{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31803541", "kind": "science-record", "revision": 5, "content_hash": "sha256:6be629dfa72b2e89b1f43c2c0814c2a4a89acca57e53a57268720ce08f1f5640", "created_at": "2026-11-01T15:40:52Z", "updated_at": "2026-11-01T22:01:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening and identification of key candidate genes and pathways in myelodysplastic syndrome by bioinformatic analysis.", "doi": "10.7717/peerj.8162", "pmid": "31803541", "authors": ["Ying Le"], "journal": "PeerJ", "year": 2019, "abstract": "Myelodysplastic syndrome (MDS) is a heterogeneous hematologic malignancy derived from hematopoietic stem cells and the molecular mechanism of MDS remains unclear. This study aimed to elucidate potential markers of diagnosis and prognosis of MDS. The gene expression profiles GSE19429 and GSE58831 were obtained and downloaded from the Gene Expression Omnibus (GEO) database. The differentially expressed genes (DEGs) in MDS were screened using GEO2R and overlapped DEGs were obtained with Venn Diagrams. Then, Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway functional enrichment analyses, protein-protein interaction network establishment and survival analyses were performed. Functional enrichment analysis indicated that these DEGs were significantly enriched in the interferon signaling pathway, immune response, hematopoietic cell lineage and the FOXO signaling pathway. Four hub genes and four significant modules including 25 module genes were obtained via Cytoscape MCODE. Survival analysis showed that the overall survival of MDS patients having BLNK, IRF4, IFITM1, IFIT1, ISG20, IFI44L alterations were worse than that without alterations. In conclusion, the identification of these genes and pathways helps understand the underlying molecular mechanisms of MDS and provides candidate targets for the diagnosis and prognosis of MDS.", "claims": [{"id": "claim-method", "statement": "The DEGs between MDS patients and healthy controls samples were screened using GEO2R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31803541", "locator": "sections[4] \"Identification of DEGs and data processing\" paragraph 2", "quote": "The DEGs between MDS patients and healthy controls samples were screened using GEO2R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental File. The gene expression profiles are available at NCBI–GEO: GSE19429, GSE58831.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31803541", "locator": "sections[29] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental File. The gene expression profiles are available at NCBI–GEO: GSE19429, GSE58831."}], "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:31803541"], "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:31803541", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.8162", "sha256": "sha256:bace416c459b2fb08b7e0a5070b666ca18c03e48cf0362abf8c0995039b76c96", "bytes": 33948, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.8162", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6886488", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:31803541:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d1bdf273df98670f2ebc00c0616bb1c15924f62221f1a03b45720e31755eb31f", "bytes": 1134, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table-2", "version": null, "note": "Gene Ontology and KEGG pathway enrichment analysis of DEGs in the significant module.", "structure": {"pmcid": "PMC6886488", "section_index": 6, "section_title": "PPI network establishment and module analysis", "row_count": 17, "column_count": 4}, "table": {"label": "Table 2", "caption": "Gene Ontology and KEGG pathway enrichment analysis of DEGs in the significant module.", "rows": [["Term", "Description", "Count", "P-value"], ["GO:0006955", "Immune response", "10", "3.15E−06"], ["GO:0030098", "Immune cell differentiation", "6", "4.93E−05"], ["GO:0098552", "Side of membrane", "5", "5.71E−04"], ["GO:0000982", "Transcription factor", "5", "4.34E−04"], ["GO:0003677", "DNA binding", "9", "5.97E−04"], ["GO:0016337", "Cell adhesion", "6", "1.24E−03"], ["GO:0030097", "Hemopoiesis", "6", "2.09E−03"], ["GO:0001775", "Cell activation", "6", "2.34E−03"], ["GO:0006952", "Defense response", "7", "2.99E−03"], ["GO:0007166", "Cell surface receptor", "8", "1.22E−02"], ["GO:0006259", "DNA metabolic", "5", "1.83E−02"], ["GO:0001822", "Kidney development", "3", "3.90E−02"], ["Hsa05340", "Primary immunodeficiency", "5", "3.02E−07"], ["Hsa04640", "Hematopoietic cell lineage", "5", "1.36E−05"], ["Hsa04662", "B cell receptor signaling pathway", "3", "6.19E−03"], ["Hsa04068", "FOXO signaling pathway", "3", "2.09E−02"]], "row_count": 17, "column_count": 4, "numeric_cells": 48, "header_rows": 1, "locator": "section[12]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:31803541:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6893cbd29b602779968090c8a1c26bf34ce0c4c073395443c6442031ed414621", "bytes": 3928, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#table-3", "version": null, "note": "Functional roles of 25 module genes.", "structure": {"pmcid": "PMC6886488", "section_index": 8, "section_title": "Survival analysis", "row_count": 26, "column_count": 4}, "table": {"label": "Table 3", "caption": "Functional roles of 25 module genes.", "rows": [["No.", "Gene symbol", "Full name", "Function"], ["1", "RAG2", "Recombination activating 2", "RAG2 is involved in B and T cell development and the expression of RAG2 is high in most AMLpatients"], ["2", "EBF1", "Transcription factor, early B cell factor 1", "EBF1 promotes of bone marrow CD34+ cell proliferation and migration,but suppresses the apoptosis of cells"], ["3", "BLNK", "B cell linker", "BLNK regulates the development, maturation and function of B cells"], ["4", "CD79B", "CD79b molecule", "CD79B is necessary for expression and function of the B-cell antigen receptor"], ["5", "VPREB1", "V-set pre-B cell surrogate light chain 1", "VPREB1 is involved in early B cell differentiation and VPREB1 deletion is often detected in relapsed leukemia"], ["6", "BLK", "BLK proto-oncogene, Src family tyrosine kinase", "BLK is involved in cell proliferation and differentiation and has a role in B-cell receptor signaling and B-cell development"], ["7", "IRF4", "Interferon regulatory factor 4", "IRF4 has oncogenic implications in a variety of hematological tumors including multiple myeloma, leukemia and lymphoma"], ["8", "IGLL1", "Immunoglobulin lambda like polypeptide 1", "IGLL1 is involved in cell proliferation and IGLL1 mutation can lead to B cell deficiency and agammaglobulinemia"], ["9", "DNTT", "DNA nucleotidy-lexotransferase", "DNTT acts as a catalyst to add nucleotides during the maturation of B cells and T cells"], ["10", "CD19", "CD19 molecule", "CD19 is a surface-specific marker of B lymphocytes and CD19 decreases the threshold of antigen receptor-dependent"], ["11", "PAX5", "Paired box 5", "PAX5 is involved in cell differentiation and neuro developmentand spermatogenesis"], ["12", "RAG1", "Recombination activating 1", "High expression of RAG1 in B-ALL patients promotes leukemic clonal evolution and high expression of RAG1 is associated with high proliferative markers"], ["13", "IFITM1", "Interferon induced transmembrane protein 1", "IFITM1 promotes proliferation, migration, and invasion of lung cancer"], ["14", "IFIT1", "Interferon induced protein with tetratricopeptide repeats 1", "IFIT1 and IFIT3 promote oral squamous cell carcinoma metastasis and contribute to theanti-tumor effect of gefitinib"], ["15", "IFIT3", "Interferon induced protein with tetratricopeptide repeats 3", "IFIT1 and IFIT3 promote oral squamous cell carcinoma metastasis and contribute to the anti-tumor effect of gefitinib"], ["16", "ISG20", "Interferon stimulated exonuclease gene 20", "ISG20 promotes local tumor immunity and has poor survival in human glioma"], ["17", "IFI44L", "Interferon induced protein 44 like", "High expression of IFI44L is associated with poor prognosis of osteosarcoma"], ["18", "IFI27", "Interferon alpha inducible protein 27", "IFI27 promotes cell proliferation and invasion in oral squamous cell carcinoma"], ["19", "CD24", "CD24 molecule", "CD24 modulates growth and differentiation signals to mature granulocytes and B cells"], ["20", "CXCR4", "C-X-C motif chemokine receptor 4", "High expression of CXCR4 has shorter OS time and shorter relapse-free survival time"], ["21", "IL7R", "Interleukin 7 receptor", "IL7R is overexpressed in adult acute lymphoblastic leukemia and is associatedwith JAK/STAT pathway mutations"], ["22", "MME", "Membrane metalloendo-peptidase", "MME inhibits tumor metastasis of esophageal squamous cell carcinoma and interrupt tumor cell adhesion"], ["23", "SKIL", "SKI like proto-oncogene", "SKIL has regulatory role in cell division or differentiation"], ["24", "SMAD7", "SMAD family member 7", "High expression of SMAD7 at diagnosis predicts poor prognosis in acute myeloid leukemia"], ["25", "SMAD1", "SMAD family member 1", "SMAD1 is involved in a range of biological activities including cell growth, apoptosis, morphogenesis, development and immune responses"]], "row_count": 26, "column_count": 4, "numeric_cells": 58, "header_rows": 1, "locator": "section[14]/table-wrap[1]#table-3"}}, {"id": "asset:table:pmid:31803541:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c72bb42491cbf2f297b492fe041ebb870df4a94b2243e67e736ee290aee8dc7a", "bytes": 2469, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#table-1", "version": null, "note": "Gene Ontology term enrichment analysis of DEGs in MDS.", "structure": {"pmcid": "PMC6886488", "section_index": 11, "section_title": "GO and KEGG pathway enrichment analyses of DEGs", "row_count": 40, "column_count": 4}, "table": {"label": "Table 1", "caption": "Gene Ontology term enrichment analysis of DEGs in MDS.", "rows": [["Term", "Description", "Count", "P-value"], ["Upregulated", "", "", ""], ["GO:0060337", "Type I interferon signaling pathway", "4", "2.28E−04"], ["GO:0098542", "Defense response", "5", "4.77E−04"], ["GO:0009605", "Response to external stimulus", "10", "4.04E−03"], ["GO:0002252", "Immune effector", "6", "6.19E−03"], ["GO:0007166", "Cell surface receptor signaling pathway", "11", "6.70E−03"], ["GO:0019221", "Cytokine-mediated signaling pathway", "5", "1.16E−02"], ["GO:0098911", "Regulation of cell action potential", "2", "2.25E−02"], ["GO:0050954", "Sensory perception", "3", "2.69E−02"], ["GO:0006955", "Immune response", "7", "3.50E−02"], ["GO:0045746", "Notch signaling pathway", "2", "4.76E−02"], ["Downregulated", "", "", ""], ["GO:0006955", "Immune response", "27", "9.26E−09"], ["GO:0007166", "Cell surface receptor signaling pathway", "33", "3.21E−07"], ["GO:0000982", "Transcription factor activity", "11", "4.51E−06"], ["GO:0001775", "Cell activation", "16", "2.84E−05"], ["GO:0040011", "Locomotion", "20", "1.06E−04"], ["GO:0005102", "Receptor binding", "19", "1.14E−04"], ["GO:0045595", "Cell differentiation", "20", "1.20E−04"], ["GO:0002684", "Regulation of immune system", "15", "1.99E−04"], ["GO:0010605", "Regulation of macromolecule metabolic", "24", "5.27E−04"], ["GO:0022407", "Cell-cell adhesion", "9", "5.71E−04"], ["GO:0009891", "Biosynthetic process", "20", "6.39E−04"], ["GO:0004871", "Signal transducer activity", "19", "1.12E−03"], ["GO:0008283", "Cell proliferation", "20", "1.26E−03"], ["GO:0060548", "Cell death", "13", "1.27E−03"], ["GO:0098552", "Side of membrane", "9", "1.54E−03"], ["GO:0043565", "Specific DNA binding", "14", "1.47E−03"], ["GO:0006915", "Apoptotic process", "19", "1.57E−03"], ["GO:0009892", "Regulation of metabolic process", "24", "1.63E−03"], ["GO:0060429", "Epithelium development", "14", "1.72E−03"], ["GO:0048514", "Blood vessel morphogenesis", "9", "2.64E−03"], ["GO:0003707", "Steroid hormone receptor activity", "4", "2.71E−03"], ["GO:0016477", "Cell migration", "14", "4.50E−03"], ["GO:0060537", "Muscle tissue development", "7", "8.93E−03"], ["GO:0005615", "Extracellular space", "14", "2.40E−03"], ["GO:0051427", "Hormone receptor binding", "4", "3.39E−02"], ["GO:0001047", "Core promoter binding", "4", "4.05E−02"], ["GO:0044877", "Macromolecular complex", "12", "4.16E−02"]], "row_count": 40, "column_count": 4, "numeric_cells": 111, "header_rows": 1, "locator": "section[11]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:31803541:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d1bdf273df98670f2ebc00c0616bb1c15924f62221f1a03b45720e31755eb31f", "bytes": 1134, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table-2", "version": null, "note": "Gene Ontology and KEGG pathway enrichment analysis of DEGs in the significant module.", "structure": {"pmcid": "PMC6886488", "section_index": 12, "section_title": "PPI network establishment and module analysis", "row_count": 17, "column_count": 4}, "table": {"label": "Table 2", "caption": "Gene Ontology and KEGG pathway enrichment analysis of DEGs in the significant module.", "rows": [["Term", "Description", "Count", "P-value"], ["GO:0006955", "Immune response", "10", "3.15E−06"], ["GO:0030098", "Immune cell differentiation", "6", "4.93E−05"], ["GO:0098552", "Side of membrane", "5", "5.71E−04"], ["GO:0000982", "Transcription factor", "5", "4.34E−04"], ["GO:0003677", "DNA binding", "9", "5.97E−04"], ["GO:0016337", "Cell adhesion", "6", "1.24E−03"], ["GO:0030097", "Hemopoiesis", "6", "2.09E−03"], ["GO:0001775", "Cell activation", "6", "2.34E−03"], ["GO:0006952", "Defense response", "7", "2.99E−03"], ["GO:0007166", "Cell surface receptor", "8", "1.22E−02"], ["GO:0006259", "DNA metabolic", "5", "1.83E−02"], ["GO:0001822", "Kidney development", "3", "3.90E−02"], ["Hsa05340", "Primary immunodeficiency", "5", "3.02E−07"], ["Hsa04640", "Hematopoietic cell lineage", "5", "1.36E−05"], ["Hsa04662", "B cell receptor signaling pathway", "3", "6.19E−03"], ["Hsa04068", "FOXO signaling pathway", "3", "2.09E−02"]], "row_count": 17, "column_count": 4, "numeric_cells": 48, "header_rows": 1, "locator": "section[12]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:31803541:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6893cbd29b602779968090c8a1c26bf34ce0c4c073395443c6442031ed414621", "bytes": 3928, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#table-3", "version": null, "note": "Functional roles of 25 module genes.", "structure": {"pmcid": "PMC6886488", "section_index": 14, "section_title": "Survival analysis", "row_count": 26, "column_count": 4}, "table": {"label": "Table 3", "caption": "Functional roles of 25 module genes.", "rows": [["No.", "Gene symbol", "Full name", "Function"], ["1", "RAG2", "Recombination activating 2", "RAG2 is involved in B and T cell development and the expression of RAG2 is high in most AMLpatients"], ["2", "EBF1", "Transcription factor, early B cell factor 1", "EBF1 promotes of bone marrow CD34+ cell proliferation and migration,but suppresses the apoptosis of cells"], ["3", "BLNK", "B cell linker", "BLNK regulates the development, maturation and function of B cells"], ["4", "CD79B", "CD79b molecule", "CD79B is necessary for expression and function of the B-cell antigen receptor"], ["5", "VPREB1", "V-set pre-B cell surrogate light chain 1", "VPREB1 is involved in early B cell differentiation and VPREB1 deletion is often detected in relapsed leukemia"], ["6", "BLK", "BLK proto-oncogene, Src family tyrosine kinase", "BLK is involved in cell proliferation and differentiation and has a role in B-cell receptor signaling and B-cell development"], ["7", "IRF4", "Interferon regulatory factor 4", "IRF4 has oncogenic implications in a variety of hematological tumors including multiple myeloma, leukemia and lymphoma"], ["8", "IGLL1", "Immunoglobulin lambda like polypeptide 1", "IGLL1 is involved in cell proliferation and IGLL1 mutation can lead to B cell deficiency and agammaglobulinemia"], ["9", "DNTT", "DNA nucleotidy-lexotransferase", "DNTT acts as a catalyst to add nucleotides during the maturation of B cells and T cells"], ["10", "CD19", "CD19 molecule", "CD19 is a surface-specific marker of B lymphocytes and CD19 decreases the threshold of antigen receptor-dependent"], ["11", "PAX5", "Paired box 5", "PAX5 is involved in cell differentiation and neuro developmentand spermatogenesis"], ["12", "RAG1", "Recombination activating 1", "High expression of RAG1 in B-ALL patients promotes leukemic clonal evolution and high expression of RAG1 is associated with high proliferative markers"], ["13", "IFITM1", "Interferon induced transmembrane protein 1", "IFITM1 promotes proliferation, migration, and invasion of lung cancer"], ["14", "IFIT1", "Interferon induced protein with tetratricopeptide repeats 1", "IFIT1 and IFIT3 promote oral squamous cell carcinoma metastasis and contribute to theanti-tumor effect of gefitinib"], ["15", "IFIT3", "Interferon induced protein with tetratricopeptide repeats 3", "IFIT1 and IFIT3 promote oral squamous cell carcinoma metastasis and contribute to the anti-tumor effect of gefitinib"], ["16", "ISG20", "Interferon stimulated exonuclease gene 20", "ISG20 promotes local tumor immunity and has poor survival in human glioma"], ["17", "IFI44L", "Interferon induced protein 44 like", "High expression of IFI44L is associated with poor prognosis of osteosarcoma"], ["18", "IFI27", "Interferon alpha inducible protein 27", "IFI27 promotes cell proliferation and invasion in oral squamous cell carcinoma"], ["19", "CD24", "CD24 molecule", "CD24 modulates growth and differentiation signals to mature granulocytes and B cells"], ["20", "CXCR4", "C-X-C motif chemokine receptor 4", "High expression of CXCR4 has shorter OS time and shorter relapse-free survival time"], ["21", "IL7R", "Interleukin 7 receptor", "IL7R is overexpressed in adult acute lymphoblastic leukemia and is associatedwith JAK/STAT pathway mutations"], ["22", "MME", "Membrane metalloendo-peptidase", "MME inhibits tumor metastasis of esophageal squamous cell carcinoma and interrupt tumor cell adhesion"], ["23", "SKIL", "SKI like proto-oncogene", "SKIL has regulatory role in cell division or differentiation"], ["24", "SMAD7", "SMAD family member 7", "High expression of SMAD7 at diagnosis predicts poor prognosis in acute myeloid leukemia"], ["25", "SMAD1", "SMAD family member 1", "SMAD1 is involved in a range of biological activities including cell growth, apoptosis, morphogenesis, development and immune responses"]], "row_count": 26, "column_count": 4, "numeric_cells": 58, "header_rows": 1, "locator": "section[14]/table-wrap[1]#table-3"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The DEGs between MDS patients and healthy controls samples were screened using GEO2R."}}], "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": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental File. The gene expression profiles are available at NCBI–GEO: GSE19429, GSE58831."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:31803541", "asset:table:pmid:31803541:1", "asset:table:pmid:31803541:2", "asset:table:pmid:31803541:3", "asset:table:pmid:31803541:4", "asset:table:pmid:31803541:5"], "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": "2026-10-31T18:53:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28687, "completion_tokens": 1698, "cached_tokens": 792}}, "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:31803541", "type": "paper", "label": "pmid:31803541"}, {"id": "source:pmid:31803541", "type": "manuscript", "label": "PMID 31803541 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31803541", "type": "paper", "label": "pmid:31803541"}, {"id": "source:pmid:31803541", "type": "manuscript", "label": "PMID 31803541 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31803541", "type": "extraction", "used": ["source:pmid:31803541"], "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:31803541", "parent_hash": "sha256:a38501b383d3b1c18080b86267c1fc036edba1ec73e843c87da8af448bb45764", "fork_of": null, "generation": 4}, "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": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "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":"2026-11-04T01:50:30+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}}}