Computational screening of potential glioma-related genes and drugs based on analysis of GEO dataset and text mining.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33635875", "kind": "science-record", "revision": 5, "content_hash": "sha256:b974755d4539c6623035c653341d3b0a4d47e7e3b0f3d5ae3dff644337c792b1", "created_at": "2026-11-01T15:41:26Z", "updated_at": "2026-11-01T21:24:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Computational screening of potential glioma-related genes and drugs based on analysis of GEO dataset and text mining.", "doi": "10.1371/journal.pone.0247612", "pmid": "33635875", "authors": ["Zhengye Jiang", "Yanxi Shi", "Guowei Tan", "Zhanxiang Wang"], "journal": "PloS one", "year": 2021, "abstract": "BACKGROUND: Considering the high invasiveness and mortality of glioma as well as the unclear key genes and signaling pathways involved in the development of gliomas, there is a strong need to find potential gene biomarkers and available drugs.\nMETHODS: Eight glioma samples and twelve control samples were analyzed on the GSE31095 datasets, and differentially expressed genes (DEGs) were obtained via the R software. The related glioma genes were further acquired from the text mining. Additionally, Venny program was used to screen out the common genes of the two gene sets and DAVID analysis was used to conduct the corresponding gene ontology analysis and cell signal pathway enrichment. We also constructed the protein interaction network of common genes through STRING, and selected the important modules for further drug-gene analysis. The existing antitumor drugs that targeted these module genes were screened to explore their efficacy in glioma treatment.\nRESULTS: The gene set obtained from text mining was intersected with the previously obtained DEGs, and 128 common genes were obtained. Through the functional enrichment analysis of the identified 128 DEGs, a hub gene module containing 25 genes was obtained. Combined with the functional terms in GSE109857 dataset, some overlap of the enriched function terms are both in GSE31095 and GSE109857. Finally, 4 antitumor drugs were identified through drug-gene interaction analysis.\nCONCLUSIONS: In this study, we identified that two potential genes and their corresponding four antitumor agents could be used as targets and drugs for glioma exploration.", "claims": [{"id": "claim-data-access", "statement": "We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33635875", "locator": "sections[3] \"Data collection\" paragraph 2", "quote": "We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:33635875"], "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:GSE109857"], "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:GSE109857"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33635875", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0247612", "sha256": "sha256:e05789480b252e1e7d0c3b2e09f564686054110270e38314a9b0a255d5fcd907", "bytes": 20728, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0247612", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7909668", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE109857", "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=GSE109857", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE109857", "version": null, "note": "We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2971329", "GSM2971330", "GSM2971331", "GSM2971332", "GSM2971333", "GSM2971334", "GSM2971335", "GSM2971336", "GSM2971337", "GSM2971338", "GSM2971339", "GSM2971340", "GSM2971341", "GSM2971342", "GSM2971343", "GSM2971344", "GSM2971345", "GSM2971346", "GSM2971347", "GSM2971348", "GSM2971349", "GSM2971350", "GSM2971351", "GSM2971352", "GSM2971353", "GSM2971354", "GSM2971355", "GSM2971356", "GSM2971357", "GSM2971358", "GSM2971359", "GSM2971360", "GSM2971361", "GSM2971362", "GSM2971363", "GSM2971364", "GSM2971365", "GSM2971366", "GSM2971367", "GSM2971368", "GSM2971369", "GSM2971370", "GSM2971371", "GSM2971372", "GSM2971373", "GSM2971374", "GSM2971375", "GSM2971376", "GSM2971377", "GSM2971378", "GSM2971379", "GSM2971380", "GSM2971381", "GSM2971382", "GSM2971383", "GSM2971384", "GSM2971385", "GSM2971386", "GSM2971387", "GSM2971388", "GSM2971389", "GSM2971390", "GSM2971391", "GSM2971392", "GSM2971393", "GSM2971394", "GSM2971395", "GSM2971396", "GSM2971397", "GSM2971398", "GSM2971399", "GSM2971400", "GSM2971401", "GSM2971402", "GSM2971403", "GSM2971404", "GSM2971405", "GSM2971406", "GSM2971407", "GSM2971408", "GSM2971409", "GSM2971410", "GSM2971411", "GSM2971412", "GSM2971413", "GSM2971414", "GSM2971415", "GSM2971416", "GSM2971417", "GSM2971418", "GSM2971419", "GSM2971420", "GSM2971421", "GSM2971422", "GSM2971423", "GSM2971424", "GSM2971425", "GSM2971426", "GSM2971427", "GSM2971428", "GSM2971429", "GSM2971430", "GSM2971431", "GSM2971432", "GSM2971433", "GSM2971434", "GSM2971435", "GSM2971436", "GSM2971437", "GSM2971438", "GSM2971439", "GSM2971440", "GSM2971441", "GSM2971442", "GSM2971443", "GSM2971444", "GSM2971445", "GSM2971446", "GSM2971447", "GSM2971448", "GSM2971449", "GSM2971450", "GSM2971451", "GSM2971452", "GSM2971453", "GSM2971454", "GSM2971455", "GSM2971456", "GSM2971457", "GSM2971458", "GSM2971459", "GSM2971460", "GSM2971461", "GSM2971462", "GSM2971463", "GSM2971464", "GSM2971465", "GSM2971466", "GSM2971467", "GSM2971468", "GSM2971469", "GSM2971470", "GSM2971471", "GSM2971472", "GSM2971473", "GSM2971474", "GSM2971475", "GSM2971476", "GSM2971477", "GSM2971478", "GSM2971479", "GSM2971480", "GSM2971481", "GSM2971482", "GSM2971483", "GSM2971484", "GSM2971485", "GSM2971486", "GSM2971487", "GSM2971488", "GSM2971489", "GSM2971490", "GSM2971491", "GSM2971492", "GSM2971493", "GSM2971494", "GSM2971495", "GSM2971496", "GSM2971497", "GSM2971498", "GSM2971499", "GSM2971500", "GSM2971501", "GSM2971502", "GSM2971503", "GSM2971504", "GSM2971505", "GSM2971506", "GSM2971507", "GSM2971508", "GSM2971509", "GSM2971510", "GSM2971511", "GSM2971512", "GSM2971513", "GSM2971514", "GSM2971515", "GSM2971516", "GSM2971517", "GSM2971518", "GSM2971519", "GSM2971520", "GSM2971521", "GSM2971522", "GSM2971523", "GSM2971524", "GSM2971525", "GSM2971526", "GSM2971527", "GSM2971528", "GSM2971529", "GSM2971530", "GSM2971531", "GSM2971532", "GSM2971533", "GSM2971534", "GSM2971535", "GSM2971536", "GSM2971537", "GSM2971538", "GSM2971539", "GSM2971540", "GSM2971541", "GSM2971542", "GSM2971543", "GSM2971544", "GSM2971545", "GSM2971546", "GSM2971547", "GSM2971548", "GSM2971549", "GSM2971550", "GSM2971551", "GSM2971552", "GSM2971553"], "sample_count": 225, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "A model of molecular characteristics to classify WHO Grade III glioma patients", "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:GSE31095", "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=GSE31095", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31095", "version": null, "note": "We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM769920", "GSM769921", "GSM769922", "GSM769923", "GSM769924", "GSM769925", "GSM769926", "GSM769927", "GSM769928", "GSM769929", "GSM769930", "GSM769931", "GSM769932", "GSM769933", "GSM769934", "GSM769935", "GSM769936", "GSM769937", "GSM769938", "GSM769939"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Gene expression signature in platelets from healty vs. glioma patients", "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:33635875:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9289e73564a24feddee9e8e59dcb719b452d5c0c1f49157c4868a0d7e8c4133a", "bytes": 227, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#pone.0247612.t001", "version": null, "note": "Overlap of the enriched function terms between the two datasets.", "structure": {"pmcid": "PMC7909668", "section_index": 13, "section_title": "Validation in GSE109857 dataset", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Overlap of the enriched function terms between the two datasets.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[13]/table-wrap[1]#pone.0247612.t001"}}], "gaps": ["asset:data:geo:GSE109857 not downloaded", "asset:data:geo:GSE109857 licence not read", "asset:data:geo:GSE31095 not downloaded", "asset:data:geo:GSE31095 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["GSE31095", "GSE109857"], "resolved_accessions": ["GSE31095", "GSE109857"], "statements": ["We abstracted the gene expression chip data GSE31095 [13] and GSE109857 from the NCBI Gene Expression Comprehensive (GEO) web resource (https://www.ncbi.nlm.nih.gov/geo/) [6,14]. The GSE31095 cohort contains eight glioma samples and twelve normal control samples, while the GSE109857 dataset includes five glioma samples and five normal control samples."], "basis": "The paper names GSE31095, GSE109857 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pathway_enrich"], "assets": ["source:pmid:33635875", "data:geo:GSE109857", "asset:table:pmid:33635875:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE109857"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:30Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 3, "usage": {"prompt_tokens": 14946, "completion_tokens": 1515, "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:33635875", "type": "paper", "label": "pmid:33635875"}, {"id": "source:pmid:33635875", "type": "manuscript", "label": "PMID 33635875 full text"}, {"id": "data:geo:GSE109857", "type": "dataset", "label": "GEO GSE109857"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33635875", "type": "paper", "label": "pmid:33635875"}, {"id": "source:pmid:33635875", "type": "manuscript", "label": "PMID 33635875 full text"}, {"id": "data:geo:GSE109857", "type": "dataset", "label": "GEO GSE109857"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33635875", "type": "extraction", "used": ["source:pmid:33635875"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE109857", "type": "accession_resolution", "used": ["data:geo:GSE109857"], "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:33635875", "parent_hash": "sha256:303eaf715fee98a901778ac7cd4b3cd6623d8e3f9a7d167aae38e343f98478cd", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE109857 licence not read", "asset:data:geo:GSE109857 not downloaded", "asset:data:geo:GSE31095 licence not read", "asset:data:geo:GSE31095 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["pathway enrichment"], "order_basis": "analysis_only", "id": "assay:1"}]}