{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32547141", "kind": "science-record", "revision": 8, "content_hash": "sha256:b084df0c70c9faa539af1928f3b21a1f04c822ff12b7f93663a7d3be8617bccb", "created_at": "2026-11-01T15:41:03Z", "updated_at": "2026-11-01T22:01:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Hub Genes in Type 2 Diabetes Mellitus Using Bioinformatics Analysis.", "doi": "10.2147/DMSO.S245165", "pmid": "32547141", "authors": ["YiXuan Lin", "Jinju Li", "Di Wu", "FanJing Wang", "ZhaoHui Fang", "GuoMing Shen"], "journal": "Diabetes, metabolic syndrome and obesity : targets and therapy", "year": 2020, "abstract": "BACKGROUND: Type 2 diabetes mellitus (T2DM) is one of the most common chronic diseases in the world with complicated pathogenesis. This study aimed to identify differentially expressed genes (DEGs) and molecular pathways in T2DM using bioinformatics analysis.\nMATERIALS AND METHODS: To explore potential therapeutic targets for T2DM, we analyzed three microarray datasets (GSE50397, GSE38642, and GSE44035) acquired from the Gene Expression Omnibus (GEO) database. DEGs between T2DM islet and normal islet were picked out by the GEO2R tool and Venn diagram software. Gene Ontology (GO) function and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis were performed using the Database for Annotation, Visualization, and Integrated Discovery (DAVID) to identify the pathways and functional annotation of DEGs. Then, protein-protein interaction (PPI) of these DEGs was visualized by Cytoscape with Search Tool for the Retrieval of Interacting Genes/Proteins (STRING).\nRESULTS: In total, we identified 36 DEGs in the three datasets, including 32 up-regulated genes and four down-regulated genes. The improved functions and pathways of the DEGs enriched in cytokine-cytokine receptor interaction, pathways in cancer, PI3K-Akt signaling pathway, and Rheumatoid arthritis. Among them, ten hub genes with a high degree of connectivity were selected. Furthermore, via the re-analysis of DAVID, four genes (IL6, MMP3, MMP1, and IL11) were significantly enriched in the Rheumatoid arthritis pathway.\nCONCLUSION: Our study, based on the GEO database, identified four significant up-regulated DEGs and provided novel targets for diagnosis and treatment of T2DM.", "claims": [{"id": "claim-method", "statement": "The DEGs between DM and non-diabetic samples were screened using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32547141", "locator": "sections[4] \"Data Processing of DEGs\" paragraph 2", "quote": "The DEGs between DM and non-diabetic samples were screened using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32547141", "locator": "sections[3] \"Microarray Data Information\" paragraph 2", "quote": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets 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:32547141"], "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:GSE38642"], "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:GSE38642"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32547141", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/DMSO.S245165", "sha256": "sha256:e122b1915ac20e2180f171defc7863875768e18392929288d6e98fd5d061805b", "bytes": 22649, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/DMSO.S245165", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7250707", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE38642", "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=GSE38642", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38642", "version": null, "note": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM946700", "GSM946701", "GSM946702", "GSM946703", "GSM946704", "GSM946705", "GSM946706", "GSM946707", "GSM946708", "GSM946709", "GSM946710", "GSM946711", "GSM946712", "GSM946713", "GSM946714", "GSM946715", "GSM946716", "GSM946717", "GSM946718", "GSM946719", "GSM946720", "GSM946721", "GSM946722", "GSM946723", "GSM946724", "GSM946725", "GSM946726", "GSM946727", "GSM946728", "GSM946729", "GSM946730", "GSM946731", "GSM946732", "GSM946733", "GSM946734", "GSM946735", "GSM946736", "GSM946737", "GSM946738", "GSM946739", "GSM946740", "GSM946741", "GSM946742", "GSM946743", "GSM946744", "GSM946745", "GSM946746", "GSM946747", "GSM946748", "GSM946749", "GSM946750", "GSM946751", "GSM946752", "GSM946753", "GSM946754", "GSM946755", "GSM946756", "GSM946757", "GSM946758", "GSM946759", "GSM946760", "GSM946761", "GSM946762"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Expression data from human pancreatic islets", "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:GSE44035", "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=GSE44035", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44035", "version": null, "note": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1077110", "GSM1077111", "GSM1077112", "GSM1077113", "GSM1077114", "GSM1077115", "GSM1077116", "GSM1077117", "GSM1077118", "GSM1077119"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression from human pancreatic islet", "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:GSE50397", "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=GSE50397", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50397", "version": null, "note": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1218048", "GSM1218049", "GSM1218050", "GSM1218051", "GSM1218052", "GSM1218053", "GSM1218054", "GSM1218055", "GSM1218056", "GSM1218057", "GSM1218058", "GSM1218059", "GSM1218060", "GSM1218061", "GSM1218062", "GSM1218063", "GSM1218064", "GSM1218065", "GSM1218066", "GSM1218067", "GSM1218068", "GSM1218069", "GSM1218070", "GSM1218071", "GSM1218072", "GSM1218073", "GSM1218074", "GSM1218075", "GSM1218076", "GSM1218077", "GSM1218078", "GSM1218079", "GSM1218080", "GSM1218081", "GSM1218082", "GSM1218083", "GSM1218084", "GSM1218085", "GSM1218086", "GSM1218087", "GSM1218088", "GSM1218089", "GSM1218090", "GSM1218091", "GSM1218092", "GSM1218093", "GSM1218094", "GSM1218095", "GSM1218096", "GSM1218097", "GSM1218098", "GSM1218099", "GSM1218100", "GSM1218101", "GSM1218102", "GSM1218103", "GSM1218104", "GSM1218105", "GSM1218106", "GSM1218107", "GSM1218108", "GSM1218109", "GSM1218110", "GSM1218111", "GSM1218112", "GSM1218113", "GSM1218114", "GSM1218115", "GSM1218116", "GSM1218117", "GSM1218118", "GSM1218119", "GSM1218120", "GSM1218121", "GSM1218122", "GSM1218123", "GSM1218124", "GSM1218125", "GSM1218126", "GSM1218127", "GSM1218128", "GSM1218129", "GSM1218130", "GSM1218131", "GSM1218132", "GSM1218133", "GSM1218134", "GSM1218135", "GSM1218136"], "sample_count": 89, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Global transcriptomic analysis of human pancreatic islets reveals novel genes influencing glucose metabolism [expression array]", "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:32547141:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7c73cc017037c0565b41d40e27b6ae7f5adb5bcba7041050e32662d79f250331", "bytes": 1507, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T0004", "version": null, "note": "Function and Connectivity of the Ten Hub Genes", "structure": {"pmcid": "PMC7250707", "section_index": 6, "section_title": "PPI Network and CytoHubba Analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 4", "caption": "Function and Connectivity of the Ten Hub Genes", "rows": [["Gene Symbol", "Gene Description", "Function", "Degree"], ["IL6", "Interleukin-6", "IL6 is implicated in a wide variety of inflammation associated disease states", "25"], ["MMP3", "Matrix metallopeptidase 3", "MMP3 can involve in the breakdown of extracellular matrix", "23"], ["INHBA", "Inhibin subunit beta A", "INHBA may involve in regulating insulin secretion", "20"], ["MMP1", "Matrix metallopeptidase 1", "MMP1 may related to tumor-induced angiogenesis.", "20"], ["VCAN", "Versican core protein", "VCAN is involved in cell adhesion, proliferation, proliferation migration and angiogenesis", "19"], ["FGF7", "Fibroblast growth factor 7", "FGF7 Plays an important role in the regulation of embryonic development, cell proliferation and cell differentiation", "19"], ["PDGFRA", "Platelet derived growth factor receptor alpha", "PDGFRA plays an essential role in the regulation of embryonic development, cell proliferation, survival and chemo taxis", "19"], ["THBS2", "Thrombospondin 2", "THBS2 can mediates cell-to-cell and cell-to-matrix interactions, inhibit angiogenesis.", "18"], ["IL11", "Interleukin-11", "IL11 can support the proliferation of hematopoietic stem cells and megakaryocyte progenitor cells.", "18"], ["CYR61", "Cysteine rich angiogenic inducer 61", "CYR61 may involve in angiogenesis, inflammation and matrix remodeling", "17"]], "row_count": 11, "column_count": 4, "numeric_cells": 21, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T0004"}}, {"id": "asset:table:pmid:32547141:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:597afe7b2251898bbc8c7f4ee2b8fe96f4cf5930f3e38e4b70e656fdb9e60e3b", "bytes": 552, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T0001", "version": null, "note": "36 Differentially Expressed Genes (DEGs) Were Detected from Three Datasets, Including 32 Up-Regulated Genes and 4 Down-Regulated Genes", "structure": {"pmcid": "PMC7250707", "section_index": 8, "section_title": "Identification of DEGs in DM", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "36 Differentially Expressed Genes (DEGs) Were Detected from Three Datasets, Including 32 Up-Regulated Genes and 4 Down-Regulated Genes", "rows": [["DEGs", "Genes Name"], ["Up-regulated", "GJA1 CCL22 GFPT2 RASD2 IL24 BDKRB1 LTBP1 ABCA8 SPON1 NT5E ABI3BPSFRP4 SRGN MMP1 IL6 MFAP4 MMP3 FGF7 CEMIP THBS2 CYTIP TGFA IL7RVCAN IL33 CXCL5 PDGFRA IL11 SLIT2 MMP10 CYR61 INHBA"], ["Down-regulated", "CACNA2D1 WNT4 MCF2L2 INPP5F"]], "row_count": 3, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[8]/table-wrap[1]#T0001"}}, {"id": "asset:table:pmid:32547141:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:30af385ede99e8fc2237c253da0401d7aa62bd78279e6b93d517c47e6537e93c", "bytes": 1590, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T0002", "version": null, "note": "Gene Ontology Analysis of Differentially Expressed Genes in T2DM", "structure": {"pmcid": "PMC7250707", "section_index": 9, "section_title": "GO and KEGG Enrichment Analyses", "row_count": 19, "column_count": 4}, "table": {"label": "Table 2", "caption": "Gene Ontology Analysis of Differentially Expressed Genes in T2DM", "rows": [["Category", "Term", "Count", "P-value"], ["GOTERM_CC_DIRECT", "GO:0005576~extracellular region", "22", "1.97E-14"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "16", "4.82E-09"], ["GOTERM_CC_DIRECT", "GO:0005578~proteinaceous extracellular matrix", "9", "2.57E-08"], ["GOTERM_CC_DIRECT", "GO:0031012~extracellular matrix", "9", "5.54E-08"], ["GOTERM_CC_DIRECT", "GO:0009986~cell surface", "5", "1.77E-02"], ["GOTERM_CC_DIRECT", "GO:0001527~microfibril", "2", "1.85E-02"], ["GOTERM_MF_DIRECT", "GO:0008201~heparin binding", "5", "3.24E-04"], ["GOTERM_MF_DIRECT", "GO:0008083~growth factor activity", "5", "3.39E-04"], ["GOTERM_MF_DIRECT", "GO:0005125~cytokine activity", "5", "4.65E-04"], ["GOTERM_MF_DIRECT", "GO:0005509~calcium ion binding", "7", "3.25E-03"], ["GOTERM_MF_DIRECT", "GO:0004222~metalloendopeptidase activity", "3", "2.29E-02"], ["GOTERM_MF_DIRECT", "GO:0005540~hyaluronic acid binding", "2", "4.66E-02"], ["GOTERM_BP_DIRECT", "GO:0007267~cell-cell signaling", "6", "1.71E-04"], ["GOTERM_BP_DIRECT", "GO:0045669~positive regulation of osteoblast differentiation", "4", "2.62E-04"], ["GOTERM_BP_DIRECT", "GO:0008284~positive regulation of cell proliferation", "7", "3.62E-04"], ["GOTERM_BP_DIRECT", "GO:0042060~wound healing", "4", "6.11E-04"], ["GOTERM_BP_DIRECT", "GO:0030308~negative regulation of cell growth", "4", "2.02E-03"], ["GOTERM_BP_DIRECT", "GO:0010628~positive regulation of gene expression", "5", "2.07E-03"]], "row_count": 19, "column_count": 4, "numeric_cells": 54, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T0002"}}, {"id": "asset:table:pmid:32547141:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6d2925d2ed6e3ec62ac860bfdac9d7b06443ece478588f40d61f49463f6cf948", "bytes": 894, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#T0003", "version": null, "note": "The Kyoto Encyclopedia of Genes and Genomes (KEGG) Pathway Analysis in T2DM", "structure": {"pmcid": "PMC7250707", "section_index": 9, "section_title": "GO and KEGG Enrichment Analyses", "row_count": 7, "column_count": 5}, "table": {"label": "Table 3", "caption": "The Kyoto Encyclopedia of Genes and Genomes (KEGG) Pathway Analysis in T2DM", "rows": [["Category", "Term", "Count", "P-value", "Genes"], ["KEGG_PATHWAY", "hsa04060: Cytokine–cytokine receptor interaction", "7", "1.44E-04", "INHBA, IL6, CCL22, CXCL5, IL24, IL7R, IL11"], ["KEGG_PATHWAY", "hsa05323: Rheumatoid arthritis", "5", "2.19E-04", "IL6, CXCL5, MMP3, MMP1, IL11"], ["KEGG_PATHWAY", "hsa05200: Pathways in cancer", "7", "1.87E-03", "WNT4, IL6, FGF7, PDGFRA, TGFA, BDKRB1, MMP1"], ["KEGG_PATHWAY", "hsa04630: Jak-STAT signaling pathway", "4", "1.34E-02", "IL6, IL24, IL7R, IL11"], ["KEGG_PATHWAY", "hsa04151: PI3K-Akt signaling pathway", "5", "2.98E-02", "IL6, FGF7, PDGFRA, IL7R, THBS2"], ["KEGG_PATHWAY", "hsa04640: Hematopoietic cell lineage", "3", "3.64E-02", "IL6, IL7R, IL11"]], "row_count": 7, "column_count": 5, "numeric_cells": 22, "header_rows": 1, "locator": "section[9]/table-wrap[2]#T0003"}}, {"id": "asset:table:pmid:32547141:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7c73cc017037c0565b41d40e27b6ae7f5adb5bcba7041050e32662d79f250331", "bytes": 1507, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T0004", "version": null, "note": "Function and Connectivity of the Ten Hub Genes", "structure": {"pmcid": "PMC7250707", "section_index": 10, "section_title": "PPI Network and CytoHubba Analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 4", "caption": "Function and Connectivity of the Ten Hub Genes", "rows": [["Gene Symbol", "Gene Description", "Function", "Degree"], ["IL6", "Interleukin-6", "IL6 is implicated in a wide variety of inflammation associated disease states", "25"], ["MMP3", "Matrix metallopeptidase 3", "MMP3 can involve in the breakdown of extracellular matrix", "23"], ["INHBA", "Inhibin subunit beta A", "INHBA may involve in regulating insulin secretion", "20"], ["MMP1", "Matrix metallopeptidase 1", "MMP1 may related to tumor-induced angiogenesis.", "20"], ["VCAN", "Versican core protein", "VCAN is involved in cell adhesion, proliferation, proliferation migration and angiogenesis", "19"], ["FGF7", "Fibroblast growth factor 7", "FGF7 Plays an important role in the regulation of embryonic development, cell proliferation and cell differentiation", "19"], ["PDGFRA", "Platelet derived growth factor receptor alpha", "PDGFRA plays an essential role in the regulation of embryonic development, cell proliferation, survival and chemo taxis", "19"], ["THBS2", "Thrombospondin 2", "THBS2 can mediates cell-to-cell and cell-to-matrix interactions, inhibit angiogenesis.", "18"], ["IL11", "Interleukin-11", "IL11 can support the proliferation of hematopoietic stem cells and megakaryocyte progenitor cells.", "18"], ["CYR61", "Cysteine rich angiogenic inducer 61", "CYR61 may involve in angiogenesis, inflammation and matrix remodeling", "17"]], "row_count": 11, "column_count": 4, "numeric_cells": 21, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T0004"}}, {"id": "asset:table:pmid:32547141:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6e442ac8772aa9f61eeb0538e4160cf6c8db24ece67a2c3919b150b5aa8c9cd2", "bytes": 656, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T0005", "version": null, "note": "The Kyoto Encyclopedia of Genes and Genomes (KEGG) Pathway Analysis of 10 Hub Genes", "structure": {"pmcid": "PMC7250707", "section_index": 11, "section_title": "Re-Analysis of 10 Hub Genes via KEGG Pathway Enrichment", "row_count": 5, "column_count": 5}, "table": {"label": "Table 5", "caption": "The Kyoto Encyclopedia of Genes and Genomes (KEGG) Pathway Analysis of 10 Hub Genes", "rows": [["Category", "Term", "Count", "P-value", "Genes"], ["KEGG_PATHWAY", "hsa05323:Rheumatoid arthritis", "4", "1.08E-04", "IL6, MMP3, MMP1, IL11"], ["KEGG_PATHWAY", "hsa04151:PI3K-Akt signaling pathway", "4", "5.80E-03", "IL6, FGF7, PDGFRA, THBS2"], ["KEGG_PATHWAY", "hsa05200:Pathways in cancer", "4", "8.35E-03", "IL6, FGF7, PDGFRA, MMP1"], ["KEGG_PATHWAY", "hsa04060:Cytokine–cytokine receptor interaction", "3", "3.02E-02", "INHBA, IL6, IL11"]], "row_count": 5, "column_count": 5, "numeric_cells": 14, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T0005"}}], "gaps": ["asset:data:geo:GSE38642 not downloaded", "asset:data:geo:GSE38642 licence not read", "asset:data:geo:GSE44035 not downloaded", "asset:data:geo:GSE44035 licence not read", "asset:data:geo:GSE50397 not downloaded", "asset:data:geo:GSE50397 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": "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"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The DEGs between DM and non-diabetic samples were screened using GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r)."}}], "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": ["GSE50397", "GSE38642", "GSE44035"], "resolved_accessions": ["GSE50397", "GSE38642", "GSE44035"], "statements": ["The GSE50397 dataset contained 66 non-diabetic pancreatic islets samples and 11 diabetic pancreatic islets samples."], "basis": "The paper names GSE50397, GSE38642, GSE44035 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:32547141", "data:geo:GSE38642", "asset:table:pmid:32547141:1", "asset:table:pmid:32547141:2", "asset:table:pmid:32547141:3", "asset:table:pmid:32547141:4", "asset:table:pmid:32547141:5", "asset:table:pmid:32547141:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE38642"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 18193, "completion_tokens": 1133, "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:32547141", "type": "paper", "label": "pmid:32547141"}, {"id": "source:pmid:32547141", "type": "manuscript", "label": "PMID 32547141 full text"}, {"id": "data:geo:GSE38642", "type": "dataset", "label": "GEO GSE38642"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32547141", "type": "paper", "label": "pmid:32547141"}, {"id": "source:pmid:32547141", "type": "manuscript", "label": "PMID 32547141 full text"}, {"id": "data:geo:GSE38642", "type": "dataset", "label": "GEO GSE38642"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32547141", "type": "extraction", "used": ["source:pmid:32547141"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE38642", "type": "accession_resolution", "used": ["data:geo:GSE38642"], "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:32547141", "parent_hash": "sha256:f90868d82ec15b1e5ed018452a7639b4c4505547f46643927692d44c7b4441d1", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE38642 licence not read", "asset:data:geo:GSE38642 not downloaded", "asset:data:geo:GSE44035 licence not read", "asset:data:geo:GSE44035 not downloaded", "asset:data:geo:GSE50397 licence not read", "asset:data:geo:GSE50397 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["rapeutic targets for T2DM, we analyzed three microarray datasets (GSE50397, GSE38642, and GSE44035)"], "order_basis": "paper_text_order:394", "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":"2026-11-04T01:44:27+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}}}