{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30497506", "kind": "science-record", "revision": 8, "content_hash": "sha256:2067b13bcb56035ef2d6b884b3bacecbcf33a20ae45c3e1d0e0996e685d129ae", "created_at": "2026-11-01T15:40:39Z", "updated_at": "2026-11-01T22:43:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Genomics of neonatal sepsis: has-miR-150 targeting BCL11B functions in disease progression.", "doi": "10.1186/s13052-018-0575-9", "pmid": "30497506", "authors": ["Li Huang", "Lixing Qiao", "Huan Zhu", "Li Jiang", "Liping Yin"], "journal": "Italian journal of pediatrics", "year": 2018, "abstract": "BACKGROUND: Neonatal sepsis is an inflammatory systemic syndrome, which is a major cause of morbidity and mortality in premature infants. We analyzed the expression profile data of E-MTAB-4785 to reveal the pathogenesis of the disease.\nMETHODS: The expression profile dataset E-MTAB-4785, which contained 17 sepsis samples and 19 normal samples, was obtained from the ArrayExpress database. The differentially expressed genes (DEGs) were analyzed by the Bayesian testing method in limma package. Based on the DAVID online tool, enrichment analysis was conducted for the DEGs. Using STRING database and Cytoscape software, protein-protein interaction (PPI) network and module analyses were performed. Besides, transcription factor (TF)-DEG regulatory network was also constructed by Cytoscape software. Additionally, miRNA-DEG pairs were searched using miR2Disease and miRWalk 2.0 databases, followed by miRNA-DEG regulatory network was visualized by Cytoscape software.\nRESULTS: A total of 275 DEGs were identified from the sepsis samples in comparison to normal samples. TSPO, MAPK14, and ZAP70 were the hub nodes in the PPI network. Pathway enrichment analysis indicated that CEBPB and MAPK14 were enriched in TNF signaling pathway. Moreover, CEBPB and has-miR-150 might function in neonatal sepsis separately through targeting MAPK14 and BCL11B in the regulatory networks. These genes and miRNA might be novel targets for the clinical treatment of neonatal sepsis.\nCONCLUSION: TSPO, ZAP70, CEBPB targeting MAPK14, has-miR-150 targeting BCL11B might affect the pathogenesis of neonatal sepsis. However, their roles in neonatal sepsis still needed to be confirmed by further experimental researches.", "claims": [{"id": "claim-method", "statement": "The Bayesian testing method [16] in limma package (http://www.bioconductor.org/packages/release/bioc/html/limma.html) [17] was utilized to identify the DEGs between the two group samples. The p-values were conducted with multiple testing adjustment based on the Benjamini & Hochberg method [18].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30497506", "locator": "sections[4] \"Data preprocessing and differentially expressed genes (DEGs) screening\" paragraph 2", "quote": "The Bayesian testing method [16] in limma package (http://www.bioconductor.org/packages/release/bioc/html/limma.html) [17] was utilized to identify the DEGs between the two group samples. The p-values were conducted with multiple testing adjustment based on the Benjamini & Hochberg method [18]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30497506", "locator": "sections[16] \"ack\" paragraph 1", "quote": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request."}], "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:30497506"], "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:E-MTAB-4785"], "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:E-MTAB-4785"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30497506", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13052-018-0575-9", "sha256": "sha256:db41859ff200b8adfc1cd8df6065ea767daf257d0b2036e181965772f55f861c", "bytes": 21808, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13052-018-0575-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6267077", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-4785", "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=E-MTAB-4785", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-4785", "version": null, "note": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:00Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30497506:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2fd4f389b961dab49c8cc08b7afc3e8c175f3dd83935190e888cfa5b14ae9883", "bytes": 1469, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "The functions and pathways enriched for the up-regulated genes", "structure": {"pmcid": "PMC6267077", "section_index": 5, "section_title": "Functional and pathway enrichment analysis", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "The functions and pathways enriched for the up-regulated genes", "rows": [["Category", "Description", "P-value", "Gene number"], ["BP", "GO:0071222~cellular response to lipopolysaccharide", "3.05E-06", "10"], ["GO:0051384~response to glucocorticoid", "1.75E-05", "8"], ["GO:0006955~immune response", "6.59E-05", "14"], ["GO:0045766~positive regulation of angiogenesis", "1.31E-04", "8"], ["GO:0045087~innate immune response", "3.22E-04", "22"], ["CC", "GO:0070062~extracellular exosome", "3.26E-06", "51"], ["GO:0005615~extracellular space", "3.15E-05", "29"], ["GO:0005886~plasma membrane", "1.58E-04", "59"], ["GO:0016020~membrane", "2.03E-03", "32"], ["GO:0031093~platelet alpha granule lumen", "1.08E-02", "4"], ["MF", "GO:0035035~histone acetyltransferase binding", "2.54E-03", "4"], ["GO:0001077~transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding", "9.14E-03", "8"], ["GO:0002020~protease binding", "1.40E-02", "5"], ["GO:0016787~hydrolase activity", "1.56E-02", "5"], ["GO:0019899~enzyme binding", "1.88E-02", "9"], ["Pathway", "hsa04668:TNF signaling pathway", "3.65E-06", "10"], ["hsa05150:Staphylococcus aureus infection", "3.23E-04", "6"], ["hsa05142:Chagas disease (American trypanosomiasis)", "7.74E-03", "6"], ["hsa04380:Osteoclast differentiation", "1.90E-02", "6"], ["hsa04910:Insulin signaling pathway", "2.39E-02", "6"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30497506:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:88f3cdf8c86dfdbb8a6385a2d1cdd62a1db21d885d5efa9131e487cb0b8c4625", "bytes": 1498, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#Tab2", "version": null, "note": "The functions and pathways enriched for the down-regulated genes", "structure": {"pmcid": "PMC6267077", "section_index": 5, "section_title": "Functional and pathway enrichment analysis", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "The functions and pathways enriched for the down-regulated genes", "rows": [["Category", "Description", "P-value", "Gene number"], ["BP", "GO:0050776~regulation of immune response", "4.11E-15", "15"], ["GO:0007166~cell surface receptor signaling pathway", "2.56E-06", "11"], ["GO:0050852~T cell receptor signaling pathway", "8.71E-05", "7"], ["GO:0072678~T cell migration", "3.56E-04", "3"], ["GO:0045059~positive thymic T cell selection", "8.47E-04", "3"], ["CC", "GO:0042101~T cell receptor complex", "1.22E-10", "7"], ["GO:0005886~plasma membrane", "1.40E-04", "35"], ["GO:0042105~alpha-beta T cell receptor complex", "2.26E-04", "3"], ["GO:0001772~immunological synapse", "5.25E-04", "4"], ["GO:0009897~external side of plasma membrane", "4.83E-03", "6"], ["MF", "GO:0004888~transmembrane signaling receptor activity", "4.20E-06", "9"], ["GO:1990405~protein antigen binding", "4.46E-04", "3"], ["GO:0030246~carbohydrate binding", "1.62E-03", "6"], ["GO:0023024~MHC class I protein complex binding", "1.40E-02", "2"], ["GO:0032393~MHC class I receptor activity", "2.31E-02", "2"], ["Pathway", "hsa04660:T cell receptor signaling pathway", "4.90E-07", "8"], ["hsa04672:Intestinal immune network for IgA production", "7.58E-05", "5"], ["hsa05340:Primary immunodeficiency", "5.41E-04", "4"], ["hsa04514:Cell adhesion molecules (CAMs)", "5.95E-04", "6"], ["hsa04650:Natural killer cell mediated cytotoxicity", "2.80E-03", "5"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[10]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:30497506:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:669902c361b376eeebf736799d64009cdd9fbe0cd570f4a72a9710c2385d0459", "bytes": 1042, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab3", "version": null, "note": "The top 15 nodes in the protein-protein interaction (PPI) network", "structure": {"pmcid": "PMC6267077", "section_index": 6, "section_title": "PPI network and module analyses", "row_count": 16, "column_count": 6}, "table": {"label": "Table 3", "caption": "The top 15 nodes in the protein-protein interaction (PPI) network", "rows": [["Node", "DC", "Node", "BC", "Node", "CC"], ["TSPO", "42", "TSPO", "8787.401", "TSPO", "0.084416"], ["MAPK14", "30", "MAPK14", "3945.718", "MAPK14", "0.082755"], ["ZAP70", "18", "ZAP70", "2945.19", "ZAP70", "0.081621"], ["ICAM1", "18", "PLEK", "1416.809", "ICAM1", "0.081481"], ["MMP9", "16", "CD40LG", "1228.869", "CD40LG", "0.081066"], ["GATA3", "13", "GATA3", "1149.809", "NFATC2", "0.080882"], ["PPARG", "13", "PPP3CC", "1065.391", "THBS1", "0.080609"], ["NFKBIA", "12", "SLC2A3", "878.1572", "MMP9", "0.080609"], ["HIF1A", "12", "PDE7A", "786", "NFKBIA", "0.080473"], ["CD40LG", "11", "LDHA", "778.0661", "GATA3", "0.080292"], ["THBS1", "11", "NFKBIA", "706.2174", "HIF1A", "0.080292"], ["CEBPB", "11", "GNA15", "660.3287", "CEBPB", "0.080247"], ["SOCS3", "10", "HIF1A", "614.6019", "PPARG", "0.080157"], ["IRF1", "10", "CD3E", "583.8388", "SOCS3", "0.080157"], ["PLEK", "9", "CD82", "550.5645", "PLEK", "0.079844"]], "row_count": 16, "column_count": 6, "numeric_cells": 56, "header_rows": 1, "locator": "section[11]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:30497506:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ce227b24fe4d0d260638f42fc6a8927e3c71d640ec0930858cf27b4906091e36", "bytes": 526, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#Tab4", "version": null, "note": "The pathways enriched for the genes involved in module 1", "structure": {"pmcid": "PMC6267077", "section_index": 6, "section_title": "PPI network and module analyses", "row_count": 7, "column_count": 3}, "table": {"label": "Table 4", "caption": "The pathways enriched for the genes involved in module 1", "rows": [["Description", "Gene number", "P-value"], ["hsa04668:TNF signaling pathway", "3", "4.59E-03"], ["hsa05200:Pathways in cancer", "4", "5.42E-03"], ["hsa04380:Osteoclast differentiation", "3", "6.97E-03"], ["hsa05160:Hepatitis C", "3", "7.18E-03"], ["hsa05205:Proteoglycans in cancer", "3", "1.57E-02"], ["hsa05144:Malaria", "2", "4.87E-02"]], "row_count": 7, "column_count": 3, "numeric_cells": 18, "header_rows": 1, "locator": "section[11]/table-wrap[2]#Tab4"}}, {"id": "asset:table:pmid:30497506:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2fd4f389b961dab49c8cc08b7afc3e8c175f3dd83935190e888cfa5b14ae9883", "bytes": 1469, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "The functions and pathways enriched for the up-regulated genes", "structure": {"pmcid": "PMC6267077", "section_index": 10, "section_title": "Functional and pathway enrichment analysis", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "The functions and pathways enriched for the up-regulated genes", "rows": [["Category", "Description", "P-value", "Gene number"], ["BP", "GO:0071222~cellular response to lipopolysaccharide", "3.05E-06", "10"], ["GO:0051384~response to glucocorticoid", "1.75E-05", "8"], ["GO:0006955~immune response", "6.59E-05", "14"], ["GO:0045766~positive regulation of angiogenesis", "1.31E-04", "8"], ["GO:0045087~innate immune response", "3.22E-04", "22"], ["CC", "GO:0070062~extracellular exosome", "3.26E-06", "51"], ["GO:0005615~extracellular space", "3.15E-05", "29"], ["GO:0005886~plasma membrane", "1.58E-04", "59"], ["GO:0016020~membrane", "2.03E-03", "32"], ["GO:0031093~platelet alpha granule lumen", "1.08E-02", "4"], ["MF", "GO:0035035~histone acetyltransferase binding", "2.54E-03", "4"], ["GO:0001077~transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding", "9.14E-03", "8"], ["GO:0002020~protease binding", "1.40E-02", "5"], ["GO:0016787~hydrolase activity", "1.56E-02", "5"], ["GO:0019899~enzyme binding", "1.88E-02", "9"], ["Pathway", "hsa04668:TNF signaling pathway", "3.65E-06", "10"], ["hsa05150:Staphylococcus aureus infection", "3.23E-04", "6"], ["hsa05142:Chagas disease (American trypanosomiasis)", "7.74E-03", "6"], ["hsa04380:Osteoclast differentiation", "1.90E-02", "6"], ["hsa04910:Insulin signaling pathway", "2.39E-02", "6"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30497506:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:88f3cdf8c86dfdbb8a6385a2d1cdd62a1db21d885d5efa9131e487cb0b8c4625", "bytes": 1498, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#Tab2", "version": null, "note": "The functions and pathways enriched for the down-regulated genes", "structure": {"pmcid": "PMC6267077", "section_index": 10, "section_title": "Functional and pathway enrichment analysis", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "The functions and pathways enriched for the down-regulated genes", "rows": [["Category", "Description", "P-value", "Gene number"], ["BP", "GO:0050776~regulation of immune response", "4.11E-15", "15"], ["GO:0007166~cell surface receptor signaling pathway", "2.56E-06", "11"], ["GO:0050852~T cell receptor signaling pathway", "8.71E-05", "7"], ["GO:0072678~T cell migration", "3.56E-04", "3"], ["GO:0045059~positive thymic T cell selection", "8.47E-04", "3"], ["CC", "GO:0042101~T cell receptor complex", "1.22E-10", "7"], ["GO:0005886~plasma membrane", "1.40E-04", "35"], ["GO:0042105~alpha-beta T cell receptor complex", "2.26E-04", "3"], ["GO:0001772~immunological synapse", "5.25E-04", "4"], ["GO:0009897~external side of plasma membrane", "4.83E-03", "6"], ["MF", "GO:0004888~transmembrane signaling receptor activity", "4.20E-06", "9"], ["GO:1990405~protein antigen binding", "4.46E-04", "3"], ["GO:0030246~carbohydrate binding", "1.62E-03", "6"], ["GO:0023024~MHC class I protein complex binding", "1.40E-02", "2"], ["GO:0032393~MHC class I receptor activity", "2.31E-02", "2"], ["Pathway", "hsa04660:T cell receptor signaling pathway", "4.90E-07", "8"], ["hsa04672:Intestinal immune network for IgA production", "7.58E-05", "5"], ["hsa05340:Primary immunodeficiency", "5.41E-04", "4"], ["hsa04514:Cell adhesion molecules (CAMs)", "5.95E-04", "6"], ["hsa04650:Natural killer cell mediated cytotoxicity", "2.80E-03", "5"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[10]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:30497506:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:669902c361b376eeebf736799d64009cdd9fbe0cd570f4a72a9710c2385d0459", "bytes": 1042, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab3", "version": null, "note": "The top 15 nodes in the protein-protein interaction (PPI) network", "structure": {"pmcid": "PMC6267077", "section_index": 11, "section_title": "PPI network and module analyses", "row_count": 16, "column_count": 6}, "table": {"label": "Table 3", "caption": "The top 15 nodes in the protein-protein interaction (PPI) network", "rows": [["Node", "DC", "Node", "BC", "Node", "CC"], ["TSPO", "42", "TSPO", "8787.401", "TSPO", "0.084416"], ["MAPK14", "30", "MAPK14", "3945.718", "MAPK14", "0.082755"], ["ZAP70", "18", "ZAP70", "2945.19", "ZAP70", "0.081621"], ["ICAM1", "18", "PLEK", "1416.809", "ICAM1", "0.081481"], ["MMP9", "16", "CD40LG", "1228.869", "CD40LG", "0.081066"], ["GATA3", "13", "GATA3", "1149.809", "NFATC2", "0.080882"], ["PPARG", "13", "PPP3CC", "1065.391", "THBS1", "0.080609"], ["NFKBIA", "12", "SLC2A3", "878.1572", "MMP9", "0.080609"], ["HIF1A", "12", "PDE7A", "786", "NFKBIA", "0.080473"], ["CD40LG", "11", "LDHA", "778.0661", "GATA3", "0.080292"], ["THBS1", "11", "NFKBIA", "706.2174", "HIF1A", "0.080292"], ["CEBPB", "11", "GNA15", "660.3287", "CEBPB", "0.080247"], ["SOCS3", "10", "HIF1A", "614.6019", "PPARG", "0.080157"], ["IRF1", "10", "CD3E", "583.8388", "SOCS3", "0.080157"], ["PLEK", "9", "CD82", "550.5645", "PLEK", "0.079844"]], "row_count": 16, "column_count": 6, "numeric_cells": 56, "header_rows": 1, "locator": "section[11]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:30497506:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ce227b24fe4d0d260638f42fc6a8927e3c71d640ec0930858cf27b4906091e36", "bytes": 526, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#Tab4", "version": null, "note": "The pathways enriched for the genes involved in module 1", "structure": {"pmcid": "PMC6267077", "section_index": 11, "section_title": "PPI network and module analyses", "row_count": 7, "column_count": 3}, "table": {"label": "Table 4", "caption": "The pathways enriched for the genes involved in module 1", "rows": [["Description", "Gene number", "P-value"], ["hsa04668:TNF signaling pathway", "3", "4.59E-03"], ["hsa05200:Pathways in cancer", "4", "5.42E-03"], ["hsa04380:Osteoclast differentiation", "3", "6.97E-03"], ["hsa05160:Hepatitis C", "3", "7.18E-03"], ["hsa05205:Proteoglycans in cancer", "3", "1.57E-02"], ["hsa05144:Malaria", "2", "4.87E-02"]], "row_count": 7, "column_count": 3, "numeric_cells": 18, "header_rows": 1, "locator": "section[11]/table-wrap[2]#Tab4"}}, {"id": "asset:table:pmid:30497506:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7b676f1125fb4e7b322cf31752341090f5be0d551573f7f60a3f633a468d3af9", "bytes": 860, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab5", "version": null, "note": "The pathways enriched for the genes involved in the transcriptional regulatory network", "structure": {"pmcid": "PMC6267077", "section_index": 12, "section_title": "Regulatory network analysis", "row_count": 12, "column_count": 3}, "table": {"label": "Table 5", "caption": "The pathways enriched for the genes involved in the transcriptional regulatory network", "rows": [["Description", "Gene number", "P-value"], ["hsa04668:TNF signaling pathway", "7", "4.89E-07"], ["hsa05169:Epstein-Barr virus infection", "6", "2.09E-04"], ["hsa04380:Osteoclast differentiation", "5", "5.64E-04"], ["hsa04064:NF-kappa B signaling pathway", "4", "2.19E-03"], ["hsa05145:Toxoplasmosis", "4", "5.20E-03"], ["hsa04621:NOD-like receptor signaling pathway", "3", "1.19E-02"], ["hsa05164:Influenza A", "4", "1.51E-02"], ["hsa05152:Tuberculosis", "4", "1.58E-02"], ["hsa05140:Leishmaniasis", "3", "1.94E-02"], ["hsa05142:Chagas disease (American trypanosomiasis)", "3", "3.93E-02"], ["hsa04620:Toll-like receptor signaling pathway", "3", "4.07E-02"]], "row_count": 12, "column_count": 3, "numeric_cells": 33, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab5"}}], "gaps": ["asset:data:geo:E-MTAB-4785 not downloaded", "asset:data:geo:E-MTAB-4785 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Bayesian testing method [16] in limma package (http://www.bioconductor.org/packages/release/bioc/html/limma.html) [17] was utilized to identify the DEGs between the two group samples. The p-values were conducted with multiple testing adjustment based on the Benjamini & Hochberg method [18]."}}, {"id": "method-2", "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-3", "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["E-MTAB-4785"], "resolved_accessions": ["E-MTAB-4785"], "statements": ["The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names E-MTAB-4785 in ArrayExpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:30497506", "data:geo:E-MTAB-4785", "asset:table:pmid:30497506:1", "asset:table:pmid:30497506:2", "asset:table:pmid:30497506:3", "asset:table:pmid:30497506:4", "asset:table:pmid:30497506:5", "asset:table:pmid:30497506:6", "asset:table:pmid:30497506:7", "asset:table:pmid:30497506:8", "asset:table:pmid:30497506:9"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-4785"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 18334, "completion_tokens": 1226, "cached_tokens": 792}}, "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:30497506", "type": "paper", "label": "pmid:30497506"}, {"id": "source:pmid:30497506", "type": "manuscript", "label": "PMID 30497506 full text"}, {"id": "data:geo:E-MTAB-4785", "type": "dataset", "label": "GEO E-MTAB-4785"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30497506", "type": "paper", "label": "pmid:30497506"}, {"id": "source:pmid:30497506", "type": "manuscript", "label": "PMID 30497506 full text"}, {"id": "data:geo:E-MTAB-4785", "type": "dataset", "label": "GEO E-MTAB-4785"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30497506", "type": "extraction", "used": ["source:pmid:30497506"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-4785", "type": "accession_resolution", "used": ["data:geo:E-MTAB-4785"], "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:30497506", "parent_hash": "sha256:4fc9e2cf5a71dfd6e96b5b24d49687092bcf9e6b2ac236430710527d36b193d6", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:E-MTAB-4785 licence not read", "asset:data:geo:E-MTAB-4785 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The Bayesian testing method [16] in limma package (http://www.bioconductor.org/packages/release/bioc/html/limma.html) [17] was utilized to identify the DEGs between the two group samples. The p-values were conducted with multiple testing adjustment based on the Benjamini & Hochberg method [18]."], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T02:53:09+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}}}