{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33976979", "kind": "science-record", "revision": 7, "content_hash": "sha256:46bde9ca3d4cf92e1384861c6565985553ae009322c3c6e1c79c784b1c930d52", "created_at": "2026-11-01T15:41:35Z", "updated_at": "2026-11-01T22:03:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prediction and analysis of novel key genes ITGAX, LAPTM5, SERPINE1 in clear cell renal cell carcinoma through bioinformatics analysis.", "doi": "10.7717/peerj.11272", "pmid": "33976979", "authors": ["Yingli Sui", "Kun Lu", "Lin Fu"], "journal": "PeerJ", "year": 2021, "abstract": "BACKGROUND: Clear Cell Renal Cell Carcinoma (CCRCC) is the most aggressive subtype of Renal Cell Carcinoma (RCC) with high metastasis and recurrence rates. This study aims to find new potential key genes of CCRCC.\nMETHODS: Four gene expression profiles (GSE12606, GSE53000, GSE68417, and GSE66272) were downloaded from the Gene Expression Omnibus (GEO) database. The TCGA KIRC data was downloaded from The Cancer Genome Atlas (TCGA). Using GEO2R, the differentially expressed genes (DEG) in CCRCC tissues and normal samples were analyzed. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed in DAVID database. A protein-protein interaction (PPI) network was constructed and the hub gene was predicted by STRING and Cytoscape. GEPIA and Kaplan-Meier plotter databases were used for further screening of Key genes. Expression verification and survival analysis of key genes were performed using TCGA database, GEPIA database, and Kaplan-Meier plotter. Receiver operating characteristic (ROC) curve was used to analyze the diagnostic value of key genes in CCRCC, which is plotted by R software based on TCGA database. UALCAN database was used to analyze the relationship between key genes and clinical pathology in CCRCC and the methylation level of the promoter of key genes in CCRCC.\nRESULTS: A total of 289 up-regulated and 449 down-regulated genes were identified based on GSE12606, GSE53000, GSE68417, and GSE66272 profiles in CCRCC. The upregulated DEGs were mainly enriched with protein binding and PI3K-Akt signaling pathway, whereas down-regulated genes were enriched with the integral component of the membrane and metabolic pathways. Next, the top 35 genes were screened out from the PPI network according to Degree, and three new key genes ITGAX, LAPTM5 and SERPINE1 were further screened out through survival and prognosis analysis. Further results showed that the ITGAX, LAPTM5, and SERPINE1 levels in CCRCC tumor tissues were significantly higher than those in normal tissues and were associated with poor prognosis. ROC curve shows that ITGAX, LAPTM5, and SERPINE1 have good diagnostic value with good specificity and sensitivity. The promoter methylation levels of ITGAX, LAPTM5 and SERPINE1 in CCRCC tumor tissues were significantly lower than those in normal tissues. We also found that key genes were associated with clinical pathology in CCRCC.\nCONCLUSION: ITGAX, LAPTM5, and SERPINE1 were identified as novel key candidate genes that could be used as prognostic biomarkers and potential therapeutic targets for CCRCC.", "claims": [{"id": "claim-method", "statement": "Statistically significant differences between the normal tissues group and tumor tissues group were determined using Student’s t tests.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33976979", "locator": "sections[8] \"Statistical analysis\" paragraph 2", "quote": "Statistically significant differences between the normal tissues group and tumor tissues group were determined using Student’s t tests."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33976979", "locator": "sections[28] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files."}], "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:33976979"], "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:GSE12606"], "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:GSE12606"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33976979", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.11272", "sha256": "sha256:a5f4f3daae4729a778a770afe68918ce89cb747e5967e6a07fb5dfb6646be0b9", "bytes": 49353, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.11272", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8063882", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12606", "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=GSE12606", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12606", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM315855", "GSM315856", "GSM315857", "GSM315858", "GSM315859", "GSM315860", "GSM315861", "GSM315862", "GSM315863", "GSM315864"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "HLA ligand profiles of primary renal cell carcinoma maintained in metastases.sue", "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:GSE53000", "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=GSE53000", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53000", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1279951", "GSM1279952", "GSM1279953", "GSM1279954", "GSM1279955", "GSM1279956", "GSM1279957", "GSM1279959", "GSM1279960", "GSM1279962", "GSM1279963", "GSM1279964", "GSM1279965", "GSM1279966", "GSM1279967", "GSM1279968", "GSM1279969", "GSM1279970", "GSM1279971", "GSM1279972", "GSM1279973", "GSM1279974", "GSM1279975", "GSM1279976", "GSM1279977", "GSM1279978", "GSM1279979", "GSM1279980", "GSM1279982", "GSM1279983", "GSM1279984", "GSM1279985", "GSM1279986", "GSM1279987", "GSM1279988", "GSM1279989", "GSM1279990", "GSM1279991", "GSM1279992", "GSM1279993", "GSM1279994", "GSM1279995", "GSM1279996", "GSM1279997", "GSM1279998", "GSM1279999", "GSM1280000", "GSM1280001", "GSM1280002", "GSM1280003", "GSM1280004", "GSM1280005", "GSM1280006", "GSM1280007", "GSM1280010", "GSM1280012", "GSM1280013", "GSM1280014", "GSM1280015", "GSM1280016", "GSM1280017", "GSM1280018"], "sample_count": 62, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Expression data from spatially separated samples of different ccRCC patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE66272", "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=GSE66272", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66272", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1618387", "GSM1618388", "GSM1618389", "GSM1618390", "GSM1618391", "GSM1618392", "GSM1618393", "GSM1618394", "GSM1618395", "GSM1618396", "GSM1618397", "GSM1618398", "GSM1618399", "GSM1618400", "GSM1618401", "GSM1618402", "GSM1618403", "GSM1618404", "GSM1618405", "GSM1618406", "GSM1618407", "GSM1618408", "GSM1618409", "GSM1618410", "GSM1618411", "GSM1618412", "GSM1618413", "GSM1618414", "GSM1618415", "GSM1618416", "GSM1618417", "GSM1618418", "GSM1618419", "GSM1618420", "GSM1618421", "GSM1618422", "GSM1618423", "GSM1618424", "GSM1618425", "GSM1618426", "GSM1618427", "GSM1618428", "GSM1618429", "GSM1618430", "GSM1618431", "GSM1618432", "GSM1618433", "GSM1618434", "GSM1618435", "GSM1618436", "GSM1618437", "GSM1618438", "GSM1618439", "GSM1618440"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression patterns in human kidney cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE68417", "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=GSE68417", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68417", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1671350", "GSM1671351", "GSM1671352", "GSM1671353", "GSM1671354", "GSM1671355", "GSM1671356", "GSM1671357", "GSM1671358", "GSM1671359", "GSM1671360", "GSM1671361", "GSM1671362", "GSM1671363", "GSM1671364", "GSM1671365", "GSM1671366", "GSM1671367", "GSM1671368", "GSM1671369", "GSM1671370", "GSM1671371", "GSM1671372", "GSM1671373", "GSM1671374", "GSM1671375", "GSM1671376", "GSM1671377", "GSM1671378", "GSM1671379", "GSM1671380", "GSM1671381", "GSM1671382", "GSM1671383", "GSM1671384", "GSM1671385", "GSM1671386", "GSM1671387", "GSM1671388", "GSM1671389", "GSM1671390", "GSM1671391", "GSM1671392", "GSM1671393", "GSM1671394", "GSM1671395", "GSM1671396", "GSM1671397", "GSM1671398"], "sample_count": 49, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression characterization of high and low grade clear cell renal cell carcinoma", "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:33976979:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:80410a258a2f5ec5856e2ca45509043c207fb8cba06174639fc2326058462835", "bytes": 705, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "Summary of TCGA and GEO Clear Cell Renal Cell Carcinoma datasets.", "structure": {"pmcid": "PMC8063882", "section_index": 10, "section_title": "Volcano plots of the differentially expressed genes in four datasets", "row_count": 6, "column_count": 7}, "table": {"label": "Table 1", "caption": "Summary of TCGA and GEO Clear Cell Renal Cell Carcinoma datasets.", "rows": [["Author, year", "Sample", "GEO no.", "Platform", "Normal", "Tumor", "(Refs.)"], ["Stickel JS et al, 2009", "CCRCC", "GSE12606", "GPL570", "3", "3", "Stickel et al. (2009)"], ["Gerlinger M et al, 2014", "CCRCC", "GSE53000", "GPL6244", "6", "54", "Gerlinger et al. (2014)"], ["Thibodeau BJ et al, 2016", "CCRCC", "GSE68417", "GPL6244", "29", "14", "Thibodeau et al. (2016)"], ["Wotschofsky Z et al, 2016", "CCRCC", "GSE66272", "GPL5029", "27", "26", "Wotschofsky et al. (2016)"], ["TCGA", "CCRCC", "–", "–", "72", "539", ""]], "row_count": 6, "column_count": 7, "numeric_cells": 26, "header_rows": 1, "locator": "section[10]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:33976979:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e7a52f5ab666369e0bc2f7e7e3045c46e37081b7a2a648585a15a9d156ae522e", "bytes": 5835, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#table-2", "version": null, "note": "GO and KEGG analysis of differentially expressed DEG associated with CCRCC.", "structure": {"pmcid": "PMC8063882", "section_index": 11, "section_title": "GO and KEGG enrichment analysis of DEGs", "row_count": 81, "column_count": 5}, "table": {"label": "Table 2", "caption": "GO and KEGG analysis of differentially expressed DEG associated with CCRCC.", "rows": [["Expression", "Category", "Term", "Count", "P-value"], ["Upregulated", "GO_BP", "GO:0006954∼inflammatory response", "30", "1.30E−12"], ["", "GO_BP", "GO:0007165∼signal transduction", "29", "1.31E−02"], ["", "GO_BP", "GO:0007155∼cell adhesion", "26", "5.33E−08"], ["", "GO_BP", "GO:0006955∼immune response", "24", "1.76E−07"], ["", "GO_BP", "GO:0042493∼response to drug", "21", "5.92E−08"], ["", "GO_BP", "GO:0045087∼innate immune response", "19", "1.36E−04"], ["", "GO_BP", "GO:0030198∼extracellular matrix organization", "18", "1.08E−08"], ["", "GO_BP", "GO:0050900∼leukocyte migration", "17", "6.55E−11"], ["", "GO_BP", "GO:0001525∼angiogenesis", "17", "4.06E−07"], ["", "GO_BP", "GO:0008284∼positive regulation of cell proliferation", "17", "2.57E−03"], ["", "GO_CC", "GO:0005886∼plasma membrane", "108", "1.13E−09"], ["", "GO_CC", "GO:0016021∼integral component of membrane", "107", "2.03E−04"], ["", "GO_CC", "GO:0070062∼extracellular exosome", "66", "2.68E−04"], ["", "GO_CC", "GO:0016020∼membrane", "64", "4.11E−07"], ["", "GO_CC", "GO:0005887∼integral component of plasma membrane", "62", "6.07E−14"], ["", "GO_CC", "GO:0005576∼extracellular region", "50", "1.98E−06"], ["", "GO_CC", "GO:0005615∼extracellular space", "49", "2.48E−08"], ["", "GO_CC", "GO:0009986∼cell surface", "31", "1.08E−09"], ["", "GO_CC", "GO:0005783∼endoplasmic reticulum", "20", "4.86E−02"], ["", "GO_CC", "GO:0000139∼Golgi membrane", "17", "1.94E−02"], ["", "GO_MF", "GO:0005515∼protein binding", "154", "6.05E−03"], ["", "GO_MF", "GO:0005524∼ATP binding", "36", "6.15E−03"], ["", "GO_MF", "GO:0042803∼protein homodimerization activity", "21", "7.66E−03"], ["", "GO_MF", "GO:0042802∼identical protein binding", "20", "1.92E−02"], ["", "GO_MF", "GO:0005102∼receptor binding", "19", "7.41E−06"], ["", "GO_MF", "GO:0004872∼receptor activity", "14", "2.70E−05"], ["", "GO_MF", "GO:0004672∼protein kinase activity", "12", "2.09E−02"], ["", "GO_MF", "GO:0005215∼transporter activity", "8", "3.41E−02"], ["", "GO_MF", "GO:0004888∼transmembrane signaling receptor activity", "8", "4.43E−02"], ["", "GO_MF", "GO:0005201∼extracellular matrix structural constituent", "7", "5.17E−04"], ["", "KEGG", "hsa04151: PI3K-Akt signaling pathway", "19", "2.01E−04"], ["", "KEGG", "hsa04510: Focal adhesion", "17", "3.76E−06"], ["", "KEGG", "hsa05200: Pathways in cancer", "17", "5.96E−03"], ["", "KEGG", "hsa04066: HIF-1 signaling pathway", "12", "3.37E−06"], ["", "KEGG", "hsa04015: Rap1 signaling pathway", "12", "3.56E−03"], ["", "KEGG", "hsa04145: Phagosome", "10", "3.39E−03"], ["", "KEGG", "hsa05205: Proteoglycans in cancer", "10", "2.05E−02"], ["", "KEGG", "hsa05150: Staphylococcus aureus infection", "9", "1.14E−05"], ["", "KEGG", "hsa04611: Platelet activation", "9", "4.86E−03"], ["", "KEGG", "hsa05133: Pertussis", "8", "7.79E−04"], ["Downregulated", "GO_BP", "GO:0055114∼oxidation–reduction process", "33", "3.33E−05"], ["", "GO_BP", "GO:0034220∼ion transmembrane transport", "19", "5.29E−06"], ["", "GO_BP", "GO:0042493∼response to drug", "18", "1.62E−03"], ["", "GO_BP", "GO:0006811∼ion transport", "14", "1.66E−05"], ["", "GO_BP", "GO:0055085∼transmembrane transport", "14", "8.16E−03"], ["", "GO_BP", "GO:0007588∼excretion", "13", "4.97E−11"], ["", "GO_BP", "GO:0010628∼positive regulation of gene expression", "13", "3.13E−02"], ["", "GO_BP", "GO:0006814∼sodium ion transport", "12", "4.94E−06"], ["", "GO_BP", "GO:0001822∼kidney development", "12", "8.92E−06"], ["", "GO_BP", "GO:0008152∼metabolic process", "12", "3.22E−03"], ["", "GO_CC", "GO:0016021∼integral component of membrane", "171", "4.63E−07"], ["", "GO_CC", "GO:0070062∼extracellular exosome", "170", "1.01E−33"], ["", "GO_CC", "GO:0005886∼plasma membrane", "162", "2.99E−12"], ["", "GO_CC", "GO:0005887∼integral component of plasma membrane", "76", "3.16E−11"], ["", "GO_CC", "GO:0005615∼extracellular space", "50", "1.87E−03"], ["", "GO_CC", "GO:0016324∼apical plasma membrane", "44", "4.39E−22"], ["", "GO_CC", "GO:0016323∼basolateral plasma membrane", "28", "2.05E−14"], ["", "GO_CC", "GO:0009986∼cell surface", "24", "5.53E−03"], ["", "GO_CC", "GO:0005759∼mitochondrial matrix", "19", "8.74E−04"], ["", "GO_CC", "GO:0043025∼neuronal cell body", "15", "1.88E−02"], ["", "GO_MF", "GO:0042803∼protein homodimerization activity", "33", "7.43E−04"], ["", "GO_MF", "GO:0005509∼calcium ion binding", "29", "7.77E−03"], ["", "GO_MF", "GO:0043565∼sequence-specific DNA binding", "20", "4.43E−02"], ["", "GO_MF", "GO:0016491∼oxidoreductase activity", "13", "3.24E−03"], ["", "GO_MF", "GO:0046983∼protein dimerization activity", "11", "3.31E−03"], ["", "GO_MF", "GO:0008201∼heparin binding", "11", "5.22E−03"], ["", "GO_MF", "GO:0005088∼Ras guanyl-nucleotide exchange factor activity", "10", "1.78E−03"], ["", "GO_MF", "GO:0003824∼catalytic activity", "10", "3.74E−02"], ["", "GO_MF", "GO:0016787∼hydrolase activity", "10", "4.07E−02"], ["", "GO_MF", "GO:0046934∼phosphatidylinositol-4,5-bisphosphate 3-kinase activity", "9", "1.10E−04"], ["", "KEGG", "hsa01100: Metabolic pathways", "68", "8.56E−08"], ["", "KEGG", "hsa01130: Biosynthesis of antibiotics", "19", "5.17E−05"], ["", "KEGG", "hsa01200: Carbon metabolism", "11", "1.83E−03"], ["", "KEGG", "hsa04960: Aldosterone-regulated sodium reabsorption", "9", "1.45E−05"], ["", "KEGG", "hsa04978: Mineral absorption", "9", "3.69E−05"], ["", "KEGG", "hsa00010: Glycolysis / Gluconeogenesis", "9", "7.57E−04"], ["", "KEGG", "hsa04610: Complement and coagulation cascades", "8", "4.14E−03"], ["", "KEGG", "hsa04966: Collecting duct acid secretion", "7", "1.11E−04"], ["", "KEGG", "hsa00260: Glycine, serine and threonine metabolism", "7", "9.10E−04"], ["", "KEGG", "hsa00280: Valine, leucine and isoleucine degradation", "7", "2.46E−03"]], "row_count": 81, "column_count": 5, "numeric_cells": 240, "header_rows": 1, "locator": "section[11]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:33976979:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b4b87f3e262914ab3128620e87c96130ea04f78929122b0ee376e00f1bdf82e2", "bytes": 837, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table-3", "version": null, "note": "The top 35 DEGs identified with the degree in the PPI network (Degree ≥ 37).", "structure": {"pmcid": "PMC8063882", "section_index": 12, "section_title": "Construction of PPI network and screening of key genes", "row_count": 19, "column_count": 5}, "table": {"label": "Table 3", "caption": "The top 35 DEGs identified with the degree in the PPI network (Degree ≥ 37).", "rows": [["Expression", "Genes", "Degree", "Genes", "Degree"], ["Upregulated", "EGFR", "110", "C3AR1", "52"], ["", "VEGFA", "100", "CYBB", "51"], ["", "PTPRC", "93", "LCP2", "50"], ["", "FN1", "90", "TLR7", "49"], ["", "ITGB2", "70", "C3", "45"], ["", "TLR2", "67", "CCL5", "44"], ["", "MMP9", "66", "TIMP1", "43"], ["", "CD86", "64", "HCK", "43"], ["", "CXCR4", "62", "FCGR2A", "42"], ["", "ICAM1", "62", "CD53", "41"], ["", "CCND1", "61", "CTSS", "41"], ["", "TYROBP", "59", "LAPTM5", "40"], ["", "CSF1R", "58", "LOX", "38"], ["", "PLEK", "55", "SERPINE1", "37"], ["", "ITGAX", "53", "CAV1", "37"], ["Downregulated", "ALB", "134", "KNG1", "52"], ["", "EGF", "80", "KIT", "44"], ["", "ERBB2", "67", "", ""]], "row_count": 19, "column_count": 5, "numeric_cells": 37, "header_rows": 1, "locator": "section[12]/table-wrap[1]#table-3"}}], "gaps": ["asset:data:geo:GSE12606 not downloaded", "asset:data:geo:GSE12606 licence not read", "asset:data:geo:GSE53000 not downloaded", "asset:data:geo:GSE53000 licence not read", "asset:data:geo:GSE66272 not downloaded", "asset:data:geo:GSE66272 licence not read", "asset:data:geo:GSE68417 not downloaded", "asset:data:geo:GSE68417 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"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": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-4", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}, {"id": "method-5", "family": null, "specific": null, "label": "Student’s t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Statistically significant differences between the normal tissues group and tumor tissues group were determined using Student’s t tests."}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE12606", "GSE53000", "GSE68417", "GSE66272"], "resolved_accessions": ["GSE12606", "GSE53000", "GSE68417", "GSE66272"], "statements": ["The following information was supplied regarding data availability:\nThe raw data and code are available in the Supplemental Files."], "basis": "The paper names GSE12606, GSE53000, GSE68417, GSE66272 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": ["survival_km"], "assets": ["source:pmid:33976979", "data:geo:GSE12606", "asset:table:pmid:33976979:1", "asset:table:pmid:33976979:2", "asset:table:pmid:33976979:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12606"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:49Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 40815, "completion_tokens": 1641, "cached_tokens": 784}}, "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:33976979", "type": "paper", "label": "pmid:33976979"}, {"id": "source:pmid:33976979", "type": "manuscript", "label": "PMID 33976979 full text"}, {"id": "data:geo:GSE12606", "type": "dataset", "label": "GEO GSE12606"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33976979", "type": "paper", "label": "pmid:33976979"}, {"id": "source:pmid:33976979", "type": "manuscript", "label": "PMID 33976979 full text"}, {"id": "data:geo:GSE12606", "type": "dataset", "label": "GEO GSE12606"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33976979", "type": "extraction", "used": ["source:pmid:33976979"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12606", "type": "accession_resolution", "used": ["data:geo:GSE12606"], "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:33976979", "parent_hash": "sha256:4bd84225056a2fd1dde27c2e9e3a98544f09dab80246e25d228d1a217c1ac4c2", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE12606 licence not read", "asset:data:geo:GSE12606 not downloaded", "asset:data:geo:GSE53000 licence not read", "asset:data:geo:GSE53000 not downloaded", "asset:data:geo:GSE66272 licence not read", "asset:data:geo:GSE66272 not downloaded", "asset:data:geo:GSE68417 licence not read", "asset:data:geo:GSE68417 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "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":"2026-11-04T04:01:05+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}}}