{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34266411", "kind": "science-record", "revision": 6, "content_hash": "sha256:9f3d85b96e77f2901451489bc0c3bfe64dbc718818e3b1d4e4ba481c0c4fd01d", "created_at": "2026-11-01T15:41:43Z", "updated_at": "2026-11-01T21:25:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A novel immune-related gene pair prognostic signature for predicting overall survival in bladder cancer.", "doi": "10.1186/s12885-021-08486-0", "pmid": "34266411", "authors": ["Yang Fu", "Shanshan Sun", "Jianbin Bi", "Chuize Kong", "Lei Yin"], "journal": "BMC cancer", "year": 2021, "abstract": "BACKGROUND: Bladder cancer (BC) is the ninth most common malignant tumor. We constructed a risk signature using immune-related gene pairs (IRGPs) to predict the prognosis of BC patients.\nMETHODS: The mRNA transcriptome, simple nucleotide variation and clinical data of BC patients were downloaded from The Cancer Genome Atlas (TCGA) database (TCGA-BLCA). The mRNA transcriptome and clinical data were also extracted from Gene Expression Omnibus (GEO) datasets (GSE31684). A risk signature was built based on the IRGPs. The ability of the signature to predict prognosis was analyzed with survival curves and Cox regression. The relationships between immunological parameters [immune cell infiltration, immune checkpoints, tumor microenvironment (TME) and tumor mutation burden (TMB)] and the risk score were investigated. Finally, gene set enrichment analysis (GSEA) was used to explore molecular mechanisms underlying the risk score.\nRESULTS: The risk signature utilized 30 selected IRGPs. The prognosis of the high-risk group was significantly worse than that of the low-risk group. We used the GSE31684 dataset to validate the signature. Close relationships were found between the risk score and immunological parameters. Finally, GSEA showed that gene sets related to the extracellular matrix (ECM), stromal cells and epithelial-mesenchymal transition (EMT) were enriched in the high-risk group. In the low-risk group, we found a number of immune-related pathways in the enriched pathways and biofunctions.\nCONCLUSIONS: We used a new tool, IRGPs, to build a risk signature to predict the prognosis of BC. By evaluating immune parameters and molecular mechanisms, we gained a better understanding of the mechanisms underlying the risk signature. This signature can also be used as a tool to predict the effect of immunotherapy in patients with BC.", "claims": [{"id": "claim-method", "statement": "Pearson test was used for all correlation analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34266411", "locator": "sections[8] \"Statistical analysis\" paragraph 2", "quote": "Pearson test was used for all correlation analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and/or analyzed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GSE31684 repository, (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31684), and IMvigor210 (http://research-pub.gene.com/IMvigor210CoreBiologies/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34266411", "locator": "sections[21] \"Availability of data and materials\" paragraph 2", "quote": "The datasets generated and/or analyzed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GSE31684 repository, (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31684), and IMvigor210 (http://research-pub.gene.com/IMvigor210CoreBiologies/)."}], "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:34266411"], "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:GSE31684"], "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:GSE31684"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34266411", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-021-08486-0", "sha256": "sha256:d828ef046bc17697ca06d42d3802af3ee56c338d28949acaaab8ca16949722f3", "bytes": 63365, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-021-08486-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8281685", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31684", "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=GSE31684", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31684", "version": null, "note": "The datasets generated and/or analyzed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GSE31684 repository, (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31684), and IMvigor210 (http://research-pub.gene.com/IMvigor210CoreBiologies/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analyzed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GSE31684 repository, (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31684), and IMvigor210 (http://research-pub.gene.com/IMvigor210CoreBiologies/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM786491", "GSM786492", "GSM786493", "GSM786494", "GSM786495", "GSM786496", "GSM786497", "GSM786498", "GSM786499", "GSM786500", "GSM786501", "GSM786502", "GSM786503", "GSM786504", "GSM786505", "GSM786506", "GSM786507", "GSM786508", "GSM786509", "GSM786510", "GSM786511", "GSM786512", "GSM786513", "GSM786514", "GSM786515", "GSM786516", "GSM786517", "GSM786518", "GSM786519", "GSM786520", "GSM786521", "GSM786522", "GSM786523", "GSM786524", "GSM786525", "GSM786526", "GSM786527", "GSM786528", "GSM786529", "GSM786530", "GSM786531", "GSM786532", "GSM786533", "GSM786534", "GSM786535", "GSM786536", "GSM786537", "GSM786538", "GSM786539", "GSM786540", "GSM786541", "GSM786542", "GSM786543", "GSM786544", "GSM786545", "GSM786546", "GSM786547", "GSM786548", "GSM786549", "GSM786550", "GSM786551", "GSM786552", "GSM786553", "GSM786554", "GSM786555", "GSM786556", "GSM786557", "GSM786558", "GSM786559", "GSM786560", "GSM786561", "GSM786562", "GSM786563", "GSM786564", "GSM786565", "GSM786566", "GSM786567", "GSM786568", "GSM786569", "GSM786570", "GSM786571", "GSM786572", "GSM786573", "GSM786574", "GSM786575", "GSM786576", "GSM786577", "GSM786578", "GSM786579", "GSM786580", "GSM786581", "GSM786582", "GSM786583"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Combination of a novel gene expression signature with a clinical nomogram improves the prediction of survival in high-risk bladder 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": "asset:table:pmid:34266411:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b34723120da6f770917b5500eba9373e3f820cf349fc597b14e9529f66db30c4", "bytes": 824, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Characteristics of the patients obtained from the TCGA database and GSE31684", "structure": {"pmcid": "PMC8281685", "section_index": 3, "section_title": "Data acquisition", "row_count": 22, "column_count": 4}, "table": {"label": "Table 1", "caption": "Characteristics of the patients obtained from the TCGA database and GSE31684", "rows": [["Basic information", "", "TCGA (n = 409)", "GSE31684 (n = 72)"], ["Age", "", "69 (median)", "68.015 (median)"], ["Gender", "Female", "106", "55"], ["Male", "303", "17"], ["Grade", "High", "385", "69"], ["Low", "21", "3"], ["Unknow", "3", "–"], ["Stage", "I & II", "132", "14"], ["III & IV", "275", "58"], ["Unknow", "2", "–"], ["T classification", "T1 & T2", "124", "22"], ["T3 & T4", "253", "50"], ["TX", "1", "–"], ["Unknow", "31", "–"], ["N classification", "N0", "237", "44"], ["N1 &N2 & N3", "131", "28"], ["NX", "36", "–"], ["Unknow", "5", "–"], ["M classification", "M0", "194", "41"], ["M1", "11", "31"], ["MX", "202", "–"], ["Unknow", "2", "–"]], "row_count": 22, "column_count": 4, "numeric_cells": 36, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:34266411:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5829f43ce8038bec73e5d114a97b616f79f4a8dbdb5e9aee808cf1f02680ae3f", "bytes": 479, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab2", "version": null, "note": "Characteristics of the patients obtained from the IMvigor210", "structure": {"pmcid": "PMC8281685", "section_index": 3, "section_title": "Data acquisition", "row_count": 11, "column_count": 3}, "table": {"label": "Table 2", "caption": "Characteristics of the patients obtained from the IMvigor210", "rows": [["Basic information", "", "IMvigor210 (n = 348)"], ["Age", "Less than 1 year", "176"], ["1–2 years", "99"], ["More than 2 years", "73"], ["Gender", "Female", "76"], ["Male", "272"], ["Subtype", "I & II", "213"], ["III & IV", "135"], ["Response", "CR/PR", "68"], ["SD/PD", "230"], ["NA", "50"]], "row_count": 11, "column_count": 3, "numeric_cells": 14, "header_rows": 1, "locator": "section[3]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:34266411:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:661576aa452a3793f0a80685208fd56b7d96f5aaa8cced05af96f32120bdd881", "bytes": 2754, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab3", "version": null, "note": "Information on the 30 selected IRGPs", "structure": {"pmcid": "PMC8281685", "section_index": 10, "section_title": "Construction of the IRGP signature", "row_count": 31, "column_count": 5}, "table": {"label": "Table 3", "caption": "Information on the 30 selected IRGPs", "rows": [["Gena pair 1", "Full name", "Gene pair 2", "Full name", "Coefficient"], ["FCER1G", "Fc fragment of IgE receptor Ig", "PLA2G2A", "phospholipase A2 group IIA", "0.115"], ["FCER1G", "Fc fragment of IgE receptor Ig", "SEMA5A", "semaphorin 5A", "0.085"], ["ERAP2", "endoplasmic reticulum aminopeptidase 2", "CXCL13", "C-X-C motif chemokine ligand 13", "0.025"], ["ERAP2", "endoplasmic reticulum aminopeptidase 2", "FAM3B", "FAM3 metabolism regulating signaling molecule B", "0.390"], ["CXCL9", "C-X-C motif chemokine ligand 9", "PTN", "pleiotrophin", "−0.182"], ["CXCL11", "C-X-C motif chemokine ligand 11", "MMP9", "matrix metallopeptidase 9", "−0.334"], ["CXCL6", "C-X-C motif chemokine ligand 6", "DES", "desmin", "−0.055"], ["CXCL12", "C-X-C motif chemokine ligand 12", "IL18", "interleukin 18", "0.210"], ["CXCL12", "C-X-C motif chemokine ligand 12", "C5AR1", "complement C5a receptor 1", "0.128"], ["CXCL13", "C-X-C motif chemokine ligand 13", "DEFB1", "defensin beta 1", "−0.010"], ["CXCL13", "C-X-C motif chemokine ligand 13", "CCL11", "C-C motif chemokine ligand 11", "−0.087"], ["CXCL13", "C-X-C motif chemokine ligand 13", "GREM1", "gremlin 1, DAN family BMP antagonist", "−0.112"], ["CXCL13", "C-X-C motif chemokine ligand 13", "PTN", "pleiotrophin", "−0.254"], ["DEFB1", "defensin beta 1", "TNFSF13B", "TNF superfamily member 13b", "0.183"], ["MMP9", "matrix metallopeptidase 9", "SEMA5A", "semaphorin 5A", "0.164"], ["ISG20", "interferon stimulated exonuclease gene 20", "DKK1", "dickkopf WNT signaling pathway inhibitor 1", "−0.183"], ["DUOX2", "dual oxidase 2", "DES", "desmin", "−0.090"], ["PLA2G2A", "phospholipase A2 group IIA", "CD14", "CD14 molecule", "−0.221"], ["IL18", "interleukin 18", "SEMA5A", "semaphorin 5A", "0.066"], ["IL18", "interleukin 18", "FAM3B", "FAM3 metabolism regulating signaling molecule B", "0.087"], ["IL18", "interleukin 18", "GZMB", "granzyme B", "0.124"], ["PTX3", "pentraxin 3", "IL10RA", "interleukin 10 receptor subunit alpha", "0.173"], ["SEMA6A", "semaphorin 6A", "DKK1", "dickkopf WNT signaling pathway inhibitor 1", "−0.057"], ["C5AR1", "complement C5a receptor 1", "GZMB", "granzyme B", "0.091"], ["DKK1", "dickkopf WNT signaling pathway inhibitor 1", "TNFSF13B", "TNF superfamily member 13b", "0.084"], ["DKK1", "dickkopf WNT signaling pathway inhibitor 1", "VIPR1", "vasoactive intestinal peptide receptor 1", "0.007"], ["DKK1", "dickkopf WNT signaling pathway inhibitor 1", "GZMB", "granzyme B", "0.097"], ["GREM1", "gremlin 1, DAN family BMP antagonist", "GZMB", "granzyme B", "0.082"], ["IL33", "interleukin 33", "GZMB", "granzyme B", "0.009"], ["CSF2RB", "colony stimulating factor 2 receptor subunit beta", "GZMB", "granzyme B", "< 0.001"]], "row_count": 31, "column_count": 5, "numeric_cells": 95, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:34266411:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ff5ad8f42e97a42264dbd555ebe970dd7a78b9f3b8bec6e842eef7545522afa0", "bytes": 766, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#Tab4", "version": null, "note": "Differences in the characteristics of BC patients between the high risk and low risk in TCGA", "structure": {"pmcid": "PMC8281685", "section_index": 10, "section_title": "Construction of the IRGP signature", "row_count": 19, "column_count": 5}, "table": {"label": "Table 4", "caption": "Differences in the characteristics of BC patients between the high risk and low risk in TCGA", "rows": [["Basic information", "", "Low risk", "High risk", "P value"], ["Age", "", "", "", "0.021"], ["", "≤ 69", "138", "75", ""], ["", "> 69", "100", "87", ""], ["Gender", "", "", "", "0.143"], ["", "Female", "55", "48", ""], ["", "Male", "183", "114", ""], ["Stage", "", "", "", "< 0.001"], ["", "I&II", "93", "36", ""], ["", "III&IV", "143", "126", ""], ["T", "", "", "", "0.007"], ["", "T1&T2", "83", "38", ""], ["", "T3&T4", "133", "114", ""], ["N", "", "", "", "0.002"], ["", "N0", "152", "81", ""], ["", "N1–3", "61", "65", ""], ["M", "", "", "", "< 0.001"], ["", "M0", "132", "61", ""], ["", "M1", "2", "9", ""]], "row_count": 19, "column_count": 5, "numeric_cells": 33, "header_rows": 1, "locator": "section[10]/table-wrap[2]#Tab4"}}, {"id": "asset:table:pmid:34266411:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:54cffe6ddea7988eca3ff178299cb459c44460f536971a875a796565acfdd4ca", "bytes": 1641, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab5", "version": null, "note": "Gene sets enriched in the high risk phenotype via GO", "structure": {"pmcid": "PMC8281685", "section_index": 12, "section_title": "GSEA", "row_count": 21, "column_count": 4}, "table": {"label": "Table 5", "caption": "Gene sets enriched in the high risk phenotype via GO", "rows": [["Gene set name", "NES", "NOM p-val", "FDR q-val"], ["GO_CHONDROCYTE_DIFFERENTIATION", "2.459", "< 0.001", "< 0.001"], ["GO_EXTRACELLULAR_MATRIX_STRUCTURAL_CONSTITUENT", "2.444", "< 0.001", "< 0.001"], ["GO_CHONDROCYTE_DEVELOPMENT", "2.400", "< 0.001", "< 0.001"], ["GO_COLLAGEN_CONTAINING_EXTRACELLULAR_MATRIX", "2.389", "< 0.001", "< 0.001"], ["GO_EXTRACELLULAR_STRUCTURE_ORGANIZATION", "2.301", "< 0.001", "0.001"], ["GO_EXTRACELLULAR_MATRIX_COMPONENT", "2.264", "< 0.001", "0.002"], ["GO_COLLAGEN_FIBRIL_ORGANIZATION", "2.253", "< 0.001", "0.002"], ["GO_COLLAGEN_BINDING", "2.250", "< 0.001", "0.002"], ["GO_COLLAGEN_TRIMER", "2.241", "0.002", "0.003"], ["GO_EXTRACELLULAR_MATRIX_STRUCTURAL_CONSTITUENT_CONFERRING_TENSILE_STRENGTH", "2.222", "< 0.001", "0.003"], ["GO_POSITIVE_REGULATION_OF_EPITHELIAL_TO_MESENCHYMAL_TRANSITION", "2.219", "< 0.001", "0.003"], ["GO_REGULATION_OF_CHONDROCYTE_DIFFERENTIATION", "2.175", "< 0.001", "0.005"], ["GO_EXTRACELLULAR_MATRIX_BINDING", "2.105", "< 0.001", "0.011"], ["GO_POSITIVE_REGULATION_OF_FIBROBLAST_PROLIFERATION", "2.042", "< 0.001", "0.018"], ["GO_ENDOTHELIAL_CELL_PROLIFERATION", "1.990", "0.002", "0.024"], ["GO_POSITIVE_REGULATION_OF_ENDOTHELIAL_CELL_PROLIFERATION", "1.942", "0.002", "0.031"], ["GO_ENDOTHELIAL_CELL_MIGRATION", "1.881", "0.006", "0.040"], ["GO_REGULATION_OF_ENDOTHELIAL_CELL_MIGRATION", "1.833", "0.006", "0.049"], ["GO_FIBROBLAST_PROLIFERATION", "1.801", "0.006", "0.056"], ["GO_BLOOD_VESSEL_ENDOTHELIAL_CELL_MIGRATION", "1.770", "0.011", "0.063"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab5"}}, {"id": "asset:table:pmid:34266411:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:84f8d5dd00b9249c7efe473d5e194a238d37efd805cb40bcf19e7e166375456d", "bytes": 1688, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#Tab6", "version": null, "note": "Gene sets enriched in the low risk phenotype via GO", "structure": {"pmcid": "PMC8281685", "section_index": 12, "section_title": "GSEA", "row_count": 21, "column_count": 4}, "table": {"label": "Table 6", "caption": "Gene sets enriched in the low risk phenotype via GO", "rows": [["Gene set name", "NES", "NOM p-val", "FDR q-val"], ["GO_T_CELL_CYTOKINE_PRODUCTION", "−1.594", "0.034", "0.227"], ["GO_T_CELL_ACTIVATION_INVOLVED_IN_IMMUNE_RESPONSE", "−1.721", "0.036", "0.195"], ["GO_PRODUCTION_OF_MOLECULAR_MEDIATOR_OF_IMMUNE_RESPONSE", "−1.740", "0.034", "0.192"], ["GO_CD4_POSITIVE_ALPHA_BETA_T_CELL_ACTIVATION", "−1.747", "0.028", "0.188"], ["GO_CD4_POSITIVE_ALPHA_BETA_T_CELL_LINEAGE_COMMITMENT", "−1.754", "0.019", "0.183"], ["GO_CD8_POSITIVE_ALPHA_BETA_T_CELL_ACTIVATION", "− 1.798", "0.019", "0.160"], ["GO_T_CELL_DIFFERENTIATION_INVOLVED_IN_IMMUNE_RESPONSE", "−1.807", "0.024", "0.161"], ["GO_POSITIVE_REGULATION_OF_PROTEIN_DEACETYLATION", "−1.836", "0.006", "0.146"], ["GO_POSITIVE_REGULATION_OF_SIGNAL_TRANSDUCTION_BY_P53_CLASS_MEDIATOR", "−1.838", "0.004", "0.149"], ["GO_MHC_PROTEIN_COMPLEX", "−1.838", "0.002", "0.150"], ["GO_POSITIVE_REGULATION_OF_INTERLEUKIN_12_PRODUCTION", "−1.859", "0.006", "0.146"], ["GO_FATTY_ACID_BETA_OXIDATION", "−1.872", "0.004", "0.147"], ["GO_T_CELL_SELECTION", "−1.889", "0.017", "0.156"], ["GO_IMMUNOGLOBULIN_PRODUCTION", "−1.898", "0.002", "0.163"], ["GO_CD4_POSITIVE_OR_CD8_POSITIVE_ALPHA_BETA_T_CELL_LINEAGE_COMMITMENT", "−1.919", "0.004", "0.157"], ["GO_T_CELL_RECEPTOR_SIGNALING_PATHWAY", "−1.920", "0.008", "0.161"], ["GO_FATTY_ACID_CATABOLIC_PROCESS", "−1.936", "0.004", "0.168"], ["GO_POSITIVE_T_CELL_SELECTION", "−1.944", "0.004", "0.194"], ["GO_T_CELL_RECEPTOR_COMPLEX", "−1.972", "0.002", "0.260"], ["GO_MHC_PROTEIN_BINDING", "−1.994", "0.006", "0.369"]], "row_count": 21, "column_count": 4, "numeric_cells": 62, "header_rows": 1, "locator": "section[12]/table-wrap[2]#Tab6"}}, {"id": "asset:table:pmid:34266411:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bd2b68322c9cdf2b22b03cbd35e630cdde5cea2fdd3eaee10e35ab7dc89db107", "bytes": 1303, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[3]#Tab7", "version": null, "note": "Gene sets enriched in the high risk phenotype via KEGG", "structure": {"pmcid": "PMC8281685", "section_index": 12, "section_title": "GSEA", "row_count": 19, "column_count": 4}, "table": {"label": "Table 7", "caption": "Gene sets enriched in the high risk phenotype via KEGG", "rows": [["Gene set name", "NES", "NOM p-val", "FDR q-val"], ["KEGG_FOCAL_ADHESION", "2.390", "< 0.001", "< 0.001"], ["KEGG_ECM_RECEPTOR_INTERACTION", "2.374", "< 0.001", "< 0.001"], ["KEGG_HYPERTROPHIC_CARDIOMYOPATHY_HCM", "2.115", "0.002", "0.003"], ["KEGG_GAP_JUNCTION", "1.932", "< 0.001", "0.027"], ["KEGG_CALCIUM_SIGNALING_PATHWAY", "1.896", "0.002", "0.031"], ["KEGG_VASCULAR_SMOOTH_MUSCLE_CONTRACTION", "1.860", "0.006", "0.035"], ["KEGG_ADHERENS_JUNCTION", "1.809", "0.008", "0.042"], ["KEGG_MELANOGENESIS", "1.763", "< 0.001", "0.057"], ["KEGG_TGF_BETA_SIGNALING_PATHWAY", "1.648", "0.031", "0.114"], ["KEGG_PATHWAYS_IN_CANCER", "1.633", "0.017", "0.118"], ["KEGG_NEUROACTIVE_LIGAND_RECEPTOR_INTERACTION", "1.625", "0.017", "0.119"], ["KEGG_WNT_SIGNALING_PATHWAY", "1.606", "0.034", "0.117"], ["KEGG_MAPK_SIGNALING_PATHWAY", "1.590", "0.028", "0.123"], ["KEGG_GLYCOSAMINOGLYCAN_DEGRADATION", "1.586", "0.038", "0.121"], ["KEGG_PROGESTERONE_MEDIATED_OOCYTE_MATURATION", "1.572", "0.041", "0.126"], ["KEGG_HEDGEHOG_SIGNALING_PATHWAY", "1.568", "0.030", "0.124"], ["KEGG_GNRH_SIGNALING_PATHWAY", "1.537", "0.028", "0.137"], ["KEGG_TIGHT_JUNCTION", "1.522", "0.039", "0.138"]], "row_count": 19, "column_count": 4, "numeric_cells": 54, "header_rows": 1, "locator": "section[12]/table-wrap[3]#Tab7"}}, {"id": "asset:table:pmid:34266411:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fb6e6302f5fb42fd1b044142c452f9fa8a91812b4f6702395419d8d94c232d10", "bytes": 1099, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[4]#Tab8", "version": null, "note": "Gene sets enriched in low risk phenotype via KEGG", "structure": {"pmcid": "PMC8281685", "section_index": 12, "section_title": "GSEA", "row_count": 14, "column_count": 4}, "table": {"label": "Table 8", "caption": "Gene sets enriched in low risk phenotype via KEGG", "rows": [["Gene set name", "NES", "NOM p-val", "FDR q-val"], ["KEGG_PEROXISOME", "−1.986", "< 0.001", "1.467"], ["KEGG_LINOLEIC_ACID_METABOLISM", "−1.934", "< 0.001", "1.397"], ["KEGG_ANTIGEN_PROCESSING_AND_PRESENTATION", "−2.150", "0.002", "1.568"], ["KEGG_CYTOSOLIC_DNA_SENSING_PATHWAY", "−2.070", "0.004", "1.419"], ["KEGG_RIG_I_LIKE_RECEPTOR_SIGNALING_PATHWAY", "−1.912", "0.008", "1.425"], ["KEGG_AUTOIMMUNE_THYROID_DISEASE", "−2.013", "0.008", "1.479"], ["KEGG_GRAFT_VERSUS_HOST_DISEASE", "−1.959", "0.008", "1.425"], ["KEGG_ALLOGRAFT_REJECTION", "−1.926", "0.012", "1.431"], ["KEGG_PRIMARY_IMMUNODEFICIENCY", "−1.777", "0.028", "1.053"], ["KEGG_METABOLISM_OF_XENOBIOTICS_BY_CYTOCHROME_P450", "−1.678", "0.030", "0.943"], ["KEGG_ETHER_LIPID_METABOLISM", "−1.507", "0.031", "0.691"], ["KEGG_AMINOACYL_TRNA_BIOSYNTHESIS", "−1.645", "0.036", "0.895"], ["KEGG_INTESTINAL_IMMUNE_NETWORK_FOR_IGA_PRODUCTION", "−1.716", "0.039", "0.969"]], "row_count": 14, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[12]/table-wrap[4]#Tab8"}}], "gaps": ["asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE31684 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-3", "family": null, "specific": null, "label": "Pearson test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Pearson test was used for all correlation analysis."}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE31684"], "resolved_accessions": ["GSE31684"], "statements": ["The datasets generated and/or analyzed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GSE31684 repository, (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31684), and IMvigor210 (http://research-pub.gene.com/IMvigor210CoreBiologies/)."], "basis": "The paper names GSE31684 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": ["cox_ph"], "assets": ["source:pmid:34266411", "data:geo:GSE31684", "asset:table:pmid:34266411:1", "asset:table:pmid:34266411:2", "asset:table:pmid:34266411:3", "asset:table:pmid:34266411:4", "asset:table:pmid:34266411:5", "asset:table:pmid:34266411:6", "asset:table:pmid:34266411:7", "asset:table:pmid:34266411:8"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31684"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:28Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 51485, "completion_tokens": 2433, "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:34266411", "type": "paper", "label": "pmid:34266411"}, {"id": "source:pmid:34266411", "type": "manuscript", "label": "PMID 34266411 full text"}, {"id": "data:geo:GSE31684", "type": "dataset", "label": "GEO GSE31684"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34266411", "type": "paper", "label": "pmid:34266411"}, {"id": "source:pmid:34266411", "type": "manuscript", "label": "PMID 34266411 full text"}, {"id": "data:geo:GSE31684", "type": "dataset", "label": "GEO GSE31684"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34266411", "type": "extraction", "used": ["source:pmid:34266411"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31684", "type": "accession_resolution", "used": ["data:geo:GSE31684"], "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:34266411", "parent_hash": "sha256:71ef0cd002d3d9f91331991bf819464db7808f8f4325725fb349a938d65555dd", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE31684 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": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Cox regression"], "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":"2026-11-04T03:51:27+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}