "33", "13.55", "9.99E-17"], ["hsa04020", "Calcium signaling pathway", "41", "8.82", "5.36E-12"], ["hsa04724", "Glutamatergic synapse", "26", "8.60", "2.97E-11"], ["hsa04024", "cAMP signaling pathway", "24", "8.60", "1.33E-10"], ["hsa04723", "Retrograde endocannabinoid signaling", "40", "7.96", "7.85E-10"], ["hsa04727", "GABAergic synapse", "30", "7.31", "1.25E-09"], ["hsa05032", "Morphine addiction", "31", "7.10", "5.96E-09"], ["hsa04713", "Circadian entrainment", "20", "7.10", "1.09E-08"], ["hsa04261", "Adrenergic signaling in cardiomyocytes", "30", "6.67", "4.99E-08"], ["hsa04360", "Axon guidance", "18", "6.67", "6.05E-08"]], "row_count": 34, "column_count": 5, "numeric_cells": 121, "header_rows": 1, "locator": "section[12]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:33545929:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:907e31ec2db259ffdcd0a4100c14127b3c4f6750e1b79a9c0e678389f5594fab", "bytes": 1190, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T3", "version": null, "note": "Hub genes for DEGs ranked in cytoHubba using different methods.", "structure": {"pmcid": "PMC7837950", "section_index": 13, "section_title": "Hub genes screening from PPI network", "row_count": 12, "column_count": 11}, "table": {"label": "Table 3", "caption": "Hub genes for DEGs ranked in cytoHubba using different methods.", "rows": [["", "Rank methods in cytoHubba"], ["Catalog", "MCC", "MNC", "Degree", "EPC", "BottleNeck", "EcCentricity", "Closeness", "Radiality", "Betweenness", "Stress"], ["Hub gene top 10", "CXCL8", "FN1", "FN1", "FN1", "CXCL8", "CXCL8", "CXCL8", "CXCL8", "CXCL8", "CXCL8"], ["", "GABBR1", "CXCL8", "CXCL8", "MMP9", "FN1", "FN1", "FN1", "FN1", "FN1", "FN1"], ["", "HTR1A", "MMP9", "MMP9", "CXCL8", "MMP9", "MMP9", "MMP9", "MMP9", "MMP9", "MMP9"], ["", "ANXA1", "TIMP1", "TIMP1", "COL1A2", "GRM5", "GRM5", "TIMP1", "TIMP1", "GRM5", "GRM5"], ["", "SAA1", "COL1A1", "GRIN1", "TIMP1", "POSTN", "POSTN", "COL1A1", "GRM5", "GRIN1", "GRIN1"], ["", "BDKRB2", "COL1A2", "COL1A1", "COL1A1", "TIMP1", "TIMP1", "GRM5", "ANXA1", "LOX", "GABBR1"], ["", "HRH3", "GRIN1", "COL1A2", "POSTN", "KCNJ9", "MDM2", "LOX", "CXCL10", "KCNJ9", "KCNJ9"], ["", "CXCL10", "POSTN", "POSTN", "COL3A1", "MDM2", "NTRK1", "POSTN", "LOX", "TIMP1", "LOX"], ["", "GAL", "SERPINE1", "LOX", "LOX", "LOX", "GRIN1", "SERPINE1", "SERPINE1", "MDM2", "HTR1A"], ["", "SSTR2", "SPP1", "SERPINE1", "THBS1", "NTRK1", "SNAI2", "SPP1", "SPP1", "SDC1", "HRH3"]], "row_count": 12, "column_count": 11, "numeric_cells": 3, "header_rows": 2, "locator": "section[13]/table-wrap[1]#T3"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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"}}, {"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": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "False discovery rate (FDR) control", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To clarify the DEGs between LGG and GBM, the fold change (FC) >2 (|log2FC| ≥1) and false discovery rate (FDR) < 0.05 were used as the threshold to identify DEGs."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The datasets generated during and/or analyzed during the current study are publicly available."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33545929", "asset:table:pmid:33545929:1", "asset:table:pmid:33545929:2", "asset:table:pmid:33545929:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:24:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28605, "completion_tokens": 3783, "cached_tokens": 18688}}, "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:33545929", "type": "paper", "label": "pmid:33545929"}, {"id": "source:pmid:33545929", "type": "manuscript", "label": "PMID 33545929 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33545929", "type": "paper", "label": "pmid:33545929"}, {"id": "source:pmid:33545929", "type": "manuscript", "label": "PMID 33545929 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33545929", "type": "extraction", "used": ["source:pmid:33545929"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33545929", "parent_hash": "sha256:90432e396649b96705c2cd34008e92fb469f38daf667357193c5daac91eb2e5a", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["entified the top 6 hub genes in gliomas. The microarray data of the datasets GSE52009 and GSE4412, w"], "order_basis": "paper_text_order:791", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}