{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23836465", "kind": "science-record", "revision": 8, "content_hash": "sha256:dde8273e84f4f31018b6fa6f12be482de5041b75a7cb280ae78ca58e5ca124d3", "created_at": "2026-11-01T15:40:03Z", "updated_at": "2026-11-01T22:41:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene expression patterns unveil a new level of molecular heterogeneity in colorectal cancer.", "doi": "10.1002/path.4212", "pmid": "23836465", "authors": ["Eva Budinska", "Vlad Popovici", "Sabine Tejpar", "Giovanni D'Ario", "Nicolas Lapique", "Katarzyna Otylia Sikora", "Antonio Fabio Di Narzo", "Pu Yan", "John Graeme Hodgson", "Scott Weinrich", "Fred Bosman", "Arnaud Roth", "Mauro Delorenzi"], "journal": "The Journal of pathology", "year": 2013, "abstract": "The recognition that colorectal cancer (CRC) is a heterogeneous disease in terms of clinical behaviour and response to therapy translates into an urgent need for robust molecular disease subclassifiers that can explain this heterogeneity beyond current parameters (MSI, KRAS, BRAF). Attempts to fill this gap are emerging. The Cancer Genome Atlas (TGCA) reported two main CRC groups, based on the incidence and spectrum of mutated genes, and another paper reported an EMT expression signature defined subgroup. We performed a prior free analysis of CRC heterogeneity on 1113 CRC gene expression profiles and confronted our findings to established molecular determinants and clinical, histopathological and survival data. Unsupervised clustering based on gene modules allowed us to distinguish at least five different gene expression CRC subtypes, which we call surface crypt-like, lower crypt-like, CIMP-H-like, mesenchymal and mixed. A gene set enrichment analysis combined with literature search of gene module members identified distinct biological motifs in different subtypes. The subtypes, which were not derived based on outcome, nonetheless showed differences in prognosis. Known gene copy number variations and mutations in key cancer-associated genes differed between subtypes, but the subtypes provided molecular information beyond that contained in these variables. Morphological features significantly differed between subtypes. The objective existence of the subtypes and their clinical and molecular characteristics were validated in an independent set of 720 CRC expression profiles. Our subtypes provide a novel perspective on the heterogeneity of CRC. The proposed subtypes should be further explored retrospectively on existing clinical trial datasets and, when sufficiently robust, be prospectively assessed for clinical relevance in terms of prognosis and treatment response predictive capacity. Original microarray data were uploaded to the ArrayExpress database (http://www.ebi.ac.uk/arrayexpress/) under Accession Nos E-MTAB-990 and E-MTAB-1026.", "claims": [{"id": "claim-method", "statement": "Hierarchical clustering (complete linkage, Pearson correlation similarity measure) and dynamic cut tree 20 were used to produce gene modules (groups of genes with correlated expression)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23836465", "locator": "sections[4] \"Subtype definition and validation\" paragraph 2", "quote": "Hierarchical clustering (complete linkage, Pearson correlation similarity measure) and dynamic cut tree 20 were used to produce gene modules (groups of genes with correlated expression)"}], "state": "complete"}, {"id": "claim-data-access", "statement": "which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23836465", "locator": "sections[3] \"Data acquisition and processing\" paragraph 3", "quote": "which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively."}], "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:23836465"], "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-1026"], "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:E-MTAB-1026"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:23836465", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/path.4212", "sha256": "sha256:e086752af1e5b6d5e4638c26d5e388eab161e1fab138b67a08fcc3b697009d96", "bytes": 57477, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/path.4212", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3840702", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-1026", "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-1026", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-1026", "version": null, "note": "which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:28:56Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:E-MTAB-990", "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-990", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-990", "version": null, "note": "which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:04Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:23836465:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b4efe29cf828373c1cab58dbb8fdd717230565f666e6d9201b4d0f6b41f828bf", "bytes": 4504, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tbl1", "version": null, "note": "Biological identification of gene modules", "structure": {"pmcid": "PMC3840702", "section_index": 10, "section_title": "Subtypes are characterized by distinct biological components", "row_count": 24, "column_count": 4}, "table": {"label": "Table 1", "caption": "Biological identification of gene modules", "rows": [["Cluster name", "Number of genes", "Pathway analysis result (number of overlapping genes, p value) OR description based on literature search", "Selected genes"], ["1. GDC", "27", "Genes involved in differentiation of colon crypt and/or whose expression was reported to be affected in colorectal cancer and/or with prognostic effect in CRC", "Intestinal differentiation genes: CDX245, IHH46, VAV347, ASCL235, PLAGL248 Genes reported altered in colorectal cancer with prognostic effect: PITX249, DDC50, PRLR51, SPINK152 Other genes connected to CRC: GGH–connected to CIMP+ phenotype 53 NR1I2–connected to chemoresistance 54"], ["2. Chromosome 20q genes", "33", "Chromosome 20 (26 genes, 9.2E-34)", "Other, non-20q genes: TP53RK, ANO9, NEU1, CLDN3, PRSS8"], ["3. Proliferation", "83", "Cell cycle (36 genes, 3.0E-33) Mitosis (26 genes, 1.4E-29) Chromosome (26 genes, 2.5E-17) DNA metabolic process (20 genes, 4.9E-10) Lipid synthesis (4 genes, 5.0E-2)", "Mitotic checkpoint kinases: BUB1, BUB1B Cyclins: CCNA2, CCNB2 Centromere proteins: CENPA, CENPE, CENPN Kinesins: KIF11, KIF23, KIF4A Topoisomerase II (TOP2A) Cell division cycle 2 CDC2"], ["4. Colon crypt markers (secretory cells)", "16", "", "AGR255, AGR3, MUC2, SPINK456, RETNLB57, REG458"], ["5. EMT/stroma", "310", "Extracellular region part (90 genes) 2.7E-36 Cell adhesion (57 genes) 1.2E-17 Extracellular matrix (44 genes) 5.3E-30 Collagen (16 genes) 1.2E-15 EGF-like domain (26 genes) 1.6E-12 Cell motion (33 genes) 7.2E-8 Blood vessel development (25 genes) 1.1E-8 Growth factor binding (6 genes) 6.0E-5 Frizzled related (5 genes) 6.7E-3 Cell junction organization (7 genes) 1.8E-2 WNT receptor signalling pathway (8 genes) 1.4E-1", "Inhibitors of β-catenin-dependent canonical WNT: SFRP1, SFRP2, SFRP4, DKK3, FZD1,7, PRICKLE1, NXN Mesenchymal markers: N-cadherin, OB cadherin, SPARC, DDR2 EMT inducers(TFs): SNAI2, ZEB1, ZEB2, TWIST1, CDH11 ECM remodelling and invasion: MMP14, VIM ECM proteins: fibronectin 1, collagens Angiogenesis: PLAT, PLAU, NRP1, NRP2, THBS1, THBS2, THBS4 TGFs, their receptors and binding proteins: IGF1, IGFBP5, IGFBP7,TGFB, LTBP1, LTBP2, PDGFRA, PDGFRB"], ["6. Unidentified", "14", "", "DUSP1, EGR2, SERPINE1"], ["7 and 8. Immune response", "103", "Immune response (42 genes) 2.0E-28 Positive regulation of immune system process (16 genes) 4.0E-9 Antigen processing and presentation via MHC class II (6 genes) 7.5E-5 Defence response (31 genes) 3.3E-17 Chemokine signalling pathway (9 genes) 2.2E-3 Lymphocyte activation (11 genes) 2.1E-5 Regulation of programmed cell death (14 genes) 2.1E-2", "Cytokines: CCL3, CXCL5, CXCL9,CXCL10, CXCL11, SPP1, LTB MHC class II: HLA-DMB, HLA-DPA1, HLA-DRA, CD74 MHC class I: HLA-F, TAP1, TAP2 Anti-apoptotic: BCL2A1, CD74, BIRC3, IFI6, TNFAIP3, TNFAIP3 Apoptotic: STAT1, XAF1 Interferon-induced proteins: IFI30, IFI16, IFI44, IFI16, IFIH1, IFIT3"], ["Cluster-unassigned meta-genes with colon crypt cell markers (enterocytes/top of the crypt)"], ["Meta-gene 105", "6", "Top of the crypt genes", "FAM55A, FAM55D, MUC12 and CEACAM759, SLC26A259, SLC26A359"], ["Meta-gene 144", "5", "Enterocytes, goblet cells markers", "LOC644844, NGEF, HEPH, KRT2059, MUC2059"], ["Cluster-unassigned meta-genes associated with chromosomal location 0"], ["Meta-gene 81", "7", "Chromosome X (7 genes) 1.1E-8", "CXorf15, EIF1AX, HDHD1A, MED14, PNPLA4, SCML1, SMC1A"], ["Meta-gene 97", "6", "Chromosome 20p (5 genes) 5.0E-11", "CDC25B, CSNK2A1, MRPS26, PTPRA, RP5-1022P6.2, SNRPB"], ["Meta-gene 84", "7", "Chromosome 8 (7 genes) 5.4E-9", "AGPAT5, FDFT1, GTF2E2, LONRF1, MTUS1, VPS37A, ZNF395"], ["Other cluster-unassigned meta-genes"], ["Meta-gene 141", "5", "EREG", "AK3L1, ARID3A, EREG, LDLRAD3, ZBTB10"], ["Meta-gene 112", "6", "Lipid synthesis (4 genes) 5.0E-2", "DHCR7, FASN, FGFBP1, HMGCS1, IDI1, PCSK9"], ["Meta-gene 95", "6", "Homeobox genes", "HOXA10, HOXA11, HOXA13, HOXA5, HOXA7, HOXA9"], ["Meta-gene 124", "5", "Metallothioneins", "MT1E, MT1F, MT1G, MT1M, MT1X"], ["Meta-gene 131", "5", "Disulphide bonds (5 genes) 1.7E-02", "CXCL5, IL6, MMP1, MMP3, PTGS2"], ["Meta-gene 143", "5", "Unidentified", "DUSP5, ERRFI1, KLF6, MXD1, PLAUR"], ["Meta-gene 80", "7", "Regulation of RNA metabolic process (6 genes) 4.9E-2", "ATF3, C8orf4, FOS, JUNB, NR4A1, SIK1, ZFP36"], ["Meta-gene 71", "8", "Gut development (3 genes) 3.5E-2", "CCL11, CH25H, EDNRB, F2RL2, FOXF1, FOXF2, PCDH18, WNT5A"]], "row_count": 24, "column_count": 4, "numeric_cells": 67, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:23836465:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:72b55ee671557f292c8468f3a705d04592828f1ae2feb1acafbf39d3448bb92a", "bytes": 1057, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#tbl2", "version": null, "note": "Subtype-specific minimal gene set as identified by Elastic net", "structure": {"pmcid": "PMC3840702", "section_index": 10, "section_title": "Subtypes are characterized by distinct biological components", "row_count": 7, "column_count": 3}, "table": {"label": "Table 2", "caption": "Subtype-specific minimal gene set as identified by Elastic net", "rows": [["", "Minimal gene sets specifying a subtype"], ["Subtype", "Up-regulated from population mean", "Down-regulated from population mean"], ["A. Surface crypt-like", "ADTRP, B3GNT7, CLCA1, MUC2, NR3C2, PADI2, RETNLB, STYK1", "CHI3L1, FNDC1, TIMP3, SULF1"], ["B. Lower crypt-like", "CCDC113, CDHR1, FARP1, GPSM2, GRM8, HNF4A, IHH, KCNK5, KIAA0226L, MYRIP, PLAGL2, PRR15, QPRT, RNF43, RPS6KA3, SLC5A6, TP53RK, TSPAN6, VAV3, YAE1D1", "ALOX5, BASP1, CREB3L1, CXCR4, EPB41L3, FSCN1, GFPT2, GPX8, ITPRIP, KCNMA1, KCTD12,MT1E, RARRES3, RNASE1, SGK1, SOCS3"], ["C. CIMP-H-like", "ANP32E, EGLN3, IDO1, PLK2, RAB27B, RARRES3, RPL22L1, TFAP2A", "ATP9A, C10orf99, CXCL14, KIAA0226L"], ["D. Mesenchymal", "ANK2, BOC, C7, CRYAB, DCHS1, DDR2, GEM, PRICKLE1, TAGLN", "HOOK1, RBM47"], ["E. Mixed", "CEACAM6, CXCL5, HSD11B1, IL1B, IL6, MRPS31, PI15, RAP2A, UQCC", "AGR3, RAB27B, REG4"]], "row_count": 7, "column_count": 3, "numeric_cells": 7, "header_rows": 2, "locator": "section[10]/table-wrap[2]#tbl2"}}, {"id": "asset:table:pmid:23836465:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d5d8b1960d6a07f7b5eae7fe656da88293176601370213d216fdc3cac20547fa", "bytes": 715, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tbl3", "version": null, "note": "Result of additive multivariate Cox proportional hazards model, with subtype, BRAF mutation, MSI and stagea", "structure": {"pmcid": "PMC3840702", "section_index": 12, "section_title": "Subtypes and patient survival", "row_count": 8, "column_count": 7}, "table": {"label": "Table 3", "caption": "Result of additive multivariate Cox proportional hazards model, with subtype, BRAF mutation, MSI and stagea", "rows": [["Variable", "RFS HR", "p", "OS HR", "p", "SAR HR", "p"], ["A", "0.906", "0.760", "1.381", "0.390", "1.726", "0.180"], ["C", "0.940", "0.850", "1.560", "0.220", "3.675", "0.0022*"], ["D", "1.688", "0.0055*", "2.161", "0.0011*", "1.906", "0.014*"], ["E", "1.506", "0.210", "2.201", "0.035*", "2.046", "0.075"], ["BRAFm", "1.633", "0.085", "2.472", "0.0034*", "3.361", "0.00072*"], ["MSI", "0.478", "0.044*", "0.275", "0.004*", "0.356", "0.036*"], ["Stage 3", "0.770", "0.190", "0.943", "0.820", "1.780", "0.062*"]], "row_count": 8, "column_count": 7, "numeric_cells": 43, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tbl3"}}, {"id": "asset:table:pmid:23836465:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:425086c01239994e5ee2e11a1eafd440a26eb1526918e3659f88c9c6aa530e8b", "bytes": 1292, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#tbl4", "version": null, "note": "Summary of subtype characteristics", "structure": {"pmcid": "PMC3840702", "section_index": 16, "section_title": "Discussion", "row_count": 7, "column_count": 14}, "table": {"label": "Table 4", "caption": "Summary of subtype characteristics", "rows": [["Subtype", "CRC markers and mutations", "Histopathology", "IHC", "Median survival (months)", "Clinical", "Gene expression"], ["MSI", "BRAF", "KRAS", "P53", "Dominant", "Nuclear β-catenin at IF", "OS", "RFS", "SAR", "Site", "Grade", "Up-regulated", "Down-regulated"], ["A: Surface crypt-like", "", "–", "+", "", "Papillary or serrated", "–", "NA", "NA", "28.9", "", "", "Top colon crypt, secretory cell, metallothioneins", "EMT/stroma, Wnt, CSC, Chr20q, proliferation"], ["B: Lower crypt-like", "–", "–", "", "", "Complex tubular", "+", "NA", "NA", "50.4", "Left", "2", "Top colon crypt, proliferation, Wnt", "EMT/stroma, immune, secretory cell"], ["C: CIMP-H-like", "+", "+", "", "–", "Solid/trabecular or mucinous", "–", "NA", "NA", "6.9", "Right", "3", "Proliferation, immune, metallothioneins", "GDC, top colon crypt, Chr20q"], ["D: Mesenchymal", "", "", "", "", "Desmoplastic", "–", "NA", "79.5", "19.8", "", "", "EMT/stroma, CSC, immune", "Proliferation, secretory cell, top colon crypt, GDC, Wnt, Chr20q"], ["E: Mixed", "–", "–", "", "+", "Complex tubular", "+", "NA", "NA", "19.6", "Left", "", "EMT/stroma, immune, top colon crypt, Chr20q, GDC, CSC", "Secretory cell"]], "row_count": 7, "column_count": 14, "numeric_cells": 13, "header_rows": 2, "locator": "section[16]/table-wrap[1]#tbl4"}}], "gaps": ["asset:data:geo:E-MTAB-1026 not downloaded", "asset:data:geo:E-MTAB-1026 licence not read", "asset:data:geo:E-MTAB-990 not downloaded", "asset:data:geo:E-MTAB-990 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Hierarchical clustering (complete linkage, Pearson correlation similarity measure) and dynamic cut tree 20 were used to produce gene modules (groups of genes with correlated expression)"}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Cox proportional hazards"}}, {"id": "method-3", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "dendrogram"}}], "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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-990", "E-MTAB-1026"], "resolved_accessions": ["E-MTAB-990", "E-MTAB-1026"], "statements": ["which were uploaded to ArrayExpress (http://www.ebi.ac.uk/arrayexpress/), under Accession Nos E-MTAB-990 and E-MTAB-1026, respectively."], "basis": "The paper names E-MTAB-990, E-MTAB-1026 in ArrayExpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:23836465", "data:geo:E-MTAB-1026", "asset:table:pmid:23836465:1", "asset:table:pmid:23836465:2", "asset:table:pmid:23836465:3", "asset:table:pmid:23836465:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-1026"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:23836465", "type": "paper", "label": "pmid:23836465"}, {"id": "source:pmid:23836465", "type": "manuscript", "label": "PMID 23836465 full text"}, {"id": "data:geo:E-MTAB-1026", "type": "dataset", "label": "GEO E-MTAB-1026"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23836465", "type": "paper", "label": "pmid:23836465"}, {"id": "source:pmid:23836465", "type": "manuscript", "label": "PMID 23836465 full text"}, {"id": "data:geo:E-MTAB-1026", "type": "dataset", "label": "GEO E-MTAB-1026"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23836465", "type": "extraction", "used": ["source:pmid:23836465"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-1026", "type": "accession_resolution", "used": ["data:geo:E-MTAB-1026"], "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:23836465", "parent_hash": "sha256:2791c95192b718263a4cd83a7978295c9753355a749da2aa9bd324f3415cf690", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:E-MTAB-1026 licence not read", "asset:data:geo:E-MTAB-1026 not downloaded", "asset:data:geo:E-MTAB-990 licence not read", "asset:data:geo:E-MTAB-990 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": ["tment response predictive capacity. Original microarray data were uploaded to the ArrayExpress datab"], "order_basis": "paper_text_order:1974", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["subtypes Figure S9Distribution of β-catenin immunoreactivity of the invasion front counts between subtype"], "order_basis": "paper_text_order:6136", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Hierarchical clustering (complete linkage, Pearson correlation similarity measure) and dynamic cut tree 20 were used to produce gene modules (groups of genes with correlated expression)"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:32:12+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}}}