{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31423235", "kind": "science-record", "revision": 6, "content_hash": "sha256:b5ea34a8c8e7970a17ae76e512eb2ffd97d6579d9d8cdb45493b3071f129beea", "created_at": "2026-11-01T15:40:48Z", "updated_at": "2026-11-01T22:00:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "DNA methylation profiling identifies potentially significant epigenetically-regulated genes in glioblastoma multiforme.", "doi": "10.3892/ol.2019.10512", "pmid": "31423235", "authors": ["Shifeng Kan", "Song Chai", "Wenhua Chen", "Bo Yu"], "journal": "Oncology letters", "year": 2019, "abstract": "Glioblastoma multiforme (GBM) is one of the most lethal and damaging types of human cancer. The current study was conducted to identify differentially methylated genes (DMGs) between GBM and normal controls, and to improve our understanding of GBM at the epigenetic level. The DNA methylation profile of GBM was downloaded from the Gene Expression Omnibus (GEO) database using the accession number GSE50923. The MethyAnalysis package was applied to identify DMGs between GBM and controls, which were then analyzed by functional enrichment analysis. Protein-protein interaction (PPI) networks were constructed using the hypermethylated and hypomethylated genes. Finally, transcription factors (TFs) that can regulate the hypermethylated and hypomethylated genes were predicted, followed by construction of transcriptional regulatory networks. Furthermore, another relevant dataset, GSE22867, was downloaded from the GEO database for data validation. A total of 476 hypermethylated and 850 hypomethylated genes were identified, which were mainly associated with the functions of 'G-protein-coupled receptors ligand binding', 'cytokine activity', 'cytokine-cytokine receptor interaction', and 'D-glutamine and D-glutamate metabolism'. The hypermethylated gene neuropeptide Y (NPY) and the hypomethylated gene tumor necrosis factor (TNF) demonstrated high degrees in the PPI network. Forkhead box protein A1 (FOXA1), potassium voltage-gated channel subfamily C member 3 (KCNC3) and caspase-8 (CASP8) exhibited high degrees in the transcriptional regulatory networks. In addition, the methylation profiles of NPY, TNF, FOXA1, KCNC3 and CASP8 were confirmed by another dataset. In summary, the present study systematically analyzed the DNA methylation profile of GBM using bioinformatics approaches and identified several abnormally methylated genes, providing insight into the molecular mechanism underlying GBM.", "claims": [{"id": "claim-method", "statement": "The methyAnalysis package version 1.8.0 (20) was applied to identify DMRs between GBM and controls.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31423235", "locator": "sections[5] \"Identification of differentially methylated regions (DMRs)\" paragraph 2", "quote": "The methyAnalysis package version 1.8.0 (20) was applied to identify DMRs between GBM and controls."}], "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:31423235"], "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:GSE22867"], "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:GSE22867"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31423235", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ol.2019.10512", "sha256": "sha256:33e3d415e1cffed7a1919c8254112386680d376010ce758d13decac7b67a8dbc", "bytes": 30654, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ol.2019.10512", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6614665", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE22867", "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=GSE22867", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22867", "version": null, "note": "“DNA methylation data from the GBM study by Lai et al (17) were retrieved from the National Center for Biotechnology Information Gene Expression Omnibus (GEO) database (http://www.ncbi.nlm.nih.gov/projects/geo/) with the accession number GSE50923.” “The DNA methylation profiles of 54 GBM samples and 24 control brain samples were previously investigated using Illumina HumanMethylation27 BeadChip.” “Only data from 31 GBM and 24 control brain samples were present in the GEO database, therefore, only these data were analyzed in the current study.”", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "“DNA methylation data from the GBM study by Lai et al (17) were retrieved from the National Center for Biotechnology Information Gene Expression Omnibus (GEO) database (http://www.ncbi.nlm.nih.gov/projects/geo/) with the accession number GSE50923.” “The DNA methylation profiles of 54 GBM samples and 24 control brain samples were previously investigated using Illumina HumanMethylation27 BeadChip.” “Only data from 31 GBM and 24 control brain samples were present in the GEO database, therefore, only these data were analyzed in the current study.”", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM565024", "GSM565025", "GSM565026", "GSM565027", "GSM565028", "GSM565029", "GSM565030", "GSM565031", "GSM565032", "GSM565033", "GSM565034", "GSM565035", "GSM565036", "GSM565037", "GSM565038", "GSM565039", "GSM565040", "GSM565041", "GSM565042", "GSM565043", "GSM565044", "GSM565045", "GSM565046", "GSM565047", "GSM565048", "GSM565049", "GSM565050", "GSM565051", "GSM565052", "GSM565053", "GSM565054", "GSM565055", "GSM565056", "GSM565057", "GSM565058", "GSM565059", "GSM565060", "GSM565061", "GSM565062", "GSM565063", "GSM565064", "GSM565065", "GSM565066", "GSM565067", "GSM565068", "GSM565069", "GSM565070", "GSM565071", "GSM565072", "GSM565073", "GSM565074", "GSM565075", "GSM565076", "GSM565077", "GSM565078", "GSM565079", "GSM565080", "GSM565081", "GSM565082", "GSM565083"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "DNA Methylation Profiling of Glioblastoma: Impact on Gene Expression and Clinical Outcome (Illumina)", "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:GSE50923", "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=GSE50923", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50923", "version": null, "note": "“DNA methylation data from the GBM study by Lai et al (17) were retrieved from the National Center for Biotechnology Information Gene Expression Omnibus (GEO) database (http://www.ncbi.nlm.nih.gov/projects/geo/) with the accession number GSE50923.” “The DNA methylation profiles of 54 GBM samples and 24 control brain samples were previously investigated using Illumina HumanMethylation27 BeadChip.” “Only data from 31 GBM and 24 control brain samples were present in the GEO database, therefore, only these data were analyzed in the current study.”", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "“DNA methylation data from the GBM study by Lai et al (17) were retrieved from the National Center for Biotechnology Information Gene Expression Omnibus (GEO) database (http://www.ncbi.nlm.nih.gov/projects/geo/) with the accession number GSE50923.” “The DNA methylation profiles of 54 GBM samples and 24 control brain samples were previously investigated using Illumina HumanMethylation27 BeadChip.” “Only data from 31 GBM and 24 control brain samples were present in the GEO database, therefore, only these data were analyzed in the current study.”", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1232478", "GSM1232479", "GSM1232480", "GSM1232481", "GSM1232482", "GSM1232483", "GSM1232484", "GSM1232485", "GSM1232486", "GSM1232487", "GSM1232488", "GSM1232489", "GSM1232490", "GSM1232491", "GSM1232492", "GSM1232493", "GSM1232494", "GSM1232495", "GSM1232496", "GSM1232497", "GSM1232498", "GSM1232499", "GSM1232500", "GSM1232501", "GSM1232502", "GSM1232503", "GSM1232504", "GSM1232505", "GSM1232506", "GSM1232507", "GSM1232508", "GSM1232509", "GSM1232510", "GSM1232511", "GSM1232512", "GSM1232513", "GSM1232514", "GSM1232515", "GSM1232516", "GSM1232517", "GSM1232518", "GSM1232519", "GSM1232520", "GSM1232521", "GSM1232522", "GSM1232523", "GSM1232524", "GSM1232525", "GSM1232526", "GSM1232527", "GSM1232528", "GSM1232529", "GSM1232530", "GSM1232531", "GSM1232532", "GSM1232533", "GSM1232534", "GSM1232535", "GSM1232536", "GSM1232537", "GSM1232538", "GSM1232539", "GSM1232540", "GSM1232541", "GSM1232542", "GSM1232543", "GSM1232544", "GSM1232545", "GSM1232546", "GSM1232547", "GSM1232548", "GSM1232549", "GSM1232550", "GSM1232551", "GSM1232552", "GSM1232553", "GSM1232554", "GSM1232555"], "sample_count": 78, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "Genome-wide methylation analyses in glioblastoma multiforme (GBM)", "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:31423235:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b1d280a08ee4c1a81855022609612fff5f1d9cdac2718a9ffa934c7619d776a9", "bytes": 924, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#tI-ol-0-0-10512", "version": null, "note": "Top five KEGG pathways enriched by hypermethylated genes and hypomethylated genes.", "structure": {"pmcid": "PMC6614665", "section_index": 6, "section_title": "Functional enrichment analysis", "row_count": 17, "column_count": 3}, "table": {"label": "Table I.", "caption": "Top five KEGG pathways enriched by hypermethylated genes and hypomethylated genes.", "rows": [["A, Hypermethylated genes"], [""], ["KEGG ID", "KEGG pathway", "P-value"], ["4080", "Neuroactive ligand-receptor interaction", "1.18×10−3"], ["471", "D-Glutamine and D-glutamate metabolism", "3.62×10−3"], ["4114", "Oocyte meiosis", "6.76×10−3"], ["250", "Alanine, aspartate and glutamate metabolism", "7.87×10−3"], ["4971", "Gastric acid secretion", "1.02×10−2"], [""], ["B, Hypomethylated genes"], [""], ["KEGG ID", "KEGG pathway", "P-value"], [""], ["4060", "Cytokine-cytokine receptor interaction", "1.22×10−10"], ["4640", "Hematopoietic cell lineage", "1.49×10−5"], ["5150", "Staphylococcus aureus infection", "1.35×10−4"], ["4610", "Complement and coagulation cascades", "2.72×10−4"]], "row_count": 17, "column_count": 3, "numeric_cells": 18, "header_rows": 3, "locator": "section[14]/table-wrap[1]#tI-ol-0-0-10512"}}, {"id": "asset:table:pmid:31423235:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:47adc0f10810e8b5bbb8bb7d4862cad06740712c9900361ce005451491eb26e7", "bytes": 2334, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#tII-ol-0-0-10512", "version": null, "note": "Top five GO terms enriched by hypermethylated genes and hypomethylated genes.", "structure": {"pmcid": "PMC6614665", "section_index": 6, "section_title": "Functional enrichment analysis", "row_count": 44, "column_count": 3}, "table": {"label": "Table II.", "caption": "Top five GO terms enriched by hypermethylated genes and hypomethylated genes.", "rows": [["A, Hypermethylated genes"], [""], ["GO ID", "GO term", "P-value"], ["Biological process", "", ""], ["GO:0048856", "Anatomical structure development", "3.19×10−8"], ["GO:0032502", "Developmental process", "4.06×10−8"], ["GO:0044707", "Single-multicellular organism process", "4.85×10−8"], ["GO:0032501", "Multicellular organismal process", "8.26×10−8"], ["GO:0007275", "Multicellular organismal development", "3.47×10−7"], ["Molecular function", "", ""], ["GO:0003700", "Sequence-specific DNA binding transcription factor activity", "5.04×10−9"], ["GO:0001071", "Nucleic acid binding transcription factor activity", "5.51×10−9"], ["GO:0043565", "Sequence-specific DNA binding", "1.76×10−8"], ["GO:0044212", "Transcription regulatory region DNA binding", "6.04×10−7"], ["GO:0000975", "Regulatory region DNA binding", "9.99×10−7"], ["Cellular component", "", ""], ["GO:0044459", "Plasma membrane part", "2.37×10−1"], ["GO:0019897", "Extrinsic to plasma membrane", "2.61×10−1"], ["GO:0008076", "Voltage-gated potassium channel complex", "4.53×10−1"], ["GO:0034705", "Potassium channel complex", "4.53×10−1"], ["GO:0019898", "Extrinsic to membrane", "5.85×10−1"], [""], ["B, Hypomethylated genes"], [""], ["GO ID", "GO term", "P-value"], [""], ["Biological process", "", ""], ["GO:0006952", "Defense response", "8.19×10−12"], ["GO:0006954", "Inflammatory response", "9.55×10−12"], ["GO:0050896", "Response to stimulus", "6.68×10−11"], ["GO:0002376", "Immune system process", "8.73×10−11"], ["GO:0009611", "Response to wounding", "6.82×10−10"], ["Molecular function", "", ""], ["GO:0005125", "Cytokine activity", "3.13×10−7"], ["GO:0005126", "Cytokine receptor binding", "1.30×10−5"], ["GO:0004872", "Receptor activity", "6.25×10−5"], ["GO:0005102", "Receptor binding", "1.39×10−3"], ["GO:0005506", "Iron ion binding", "8.86×10−3"], ["Cellular component", "", ""], ["GO:0005576", "Extracellular region", "<1.00×10−3"], ["GO:0005615", "Extracellular space", "<1.00×10−3"], ["GO:0044421", "Extracellular region part", "<1.00×10−3"], ["GO:0071944", "Cell periphery", "3.84×10−9"], ["GO:0005886", "Plasma membrane", "5.56×10−9"]], "row_count": 44, "column_count": 3, "numeric_cells": 60, "header_rows": 3, "locator": "section[14]/table-wrap[2]#tII-ol-0-0-10512"}}, {"id": "asset:table:pmid:31423235:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aba9bd55e29fb86eea188a80ec7da3fa7098a7169a30063634d717828ef8d825", "bytes": 920, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[3]#tIII-ol-0-0-10512", "version": null, "note": "Top five Reactome pathways enriched by hypermethylated genes and hypomethylated genes.", "structure": {"pmcid": "PMC6614665", "section_index": 6, "section_title": "Functional enrichment analysis", "row_count": 17, "column_count": 3}, "table": {"label": "Table III.", "caption": "Top five Reactome pathways enriched by hypermethylated genes and hypomethylated genes.", "rows": [["A, Hypermethylated genes"], [""], ["Reactome ID", "Name", "P-value"], ["500792", "GPCR ligand binding", "8.88×10−2"], ["112316", "Neuronal system", "1.61×10−1"], ["373076", "Class A/1 (Rhodopsin-like receptors)", "3.55×10−1"], ["418597", "G α (z) signaling events", "4.98×10−1"], ["1296072", "Voltage-gated potassium channels", "9.92×10−1"], [""], ["B, Hypomethylated genes"], [""], ["Reactome ID", "Name", "P-value"], [""], ["500792", "GPCR ligand binding", "5.94×10−4"], ["211897", "Cytochrome P450-arranged by substrate type", "1.05×10−3"], ["373076", "Class A/1 (Rhodopsin-like receptors)", "5.68×10−3"], ["211945", "Phase 1-Functionalization of compounds", "6.96×10−3"]], "row_count": 17, "column_count": 3, "numeric_cells": 22, "header_rows": 3, "locator": "section[14]/table-wrap[3]#tIII-ol-0-0-10512"}}, {"id": "asset:table:pmid:31423235:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b1d280a08ee4c1a81855022609612fff5f1d9cdac2718a9ffa934c7619d776a9", "bytes": 924, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#tI-ol-0-0-10512", "version": null, "note": "Top five KEGG pathways enriched by hypermethylated genes and hypomethylated genes.", "structure": {"pmcid": "PMC6614665", "section_index": 14, "section_title": "Functional enrichment analysis", "row_count": 17, "column_count": 3}, "table": {"label": "Table I.", "caption": "Top five KEGG pathways enriched by hypermethylated genes and hypomethylated genes.", "rows": [["A, Hypermethylated genes"], [""], ["KEGG ID", "KEGG pathway", "P-value"], ["4080", "Neuroactive ligand-receptor interaction", "1.18×10−3"], ["471", "D-Glutamine and D-glutamate metabolism", "3.62×10−3"], ["4114", "Oocyte meiosis", "6.76×10−3"], ["250", "Alanine, aspartate and glutamate metabolism", "7.87×10−3"], ["4971", "Gastric acid secretion", "1.02×10−2"], [""], ["B, Hypomethylated genes"], [""], ["KEGG ID", "KEGG pathway", "P-value"], [""], ["4060", "Cytokine-cytokine receptor interaction", "1.22×10−10"], ["4640", "Hematopoietic cell lineage", "1.49×10−5"], ["5150", "Staphylococcus aureus infection", "1.35×10−4"], ["4610", "Complement and coagulation cascades", "2.72×10−4"]], "row_count": 17, "column_count": 3, "numeric_cells": 18, "header_rows": 3, "locator": "section[14]/table-wrap[1]#tI-ol-0-0-10512"}}, {"id": "asset:table:pmid:31423235:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:47adc0f10810e8b5bbb8bb7d4862cad06740712c9900361ce005451491eb26e7", "bytes": 2334, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#tII-ol-0-0-10512", "version": null, "note": "Top five GO terms enriched by hypermethylated genes and hypomethylated genes.", "structure": {"pmcid": "PMC6614665", "section_index": 14, "section_title": "Functional enrichment analysis", "row_count": 44, "column_count": 3}, "table": {"label": "Table II.", "caption": "Top five GO terms enriched by hypermethylated genes and hypomethylated genes.", "rows": [["A, Hypermethylated genes"], [""], ["GO ID", "GO term", "P-value"], ["Biological process", "", ""], ["GO:0048856", "Anatomical structure development", "3.19×10−8"], ["GO:0032502", "Developmental process", "4.06×10−8"], ["GO:0044707", "Single-multicellular organism process", "4.85×10−8"], ["GO:0032501", "Multicellular organismal process", "8.26×10−8"], ["GO:0007275", "Multicellular organismal development", "3.47×10−7"], ["Molecular function", "", ""], ["GO:0003700", "Sequence-specific DNA binding transcription factor activity", "5.04×10−9"], ["GO:0001071", "Nucleic acid binding transcription factor activity", "5.51×10−9"], ["GO:0043565", "Sequence-specific DNA binding", "1.76×10−8"], ["GO:0044212", "Transcription regulatory region DNA binding", "6.04×10−7"], ["GO:0000975", "Regulatory region DNA binding", "9.99×10−7"], ["Cellular component", "", ""], ["GO:0044459", "Plasma membrane part", "2.37×10−1"], ["GO:0019897", "Extrinsic to plasma membrane", "2.61×10−1"], ["GO:0008076", "Voltage-gated potassium channel complex", "4.53×10−1"], ["GO:0034705", "Potassium channel complex", "4.53×10−1"], ["GO:0019898", "Extrinsic to membrane", "5.85×10−1"], [""], ["B, Hypomethylated genes"], [""], ["GO ID", "GO term", "P-value"], [""], ["Biological process", "", ""], ["GO:0006952", "Defense response", "8.19×10−12"], ["GO:0006954", "Inflammatory response", "9.55×10−12"], ["GO:0050896", "Response to stimulus", "6.68×10−11"], ["GO:0002376", "Immune system process", "8.73×10−11"], ["GO:0009611", "Response to wounding", "6.82×10−10"], ["Molecular function", "", ""], ["GO:0005125", "Cytokine activity", "3.13×10−7"], ["GO:0005126", "Cytokine receptor binding", "1.30×10−5"], ["GO:0004872", "Receptor activity", "6.25×10−5"], ["GO:0005102", "Receptor binding", "1.39×10−3"], ["GO:0005506", "Iron ion binding", "8.86×10−3"], ["Cellular component", "", ""], ["GO:0005576", "Extracellular region", "<1.00×10−3"], ["GO:0005615", "Extracellular space", "<1.00×10−3"], ["GO:0044421", "Extracellular region part", "<1.00×10−3"], ["GO:0071944", "Cell periphery", "3.84×10−9"], ["GO:0005886", "Plasma membrane", "5.56×10−9"]], "row_count": 44, "column_count": 3, "numeric_cells": 60, "header_rows": 3, "locator": "section[14]/table-wrap[2]#tII-ol-0-0-10512"}}, {"id": "asset:table:pmid:31423235:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aba9bd55e29fb86eea188a80ec7da3fa7098a7169a30063634d717828ef8d825", "bytes": 920, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[3]#tIII-ol-0-0-10512", "version": null, "note": "Top five Reactome pathways enriched by hypermethylated genes and hypomethylated genes.", "structure": {"pmcid": "PMC6614665", "section_index": 14, "section_title": "Functional enrichment analysis", "row_count": 17, "column_count": 3}, "table": {"label": "Table III.", "caption": "Top five Reactome pathways enriched by hypermethylated genes and hypomethylated genes.", "rows": [["A, Hypermethylated genes"], [""], ["Reactome ID", "Name", "P-value"], ["500792", "GPCR ligand binding", "8.88×10−2"], ["112316", "Neuronal system", "1.61×10−1"], ["373076", "Class A/1 (Rhodopsin-like receptors)", "3.55×10−1"], ["418597", "G α (z) signaling events", "4.98×10−1"], ["1296072", "Voltage-gated potassium channels", "9.92×10−1"], [""], ["B, Hypomethylated genes"], [""], ["Reactome ID", "Name", "P-value"], [""], ["500792", "GPCR ligand binding", "5.94×10−4"], ["211897", "Cytochrome P450-arranged by substrate type", "1.05×10−3"], ["373076", "Class A/1 (Rhodopsin-like receptors)", "5.68×10−3"], ["211945", "Phase 1-Functionalization of compounds", "6.96×10−3"]], "row_count": 17, "column_count": 3, "numeric_cells": 22, "header_rows": 3, "locator": "section[14]/table-wrap[3]#tIII-ol-0-0-10512"}}, {"id": "asset:table:pmid:31423235:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4d55fc178f0eeffa6760c40824e20565ebd038241682f0e9f9c578a086d51507", "bytes": 655, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#tIV-ol-0-0-10512", "version": null, "note": "Top 10 hypermethylated and hypomethylated genes with high node degree in the transcriptional regulatory networks.", "structure": {"pmcid": "PMC6614665", "section_index": 17, "section_title": "Prediction of TFs that target the DMGs and construction of transcriptional regulatory networks", "row_count": 23, "column_count": 2}, "table": {"label": "Table IV.", "caption": "Top 10 hypermethylated and hypomethylated genes with high node degree in the transcriptional regulatory networks.", "rows": [["Gene", "Node degree"], ["Hypermethylated", ""], ["FOXA1", "35"], ["APRT", "17"], ["KCNC3", "15"], ["LSR", "15"], ["SNAI1", "13"], ["NUP98", "13"], ["PDE4D", "12"], ["RPL31", "12"], ["RPL31", "12"], ["CREM", "12"], ["Hypomethylated", ""], ["KIAA0101", "14"], ["CASP8", "12"], ["TMA16", "12"], ["FAM107B", "11"], ["LINC00263", "11"], ["RXRB", "11"], ["PHLDA1", "10"], ["DEGS1", "10"], ["KAZALD1", "10"], ["C1RL-AS1", "9"]], "row_count": 23, "column_count": 2, "numeric_cells": 27, "header_rows": 1, "locator": "section[17]/table-wrap[1]#tIV-ol-0-0-10512"}}], "gaps": ["asset:data:geo:GSE22867 not downloaded", "asset:data:geo:GSE22867 licence not read", "asset:data:geo:GSE50923 not downloaded", "asset:data:geo:GSE50923 licence not read"]}, "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": null, "specific": null, "label": "methyAnalysis package version 1.8.0", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The methyAnalysis package version 1.8.0 (20) was applied to identify DMRs between GBM and controls."}}], "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": ["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": "R1", "reachable": true, "accessions": ["GSE50923", "GSE22867"], "resolved_accessions": ["GSE50923", "GSE22867"], "statements": ["“DNA methylation data from the GBM study by Lai et al (17) were retrieved from the National Center for Biotechnology Information Gene Expression Omnibus (GEO) database (http://www.ncbi.nlm.nih.gov/projects/geo/) with the accession number GSE50923.” “The DNA methylation profiles of 54 GBM samples and 24 control brain samples were previously investigated using Illumina HumanMethylation27 BeadChip.” “Only data from 31 GBM and 24 control brain samples were present in the GEO database, therefore, only these data were analyzed in the current study.”"], "basis": "The paper names GSE50923, GSE22867 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:31423235", "data:geo:GSE22867", "asset:table:pmid:31423235:1", "asset:table:pmid:31423235:2", "asset:table:pmid:31423235:3", "asset:table:pmid:31423235:4", "asset:table:pmid:31423235:5", "asset:table:pmid:31423235:6", "asset:table:pmid:31423235:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE22867"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:48:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 24982, "completion_tokens": 1777, "cached_tokens": 785}}, "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:31423235", "type": "paper", "label": "pmid:31423235"}, {"id": "source:pmid:31423235", "type": "manuscript", "label": "PMID 31423235 full text"}, {"id": "data:geo:GSE22867", "type": "dataset", "label": "GEO GSE22867"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31423235", "type": "paper", "label": "pmid:31423235"}, {"id": "source:pmid:31423235", "type": "manuscript", "label": "PMID 31423235 full text"}, {"id": "data:geo:GSE22867", "type": "dataset", "label": "GEO GSE22867"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31423235", "type": "extraction", "used": ["source:pmid:31423235"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE22867", "type": "accession_resolution", "used": ["data:geo:GSE22867"], "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:31423235", "parent_hash": "sha256:daf09d9f93df8aac7bf27619e74fd16227c5b947097f9a75a3a34bf030ac6a1e", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE22867 licence not read", "asset:data:geo:GSE22867 not downloaded", "asset:data:geo:GSE50923 licence not read", "asset:data:geo:GSE50923 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["ted channel subfamily C member 3 (KCNC3) and caspase-8 (CASP8) exhibited high degrees in the tran"], "order_basis": "paper_text_order:1553", "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"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:43:37+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}