{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34126961", "kind": "science-record", "revision": 8, "content_hash": "sha256:875fbca223803b0ec55398b346b082a3123fdfd335b2baa9303e3cfc242dc85c", "created_at": "2026-11-01T15:41:38Z", "updated_at": "2026-11-01T22:46:51Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of novel hub genes associated with gastric cancer using integrated bioinformatics analysis.", "doi": "10.1186/s12885-021-08358-7", "pmid": "34126961", "authors": ["Xiao-Qing Lu", "Jia-Qian Zhang", "Sheng-Xiao Zhang", "Jun Qiao", "Meng-Ting Qiu", "Xiang-Rong Liu", "Xiao-Xia Chen", "Chong Gao", "Huan-Hu Zhang"], "journal": "BMC cancer", "year": 2021, "abstract": "BACKGROUND: Gastric cancer (GC) is one of the most common solid malignant tumors worldwide with a high-recurrence-rate. Identifying the molecular signatures and specific biomarkers of GC might provide novel clues for GC prognosis and targeted therapy.\nMETHODS: Gene expression profiles were obtained from the ArrayExpress and Gene Expression Omnibus database. Differentially expressed genes (DEGs) were picked out by R software. The hub genes were screened by cytohubba plugin. Their prognostic values were assessed by Kaplan-Meier survival analyses and the gene expression profiling interactive analysis (GEPIA). Finally, qRT-PCR in GC tissue samples was established to validate these DEGs.\nRESULTS: Total of 295 DEGs were identified between GC and their corresponding normal adjacent tissue samples in E-MTAB-1440, GSE79973, GSE19826, GSE13911, GSE27342, GSE33335 and GSE56807 datasets, including 117 up-regulated and 178 down-regulated genes. Among them, 7 vital upregulated genes (HMMR, SPP1, FN1, CCNB1, CXCL8, MAD2L1 and CCNA2) were selected. Most of them had a significantly worse prognosis except SPP1. Using qRT-PCR, we validated that their transcriptions in our GC tumor tissue were upregulated except SPP1 and FN1, which correlated with tumor relapse and predicts poorer prognosis in GC patients.\nCONCLUSIONS: We have identified 5 upregulated DEGs (HMMR, CCNB1, CXCL8, MAD2L1, and CCNA2) in GC patients with poor prognosis using integrated bioinformatical methods, which could be potential biomarkers and therapeutic targets for GC treatment.", "claims": [{"id": "claim-method", "statement": "Then the statistically significant DEGs was selected by Moderated T statistic approach with “limma [8]” and “oligo [9]” package of Bioconductor. The resulting P values were adjusted by the default Benjamini & Hochberg (BH) false discovery rate method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34126961", "locator": "sections[5] \"Data processing of DEGs\" paragraph 2", "quote": "Then the statistically significant DEGs was selected by Moderated T statistic approach with “limma [8]” and “oligo [9]” package of Bioconductor."}, {"asset": "source:pmid:34126961", "locator": "sections[5] \"Data processing of DEGs\" paragraph 2", "quote": "The resulting P values were adjusted by the default Benjamini & Hochberg (BH) false discovery rate method."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during this study are included in this published article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34126961", "locator": "sections[29] \"notes\" paragraph 1", "quote": "All data generated or analyzed during this study are included in this published article."}], "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:34126961"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:E-MTAB-1440"], "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": {"fdr_threshold": "with Benjamini–Hochberg false discovery rate adjustment"}, "inputs": ["data:geo:E-MTAB-1440"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34126961", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-021-08358-7", "sha256": "sha256:526275db2cd052e64eba467a35b1c65f9231ee20e24dda3abb21f3797de827a4", "bytes": 38335, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-021-08358-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8201699", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-1440", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=E-MTAB-1440", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-1440", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE13911", "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=GSE13911", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13911", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM350411", "GSM350412", "GSM350413", "GSM350414", "GSM350415", "GSM350416", "GSM350417", "GSM350418", "GSM350419", "GSM350420", "GSM350421", "GSM350422", "GSM350423", "GSM350424", "GSM350425", "GSM350426", "GSM350427", "GSM350428", "GSM350429", "GSM350430", "GSM350431", "GSM350432", "GSM350433", "GSM350434", "GSM350435", "GSM350436", "GSM350437", "GSM350438", "GSM350439", "GSM350440", "GSM350441", "GSM350442", "GSM350443", "GSM350444", "GSM350445", "GSM350446", "GSM350447", "GSM350448", "GSM350449", "GSM350450", "GSM350451", "GSM350452", "GSM350453", "GSM350454", "GSM350455", "GSM350456", "GSM350457", "GSM350458", "GSM350459", "GSM350460", "GSM350461", "GSM350462", "GSM350463", "GSM350464", "GSM350465", "GSM350466", "GSM350467", "GSM350468", "GSM350469", "GSM350470", "GSM350471", "GSM350472", "GSM350473", "GSM350474", "GSM350475", "GSM350476", "GSM350477", "GSM350478", "GSM350479"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from primary gastric tumors (MSI and MSS) and adjacent normal samples", "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:GSE19826", "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=GSE19826", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19826", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM495051", "GSM495052", "GSM495053", "GSM495054", "GSM495055", "GSM495056", "GSM495057", "GSM495058", "GSM495059", "GSM495060", "GSM495061", "GSM495062", "GSM495063", "GSM495064", "GSM495065", "GSM495066", "GSM495067", "GSM495068", "GSM495069", "GSM495070", "GSM495071", "GSM495072", "GSM495073", "GSM495074", "GSM495075", "GSM495076", "GSM495077"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from gastric cancer", "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:GSE27342", "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=GSE27342", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27342", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM675890", "GSM675891", "GSM675892", "GSM675893", "GSM675894", "GSM675895", "GSM675896", "GSM675897", "GSM675898", "GSM675899", "GSM675900", "GSM675901", "GSM675902", "GSM675903", "GSM675904", "GSM675905", "GSM675906", "GSM675907", "GSM675908", "GSM675909", "GSM675910", "GSM675911", "GSM675912", "GSM675913", "GSM675914", "GSM675915", "GSM675916", "GSM675917", "GSM675918", "GSM675919", "GSM675920", "GSM675921", "GSM675922", "GSM675923", "GSM675924", "GSM675925", "GSM675926", "GSM675927", "GSM675928", "GSM675929", "GSM675930", "GSM675931", "GSM675932", "GSM675933", "GSM675934", "GSM675935", "GSM675936", "GSM675937", "GSM675938", "GSM675939", "GSM675940", "GSM675941", "GSM675942", "GSM675943", "GSM675944", "GSM675945", "GSM675946", "GSM675947", "GSM675948", "GSM675949", "GSM675950", "GSM675951", "GSM675952", "GSM675953", "GSM675954", "GSM675955", "GSM675956", "GSM675957", "GSM675958", "GSM675959", "GSM675960", "GSM675961", "GSM675962", "GSM675963", "GSM675964", "GSM675965", "GSM675966", "GSM675967", "GSM675968", "GSM675969", "GSM675970", "GSM675971", "GSM675972", "GSM675973", "GSM675974", "GSM675975", "GSM675976", "GSM675977", "GSM675978", "GSM675979", "GSM675980", "GSM675981", "GSM675982", "GSM675983", "GSM675984", "GSM675985", "GSM675986", "GSM675987", "GSM675988", "GSM675989", "GSM675990", "GSM675991", "GSM675992", "GSM675993", "GSM675994", "GSM675995", "GSM675996", "GSM675997", "GSM675998", "GSM675999", "GSM676000", "GSM676001", "GSM676002", "GSM676003", "GSM676004", "GSM676005", "GSM676006", "GSM676007", "GSM676008", "GSM676009", "GSM676010", "GSM676011", "GSM676012", "GSM676013", "GSM676014", "GSM676015", "GSM676016", "GSM676017", "GSM676018", "GSM676019", "GSM676020", "GSM676021", "GSM676022", "GSM676023", "GSM676024", "GSM676025", "GSM676026", "GSM676027", "GSM676028", "GSM676029", "GSM676030", "GSM676031", "GSM676032", "GSM676033", "GSM676034", "GSM676035", "GSM676036", "GSM676037", "GSM676038", "GSM676039", "GSM676040", "GSM676041", "GSM676042", "GSM676043", "GSM676044", "GSM676045", "GSM676046", "GSM676047", "GSM676048", "GSM676049"], "sample_count": 160, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Transcriptome analysis on gastric cancer", "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:GSE33335", "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=GSE33335", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33335", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM824327", "GSM824328", "GSM824329", "GSM824330", "GSM824331", "GSM824332", "GSM824333", "GSM824334", "GSM824335", "GSM824336", "GSM824337", "GSM824338", "GSM824339", "GSM824340", "GSM824341", "GSM824342", "GSM824343", "GSM824344", "GSM824345", "GSM824346", "GSM824347", "GSM824348", "GSM824349", "GSM824350", "GSM824351", "GSM824352", "GSM824353", "GSM824354", "GSM824355", "GSM824356", "GSM824357", "GSM824358", "GSM824359", "GSM824360", "GSM824361", "GSM824362", "GSM824363", "GSM824364", "GSM824365", "GSM824366", "GSM824367", "GSM824368", "GSM824369", "GSM824370", "GSM824371", "GSM824372", "GSM824373", "GSM824374", "GSM824375", "GSM824376"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Expression data from gastric tissues: Cancer Samples vs. Matched Adjacent Noncancerous Samples", "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:GSE56807", "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=GSE56807", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE56807", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1369632", "GSM1369633", "GSM1369634", "GSM1369635", "GSM1369636", "GSM1369637", "GSM1369638", "GSM1369639", "GSM1369640", "GSM1369641"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Expression data from 5 paired of gastric cancer tissues and gastric normal tissues", "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:GSE79973", "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=GSE79973", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE79973", "version": null, "note": "All data generated or analyzed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2109532", "GSM2109533", "GSM2109534", "GSM2109535", "GSM2109536", "GSM2109537", "GSM2109538", "GSM2109539", "GSM2109540", "GSM2109541", "GSM2109542", "GSM2109543", "GSM2109544", "GSM2109545", "GSM2109546", "GSM2109547", "GSM2109548", "GSM2109549", "GSM2109550", "GSM2109551"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from gastric cancer and paried normal tissues", "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:34126961:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fafcef4df465a40adfb23443cee1dcc799392d81a87fbe37470fe96c63328a96", "bytes": 691, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "Primer sequences of PCR", "structure": {"pmcid": "PMC8201699", "section_index": 10, "section_title": "Validation of selected DEGs’ transcription in fresh GC tissue specimens using quantitative real-time PCR", "row_count": 9, "column_count": 3}, "table": {"label": "Table 1", "caption": "Primer sequences of PCR", "rows": [["gene", "Forward primer(5–3)", "Reverse primer(5–3)"], ["HMMR", "GCTAAGCAAGAAGGCATGGA", "CCACTTGATCTGAAGCACAAC"], ["SPP1", "GCCGAGGTGATAGTGTGGTT", "AACGGGGATGGCCTTGTATG"], ["FN1", "AATAGATGCAACGATCAGGACA", "GCAGGTTTCCTCGATTATCCTT"], ["CCNB1", "GACTTTGCTTTTGTGACTGACA", "CCCAGACCAAAGTTTAAAGCTC"], ["CXCL8", "AACTGAGAGTGATTGAGAGTGG", "ATGAATTCTCAGCCCTCTTCAA"], ["MAD2L1", "ACGGTGACATTTCTGCCACT", "TGGTCCCGACTCTTCCCATT"], ["CCNA2", "AGAAACAGCCAGACATCACTAA", "TTCAAACTTTGAGGCTAACAGC"], ["GAPDH", "ACAGTCAGCCGCATCTTCTT", "ACGACCAAATCCGTTGACTC"]], "row_count": 9, "column_count": 3, "numeric_cells": 2, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:34126961:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ac153d28342e87083d5d90f42ae7c976f83262e1f5e87f63fb86d9374ed59615", "bytes": 1614, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab2", "version": null, "note": "Details of seven selected genes", "structure": {"pmcid": "PMC8201699", "section_index": 15, "section_title": "Identification of the selected genes", "row_count": 8, "column_count": 4}, "table": {"label": "Table 2", "caption": "Details of seven selected genes", "rows": [["N", "Gene symbol", "Full name", "Function"], ["1", "HMMR", "hyaluronan mediated motility receptor", "the driver of tumor progression, plays a important role in the modulation of motor activities and the maintenance of genome stability."], ["2", "SPP1", "secreted phosphoprotein 1", "The protein encoded by this gene is involved in the attachment of osteoclasts to the mineralized bone matrix"], ["3", "FN1", "fibronectin 1", "Fibronectin 1 (FN1) is involved in cell adhesion and migration processes including embryogenesis, wound healing, blood coagulation, host defense, metastasis, and implicated in various biochemical processes."], ["4", "CCNB1", "cyclin B1", "an important regulator in cell cycle machinery, is a monitoring protein in mitosis and expressed primarily in G2/M phase which is critical for controlling the cell cycle at the G2/M (mitosis) transition"], ["5", "CXCL8", "C-X-C motif chemokine ligand 8", "a chemokine that acts as an important multifunctional cytokine to modulate tumour proliferation, invasion and migration in an autocrine or paracrine manner."], ["6", "MAD2L1", "mitotic arrest deficient 2 like 1", "a component of the mitotic spindle assembly checkpoint that prevents the onset of anaphase until all chromosomes are properly aligned at the metaphase plate"], ["7", "CCNA2", "cyclin A2", "The protein encoded by this gene belongs to the highly conserved cyclin family, whose members function as regulators of the cell cycle."]], "row_count": 8, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:34126961:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:417fba7045466501ae80dad9a3e487634cf2c7c1b6a6f729c9391b54a3a4a073", "bytes": 3090, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab3", "version": null, "note": "Analysis of 7 selected genes by GO and KEGG pathway enrichment. FDR, false discovery rate. GO, gene ontology; BP, biological process, CC, cellular component; MF, molecular function; KEGG, Kyoto Encyclopedia of Genes and Genomes; DEMs, differentially expressed miRNAs", "structure": {"pmcid": "PMC8201699", "section_index": 18, "section_title": "Analysis of 7 selected genes via gene ontology and pathway enrichment", "row_count": 22, "column_count": 7}, "table": {"label": "Table 3", "caption": "Analysis of 7 selected genes by GO and KEGG pathway enrichment. FDR, false discovery rate. GO, gene ontology; BP, biological process, CC, cellular component; MF, molecular function; KEGG, Kyoto Encyclopedia of Genes and Genomes; DEMs, differentially expressed miRNAs", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "FDR"], ["GOTERM_BP_DIRECT", "GO:0048146 ~ positive regulation of fibroblast proliferation", "3", "0.263", "1.51E-04", "CCNB1, CCNA2, FN1", "0.174735"], ["GOTERM_BP_DIRECT", "GO:0051301 ~ cell division", "3", "0.263", "0.006147477", "CCNB1, MAD2L1, CCNA2", "6.892135"], ["GOTERM_BP_DIRECT", "GO:0051436 ~ negative regulation of ubiquitin-protein ligase activity involved in mitotic cell cycle", "2", "0.175", "0.025106263", "CCNB1, MAD2L1", "25.50655"], ["GOTERM_BP_DIRECT", "GO:0051437 ~ positive regulation of ubiquitin-protein ligase activity involved in regulation of mitotic cell cycle transition", "2", "0.175", "0.026854324", "CCNB1, MAD2L1", "27.03882"], ["GOTERM_BP_DIRECT", "GO:0022617 ~ extracellular matrix disassembly", "2", "0.175", "0.026854324", "SPP1, FN1", "27.03882"], ["GOTERM_BP_DIRECT", "GO:0031145 ~ anaphase-promoting complex-dependent catabolic process", "2", "0.175", "0.027901906", "CCNB1, MAD2L1", "27.94322"], ["GOTERM_BP_DIRECT", "GO:0071456 ~ cellular response to hypoxia", "2", "0.175", "0.033820471", "CCNB1, CCNA2", "32.86331"], ["GOTERM_BP_DIRECT", "GO:0000086 ~ G2/M transition of mitotic cell cycle", "2", "0.175", "0.047971221", "CCNB1, HMMR", "43.40814"], ["GOTERM_BP_DIRECT", "GO:0042787 ~ protein ubiquitination involved in ubiquitin-dependent protein catabolic process", "2", "0.175", "0.053446406", "CCNB1, MAD2L1", "47.06463"], ["GOTERM_BP_DIRECT", "GO:0030198 ~ extracellular matrix organization", "2", "0.175", "0.068031098", "SPP1, FN1", "55.77698"], ["GOTERM_BP_DIRECT", "GO:0001525 ~ angiogenesis", "2", "0.175", "0.077092848", "CXCL8, FN1", "60.50819"], ["GOTERM_CC_DIRECT", "GO:0000922 ~ spindle pole", "2", "0.175", "0.035359174", "CCNB1, MAD2L1", "26.96429"], ["GOTERM_CC_DIRECT", "GO:0005615 ~ extracellular space", "3", "0.263", "0.067058677", "CXCL8, SPP1, FN1", "45.44016"], ["GOTERM_CC_DIRECT", "GO:0005576 ~ extracellular region", "3", "0.263", "0.092078284", "CXCL8, SPP1, FN1", "56.9647"], ["GOTERM_MF_DIRECT", "GO:0005515 ~ protein binding", "7", "0.613", "0.019847501", "CCNB1, MAD2L1, CXCL8, CCNA2, SPP1, FN1, HMMR", "13.51086"], ["KEGG_PATHWAY", "hsa04512:ECM-receptor interaction", "3", "0.263", "0.002294922", "SPP1, FN1, HMMR", "2.054976"], ["KEGG_PATHWAY", "hsa04914:Progesterone-mediated oocyte maturation", "3", "0.263", "0.002294922", "CCNB1, MAD2L1, CCNA2", "2.054976"], ["KEGG_PATHWAY", "hsa04110:Cell cycle", "3", "0.263", "0.004611117", "CCNB1, MAD2L1, CCNA2", "4.090835"], ["KEGG_PATHWAY", "hsa05146:Amoebiasis", "2", "0.175", "0.088997082", "CXCL8, FN1", "56.93087"], ["KEGG_PATHWAY", "hsa04620:Toll-like receptor signaling pathway", "2", "0.175", "0.088997082", "CXCL8, SPP1", "56.93087"], ["KEGG_PATHWAY", "hsa04114:Oocyte meiosis", "2", "0.175", "0.093026279", "CCNB1, MAD2L1", "58.62208"]], "row_count": 22, "column_count": 7, "numeric_cells": 105, "header_rows": 1, "locator": "section[18]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:E-MTAB-1440 not downloaded", "asset:data:geo:E-MTAB-1440 licence not read", "asset:data:geo:GSE13911 not downloaded", "asset:data:geo:GSE13911 licence not read", "asset:data:geo:GSE19826 not downloaded", "asset:data:geo:GSE19826 licence not read", "asset:data:geo:GSE27342 not downloaded", "asset:data:geo:GSE27342 licence not read", "asset:data:geo:GSE33335 not downloaded", "asset:data:geo:GSE33335 licence not read", "asset:data:geo:GSE56807 not downloaded", "asset:data:geo:GSE56807 licence not read", "asset:data:geo:GSE79973 not downloaded", "asset:data:geo:GSE79973 licence not read"]}, "analysis": {"state": "partial", "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": {"fdr_threshold": "with Benjamini–Hochberg false discovery rate adjustment"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "reordered", "quote": "Then the statistically significant DEGs was selected by Moderated T statistic approach with “limma [8]” and “oligo [9]” package of Bioconductor. The resulting P values were adjusted by the default Benjamini & Hochberg (BH) false discovery rate method."}}, {"id": "method-2", "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-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"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["E-MTAB-1440", "GSE79973", "GSE19826", "GSE13911", "GSE27342", "GSE33335", "GSE56807"], "resolved_accessions": ["E-MTAB-1440", "GSE79973", "GSE19826", "GSE13911", "GSE27342", "GSE33335", "GSE56807"], "statements": ["All data generated or analyzed during this study are included in this published article."], "basis": "The paper names E-MTAB-1440, GSE79973, GSE19826, GSE13911, GSE27342, GSE33335, GSE56807 in Arrayexpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:34126961", "data:geo:E-MTAB-1440", "asset:table:pmid:34126961:1", "asset:table:pmid:34126961:2", "asset:table:pmid:34126961:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-1440"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:03Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29409, "completion_tokens": 2530, "cached_tokens": 776}}, "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:34126961", "type": "paper", "label": "pmid:34126961"}, {"id": "source:pmid:34126961", "type": "manuscript", "label": "PMID 34126961 full text"}, {"id": "data:geo:E-MTAB-1440", "type": "dataset", "label": "GEO E-MTAB-1440"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34126961", "type": "paper", "label": "pmid:34126961"}, {"id": "source:pmid:34126961", "type": "manuscript", "label": "PMID 34126961 full text"}, {"id": "data:geo:E-MTAB-1440", "type": "dataset", "label": "GEO E-MTAB-1440"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34126961", "type": "extraction", "used": ["source:pmid:34126961"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-1440", "type": "accession_resolution", "used": ["data:geo:E-MTAB-1440"], "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:34126961", "parent_hash": "sha256:4d8a86e20fdc2835ef0e1cb38a534b3fb2a8b5078fe843c188036b52e888dad4", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:E-MTAB-1440 licence not read", "asset:data:geo:E-MTAB-1440 not downloaded", "asset:data:geo:GSE13911 licence not read", "asset:data:geo:GSE13911 not downloaded", "asset:data:geo:GSE19826 licence not read", "asset:data:geo:GSE19826 not downloaded", "asset:data:geo:GSE27342 licence not read", "asset:data:geo:GSE27342 not downloaded", "asset:data:geo:GSE33335 licence not read", "asset:data:geo:GSE33335 not downloaded", "asset:data:geo:GSE56807 licence not read", "asset:data:geo:GSE56807 not downloaded", "asset:data:geo:GSE79973 licence not read", "asset:data:geo:GSE79973 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": ["bioconductor.org/) in R (version 3.6.0). The microarray data were first preprocessed using the RMA ("], "order_basis": "paper_text_order:1836", "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": ["Then the statistically significant DEGs was selected by Moderated T statistic approach with “limma [8]” and “oligo [9]” package of Bioconductor. The resulting P values were adjusted by the default Benjamini & Hochberg (BH) false discovery rate method."], "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":"2026-11-04T03:48:37+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}