{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33327311", "kind": "science-record", "revision": 7, "content_hash": "sha256:78f119f4495448978ee82d98917b2563aa32b70c3dbf88485d9a6b09fbd804f5", "created_at": "2026-11-01T15:41:19Z", "updated_at": "2026-11-01T22:02:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Screening and identification of key genes between liver hepatocellular carcinoma (LIHC) and cholangiocarcinoma (CHOL) by bioinformatic analysis.", "doi": "10.1097/MD.0000000000023563", "pmid": "33327311", "authors": ["Xindan Kang", "Li Bai", "Xiaoguang Qi", "Jing Wang"], "journal": "Medicine", "year": 2020, "abstract": "BACKGROUND: Liver hepatocellular carcinoma (LIHC) and cholangiocarcinoma (CHOL) are common primary liver cancers worldwide. Liver stem cells have biopotential to differentiate into either hepatocytes and cholangiocytes, the phenotypic overlap between LIHC and CHOL has been acceptable as a continuous liver cancer spectrum. However, few studies directly investigated the underlying molecular mechanisms between LIHC and CHOL.\nMETHOD: To identify the candidate genes between LIHC and CHOL, three data series including GSE31370, GSE15765 and GSE40367 were downloaded from Gene Expression Omnibus (GEO) database. The differentially expressed genes (DEGs) were identified, and function enrichment analyses were performed. The protein-protein interaction network (PPI) was constructed and the module analysis was performed using STRING and Cytoscape.\nRESULTS: A total of 171 DEGs were identified, consisting of 49 downregulated genes and 122 upregulated genes. Compared with CHOL, the enriched functions of the DEGs mainly included steroid metabolic process, acute inflammatory response, coagulation. Meanwhile, the pathway of KEGG enrichment analyses showed that the upregulated gene(s) were mainly enriched complement and coagulation cascades, cholesterol metabolism and PPAR signaling pathway, while the downregulated gene(s) were mainly enriched in ECM-receptor interaction, focal adhesion, bile secretion. Similarly, the most significant module was identified and biological process analysis revealed that these genes were mainly enriched in regulation of blood coagulation, acute inflammatory response, complement and coagulation cascades. Finally, two (ITIH2 and APOA2) of 10 hub genes had been screened out to help differential diagnosis.\nCONCLUSION: 171 DEGs and two (ITIH2 and APOA2) of 10 hub genes identified in the present study help us understand the different molecular mechanisms between LIHC and CHOL, and provide candidate targets for differential diagnosis.", "claims": [{"id": "claim-data-access", "statement": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33327311", "locator": "sections[16] \"fn-group\" paragraph 1", "quote": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study."}], "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:33327311"], "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:GSE15765"], "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:GSE15765"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33327311", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000023563", "sha256": "sha256:e0f0d74fec6abe5e1533e88696ca3a7c12d1b46d9b9cb68cf077193ddcb0571f", "bytes": 23396, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000023563", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7738106", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15765", "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=GSE15765", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15765", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM395647", "GSM395648", "GSM395649", "GSM395650", "GSM395651", "GSM395652", "GSM395653", "GSM395654", "GSM395655", "GSM395656", "GSM395657", "GSM395658", "GSM395659", "GSM395660", "GSM395661", "GSM395662", "GSM395663", "GSM395664", "GSM395665", "GSM395666", "GSM395667", "GSM395669", "GSM395670", "GSM395671", "GSM395672", "GSM395673", "GSM395674", "GSM395675", "GSM395676", "GSM395677", "GSM395678", "GSM395679", "GSM395680", "GSM395681", "GSM395682", "GSM395683", "GSM395684", "GSM395685", "GSM395686", "GSM395687", "GSM395688", "GSM395689", "GSM395690", "GSM395691", "GSM395692", "GSM395693", "GSM395694", "GSM395695", "GSM395696", "GSM395697", "GSM395698", "GSM395699", "GSM395700", "GSM395701", "GSM395702", "GSM395703", "GSM395704", "GSM395705", "GSM395706", "GSM395707", "GSM395708", "GSM395709", "GSM395710", "GSM395711", "GSM395712", "GSM395713", "GSM395714", "GSM395715", "GSM395716", "GSM395717", "GSM395718", "GSM395719", "GSM395720", "GSM395721", "GSM395722", "GSM395723", "GSM395724", "GSM395725", "GSM395726", "GSM395727", "GSM395728", "GSM395729", "GSM395730", "GSM395731", "GSM395732", "GSM395733", "GSM395734", "GSM395735", "GSM395736", "GSM395737"], "sample_count": 90, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Identification of cholangiocarcinoma-like gene expression traits in hepatocellular 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:GSE31370", "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=GSE31370", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31370", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM777740", "GSM777741", "GSM777742", "GSM777743", "GSM777744", "GSM777745", "GSM777746", "GSM777747", "GSM777748", "GSM777749", "GSM777750", "GSM777751", "GSM777752", "GSM777753", "GSM777754", "GSM777755", "GSM777756", "GSM777757", "GSM777758", "GSM777759", "GSM777760", "GSM777761", "GSM777762", "GSM777763", "GSM777764", "GSM777765"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Fibrous stromal component in hepatocellular carcinoma reveals a cholangiocarcinoma-like gene expression trait and epithelial-mesenchymal transition.", "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:GSE40367", "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=GSE40367", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40367", "version": null, "note": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM992272", "GSM992273", "GSM992274", "GSM992275", "GSM992276", "GSM992277", "GSM992278", "GSM992279", "GSM992280", "GSM992281", "GSM992282", "GSM992283", "GSM992284", "GSM992285", "GSM992286", "GSM992287", "GSM992288", "GSM992289", "GSM992290", "GSM992291", "GSM992292", "GSM992293", "GSM992294", "GSM992295", "GSM992296", "GSM992297", "GSM992298", "GSM992299", "GSM992300", "GSM992301", "GSM992302", "GSM992303", "GSM992304", "GSM992305", "GSM992306", "GSM992307", "GSM992308", "GSM992309", "GSM992310", "GSM992311", "GSM992312", "GSM992313", "GSM992314", "GSM992315", "GSM992316", "GSM992317", "GSM992318", "GSM992319", "GSM992320", "GSM992321", "GSM992322", "GSM992323", "GSM992324", "GSM992325", "GSM992326", "GSM992327", "GSM992328", "GSM992329", "GSM992330", "GSM992331", "GSM992332"], "sample_count": 61, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of liver and colon cancer primary tumors and metastasis", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33327311:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d2a7c3bbf11bfbb366a5818fd5d2036d8e59157fc766b2df8b9e93bf475a0ab7", "bytes": 360, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Statistics of 3 data series derived from GEO database.", "structure": {"pmcid": "PMC7738106", "section_index": 3, "section_title": "Data source", "row_count": 4, "column_count": 5}, "table": {"label": "Table 1", "caption": "Statistics of 3 data series derived from GEO database.", "rows": [["GEO series", "CHOL", "LIHC", "Total", "Tissue source"], ["GSE31370", "6", "15", "26", "liver"], ["GSE15765", "13", "70", "90", "liver"], ["GSE40367", "4", "15", "61", "liver"]], "row_count": 4, "column_count": 5, "numeric_cells": 12, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33327311:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:47ed48af522eea6064d269aeeeb2c4a76544253df2ce486c72df55c1267ff3c8", "bytes": 1608, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T3", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module.", "structure": {"pmcid": "PMC7738106", "section_index": 6, "section_title": "PPI network construction and module analysis", "row_count": 20, "column_count": 5}, "table": {"label": "Table 3", "caption": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module.", "rows": [["Category", "Term", "Pathway description", "Count in gene set", "Adjusted P"], ["BP term", "GO:0009611", "response to wounding", "16", "1.06E-11"], ["BP term", "GO:0030193", "regulation of blood coagulation", "8", "2.04E-10"], ["BP term", "GO:0050818", "regulation of coagulation", "8", "3.64E-10"], ["BP term", "GO:0032101", "regulation of response to external stimulus", "10", "3.43E-09"], ["BP term", "GO:0042060", "wound healing", "10", "1.43E-08"], ["BP term", "GO:0006953", "acute-phase response", "7", "1.91E-08"], ["BP term", "GO:0030195", "negative regulation of blood coagulation", "6", "8.61E-08"], ["BP term", "GO:0002526", "acute inflammatory response", "8", "7.76E-08"], ["BP term", "GO:0050817", "coagulation", "8", "9.16E-08"], ["BP term", "GO:0007596", "blood coagulation", "8", "9.16E-08"], ["BP term", "GO:0050819", "negative regulation of coagulation", "6", "1.17E-07"], ["BP term", "GO:0007599", "hemostasis", "8", "1.12E-07"], ["CC term", "GO:0005615", "extracellular space", "29", "5.54E-20"], ["CC term", "GO:0005576", "extracellular region", "22", "1.77E-19"], ["CC term", "GO:0044421", "extracellular region part", "22", "1.29E-16"], ["MF term", "GO:0004857", "enzyme inhibitor activity", "14", "3.38E-13"], ["MF term", "GO:0004866", "endopeptidase inhibitor activity", "12", "2.47E-13"], ["MF term", "GO:0030414", "peptidase inhibitor activity", "12", "2.99E-13"], ["KEGG pathway", "hsa04610", "Complement and coagulation cascades", "10", "4.97E-14"]], "row_count": 20, "column_count": 5, "numeric_cells": 57, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:33327311:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5ef203f3149922ea3e8be840e527732d1274453d955d74a2d4a38005c531e5bb", "bytes": 1641, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T2", "version": null, "note": "GO analysis of DEGs between LIHC and CHOL.", "structure": {"pmcid": "PMC7738106", "section_index": 10, "section_title": "GO term and KEGG pathway enrichment analyses of the common DEGs", "row_count": 22, "column_count": 5}, "table": {"label": "Table 2", "caption": "GO analysis of DEGs between LIHC and CHOL.", "rows": [["Category", "Term", "Pathway description", "Count in gene set", "Adjusted P"], ["Upregulated"], ["BP term", "GO:0008202", "steroid metabolic process", "19", "4.58E-11"], ["BP term", "GO:0009611", "response to wounding", "25", "2.68E-09"], ["BP term", "GO:0016125", "sterol metabolic process", "13", "1.25E-08"], ["BP term", "GO:0008203", "cholesterol metabolic process", "12", "6.16E-08"], ["BP term", "GO:0002526", "acute inflammatory response", "12", "9.87E-08"], ["BP term", "GO:0032101", "regulation of response to external stimulus", "14", "1.04E-07"], ["BP term", "GO:0042060", "wound healing", "14", "8.55E-07"], ["BP term", "GO:0007596", "blood coagulation", "11", "1.55E-06"], ["BP term", "GO:0050817", "coagulation", "11", "1.55E-06"], ["BP term", "GO:0030193", "regulation of blood coagulation", "8", "1.97E-06"], ["CC term", "GO:0005615", "extracellular space", "33", "1.17E-13"], ["CC term", "GO:0005576", "extracellular region", "50", "2.31E-11"], ["CC term", "GO:0044421", "extracellular region part", "33", "3.88E-10"], ["MF term", "GO:0004866", "endopeptidase inhibitor activity", "13", "8.73E-07"], ["MF term", "GO:0004867", "serine-type endopeptidase inhibitor activity", "11", "7.23E-07"], ["MF term", "GO:0030414", "peptidase inhibitor activity", "13", "5.38E-07"], ["MF term", "GO:0004857", "enzyme inhibitor activity", "16", "4.87E-07"], ["downregulated", "", "", "", ""], ["CC term", "GO:0005887", "integral to plasma membrane", "12", "0.043720371"], ["CC term", "GO:0031226", "intrinsic to plasma membrane", "12", "0.035406774"]], "row_count": 22, "column_count": 5, "numeric_cells": 57, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:33327311:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:47ed48af522eea6064d269aeeeb2c4a76544253df2ce486c72df55c1267ff3c8", "bytes": 1608, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T3", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module.", "structure": {"pmcid": "PMC7738106", "section_index": 11, "section_title": "PPI network construction and module analysis", "row_count": 20, "column_count": 5}, "table": {"label": "Table 3", "caption": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module.", "rows": [["Category", "Term", "Pathway description", "Count in gene set", "Adjusted P"], ["BP term", "GO:0009611", "response to wounding", "16", "1.06E-11"], ["BP term", "GO:0030193", "regulation of blood coagulation", "8", "2.04E-10"], ["BP term", "GO:0050818", "regulation of coagulation", "8", "3.64E-10"], ["BP term", "GO:0032101", "regulation of response to external stimulus", "10", "3.43E-09"], ["BP term", "GO:0042060", "wound healing", "10", "1.43E-08"], ["BP term", "GO:0006953", "acute-phase response", "7", "1.91E-08"], ["BP term", "GO:0030195", "negative regulation of blood coagulation", "6", "8.61E-08"], ["BP term", "GO:0002526", "acute inflammatory response", "8", "7.76E-08"], ["BP term", "GO:0050817", "coagulation", "8", "9.16E-08"], ["BP term", "GO:0007596", "blood coagulation", "8", "9.16E-08"], ["BP term", "GO:0050819", "negative regulation of coagulation", "6", "1.17E-07"], ["BP term", "GO:0007599", "hemostasis", "8", "1.12E-07"], ["CC term", "GO:0005615", "extracellular space", "29", "5.54E-20"], ["CC term", "GO:0005576", "extracellular region", "22", "1.77E-19"], ["CC term", "GO:0044421", "extracellular region part", "22", "1.29E-16"], ["MF term", "GO:0004857", "enzyme inhibitor activity", "14", "3.38E-13"], ["MF term", "GO:0004866", "endopeptidase inhibitor activity", "12", "2.47E-13"], ["MF term", "GO:0030414", "peptidase inhibitor activity", "12", "2.99E-13"], ["KEGG pathway", "hsa04610", "Complement and coagulation cascades", "10", "4.97E-14"]], "row_count": 20, "column_count": 5, "numeric_cells": 57, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:33327311:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:05d1d433a1f3924a655a31d561c8ef9a4615a4620930d7e7c5e54d1789fb071f", "bytes": 598, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T4", "version": null, "note": "The description of top 10 hub genes.", "structure": {"pmcid": "PMC7738106", "section_index": 12, "section_title": "Hub genes and analysis of hub genes", "row_count": 11, "column_count": 3}, "table": {"label": "Table 4", "caption": "The description of top 10 hub genes.", "rows": [["Gene symbol", "Gen description", "Degree"], ["FGA", "fibrinogen alpha chain", "29"], ["FGG", "fibrinogen gamma chain", "29"], ["ITIH2", "inter-alpha-trypsin inhibitor heavy chain 2", "29"], ["AHSG", "alpha 2-HS glycoprotein", "29"], ["APOA1", "apolipoprotein A1", "28"], ["APOB", "apolipoprotein B", "28"], ["F2", "coagulation factor II", "28"], ["APOA2", "apolipoprotein A2", "27"], ["PROC", "protein C", "27"], ["KNG1", "kininogen 1", "27"]], "row_count": 11, "column_count": 3, "numeric_cells": 13, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE15765 not downloaded", "asset:data:geo:GSE15765 licence not read", "asset:data:geo:GSE31370 not downloaded", "asset:data:geo:GSE31370 licence not read", "asset:data:geo:GSE40367 not downloaded", "asset:data:geo:GSE40367 licence not read"]}, "analysis": {"state": "complete", "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"}}], "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": ["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": "R1", "reachable": true, "accessions": ["GSE31370", "GSE15765", "GSE40367"], "resolved_accessions": ["GSE31370", "GSE15765", "GSE40367"], "statements": ["Data sharing not applicable to this article as no datasets were generated or analyzed during the current study."], "basis": "The paper names GSE31370, GSE15765, GSE40367 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33327311", "data:geo:GSE15765", "asset:table:pmid:33327311:1", "asset:table:pmid:33327311:2", "asset:table:pmid:33327311:3", "asset:table:pmid:33327311:4", "asset:table:pmid:33327311:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15765"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:19:02Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 17382, "completion_tokens": 1969, "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:33327311", "type": "paper", "label": "pmid:33327311"}, {"id": "source:pmid:33327311", "type": "manuscript", "label": "PMID 33327311 full text"}, {"id": "data:geo:GSE15765", "type": "dataset", "label": "GEO GSE15765"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33327311", "type": "paper", "label": "pmid:33327311"}, {"id": "source:pmid:33327311", "type": "manuscript", "label": "PMID 33327311 full text"}, {"id": "data:geo:GSE15765", "type": "dataset", "label": "GEO GSE15765"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33327311", "type": "extraction", "used": ["source:pmid:33327311"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15765", "type": "accession_resolution", "used": ["data:geo:GSE15765"], "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:33327311", "parent_hash": "sha256:3d089e0fad0375566337cfa813f8b72dc485d36edce297925046466e921ad40a", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE15765 licence not read", "asset:data:geo:GSE15765 not downloaded", "asset:data:geo:GSE31370 licence not read", "asset:data:geo:GSE31370 not downloaded", "asset:data:geo:GSE40367 licence not read", "asset:data:geo:GSE40367 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["use GEPIA as a web server for analyzing the RNA sequencing expression data from the Cancer Genome Atlas"], "order_basis": "paper_text_order:2876", "id": "assay:1"}, {"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": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T01:45:53+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}}}