{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31114367", "kind": "science-record", "revision": 7, "content_hash": "sha256:329da14d40788e06192618467922720b99faaa01b4bc036aaea4fc658920587e", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T21:22:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of a transcription factor-microRNA network in esophageal adenocarcinoma through bioinformatics analysis and validation through qRT-PCR.", "doi": "10.2147/CMAR.S201274", "pmid": "31114367", "authors": ["Di Chen", "Tong Lu", "Junying Tan", "Kun Zhao", "Yuli Li", "Wenjie Zhao", "Hao Li", "Qiuyue Wang", "Yuanyong Wang", "Liangzhou Wei"], "journal": "Cancer management and research", "year": 2019, "abstract": "Purpose: The rapidly rising incidence of esophageal adenocarcinoma (EAC), which is usually diagnosed late with a poor prognosis, has become a growing problem. This study investigated the potential transcription factor (TF)-related molecular mechanisms of EAC by using bioinformatics analysis and qRT-PCR validation. Methods: Expression profile datasets for mRNAs (GSE92396, GSE13898, GSE26886 and GSE1420) and miRNAs (GSE16456) were downloaded from the GEO database. Overlapping differentially expressed genes (DEGs) and differentially expressed miRNAs (DEMs) were identified through integrative analysis. Then, a TF-miRNA-mRNA network was constructed based on bioinformatics data from the TRRUST, TRED and miRTarBase database. Furthermore, overall survival analysis for the mRNAs and miRNAs in the TF-miRNA-mRNA network was performed with data from TCGA, and qRT-PCR was used to validate the results. Results: A total of 294 overlapping DEGs were identified in EAC tissues compared to normal tissues, including 181 downregulated and 113 upregulated genes. Then, 16 TFs that could target the DEGs and were related to cancer were predicted based on public databases, and 41 DEGs that could be targeted were identified as key genes. Additionally, 12 DEMs were predicted through miRTarBase to be associated with the key genes, and TP53-(miR-125b)-ID2 and JUN-(miR-30a)-IL1A from the TF-miRNA-mRNA network were identified to potentially play significant roles in EAC. Furthermore, CCL20, IL1A, ABCC3, hsa-miR-23b, and hsa-miR-191, which are involved in the TF-miRNA-mRNA network, were found to be significantly associated with patient survival in EAC. Finally, the expression of a miRNA-mRNA pair (hsa-miR-30a-5p and IL1A) was revealed to be correlated with prognosis. Conclusion: In this study, a TF-miRNA-mRNA network was constructed to analyze the potential molecular mechanisms of EAC. Key genes and miRNAs associated with patient survival were identified, which may reveal promising approaches for EAC diagnosis and therapy.", "claims": [{"id": "claim-method", "statement": "To verify the results obtained thus far, data for 89 EAC tissue samples and the clinical data of the patients were downloaded from TCGA, and the prognostic value of the key genes and miRNAs was identified by Kaplan-Meier analysis. The survival package in R software was used for survival analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31114367", "locator": "sections[8] \"Survival analysis validation\" paragraph 2", "quote": "To verify the results obtained thus far, data for 89 EAC tissue samples and the clinical data of the patients were downloaded from TCGA, and the prognostic value of the key genes and miRNAs was identified by Kaplan-Meier analysis. The survival package in R software was used for survival analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31114367", "locator": "sections[11] \"Microarray datasets from the GEO\" paragraph 2", "quote": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues"}], "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:31114367"], "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:GSE13898"], "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:GSE13898"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31114367", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/CMAR.S201274", "sha256": "sha256:b7b2008719763f98a3ae2c299629001d4dd1248eb92077b2219b8bad0460317b", "bytes": 32490, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/CMAR.S201274", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6489589", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13898", "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=GSE13898", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13898", "version": null, "note": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM349960", "GSM349961", "GSM349962", "GSM349963", "GSM349964", "GSM349965", "GSM349966", "GSM349967", "GSM349968", "GSM349969", "GSM349970", "GSM349971", "GSM349972", "GSM349973", "GSM349974", "GSM349975", "GSM349976", "GSM349977", "GSM349978", "GSM349979", "GSM349980", "GSM349981", "GSM349982", "GSM349983", "GSM349984", "GSM349985", "GSM349986", "GSM349987", "GSM349988", "GSM349989", "GSM349990", "GSM349991", "GSM349992", "GSM349993", "GSM349994", "GSM349995", "GSM349996", "GSM349997", "GSM349998", "GSM349999", "GSM350000", "GSM350001", "GSM350002", "GSM350003", "GSM350004", "GSM350005", "GSM350006", "GSM350007", "GSM350008", "GSM350009", "GSM350010", "GSM350011", "GSM350012", "GSM350013", "GSM350014", "GSM350015", "GSM350016", "GSM350017", "GSM350018", "GSM350019", "GSM350020", "GSM350021", "GSM350022", "GSM350023", "GSM350024", "GSM350025", "GSM350026", "GSM350027", "GSM350028", "GSM350029", "GSM350030", "GSM350031", "GSM350032", "GSM350033", "GSM350034", "GSM350035", "GSM350036", "GSM350037", "GSM350038", "GSM350039", "GSM350040", "GSM350041", "GSM350042", "GSM350043", "GSM350044", "GSM350045", "GSM350046", "GSM350047", "GSM350048", "GSM350049", "GSM350050", "GSM350051", "GSM350052", "GSM350053", "GSM350054", "GSM350055", "GSM350056", "GSM350057", "GSM350058", "GSM350059", "GSM350060", "GSM350061", "GSM350062", "GSM350063", "GSM350064", "GSM350065", "GSM350066", "GSM350067", "GSM350068", "GSM350069", "GSM350070", "GSM350071", "GSM350072", "GSM350073", "GSM350074", "GSM350075", "GSM350076", "GSM350077"], "sample_count": 118, "group_sizes": null, "group_sizes_basis": null, "platform": "6102", "taxon": "Homo sapiens", "title": "Robust prognostic biomarkers for EAC identified by systems-level characterization of tumor transcriptome", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE1420", "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=GSE1420", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE1420", "version": null, "note": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM23385", "GSM23386", "GSM23387", "GSM23388", "GSM23389", "GSM23390", "GSM23391", "GSM23392", "GSM23395", "GSM23396", "GSM23397", "GSM23398", "GSM23399", "GSM23400", "GSM23401", "GSM23402", "GSM23413", "GSM23417", "GSM23419", "GSM23422", "GSM23424", "GSM23425", "GSM23426", "GSM23427"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Barrett's esophagus, Barrett's-associated adenocarcinomas and normal esophageal epithelium", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE16456", "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=GSE16456", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16456", "version": null, "note": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM413658", "GSM413659", "GSM413660", "GSM413661", "GSM413662", "GSM413663", "GSM413664", "GSM413665", "GSM413666", "GSM413667", "GSM413668", "GSM413669", "GSM413670", "GSM413671", "GSM413672", "GSM413673", "GSM413674", "GSM413675", "GSM413676", "GSM413677", "GSM413678", "GSM413679", "GSM413680", "GSM413681", "GSM413682", "GSM413683", "GSM413684", "GSM413685", "GSM413686", "GSM413687", "GSM413688", "GSM413689"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "6955", "taxon": "Homo sapiens", "title": "MicroRNA expression signatures in Barrett's esophagus and esophageal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE26886", "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=GSE26886", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26886", "version": null, "note": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM661721", "GSM661722", "GSM661723", "GSM661724", "GSM661725", "GSM661726", "GSM661727", "GSM661728", "GSM661729", "GSM661730", "GSM661731", "GSM661732", "GSM661733", "GSM661734", "GSM661735", "GSM661736", "GSM661737", "GSM661738", "GSM661739", "GSM661740", "GSM661741", "GSM661742", "GSM661743", "GSM661744", "GSM661745", "GSM661746", "GSM661747", "GSM661748", "GSM661749", "GSM661750", "GSM661751", "GSM661752", "GSM661753", "GSM661754", "GSM661755", "GSM661756", "GSM661757", "GSM661758", "GSM661759", "GSM661760", "GSM661761", "GSM661762", "GSM661763", "GSM661764", "GSM661765", "GSM661766", "GSM661767", "GSM661768", "GSM661769", "GSM661770", "GSM661771", "GSM661772", "GSM661773", "GSM661774", "GSM661775", "GSM661776", "GSM661777", "GSM661778", "GSM661779", "GSM661780", "GSM661781", "GSM661782", "GSM661783", "GSM661784", "GSM661785", "GSM661786", "GSM661787", "GSM661788", "GSM661789"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of Barrett's esophagus, adenocarcinoma, esophageal squamous epithelium and squamous cell carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE92396", "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=GSE92396", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE92396", "version": null, "note": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2428973", "GSM2428974", "GSM2428975", "GSM2428976", "GSM2428977", "GSM2428978", "GSM2428979", "GSM2428980", "GSM2428981", "GSM2428982", "GSM2428983", "GSM2428984", "GSM2428985", "GSM2428986", "GSM2428987", "GSM2428988", "GSM2428989", "GSM2428990", "GSM2428991", "GSM2428992", "GSM2428993", "GSM2428994"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Esophageal adenocarcinoma gene expression profiling", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31114367:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9e536dd30bd1a67e85247feadcc2ec7bc41381fb1168987548a7c723e0eaa653", "bytes": 617, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T0001", "version": null, "note": "Primer sequences of qRT-PCR", "structure": {"pmcid": "PMC6489589", "section_index": 9, "section_title": "Total RNA extraction and qRT-PCR validation", "row_count": 7, "column_count": 3}, "table": {"label": "Table 1", "caption": "Primer sequences of qRT-PCR", "rows": [["Primer", "Forward primer (5′–3′)", "Reverse primer (5′–3′)"], ["IL1A", "AGATGCCTGAGATACCCAAAACC", "CCAAGCACACCCAGTAGTCT"], ["ABCC3", "TGGGGTGAAGTTTCGTACTGG", "CACGTTTGACTGAGTTGGTGATA"], ["CCL20", "TGCTGTACCAAGAGTTTGCTC", "CGCACACAGACAACTTTTTCTTT"], ["Hsa-miR-23b", "CACAAAGGCATCTCTACGCCCATC", "TGTAGCTGCCTCGCCAGAGGC"], ["Hsa-miR-191", "CTGGACAGCGGGCAACGGAAT", "GCAGGAGAGCAGGGGACGAAAT"], ["Hsa-U6", "TGCGGGTGCTCGCTTCGGCAGC", "CCAGTGCAGGGTCCGAGGT"]], "row_count": 7, "column_count": 3, "numeric_cells": 5, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T0001"}}, {"id": "asset:table:pmid:31114367:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7bdeb49559c8a42c78f71e3c847424c7ee99159a2c7ae2c6c465ae342f6cf0c1", "bytes": 853, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T0002", "version": null, "note": "Information of expression profiling microarray datasets", "structure": {"pmcid": "PMC6489589", "section_index": 11, "section_title": "Microarray datasets from the GEO", "row_count": 7, "column_count": 7}, "table": {"label": "Table 2", "caption": "Information of expression profiling microarray datasets", "rows": [["Accession number", "Platform", "Organism", "Experimenttype", "Status", "Numbers of samples"], ["EAC", "NE"], ["GSE16456", "GPL6955", "Homo sapiens", "Non-coding RNA profiling by array", "Public on December 31, 2009", "6", "16"], ["GSE1420", "GPL96", "Homo sapiens", "Expression profiling by array", "Public on November 18, 2004", "8", "8"], ["GSE13898", "GPL6102", "Homo sapiens", "Expression profiling by array", "Public on January 04, 2011", "64", "28"], ["GSE92396", "GPL6244", "Homo sapiens", "Expression profiling by array", "Public on December 15, 2016", "12", "9"], ["GSE26886", "GPL570", "Homo sapiens", "Expression profiling by array", "Public on October 18, 2013", "21", "19"]], "row_count": 7, "column_count": 7, "numeric_cells": 25, "header_rows": 2, "locator": "section[11]/table-wrap[1]#T0002"}}, {"id": "asset:table:pmid:31114367:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2f638b3495ab3c016478c2389f9c4e642240dfaffa527c014bd08716e35fdcb8", "bytes": 415, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T0003", "version": null, "note": "Regulatory relationships among TFs, key genes, and miRNAs", "structure": {"pmcid": "PMC6489589", "section_index": 13, "section_title": "Construction of the TF-miRNA-mRNA network", "row_count": 4, "column_count": 5}, "table": {"label": "Table 3", "caption": "Regulatory relationships among TFs, key genes, and miRNAs", "rows": [["Relationship", "Number of pairs/sets", "Number of TFs", "Number of key genes", "Number of miRNAs"], ["TF-key gene", "97", "16", "41", "-"], ["miRNA-key gene", "12", "-", "7", "12"], ["TF-miRNA-key gene", "2", "2", "2", "2"]], "row_count": 4, "column_count": 5, "numeric_cells": 10, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T0003"}}, {"id": "asset:table:pmid:31114367:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5b537b2eda1bb613850cee3380dc5320484edd67dce2875b09b16fd1225c6ffc", "bytes": 1538, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T0004", "version": null, "note": "GO terms of key genes", "structure": {"pmcid": "PMC6489589", "section_index": 14, "section_title": "Functional and pathway analysis of key genes", "row_count": 21, "column_count": 4}, "table": {"label": "Table 4", "caption": "GO terms of key genes", "rows": [["", "GO terms", "Number of enriched genes", "P-value"], ["Biological process", "GO:0006954-inflammatory response", "9", "2.56E-06"], ["", "GO:0022617-extracellular matrix disassembly", "5", "3.13E-05"], ["", "GO:0043123-positive regulation of I-kappaB kinase/NF-kappaB signaling", "5", "5.69 E-04"], ["", "GO:0008544-epidermis development", "4", "1.08 E-03"], ["", "GO:0001649-osteoblast differentiation", "4", "1.93 E-03"], ["", "GO:0008285-negative regulation of cell proliferation", "6", "2.37 E-03"], ["", "GO:0043066-negative regulation of apoptotic process", "6", "4.30 E-03"], ["", "GO:0031424-keratinization", "3", "5.82 E-03"], ["", "GO:0018149-peptide cross-linking", "3", "6.30 E-03"], ["", "GO:0002248~connective tissue replacement involved in inflammatory response wound healing", "2", "9.50 E-03"], ["", "GO:0030574-collagen catabolic process", "3", "1.02 E-02"], ["Cellular component", "GO:0005615-extracellular space", "17", "8.33E-09"], ["", "GO:0005576-extracellular region", "18", "1.38E-08"], ["", "GO:0070062-extracellular exosome", "21", "3.26E-07"], ["", "GO:0005578-proteinaceous extracellular matrix", "6", "2.86E-04"], ["", "GO:0001533-cornified envelope", "3", "4.57E-03"], ["Molecular function", "GO:0005125-cytokine activity", "6", "5.03E-05"], ["", "GO:0008083-growth factor activity", "5", "5.17E-04"], ["", "GO:0005515-protein binding", "31", "1.24E-03"], ["", "GO:0004175-endopeptidase activity", "3", "6.90E-03"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T0004"}}, {"id": "asset:table:pmid:31114367:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ee60491e2865b7a94f4acb2de27ed85995440e6a81081e2e4319b270ec25292d", "bytes": 515, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#T0005", "version": null, "note": "KEGG pathways of key genes", "structure": {"pmcid": "PMC6489589", "section_index": 14, "section_title": "Functional and pathway analysis of key genes", "row_count": 6, "column_count": 3}, "table": {"label": "Table 5", "caption": "KEGG pathways of key genes", "rows": [["KEGG terms", "Number of enriched genes", "P-value"], ["hsa04668:TNF signaling pathway", "5", "5.44 E-04"], ["hsa05323:Rheumatoid arthritis", "4", "3.80 E-03"], ["hsa04060:Cytokine-cytokine receptor interaction", "5", "1.07 E-02"], ["hsa05202:Transcriptional misregulation in cancer", "4", "2.18 E-02"], ["hsa05200:Pathways in cancer", "5", "4.51 E-02"]], "row_count": 6, "column_count": 3, "numeric_cells": 15, "header_rows": 1, "locator": "section[14]/table-wrap[2]#T0005"}}], "gaps": ["asset:data:geo:GSE13898 not downloaded", "asset:data:geo:GSE13898 licence not read", "asset:data:geo:GSE1420 not downloaded", "asset:data:geo:GSE1420 licence not read", "asset:data:geo:GSE16456 not downloaded", "asset:data:geo:GSE16456 licence not read", "asset:data:geo:GSE26886 not downloaded", "asset:data:geo:GSE26886 licence not read", "asset:data:geo:GSE92396 not downloaded", "asset:data:geo:GSE92396 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To verify the results obtained thus far, data for 89 EAC tissue samples and the clinical data of the patients were downloaded from TCGA, and the prognostic value of the key genes and miRNAs was identified by Kaplan-Meier analysis. The survival package in R software was used for survival analysis."}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE92396", "GSE13898", "GSE26886", "GSE1420", "GSE16456"], "resolved_accessions": ["GSE92396", "GSE13898", "GSE26886", "GSE1420", "GSE16456"], "statements": ["The GSE92396 dataset included a total of 9 normal tissues and 12 EAC tissues"], "basis": "The paper names GSE92396, GSE13898, GSE26886, GSE1420, GSE16456 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:31114367", "data:geo:GSE13898", "asset:table:pmid:31114367:1", "asset:table:pmid:31114367:2", "asset:table:pmid:31114367:3", "asset:table:pmid:31114367:4", "asset:table:pmid:31114367:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13898"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:45Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 27061, "completion_tokens": 1785, "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:31114367", "type": "paper", "label": "pmid:31114367"}, {"id": "source:pmid:31114367", "type": "manuscript", "label": "PMID 31114367 full text"}, {"id": "data:geo:GSE13898", "type": "dataset", "label": "GEO GSE13898"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31114367", "type": "paper", "label": "pmid:31114367"}, {"id": "source:pmid:31114367", "type": "manuscript", "label": "PMID 31114367 full text"}, {"id": "data:geo:GSE13898", "type": "dataset", "label": "GEO GSE13898"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31114367", "type": "extraction", "used": ["source:pmid:31114367"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13898", "type": "accession_resolution", "used": ["data:geo:GSE13898"], "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:31114367", "parent_hash": "sha256:0bec132e02f323140da2d514047b984f7eb2aeaeedd9c9735439f9c487148d68", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE13898 licence not read", "asset:data:geo:GSE13898 not downloaded", "asset:data:geo:GSE1420 licence not read", "asset:data:geo:GSE1420 not downloaded", "asset:data:geo:GSE16456 licence not read", "asset:data:geo:GSE16456 not downloaded", "asset:data:geo:GSE26886 licence not read", "asset:data:geo:GSE26886 not downloaded", "asset:data:geo:GSE92396 licence not read", "asset:data:geo:GSE92396 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To verify the results obtained thus far, data for 89 EAC tissue samples and the clinical data of the patients were downloaded from TCGA, and the prognostic value of the key genes and miRNAs was identified by Kaplan-Meier analysis. The survival package in R software was used for survival analysis."], "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":"2026-11-04T00:32:12+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}}}