{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34174849", "kind": "science-record", "revision": 7, "content_hash": "sha256:687ea3ada1826eeae67562b89f21a69bbe9e7a702509014ae59dde88b5c13038", "created_at": "2026-11-01T15:41:40Z", "updated_at": "2026-11-01T22:04:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics analysis of differentially expressed genes and pathways in the development of cervical cancer.", "doi": "10.1186/s12885-021-08412-4", "pmid": "34174849", "authors": ["Baojie Wu", "Shuyi Xi"], "journal": "BMC cancer", "year": 2021, "abstract": "BACKGROUND: This study aimed to explore and identify key genes and signaling pathways that contribute to the progression of cervical cancer to improve prognosis.\nMETHODS: Three gene expression profiles (GSE63514, GSE64217 and GSE138080) were screened and downloaded from the Gene Expression Omnibus database (GEO). Differentially expressed genes (DEGs) were screened using the GEO2R and Venn diagram tools. Then, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed. Gene set enrichment analysis (GSEA) was performed to analyze the three gene expression profiles. Moreover, a protein-protein interaction (PPI) network of the DEGs was constructed, and functional enrichment analysis was performed. On this basis, hub genes from critical PPI subnetworks were explored with Cytoscape software. The expression of these genes in tumors was verified, and survival analysis of potential prognostic genes from critical subnetworks was conducted. Functional annotation, multiple gene comparison and dimensionality reduction in candidate genes indicated the clinical significance of potential targets.\nRESULTS: A total of 476 DEGs were screened: 253 upregulated genes and 223 downregulated genes. DEGs were enriched in 22 biological processes, 16 cellular components and 9 molecular functions in precancerous lesions and cervical cancer. DEGs were mainly enriched in 10 KEGG pathways. Through intersection analysis and data mining, 3 key KEGG pathways and related core genes were revealed by GSEA. Moreover, a PPI network of 476 DEGs was constructed, hub genes from 12 critical subnetworks were explored, and a total of 14 potential molecular targets were obtained.\nCONCLUSIONS: These findings promote the understanding of the molecular mechanism of and clinically related molecular targets for cervical cancer.", "claims": [{"id": "claim-method", "statement": "The GEO2R tool was used to analyze the three expression datasets [6, 7]. Normalization and log2 conversion were carried out for each dataset to filter out the DEGs of the three datasets, and the DEGs are displayed as volcano plots. The filtering conditions were as follows: |log2-fold change| ≥ 1 and adjusted P-value (adj. P) < 0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34174849", "locator": "sections[4] \"Analysis of microarray datasets\" paragraph 2", "quote": "The GEO2R tool was used to analyze the three expression datasets [6, 7]. Normalization and log2 conversion were carried out for each dataset to filter out the DEGs of the three datasets, and the DEGs are displayed as volcano plots. The filtering conditions were as follows: |log2-fold change| ≥ 1 and adjusted P-value (adj. P) < 0.05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34174849", "locator": "sections[25] \"Availability of data and materials\" paragraph 2", "quote": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible."}], "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:34174849"], "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:GSE138080"], "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:GSE138080"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34174849", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-021-08412-4", "sha256": "sha256:7e0bacde1c660c0966dabcbb7ebc05ceee7e72f4dbe03aa2c6563e80f57925e0", "bytes": 49311, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-021-08412-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8236200", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE138080", "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=GSE138080", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE138080", "version": null, "note": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4098861", "GSM4098862", "GSM4098863", "GSM4098864", "GSM4098865", "GSM4098866", "GSM4098867", "GSM4098868", "GSM4098869", "GSM4098870", "GSM4098871", "GSM4098872", "GSM4098873", "GSM4098874", "GSM4098875", "GSM4098876", "GSM4098877", "GSM4098878", "GSM4098879", "GSM4098880", "GSM4098881", "GSM4098882", "GSM4098883", "GSM4098884", "GSM4098885", "GSM4098886", "GSM4098887", "GSM4098888", "GSM4098889", "GSM4098890", "GSM4098891", "GSM4098892", "GSM4098893", "GSM4098894", "GSM4098895"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Identification of deregulated pathways, key regulators, and novel miRNA-mRNA interactions in HPV-mediated transformation. [mRNA tissues-Agilent]", "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:GSE63514", "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=GSE63514", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63514", "version": null, "note": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1551311", "GSM1551312", "GSM1551313", "GSM1551314", "GSM1551315", "GSM1551316", "GSM1551317", "GSM1551318", "GSM1551319", "GSM1551320", "GSM1551321", "GSM1551322", "GSM1551323", "GSM1551324", "GSM1551325", "GSM1551326", "GSM1551327", "GSM1551328", "GSM1551329", "GSM1551330", "GSM1551331", "GSM1551332", "GSM1551333", "GSM1551334", "GSM1551335", "GSM1551336", "GSM1551337", "GSM1551338", "GSM1551339", "GSM1551340", "GSM1551341", "GSM1551342", "GSM1551343", "GSM1551344", "GSM1551345", "GSM1551346", "GSM1551347", "GSM1551348", "GSM1551349", "GSM1551350", "GSM1551351", "GSM1551352", "GSM1551353", "GSM1551354", "GSM1551355", "GSM1551356", "GSM1551357", "GSM1551358", "GSM1551359", "GSM1551360", "GSM1551361", "GSM1551362", "GSM1551363", "GSM1551364", "GSM1551365", "GSM1551366", "GSM1551367", "GSM1551368", "GSM1551369", "GSM1551370", "GSM1551371", "GSM1551372", "GSM1551373", "GSM1551374", "GSM1551375", "GSM1551376", "GSM1551377", "GSM1551378", "GSM1551379", "GSM1551380", "GSM1551381", "GSM1551382", "GSM1551383", "GSM1551384", "GSM1551385", "GSM1551386", "GSM1551387", "GSM1551388", "GSM1551389", "GSM1551390", "GSM1551391", "GSM1551392", "GSM1551393", "GSM1551394", "GSM1551395", "GSM1551396", "GSM1551397", "GSM1551398", "GSM1551399", "GSM1551400", "GSM1551401", "GSM1551402", "GSM1551403", "GSM1551404", "GSM1551405", "GSM1551406", "GSM1551407", "GSM1551408", "GSM1551409", "GSM1551410", "GSM1551411", "GSM1551412", "GSM1551413", "GSM1551414", "GSM1551415", "GSM1551416", "GSM1551417", "GSM1551418", "GSM1551419", "GSM1551420", "GSM1551421", "GSM1551422", "GSM1551423", "GSM1551424", "GSM1551425", "GSM1551426", "GSM1551427", "GSM1551428", "GSM1551429", "GSM1551430", "GSM1551431", "GSM1551432", "GSM1551433", "GSM1551434", "GSM1551435", "GSM1551436", "GSM1551437", "GSM1551438"], "sample_count": 128, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of cervical cancer progression", "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:GSE64217", "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=GSE64217", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE64217", "version": null, "note": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1566485", "GSM1566486", "GSM1566487", "GSM1566488", "GSM1566489", "GSM1566490"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression in Normal Cervical mucosa, Cervical intraepithelial neoplasia and Cervical squamous 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:34174849:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c8908234b26864f2fb5760c379dcdb1699ab37169d304875266022a30e3b61bf", "bytes": 3302, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab3", "version": null, "note": "Functional analysis of possible prognostic genes for the progression of cervical cancer", "structure": {"pmcid": "PMC8236200", "section_index": 9, "section_title": "Expression and prognostic value of hub genes", "row_count": 15, "column_count": 2}, "table": {"label": "Table 3", "caption": "Functional analysis of possible prognostic genes for the progression of cervical cancer", "rows": [["Gene", "Function"], ["MCM2", "Minichromosome maintenance complex component 2. MCM2 is involved in the initiation of eukaryotic genome replication. It may be involved in the formation of replication forks and in the recruitment of other DNA replication-related proteins, and it regulates the helicase activity of the complex."], ["TOP2A", "DNA topoisomerase II a. These findings might provide target genes for the prognosis and treatment of cervical carcinoma. TOP2A controls and alters the topologic state of DNA during transcription. This nuclear enzyme is involved in processes such as chromosome condensation, chromatid separation, and the relief of torsional stress that occurs during DNA transcription and replication."], ["BLM", "BLM RecQ-like helicase. This Bloom-associated helicase unwinds a variety of DNA substrates including Holliday junctions and is involved in several pathways contributing to the maintenance of genome stability."], ["RMI2", "RecQ-mediated genome instability 2. RMI2 plays a role in homologous recombination-dependent DNA repair and is essential for genome stability."], ["EXO1", "Exonuclease 1. EXO1, with 5′ to 3′ exonuclease activity as well as RNase H activity, interacts with Msh2, which is involved in mismatch repair and recombination."], ["RFC4", "Replication factor C subunit 4. The elongation of primed DNA templates by DNA polymerase delta and DNA polymerase epsilon requires the accessory proteins proliferating cell nuclear antigen (PCNA) and replication factor C (RFC)."], ["PSCA", "Prostate stem cell antigen. PSCA is highly expressed in the prostate and also expressed in the bladder, placenta, colon, kidney, and stomach. This gene is upregulated in a large proportion of prostate cancers and is also detected in cancers of the bladder and pancreas."], ["KNTC1", "Kinetochore-associated 1. KNTC1 ensures proper chromosome segregation during cell division."], ["CDC45", "Cell division cycle 45. CDC45, an essential protein required for the initiation of DNA replication, is important for the early steps of DNA replication in eukaryotes."], ["GINS2", "GINS complex subunit 2. The GINS complex is essential for the initiation of DNA replication."], ["CXCL8", "C-X-C motif chemokine ligand 8. CXC is a major mediator of the inflammatory response. This protein is also secreted by tumor cells and promotes tumor migration, invasion, angiogenesis and metastasis. This chemokine is also a potent angiogenic factor."], ["TNFAIP6", "TNF alpha-induced protein 6. TNFAIP6 is a member of the hyaluronan-binding protein family. Its hyaluronan-binding domain is involved in extracellular matrix stability and cell migration. This protein is important in the protease network associated with inflammation."], ["CXCL5", "C-X-C motif chemokine ligand 5. Chemokines, which recruit and activate leukocytes, promote angiogenesis and remodel connective tissues. It plays a role in cancer cell proliferation, migration, and invasion."], ["CDA", "Cytidine deaminase. CDA is one of several deaminases responsible for maintaining the cellular pyrimidine pool."]], "row_count": 15, "column_count": 2, "numeric_cells": 11, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:34174849:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:feaba612f1c3de5112c99ab3aeb84e89c2581f8f4606b8b1ec542b0443248cff", "bytes": 755, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab1", "version": null, "note": "KEGG pathway enrichment analysis of DEGs (DAVID)", "structure": {"pmcid": "PMC8236200", "section_index": 12, "section_title": "GO and KEGG pathway enrichment analyses", "row_count": 11, "column_count": 3}, "table": {"label": "Table 1", "caption": "KEGG pathway enrichment analysis of DEGs (DAVID)", "rows": [["Term", "Count", "P-value"], ["hsa04110: Cell cycle", "14", "7.05E-07"], ["hsa03030: DNA replication", "7", "5.88E-05"], ["hsa05323: Rheumatoid arthritis", "8", "0.001555896"], ["hsa04115: p53 signaling pathway", "7", "0.001840686"], ["hsa05219: Bladder cancer", "5", "0.007981073"], ["hsa04610: Complement and coagulation cascades", "6", "0.01080063"], ["hsa05146: Amoebiasis", "7", "0.017024795"], ["hsa04060: Cytokine-cytokine receptor interaction", "11", "0.019861501"], ["hsa04114: Oocyte meiosis", "7", "0.020898334"], ["hsa00590: Arachidonic acid metabolism", "5", "0.030571729"]], "row_count": 11, "column_count": 3, "numeric_cells": 30, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:34174849:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d4185f1867a38264eaeb7505bd971d8a813236f43c1f145fb5ac6386abe3d3e8", "bytes": 1227, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab2", "version": null, "note": "Discovering regions closely related to the PPI network (MCODE)", "structure": {"pmcid": "PMC8236200", "section_index": 14, "section_title": "PPI network construction and hub genes of cervical lesions", "row_count": 13, "column_count": 5}, "table": {"label": "Table 2", "caption": "Discovering regions closely related to the PPI network (MCODE)", "rows": [["Cluster", "Score (Density*#Nodes)", "Nodes", "Edges", "Genes"], ["1", "21.478", "24", "247", "TOP2A, KIF15, PRC1, SPAG5, KIF11, BIRC5, KIF23, MELK, DLGAP5, KIF2C, NUF2, MKI67, CENPE, NDC80, NEK2, AURKA, ASPM, CENPF, KIF20A, CDK1, TTK, CEP55, NUSAP1, KIF4A"], ["2", "16.625", "17", "133", "RPTN, SPRR1B, SPRR2E, SPRR2D, LCE3D, DSC2, SPRR2B, DSG1, PI3, TGM1, CSTA, IVL, LOR, FLG, SPRR3, SPRR1A, PPL"], ["3", "9.111", "10", "41", "CHEK1, MCM4, CDC45, MCM10, PRIM1, CDC7, CDT1, CDK2, POLE2, MCM8"], ["4", "8", "8", "28", "CRISP3, PRSS3, HP, LRG1, CSTB, TCN1, TNFAIP6, CDA"], ["5", "6", "6", "15", "SGOL2, CENPN, CASC5, CENPK, CDCA5, KNTC1"], ["6", "6", "6", "15", "KRT78, KRT2, KRT13, KRT1, KRT16, KRT4"], ["7", "6", "6", "15", "CXCR2, CXCR4, CXCL9, CXCL5, CXCL8, CXCL10"], ["8", "6", "6", "15", "LY6G6C, CEACAM7, PSCA, CEACAM5, LYPD3, LY6D"], ["9", "4", "4", "6", "RFC4, EXO1, TIPIN, RFC3"], ["10", "4", "4", "6", "PRSS3P2, SERPINB3, FABP5, S100A7"], ["11", "3.429", "8", "12", "DNA2, WDHD1, GINS2, DTL, RMI2, CDC6, BLM, MCM2"], ["12", "3", "3", "3", "ALOX12B, ALOX12, ALOX15B"]], "row_count": 13, "column_count": 5, "numeric_cells": 54, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:34174849:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c8908234b26864f2fb5760c379dcdb1699ab37169d304875266022a30e3b61bf", "bytes": 3302, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab3", "version": null, "note": "Functional analysis of possible prognostic genes for the progression of cervical cancer", "structure": {"pmcid": "PMC8236200", "section_index": 15, "section_title": "Expression and prognostic value of hub genes", "row_count": 15, "column_count": 2}, "table": {"label": "Table 3", "caption": "Functional analysis of possible prognostic genes for the progression of cervical cancer", "rows": [["Gene", "Function"], ["MCM2", "Minichromosome maintenance complex component 2. MCM2 is involved in the initiation of eukaryotic genome replication. It may be involved in the formation of replication forks and in the recruitment of other DNA replication-related proteins, and it regulates the helicase activity of the complex."], ["TOP2A", "DNA topoisomerase II a. These findings might provide target genes for the prognosis and treatment of cervical carcinoma. TOP2A controls and alters the topologic state of DNA during transcription. This nuclear enzyme is involved in processes such as chromosome condensation, chromatid separation, and the relief of torsional stress that occurs during DNA transcription and replication."], ["BLM", "BLM RecQ-like helicase. This Bloom-associated helicase unwinds a variety of DNA substrates including Holliday junctions and is involved in several pathways contributing to the maintenance of genome stability."], ["RMI2", "RecQ-mediated genome instability 2. RMI2 plays a role in homologous recombination-dependent DNA repair and is essential for genome stability."], ["EXO1", "Exonuclease 1. EXO1, with 5′ to 3′ exonuclease activity as well as RNase H activity, interacts with Msh2, which is involved in mismatch repair and recombination."], ["RFC4", "Replication factor C subunit 4. The elongation of primed DNA templates by DNA polymerase delta and DNA polymerase epsilon requires the accessory proteins proliferating cell nuclear antigen (PCNA) and replication factor C (RFC)."], ["PSCA", "Prostate stem cell antigen. PSCA is highly expressed in the prostate and also expressed in the bladder, placenta, colon, kidney, and stomach. This gene is upregulated in a large proportion of prostate cancers and is also detected in cancers of the bladder and pancreas."], ["KNTC1", "Kinetochore-associated 1. KNTC1 ensures proper chromosome segregation during cell division."], ["CDC45", "Cell division cycle 45. CDC45, an essential protein required for the initiation of DNA replication, is important for the early steps of DNA replication in eukaryotes."], ["GINS2", "GINS complex subunit 2. The GINS complex is essential for the initiation of DNA replication."], ["CXCL8", "C-X-C motif chemokine ligand 8. CXC is a major mediator of the inflammatory response. This protein is also secreted by tumor cells and promotes tumor migration, invasion, angiogenesis and metastasis. This chemokine is also a potent angiogenic factor."], ["TNFAIP6", "TNF alpha-induced protein 6. TNFAIP6 is a member of the hyaluronan-binding protein family. Its hyaluronan-binding domain is involved in extracellular matrix stability and cell migration. This protein is important in the protease network associated with inflammation."], ["CXCL5", "C-X-C motif chemokine ligand 5. Chemokines, which recruit and activate leukocytes, promote angiogenesis and remodel connective tissues. It plays a role in cancer cell proliferation, migration, and invasion."], ["CDA", "Cytidine deaminase. CDA is one of several deaminases responsible for maintaining the cellular pyrimidine pool."]], "row_count": 15, "column_count": 2, "numeric_cells": 11, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE138080 not downloaded", "asset:data:geo:GSE138080 licence not read", "asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE64217 not downloaded", "asset:data:geo:GSE64217 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The GEO2R tool was used to analyze the three expression datasets [6, 7]. Normalization and log2 conversion were carried out for each dataset to filter out the DEGs of the three datasets, and the DEGs are displayed as volcano plots. The filtering conditions were as follows: |log2-fold change| ≥ 1 and adjusted P-value (adj. P) < 0.05."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE63514", "GSE64217", "GSE138080"], "resolved_accessions": ["GSE63514", "GSE64217", "GSE138080"], "statements": ["The raw data of the three microarray datasets (accession numbers GSE63514, GSE64217 and GSE138080) were downloaded from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/). All data are publicly accessible."], "basis": "The paper names GSE63514, GSE64217, GSE138080 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:34174849", "data:geo:GSE138080", "asset:table:pmid:34174849:1", "asset:table:pmid:34174849:2", "asset:table:pmid:34174849:3", "asset:table:pmid:34174849:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE138080"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 41145, "completion_tokens": 1433, "cached_tokens": 13960}}, "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:34174849", "type": "paper", "label": "pmid:34174849"}, {"id": "source:pmid:34174849", "type": "manuscript", "label": "PMID 34174849 full text"}, {"id": "data:geo:GSE138080", "type": "dataset", "label": "GEO GSE138080"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34174849", "type": "paper", "label": "pmid:34174849"}, {"id": "source:pmid:34174849", "type": "manuscript", "label": "PMID 34174849 full text"}, {"id": "data:geo:GSE138080", "type": "dataset", "label": "GEO GSE138080"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34174849", "type": "extraction", "used": ["source:pmid:34174849"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE138080", "type": "accession_resolution", "used": ["data:geo:GSE138080"], "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:34174849", "parent_hash": "sha256:86b83da1f8ccdf0e30a4aaa3a27507512e221cab851268cc1ab6161199fb7015", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE138080 licence not read", "asset:data:geo:GSE138080 not downloaded", "asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE64217 licence not read", "asset:data:geo:GSE64217 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["20/11/27” [PDAT])). Three expression profile microarray datasets (GSE63514, GSE64217 and GSE138080)", "platform (Agilent-014850 Whole Human Genome Microarray 4x44K G4112F) and contains samples of normal", "ithelium, CIN and CESC. Samples of the three microarray expression profiling datasets were classifie", "chart of the integrated analysis Analysis of microarray datasets According to the progression of cer"], "order_basis": "paper_text_order:2501", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:16:45+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}}}