{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32682418", "kind": "science-record", "revision": 8, "content_hash": "sha256:0ffba3b528182eee18a90a673e1f4dab383b2a82b9fd795346d30a162e603a30", "created_at": "2026-11-01T15:41:06Z", "updated_at": "2026-11-01T22:45:06Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential crucial genes in atrial fibrillation: a bioinformatic analysis.", "doi": "10.1186/s12920-020-00754-5", "pmid": "32682418", "authors": ["Junguo Zhang", "Xin Huang", "Xiaojie Wang", "Yanhui Gao", "Li Liu", "Ziyi Li", "Xuejiao Chen", "Jie Zeng", "Zebing Ye", "Guowei Li"], "journal": "BMC medical genomics", "year": 2020, "abstract": "BACKGROUND: Atrial fibrillation (AF) is at least partially heritable, affecting 2-3% of the population in Europe and the USA. However, a substantial proportion of heritability is still lacking. In the present study, we aim to identify potential crucial genes associated with AF through bioinformatic analyses of public datasets.\nMETHODS: Microarray data sets of GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975 from the Gene Expression Omnibus (GEO) database were retrieved. After merging all microarray data and adjusting batch effect, differentially expressed genes (DEGs) were identified. Functional enrichment analyses based on Gene Ontology (GO) resource, Kyoto Encyclopedia of Genes and Genomes (KEGG) resource, Gene Set Enrichment Analysis (GSEA), Reactome Pathway Database and Disease Ontology (DO) were carried out. Protein-protein interaction (PPI) network was constructed using the STRING database. Combined with aforementioned significant bioinformatics information, potential crucial genes were subsequently selected. The comparative toxicogenomics database (CTD) was used to explore the interaction between potential crucial genes and AF.\nRESULT: We identified 27 of DEGs with gene expression fold change (FC) ≥ 1.5 or ≤ 2/3 (|log2 FC| ≥ 0.58) and 5 with FC ≥ 2 or ≤ 0.5 (|log2 FC| ≥ 1) of AF patients compared with sinus rhythm controls. The most significantly enriched pathway was regulation of insulin-like growth factor transport and uptake by insulin-like growth factor binding proteins. IGFBP2, C1orf105, FHL2, CHGB, ATP1B4, IGFBP3, SLC26A9, CXCR4 and HTR2B were considered the potential crucial genes. CTD showed CXCR4, IGFBP2, IGFBP3 and FHL2 had higher scores with AF.\nCONCLUSIONS: The 9 potential crucial genes, especially CXCR4, IGFBP2, IGFBP3 and FHL2, may be associated with risk of AF. Our study provided new insights of AF into genetics, molecular pathogenesis and new therapeutic targets.", "claims": [{"id": "claim-method", "statement": "To assess differential expression, using the “limma” package of R software, a linear model was fitted and a simple empirical Bayes model was used to moderate standard errors [11].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32682418", "locator": "sections[5] \"Identification of differentially expressed genes (DEGs)\" paragraph 2", "quote": "To assess differential expression, using the “limma” package of R software, a linear model was fitted and a simple empirical Bayes model was used to moderate standard errors [11]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32682418", "locator": "sections[24] \"notes\" paragraph 1", "quote": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019)."}], "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:32682418"], "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:GSE115574"], "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:GSE115574"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32682418", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-020-00754-5", "sha256": "sha256:41374f22aaf3448bbae5cb39b8a0ae383d25357b95c22989108e9f60d8077446", "bytes": 26893, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-020-00754-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7368672", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE115574", "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=GSE115574", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE115574", "version": null, "note": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3182680", "GSM3182681", "GSM3182682", "GSM3182683", "GSM3182684", "GSM3182685", "GSM3182686", "GSM3182687", "GSM3182688", "GSM3182689", "GSM3182690", "GSM3182691", "GSM3182692", "GSM3182693", "GSM3182694", "GSM3182695", "GSM3182696", "GSM3182697", "GSM3182698", "GSM3182699", "GSM3182700", "GSM3182701", "GSM3182702", "GSM3182703", "GSM3182704", "GSM3182705", "GSM3182706", "GSM3182707", "GSM3182708", "GSM3182709", "GSM3182710", "GSM3182711", "GSM3182712", "GSM3182713", "GSM3182714", "GSM3182715", "GSM3182716", "GSM3182717", "GSM3182718", "GSM3182719", "GSM3182720", "GSM3182721", "GSM3182722", "GSM3182723", "GSM3182724", "GSM3182725", "GSM3182726", "GSM3182727", "GSM3182728", "GSM3182729", "GSM3182730", "GSM3182731", "GSM3182732", "GSM3182733", "GSM3182734", "GSM3182735", "GSM3182736", "GSM3182737", "GSM3182738"], "sample_count": 59, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data from human left and right atrial tissues in patients with degenerative MR in SR and AFib.", "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:GSE14975", "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=GSE14975", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14975", "version": null, "note": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM373956", "GSM373957", "GSM373958", "GSM373959", "GSM373960", "GSM373961", "GSM373962", "GSM373963", "GSM373964", "GSM373965"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Rac1-Induced Connective Tissue Growth Factor regulates Connexin 43 and N-Cadherin Expression in Atrial Fibrillation", "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:GSE31821", "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=GSE31821", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31821", "version": null, "note": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM789270", "GSM789271", "GSM789272", "GSM789273", "GSM789274", "GSM789275"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression and miRNA profiles in atrial fibrillation. Role of miR-21.", "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:GSE41177", "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=GSE41177", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41177", "version": null, "note": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1005418", "GSM1005419", "GSM1005420", "GSM1005421", "GSM1005422", "GSM1005423", "GSM1005424", "GSM1005425", "GSM1005426", "GSM1005427", "GSM1005428", "GSM1005429", "GSM1005430", "GSM1005431", "GSM1005432", "GSM1005433", "GSM1005434", "GSM1005435", "GSM1005436", "GSM1005437", "GSM1005438", "GSM1005439", "GSM1005440", "GSM1005441", "GSM1005442", "GSM1005443", "GSM1005444", "GSM1005445", "GSM1006245", "GSM1006246", "GSM1006247", "GSM1006248", "GSM1006249", "GSM1006250", "GSM1006251", "GSM1006252", "GSM1006253", "GSM1006254"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Region-specific gene expression profiles in left atria of patients with valvular atrial fibrillation", "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:GSE79768", "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=GSE79768", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE79768", "version": null, "note": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2102184", "GSM2102185", "GSM2102186", "GSM2102187", "GSM2102188", "GSM2102189", "GSM2102190", "GSM2102191", "GSM2102192", "GSM2102193", "GSM2102194", "GSM2102195", "GSM2102196", "GSM2102197", "GSM2102198", "GSM2102199", "GSM2102200", "GSM2102201", "GSM2102202", "GSM2102203", "GSM2102204", "GSM2102205", "GSM2102206", "GSM2102207", "GSM2102208", "GSM2102209"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Atrial fibrillation is associated with altered left-to-right atria gene expression ratio: implications for arrhythmogenesis and thrombogenesis", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32682418:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c05ebe3e32c45f8e50a8a4e00c75f53277a4981bf9d6cf568af03709358c0e36", "bytes": 560, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Characteristics of datasets in this study", "structure": {"pmcid": "PMC7368672", "section_index": 3, "section_title": "Atrial fibrillation datasets", "row_count": 6, "column_count": 7}, "table": {"label": "Table 1", "caption": "Characteristics of datasets in this study", "rows": [["GSE series", "Platform", "Total", "AF", "SR", "Country", "Contributors"], ["GSE115574", "GPL570", "29", "14", "15", "Turkey", "Deniz GC et.al"], ["GSE31821", "GPL570", "6", "4", "2", "France", "Morel E et.al"], ["GSE79768", "GPL570", "13", "7", "6", "Taiwan", "Tsai F et.al"], ["GSE41177", "GPL570", "19", "16", "3", "Taiwan", "Yeh Y et.al"], ["GSE14975", "GPL570", "10", "5", "5", "Germany", "Adam O et.al"]], "row_count": 6, "column_count": 7, "numeric_cells": 25, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32682418:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d89113a61147427312fae2278ad18e6fe8cdaf49b400174be1b73411dad3fa1d", "bytes": 657, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab2", "version": null, "note": "The DEGs of merged data set with the use of criteria of adjust P value < 0.05 and |log2FC| ≥ 1", "structure": {"pmcid": "PMC7368672", "section_index": 10, "section_title": "Identification of DEGs", "row_count": 6, "column_count": 7}, "table": {"label": "Table 2", "caption": "The DEGs of merged data set with the use of criteria of adjust P value < 0.05 and |log2FC| ≥ 1", "rows": [["Gene", "Log2FC", "AveExpr", "t", "P value", "adjust P value", "B"], ["IGFBP2", "1.1746", "9.5881", "−6.0548", "< 0.0001", "0.0006", "8.0172"], ["C1orf105", "−1.0560", "7.2935", "5.6106", "< 0.0001", "0.0011", "6.3668"], ["FHL2", "1.1255", "9.9882", "−5.4755", "< 0.0001", "0.0016", "5.8742"], ["CHGB", "1.0836", "8.5851", "−5.3090", "< 0.0001", "0.0025", "5.2745"], ["ATP1B4", "1.0469", "5.0220", "−4.3592", "< 0.0001", "0.0283", "2.0308"]], "row_count": 6, "column_count": 7, "numeric_cells": 31, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:32682418:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:efb3b6ec84abb3bbacc21717ed659e2ea2e7987fc8e0bff7c7e56b9eac691445", "bytes": 977, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab3", "version": null, "note": "Significant enriched GO terms and pathways of DEGs", "structure": {"pmcid": "PMC7368672", "section_index": 11, "section_title": "Functional enrichment analyses of DEGs", "row_count": 10, "column_count": 7}, "table": {"label": "Table 3", "caption": "Significant enriched GO terms and pathways of DEGs", "rows": [["", "Term", "Count", "Genes", "P value", "adjust P value", "Q value"], ["GO terms"], ["GO:0031994", "insulin-like growth factor I binding", "2", "IGFBP2/IGFBP3", "0.0001", "0.0168", "0.0121"], ["GO:0005520", "insulin-like growth factor binding", "2", "IGFBP2/IGFBP3", "0.0006", "0.0433", "0.0311"], ["KEGG Pathway"], ["hsa04978", "Mineral absorption", "2", "SLC26A9/ATP1B4", "0.0033", "0.2088", "0.2088"], ["hsa04020", "Calcium signaling pathway", "2", "CXCR4/ HTR2B", "0.0332", "0.2741", "0.2741"], ["hsa04964", "Proximal tubule bicarbonate reclamation", "1", "ATP1B4", "0.0343", "0.2741", "0.2741"], ["Reactome Pathway"], ["R-HSA-381426", "Regulation of Insulin-like Growth Factor (IGF) transport and uptake by Insulin-like GrowthFactor Binding Proteins (IGFBPs)", "3", "IGFBP2/ IGFBP3/ CHGB", "0.0008", "0.0632", "0.0435"]], "row_count": 10, "column_count": 7, "numeric_cells": 31, "header_rows": 1, "locator": "section[11]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE115574 not downloaded", "asset:data:geo:GSE115574 licence not read", "asset:data:geo:GSE14975 not downloaded", "asset:data:geo:GSE14975 licence not read", "asset:data:geo:GSE31821 not downloaded", "asset:data:geo:GSE31821 licence not read", "asset:data:geo:GSE41177 not downloaded", "asset:data:geo:GSE41177 licence not read", "asset:data:geo:GSE79768 not downloaded", "asset:data:geo:GSE79768 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": "To assess differential expression, using the “limma” package of R software, a linear model was fitted and a simple empirical Bayes model was used to moderate standard errors [11]."}}, {"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"}}], "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": ["GSE115574", "GSE31821", "GSE79768", "GSE41177", "GSE14975"], "resolved_accessions": ["GSE115574", "GSE31821", "GSE79768", "GSE41177", "GSE14975"], "statements": ["Microarray datasets (GSE115574, GSE31821, GSE79768, GSE41177 and GSE14975) for this study are openly available in Gene Expression Omnibus database at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE115574, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31821, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79768, https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41177 and https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE14975, respectively (last accessed on 27 Dec 2019)."], "basis": "The paper names GSE115574, GSE31821, GSE79768, GSE41177, GSE14975 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32682418", "data:geo:GSE115574", "asset:table:pmid:32682418:1", "asset:table:pmid:32682418:2", "asset:table:pmid:32682418:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE115574"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 21499, "completion_tokens": 1974, "cached_tokens": 656}}, "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:32682418", "type": "paper", "label": "pmid:32682418"}, {"id": "source:pmid:32682418", "type": "manuscript", "label": "PMID 32682418 full text"}, {"id": "data:geo:GSE115574", "type": "dataset", "label": "GEO GSE115574"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32682418", "type": "paper", "label": "pmid:32682418"}, {"id": "source:pmid:32682418", "type": "manuscript", "label": "PMID 32682418 full text"}, {"id": "data:geo:GSE115574", "type": "dataset", "label": "GEO GSE115574"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32682418", "type": "extraction", "used": ["source:pmid:32682418"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE115574", "type": "accession_resolution", "used": ["data:geo:GSE115574"], "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:32682418", "parent_hash": "sha256:1988e2f69475e9f67025d4196c1058f1440cc88575b60893255c051b8eeb176f", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE115574 licence not read", "asset:data:geo:GSE115574 not downloaded", "asset:data:geo:GSE14975 licence not read", "asset:data:geo:GSE14975 not downloaded", "asset:data:geo:GSE31821 licence not read", "asset:data:geo:GSE31821 not downloaded", "asset:data:geo:GSE41177 licence not read", "asset:data:geo:GSE41177 not downloaded", "asset:data:geo:GSE79768 licence not read", "asset:data:geo:GSE79768 not downloaded", "execution.not_run", "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": 0.99, "evidence": ["rmatic analyses of public datasets. METHODS: Microarray data sets of GSE115574, GSE31821, GSE79768,", ") database were retrieved. After merging all microarray data and adjusting batch effect, differentia"], "order_basis": "paper_text_order:385", "id": "assay:1"}, {"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": ["To assess differential expression, using the “limma” package of R software, a linear model was fitted and a simple empirical Bayes model was used to moderate standard errors [11]."], "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":"2026-11-04T02:52:31+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}}}