{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33672425", "kind": "science-record", "revision": 4, "content_hash": "sha256:418d51a0a9db41e9eb53120fda0d0bac5a739dbd090165871e3e8143c47e8dea", "created_at": "2026-11-01T15:41:27Z", "updated_at": "2026-11-01T21:24:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Long Non-Coding RNA Landscape in Prostate Cancer Molecular Subtypes: A Feature Selection Approach.", "doi": "10.3390/ijms22042227", "pmid": "33672425", "authors": ["Simona De Summa", "Antonio Palazzo", "Mariapia Caputo", "Rosa Maria Iacobazzi", "Brunella Pilato", "Letizia Porcelli", "Stefania Tommasi", "Angelo Virgilio Paradiso", "Amalia Azzariti"], "journal": "International journal of molecular sciences", "year": 2021, "abstract": "Prostate cancer is one of the most common malignancies in men. It is characterized by a high molecular genomic heterogeneity and, thus, molecular subtypes, that, to date, have not been used in clinical practice. In the present paper, we aimed to better stratify prostate cancer patients through the selection of robust long non-coding RNAs. To fulfill the purpose of the study, a bioinformatic approach focused on feature selection applied to a TCGA dataset was used. In such a way, LINC00668 and long non-coding(lnc)-SAYSD1-1, able to discriminate ERG/not-ERG subtypes, were demonstrated to be positive prognostic biomarkers in ERG-positive patients. Furthermore, we performed a comparison between mutated prostate cancer, identified as \"classified\", and a group of patients with no peculiar genomic alteration, named \"not-classified\". Moreover, LINC00920 lncRNA overexpression has been linked to a better outcome of the hormone regimen. Through the feature selection approach, it was found that the overexpression of lnc-ZMAT3-3 is related to low-grade patients, and three lncRNAs: lnc-SNX10-87, lnc-AP1S2-2, and ADPGK-AS1 showed, through a co-expression analysis, significant correlation values with potentially druggable pathways. In conclusion, the data mining of publicly available data and robust bioinformatic analyses are able to explore the unknown biology of malignancies.", "claims": [{"id": "claim-method", "statement": "To gain accuracy metrics, a Bootstrap resampling strategy was applied to the dataset (number of iterations = 100).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33672425", "locator": "sections[14] \"4.2.2. Feature Selection and Evaluation of Classification Performances\" paragraph 2", "quote": "To gain accuracy metrics, a Bootstrap resampling strategy was applied to the dataset (number of iterations = 100)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available in GDC data portal (https://portal.gdc.cancer.gov/) (accessed on 23 February 2021).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33672425", "locator": "sections[23] \"Data Availability Statement\" paragraph 2", "quote": "Data are available in GDC data portal (https://portal.gdc.cancer.gov/) (accessed on 23 February 2021)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:33672425"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33672425", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms22042227", "sha256": "sha256:2245b34c60d1ef805457054f6b45a5e62d8fa6aebccca13d431f5a3ce2baab6a", "bytes": 58693, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms22042227", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7926489", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33672425:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0f5fe2186fb3a00f559815d875c320b877d0784ad0759570798f488636773cf7", "bytes": 417, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#ijms-22-02227-t001", "version": null, "note": "Distribution of the molecular subtypes in the TCGA-PRAD cohort.", "structure": {"pmcid": "PMC7926489", "section_index": 3, "section_title": "2.1. lncRNA Discriminating ERG-Positive Subtype: Feature Selection", "row_count": 9, "column_count": 2}, "table": {"label": "Table 1", "caption": "Distribution of the molecular subtypes in the TCGA-PRAD cohort.", "rows": [["MolecularSubtypes", "n (%)"], ["ERG", "151 (45.6)"], ["ETV1", "27 (8.1)"], ["ETV4", "14 (4.2)"], ["FLI1", "4 (1.2)"], ["SPOP", "38 (11.4)"], ["FOXA1", "9 (2.7)"], ["IDH1", "3 (0.9)"], ["other", "86 (25.9)"]], "row_count": 9, "column_count": 2, "numeric_cells": 8, "header_rows": 1, "locator": "section[3]/table-wrap[1]#ijms-22-02227-t001"}}, {"id": "asset:table:pmid:33672425:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7e2e306ffd4390a8ec4d88e7dcdc721fd29ba71fb0bc674ac4cc48e6283d6cf6", "bytes": 1382, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#ijms-22-02227-t002", "version": null, "note": "Co-expressed long non-coding RNAs(lncRNAs) and coding genes.", "structure": {"pmcid": "PMC7926489", "section_index": 4, "section_title": "2.2. lncRNA-mRNA Coexpression Analysis of lncRNA Discriminating ERG-Positive Subtype", "row_count": 28, "column_count": 4}, "table": {"label": "Table 2", "caption": "Co-expressed long non-coding RNAs(lncRNAs) and coding genes.", "rows": [["lncRNA", "Gene", "r", "p-Value"], ["SLC5A4-AS1", "CPSF1P1", "0.8586", "<0.0001"], ["LINC02418", "ERG", "0.7761", "<0.0001"], ["lnc-PXDN-3", "TPO", "0.6901", "<0.0001"], ["lnc-OR1D5-1", "ERG", "0.6836", "<0.0001"], ["lnc-OR1D5-1", "LINC02418", "0.6693", "<0.0001"], ["LINC02418", "CD8B2", "0.6686", "<0.0001"], ["LINC02418", "DACT2", "0.6676", "<0.0001"], ["LINC02418", "HDAC1", "0.6631", "<0.0001"], ["LINC02418", "ANKRD6", "0.6573", "<0.0001"], ["LINC02418", "OGDHL", "0.6564", "<0.0001"], ["LINC02418", "ALOX15", "0.6530", "<0.0001"], ["LINC02418", "CPNE2", "0.6489", "<0.0001"], ["LINC02418", "SEPTIN9", "0.6437", "<0.0001"], ["LINC02418", "CDH7", "0.6389", "<0.0001"], ["LINC02418", "ITPR3", "0.6339", "<0.0001"], ["lnc-OR1D5-1", "SEPTIN9", "0.6311", "<0.0001"], ["LINC02418", "HLA-DMB", "0.6308", "<0.0001"], ["LINC02418", "VSTM5", "0.6233", "<0.0001"], ["LINC02418", "KCNS3", "0.6211", "<0.0001"], ["LINC02418", "NKAIN1", "0.6202", "<0.0001"], ["LINC02418", "FZD8", "0.6138", "<0.0001"], ["LINC02418", "AMPD3", "0.6120", "<0.0001"], ["lnc-PXDN-3", "ERG", "0.6114", "<0.0001"], ["lnc-OR1D5-1", "ALOX15", "0.6073", "<0.0001"], ["LINC02418", "LAMC2", "0.6065", "<0.0001"], ["LINC02418", "SCYL3", "0.6056", "<0.0001"], ["lnc-OR1D5-1", "CD8B2", "0.6026", "<0.0001"]], "row_count": 28, "column_count": 4, "numeric_cells": 83, "header_rows": 1, "locator": "section[4]/table-wrap[1]#ijms-22-02227-t002"}}, {"id": "asset:table:pmid:33672425:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c47736a8f934b766c9a015510e23dfe8dd3b426bd9f7986877a1a51e79dc8337", "bytes": 2932, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#ijms-22-02227-t003", "version": null, "note": "Functional enrichment of the first subcluster of the protein–protein interaction (PPI) network.", "structure": {"pmcid": "PMC7926489", "section_index": 5, "section_title": "2.3. PPI Network and Identification of Highly Connected Subnetwork in ERG-Positive Subtype", "row_count": 41, "column_count": 3}, "table": {"label": "Table 3", "caption": "Functional enrichment of the first subcluster of the protein–protein interaction (PPI) network.", "rows": [["Category", "Description", "FDR Value"], ["GO Function", "inositol 1,4,5-trisphosphate-sensitive calcium-release channel activity", "4.7 × 10−6"], ["GO Function", "Cation channel activity", "4.7 × 10−6"], ["GO Function", "Ion-gated channel activity", "4.7 × 10−6"], ["GO Function", "metal ion transmembrane transporter activity", "4.7× 10−6"], ["GO Function", "Calcium channel activity", "5.56 × 10−6"], ["GO Process", "Calcium ion transport", "6.31 × 10−6"], ["KEGG Pathways", "cGMP-PKG signaling pathway", "7.6 × 10−6"], ["KEGG Pathways", "Cellular senescence", "7.6 × 10−6"], ["KEGG Pathways", "Vascular smooth muscle contraction", "7.6 × 10−6"], ["KEGG Pathways", "Circadian entrainment", "7.6 × 10−6"], ["KEGG Pathways", "Retrograde endocannabinoid signaling", "7.6 × 10−6"], ["KEGG Pathways", "Glutamatergic synapse", "7.6 × 10−6"], ["KEGG Pathways", "Cholinergic synapse", "7.6 × 10−6"], ["KEGG Pathways", "Serotonergic synapse", "7.6 × 10−6"], ["KEGG Pathways", "Dopaminergic synapse", "7.6 × 10−6"], ["KEGG Pathways", "Insulin secretion", "7.6 × 10−6"], ["KEGG Pathways", "GnRH signaling pathway", "7.6 × 10−6"], ["KEGG Pathways", "Oxytocin signaling pathway", "7.6 × 10−6"], ["KEGG Pathways", "Renin secretion", "7.6 × 10−6"], ["KEGG Pathways", "Aldosterone synthesis and secretion", "7.6 × 10−6"], ["KEGG Pathways", "Cortisol synthesis and secretion", "7.6 × 10−6"], ["KEGG Pathways", "Cushing’s syndrome", "7.6 × 10−6"], ["KEGG Pathways", "Salivary secretion", "7.6 × 10−6"], ["KEGG Pathways", "Alzheimer’s disease", "7.6 × 10−6"], ["KEGG Pathways", "Calcium signaling pathway", "8.6 × 10−6"], ["GO Function", "inositol 1,4,5 trisphosphate binding", "1.36 × 10−6"], ["GO Process", "regulation of protein secretion", "1.43 × 10−5"], ["Reactome Pathways", "Regulation of insulin secretion", "1.58 × 10−5"], ["Reactome Pathways", "Integration of energy metabolism", "1.96 × 10−5"], ["Reactome Pathways", "Cardiac conduction", "2.57 × 10−5"], ["Reactome Pathways", "CLEC7A (Dectin-1) induces NFAT activation", "3.3 × 10−5"], ["GO Process", "Inorganic cation transmembrane transport", "4.36 × 10−5"], ["Reactome Pathways", "Elevation of cytosolic Ca2+ levels", "4.58 × 10−5"], ["Reactome Pathways", "Muscle contraction", "4.58 × 10−5"], ["Reactome Pathways", "VEGFR2-mediated cell proliferation", "4.58 × 10−5"], ["GO Process", "regulation of insulin secretion", "4.82 × 10−5"], ["GO Process", "Calcium ion transmembrane transport", "5.98 × 10−5"], ["GO Process", "regulation of heart contraction", "6.38 × 10−5"], ["Reactome Pathways", "Role of phospholipids in phagocytosis", "7.41 × 10−5"], ["Reactome Pathways", "Effects of PIP2 hydrolysis", "7.62 × 10−5"]], "row_count": 41, "column_count": 3, "numeric_cells": 43, "header_rows": 1, "locator": "section[5]/table-wrap[1]#ijms-22-02227-t003"}}, {"id": "asset:table:pmid:33672425:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c9e7aac0dbaeb3ca40081650a7f30a3f198cbcbfb281c94d868524be28608a5", "bytes": 734, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[2]#ijms-22-02227-t004", "version": null, "note": "Functional enrichment of the second subcluster of the PPI network.", "structure": {"pmcid": "PMC7926489", "section_index": 5, "section_title": "2.3. PPI Network and Identification of Highly Connected Subnetwork in ERG-Positive Subtype", "row_count": 9, "column_count": 3}, "table": {"label": "Table 4", "caption": "Functional enrichment of the second subcluster of the PPI network.", "rows": [["Category", "Description", "FDR Value"], ["KEGG Pathways", "Purine metabolism", "9.3 × 10−6"], ["Reactome Pathways", "Metabolism of nucleotides", "0.002"], ["GO Process", "purine nucleotide catabolic process", "0.0038"], ["GO Process", "nucleoside metabolic process", "0.0064"], ["GO Process", "carbohydrate derivative catabolic process", "0.0064"], ["GO Process", "purine nucleotide metabolic process", "0.032"], ["GO Function", "Phosphoric ester hydrolase activity", "0.0323"], ["GO Function", "Hydrolase activity", "0.0324"]], "row_count": 9, "column_count": 3, "numeric_cells": 8, "header_rows": 1, "locator": "section[5]/table-wrap[2]#ijms-22-02227-t004"}}, {"id": "asset:table:pmid:33672425:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:31fc34b2ec5f75cf2c88a1715d69fa2cab78e4d44f4d25d35e184804b1710ee6", "bytes": 1923, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[3]#ijms-22-02227-t005", "version": null, "note": "Functional enrichment of the third subcluster of the PPI network.", "structure": {"pmcid": "PMC7926489", "section_index": 5, "section_title": "2.3. PPI Network and Identification of Highly Connected Subnetwork in ERG-Positive Subtype", "row_count": 29, "column_count": 3}, "table": {"label": "Table 5", "caption": "Functional enrichment of the third subcluster of the PPI network.", "rows": [["Category", "Description", "FDR Value"], ["GO Component", "Wnt-Frizzled-LRP5/6 complex", "7.05 × 10−6"], ["ReactomePathways", "RNF mutants show enhanced WNT signaling and proliferation", "1.2 × 10−5"], ["GO Function", "Coreceptor activity involved in Wnt signaling pathway", "2.89 × 10−5"], ["ReactomePathways", "Regulation of FZD by ubiquitination", "3.37 × 10−5"], ["GO Process", "CanonicalWnt signaling pathway", "5.31 × 10−5"], ["ReactomePathways", "Signaling by WNT in cancer", "5.59 × 10−5"], ["GO Function", "Wnt-activated receptor activity", "8.12 × 10−5"], ["GO Function", "Wnt-protein binding", "1.1 × 10−4"], ["GO Process", "Blood vessel development", "0.0013"], ["ReactomePathways", "TCF-dependent signaling in response to WNT", "0.0013"], ["GO Process", "Tube morphogenesis", "0.0018"], ["KEGG Pathways", "mTOR signaling pathway", "0.0023"], ["KEGG Pathways", "Wnt signaling pathway", "0.0023"], ["KEGG Pathways", "Breast cancer", "0.0023"], ["KEGG Pathways", "Hepatocellular carcinoma", "0.0023"], ["KEGG Pathways", "Gastric cancer", "0.0023"], ["ReactomePathways", "Signaling by WNT", "0.0023"], ["ReactomePathways", "Diseases of signal transduction", "0.0029"], ["GO Function", "Signaling receptor activity", "0.0032"], ["GO Process", "Non-canonical Wnt signaling pathway", "0.0032"], ["KEGG Pathways", "Pathways in cancer", "0.0048"], ["GO Process", "Sensory organ morphogenesis", "0.0173"], ["ReactomePathways", "Disease", "0.0191"], ["GO Process", "Epithelial tube morphogenesis", "0.0231"], ["GO Component", "Plasma membrane part", "0.0293"], ["GO Process", "Blood vessel morphogenesis", "0.0328"], ["GO Process", "Regulation of protein serine/threonine kinase activity", "0.0451"], ["GO Process", "Embryonic morphogenesis", "0.0484"]], "row_count": 29, "column_count": 3, "numeric_cells": 29, "header_rows": 1, "locator": "section[5]/table-wrap[3]#ijms-22-02227-t005"}}, {"id": "asset:table:pmid:33672425:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:22f3e4ad419cb4e3a03bb8484350a74ea9dd88bf9088b894e1c15ef8f02fdb7b", "bytes": 1346, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#ijms-22-02227-t006", "version": null, "note": "Co-expressed lncRNAs and genes.", "structure": {"pmcid": "PMC7926489", "section_index": 8, "section_title": "2.6. Co-Expression Network, Functional Enrichment and Prognostic Significance in Classified versus Nonclassified Subtypes", "row_count": 26, "column_count": 4}, "table": {"label": "Table 6", "caption": "Co-expressed lncRNAs and genes.", "rows": [["lncRNA", "Gene", "r", "p-Value"], ["lnc-AP1S2-2", "GRPR", "0.6863", "<0.0001"], ["lnc-SNX10-87", "ALOX15", "0.6841", "<0.0001"], ["lnc-SNX10-87", "SEPTIN9", "0.6841", "<0.0001"], ["lnc-SNX10-87", "ERG", "0.6795", "<0.0001"], ["lnc-SNX10-87", "KCNH8", "0.6795", "<0.0001"], ["lnc-SNX10-87", "CDH7", "0.6555", "<0.0001"], ["lnc-SNX10-87", "CACNA1D", "0.6539", "<0.0001"], ["lnc-SNX10-87", "LAMC2", "0.6372", "<0.0001"], ["lnc-SNX10-87", "TTC7B", "0.6349", "<0.0001"], ["lnc-SNX10-87", "MCOLN3", "0.6330", "<0.0001"], ["lnc-SNX10-87", "KIF16B", "0.6330", "<0.0001"], ["lnc-SNX10-87", "FZD8", "0.6286", "<0.0001"], ["lnc-SNX10-87", "OGDHL", "0.6286", "<0.0001"], ["lnc-SNX10-87", "DACT2", "0.6272", "<0.0001"], ["lnc-SNX10-87", "CPNE2", "0.6244", "<0.0001"], ["lnc-SNX10-87", "ANKRD6", "0.6234", "<0.0001"], ["lnc-SNX10-87", "EML6", "0.6161", "<0.0001"], ["lnc-SNX10-87", "ABCC8", "0.6059", "<0.0001"], ["lnc-SNX10-87", "NKAIN1", "0.6059", "<0.0001"], ["ADPGK-AS1", "ADPGK", "−0.6047", "<0.0001"], ["lnc-SNX10-87", "HDAC1", "−0.6154", "<0.0001"], ["lnc-SNX10-87", "KCNS3", "−0.6166", "<0.0001"], ["lnc-SNX10-87", "CD8B2", "−0.6204", "<0.0001"], ["lnc-SNX10-87", "HLA-DMB", "−0.6444", "<0.0001"], ["lnc-SNX10-87", "ITPR3", "−0.6802", "<0.0001"]], "row_count": 26, "column_count": 4, "numeric_cells": 76, "header_rows": 1, "locator": "section[8]/table-wrap[1]#ijms-22-02227-t006"}}, {"id": "asset:table:pmid:33672425:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:389c79865e27f0aa520e3e1c4a950a70c49a44ea81bfb6bae224cc372a6ac9f1", "bytes": 822, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#array1", "version": null, "note": null, "structure": {"pmcid": "PMC7926489", "section_index": 18, "section_title": "Abbreviations", "row_count": 19, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["PCa", "Prostate cancer"], ["PSA", "Prostate Specific Antigen"], ["lncRNA", "Long non-coding RNA"], ["CRPC", "Castration resistant prostate cancer"], ["ADT", "Deprivation Androgenic"], ["MDS plot", "Multidimensional scaling plot"], ["RF", "Random Forest"], ["SVM", "Support Vector Machine"], ["NB", "Naïve Bayes classifiers"], ["LDA", "Latent Dirichlet allocation"], ["LR", "Linear Regression"], ["kNN", "k-nearest neighbors algorithm"], ["PPI", "protein–protein interaction"], ["PFS", "Progression-Free Survival"], ["CRC", "colorectal cancer"], ["CKIs", "protein kinase inhibitors"], ["vst", "Variance stabilizing transformation"], ["sv", "Surrogate variables"], ["fve", "Fraction of Explained Variance"]], "row_count": 19, "column_count": 2, "numeric_cells": 0, "header_rows": 0, "locator": "section[18]/table-wrap[1]#array1"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Bootstrap resampling", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To gain accuracy metrics, a Bootstrap resampling strategy was applied to the dataset (number of iterations = 100)."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Bootstrap resampling), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Data are available in GDC data portal (https://portal.gdc.cancer.gov/) (accessed on 23 February 2021)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33672425", "asset:table:pmid:33672425:1", "asset:table:pmid:33672425:2", "asset:table:pmid:33672425:3", "asset:table:pmid:33672425:4", "asset:table:pmid:33672425:5", "asset:table:pmid:33672425:6", "asset:table:pmid:33672425:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 48522, "completion_tokens": 1041, "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:33672425", "type": "paper", "label": "pmid:33672425"}, {"id": "source:pmid:33672425", "type": "manuscript", "label": "PMID 33672425 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33672425", "type": "paper", "label": "pmid:33672425"}, {"id": "source:pmid:33672425", "type": "manuscript", "label": "PMID 33672425 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33672425", "type": "extraction", "used": ["source:pmid:33672425"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33672425", "parent_hash": "sha256:b3bc418d9e3ab00af135aa510f1532960c6b15b09d7ad7cfc272f79e309be6d7", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": [", identified as \"classified\", and a group of patients with no peculiar genomic alteration, named \"not-c"], "order_basis": "paper_text_order:821", "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":"2026-11-04T02:56:12+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}}}