{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34041839", "kind": "science-record", "revision": 4, "content_hash": "sha256:c38d083e741bc60e9a4fb084edaf971afada033e50ab568f0df41d82b3e34ca5", "created_at": "2026-11-01T15:41:36Z", "updated_at": "2026-11-01T21:25:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identifying potential biomarkers in hepatitis B virus infection and its response to the antiviral therapy by integrated bioinformatic analysis.", "doi": "10.1111/jcmm.16655", "pmid": "34041839", "authors": ["Yi He", "Yingzhi Zhou", "Huimin Wang", "Jingyang Yin", "Yunan Chang", "Peng Hu", "Hong Ren", "Hongmei Xu"], "journal": "Journal of cellular and molecular medicine", "year": 2021, "abstract": "The antiviral treatment efficacy varies among chronic hepatitis B (CHB) patients and the underlying mechanism is unclear. An integrated bioinformatics analysis was performed to investigate the host factors that affect the therapeutic responsiveness in CHB patients. Four GEO data sets (GSE54747, GSE27555, GSE66698 and GSE66699) were downloaded from the Gene Expression Omnibus (GEO) database and analysed to identify differentially expressed genes(DEGs). Enrichment analyses of the DEGs were conducted using the DAVID database. Immune cell infiltration characteristics were analysed by CIBERSORT. Upstream miRNAs and lncRNAs of hub DEGs were identified by miRWalk 3.0 and miRNet in combination with the MNDR platform. As a result, seventy-seven overlapping DEGs and 15 hub genes were identified including CCL5, CXCL9, MYH2, CXCR4, CD74, CCL4, HLA-DRB1, ACTA1, CD69, CXCL10, HLA-DRB5, HLA-DQB1, CXCL13, STAT1 and CKM. The enrichment analyses revealed that the DEGs were mainly enriched in immune response and chemokine signalling pathways. Investigation of immune cell infiltration in liver samples suggested significantly different infiltration between responders and non-responders, mainly characterized by higher proportions of CD8+ T cells and activated NK cells in non-responders. The prediction of upstream miRNAs and lncRNAs led to the identification of a potential mRNA-miRNA-lncRNA regulatory network composed of 2 lncRNAs (H19 and GAS5) and 5 miRNAs (hsa-mir-106b-5p, hsa-mir-17-5p, hsa-mir-20a-5p, hsa-mir-6720-5p and hsa-mir-93-5p) targeting CCL5 mRNA. In conclusion, our study suggested that host genetic factors could affect therapeutic responsiveness in CHB patients. The antiviral process might be associated with the chemokine-mediated immune response and immune cell infiltration in the liver microenvironment.", "claims": [{"id": "claim-method", "statement": "The interactive web tool GEO2R (https://www.ncbi.nlm.nih.gov/geo/geo2r), provided by the GEO database, was utilized to screen DEGs. |log2FC| > 1 was set as the cut‐off standards and P < .05 was considered to indicate statistical significance. The adjustment of P‐values and the Benjamini and Hochberg method were applied to optimize the statistical power and control false discovery rate.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34041839", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "The interactive web tool GEO2R (https://www.ncbi.nlm.nih.gov/geo/geo2r), provided by the GEO database, was utilized to screen DEGs. |log2FC| > 1 was set as the cut‐off standards and P < .05 was considered to indicate statistical significance. The adjustment of P‐values and the Benjamini and Hochberg method were applied to optimize the statistical power and control false discovery rate."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34041839", "locator": "sections[26] \"DATA AVAILABILITY STATEMENT\" paragraph 2", "quote": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request."}], "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:34041839"], "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:GSE27555"], "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:GSE27555"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34041839", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/jcmm.16655", "sha256": "sha256:57f0137465bd7bb9b978da063b03c81280da342880c028ef7413ebc6306759ef", "bytes": 57156, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/jcmm.16655", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8278120", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE27555", "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=GSE27555", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27555", "version": null, "note": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM680443", "GSM680444", "GSM680445", "GSM680446", "GSM680447", "GSM680448", "GSM680449", "GSM680450", "GSM680451", "GSM680452", "GSM680453", "GSM680454", "GSM680455"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Preactivation of the interferon signaling in liver is correlated with non-response to interferon alpha therapy in patients chronically infected with hepatitis B virus", "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:GSE54747", "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=GSE54747", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54747", "version": null, "note": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1323157", "GSM1323158", "GSM1323159", "GSM1323160", "GSM1323161", "GSM1323162", "GSM1323163", "GSM1323164", "GSM1323165", "GSM1323166", "GSM1323167", "GSM1323168", "GSM1323169", "GSM1323170", "GSM1323171"], "sample_count": 15, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "An intrahepatic gene expression signature of enhanced immune activity predicts response to peginterferon and adefovir in chronic hepatitis B patients", "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:GSE66698", "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=GSE66698", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66698", "version": null, "note": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1629354", "GSM1629355", "GSM1629356", "GSM1629357", "GSM1629358", "GSM1629359", "GSM1629360", "GSM1629361", "GSM1629362", "GSM1629363", "GSM1629364", "GSM1629365", "GSM1629366", "GSM1629367", "GSM1629368", "GSM1629369", "GSM1629370"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Liver gene expression profiles of  interferon therapy in chronic hepatitis B Patients (mRNA)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE66699", "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=GSE66699", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66699", "version": null, "note": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data sets used and analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1629371", "GSM1629372"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "5188", "taxon": "Homo sapiens", "title": "Liver gene expression profiles of  interferon therapy in chronic hepatitis B Patients (Exon)", "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:34041839:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:72eefb658917beb5b1f466204d12d6451e4e00beb1d29bb44b3d88bb9be80e58", "bytes": 763, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#jcmm16655-tbl-0001", "version": null, "note": "Hub modules and top biological process of genes involved in each module", "structure": {"pmcid": "PMC8278120", "section_index": 13, "section_title": "PPI network construction and module analyses", "row_count": 4, "column_count": 9}, "table": {"label": "TABLE 1", "caption": "Hub modules and top biological process of genes involved in each module", "rows": [["Module", "Score", "Node", "Edge", "Node ID", "Seed", "Top biological process", "Gene count", "P‐value"], ["1", "9.600", "11", "48", "CKM,MYL1,ACTA1,MB, MYL2,MYH2,TNNC1,TTN, MYBPC1,MYH1,TNNC2", "CKM", "Muscle Filament Sliding", "8", "2.0E‐17"], ["2", "9.333", "10", "42", "CXCL13,CCL20,CXCL10, STAT1,CD69,CXCL9,CXCR4, CCL4,CCL5,CXCL11", "CXCL13", "Chemokine‐mediated signalling pathway", "8", "6.4E‐16"], ["3", "6.500", "9", "26", "CD74,GBP1,CTSC,HLA‐DQB1,HLA‐DMA,HLA‐DRB1,HLA‐DOA,HLA‐DRB5,FCGR1B", "CD74", "Immune response", "8", "4.6E‐11"]], "row_count": 4, "column_count": 9, "numeric_cells": 22, "header_rows": 1, "locator": "section[13]/table-wrap[1]#jcmm16655-tbl-0001"}}, {"id": "asset:table:pmid:34041839:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e2726c9b2cbb2c9bf3bff11a7ed1be1f938039f373debbc2e8418c7e8f477f50", "bytes": 1652, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#jcmm16655-tbl-0002", "version": null, "note": "Hub genes and top GO terms and KEEG pathways of enrichment analyses", "structure": {"pmcid": "PMC8278120", "section_index": 14, "section_title": "Hub genes identification and analyses", "row_count": 13, "column_count": 5}, "table": {"label": "TABLE 2", "caption": "Hub genes and top GO terms and KEEG pathways of enrichment analyses", "rows": [["Category", "Term", "Count", "P‐Value", "Genes"], ["BP", "GO:0 006 955~immune response", "9", "3.85E‐10", "CXCL10, CD74, HLA‐DRB5, CXCL9, CCL5, CCL4, CXCL13, HLA‐DRB1, HLA‐DQB1"], ["GO:0 070 098~chemokine‐mediated signalling pathway", "6", "2.28E‐9", "CXCL10, CXCL9, CCL5, CCL4, CXCR4, CXCL13"], ["GO:0 002 381~immunoglobulin production involved in immunoglobulin mediated immune response", "3", "6.45E‐6", "HLA‐DRB5, HLA‐DRB1, HLA‐DQB1"], ["CC", "GO:0 009 897~external side of plasma membrane", "6", "3.82E‐7", "CXCL10, CD74, HLA‐DRB5, CXCL9, CD69, HLA‐DRB1"], ["GO:0 042 613~MHC class II protein complex 4", "4", "5.51E‐7", "CD74, HLA‐DRB5, HLA‐DRB1, HLA‐DQB1"], ["GO:0 071 556~integral component of lumenal side of endoplasmic reticulum membrane", "4", "1.30E‐6", "CD74, HLA‐DRB5, HLA‐DRB1, HLA‐DQB1"], ["MF", "GO:0 008 009~chemokine activity", "5", "6.14E‐8", "CXCL10, CXCL9, CCL5, CCL4, CXCL13"], ["GO:0 048 248~CXCR3 chemokine receptor binding", "3", "6.38E‐6", "CXCL10, CXCL9, CXCL13"], ["GO:0 031 730~CCR5 chemokine receptor binding", "3", "1.78E‐5", "STAT1, CCL5, CCL4"], ["KEGG", "hsa04062:Chemokine signalling pathway", "7", "2.91E‐7", "CXCL10, CXCL9, STAT1, CCL5, CCL4, CXCR4, CXCL13"], ["hsa04620:Toll‐like receptor signalling pathway", "5", "2.40E‐5", "CXCL10, CXCL9, STAT1, CCL5, CCL4"], ["hsa04060:Cytokine‐cytokine receptor interaction", "6", "3.41E‐5", "CXCL10, CXCL9, CCL5, CCL4, CXCR4, CXCL13"]], "row_count": 13, "column_count": 5, "numeric_cells": 46, "header_rows": 1, "locator": "section[14]/table-wrap[1]#jcmm16655-tbl-0002"}}, {"id": "asset:table:pmid:34041839:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:efcaa78736d38d13484af00d03f9244596c94097464ff2c711b81b06b33b3d5d", "bytes": 1620, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#jcmm16655-tbl-0003", "version": null, "note": "The validated miRNA‐mRNA pairs identified by miRWalk 3.0 database", "structure": {"pmcid": "PMC8278120", "section_index": 16, "section_title": "Prediction of related non‐coding RNAs (ncRNAs)", "row_count": 22, "column_count": 6}, "table": {"label": "TABLE 3", "caption": "The validated miRNA‐mRNA pairs identified by miRWalk 3.0 database", "rows": [["miRNA ID", "Gene symbol", "Number of pairings", "Binding region length", "Longest consecutive pairings", "Validated data source"], ["hsa‐let‐7a‐5p", "ACTA1", "15", "16", "15", "MIRT550902"], ["hsa‐let‐7b‐5p", "ACTA1", "21", "25", "14", "MIRT550901"], ["hsa‐let‐7c‐5p", "ACTA1", "19", "24", "13", "MIRT550900"], ["hsa‐miR‐98‐5p", "ACTA1", "15", "16", "15", "MIRT550892"], ["hsa‐miR‐146a‐5p", "CXCR4", "19", "27", "9", "MIRT000006"], ["hsa‐miR‐146a‐5p", "CXCR4", "20", "41", "11", "MIRT000006"], ["hsa‐miR‐494‐5p", "CXCR4", "18", "22", "12", "MIRT735294"], ["hsa‐miR‐34a‐5p", "STAT1", "15", "19", "7", "MIRT025278"], ["hsa‐miR‐661", "CXCL10", "14", "28", "8", "MIRT540505"], ["hsa‐miR‐939‐3p", "CXCL10", "9", "10", "9", "MIRT540515"], ["hsa‐miR‐3187‐5p", "CXCL10", "15", "21", "7", "MIRT540513"], ["hsa‐miR‐32‐5p", "CD69", "17", "21", "8", "MIRT728020"], ["hsa‐miR‐20a‐5p", "CCL5", "16", "23", "9", "MIRT685367"], ["hsa‐miR‐4726‐5p", "CCL5", "20", "26", "10", "MIRT518347"], ["hsa‐miR‐4726‐5p", "CCL5", "18", "23", "13", "MIRT518347"], ["hsa‐miR‐6720‐5p", "CCL5", "22", "36", "15", "MIRT685342"], ["hsa‐miR‐6849‐3p", "CCL5", "18", "25", "9", "MIRT685347"], ["hsa‐miR‐17‐5p", "CCL5", "16", "23", "9", "MIRT685368"], ["hsa‐miR‐93‐5p", "CCL5", "17", "23", "10", "MIRT685363"], ["hsa‐miR‐106b‐5p", "CCL5", "15", "21", "10", "MIRT685369"], ["hsa‐miR‐7151‐3p", "CCL5", "15", "19", "8", "MIRT518343"]], "row_count": 22, "column_count": 6, "numeric_cells": 109, "header_rows": 1, "locator": "section[16]/table-wrap[1]#jcmm16655-tbl-0003"}}, {"id": "asset:table:pmid:34041839:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:71bb6465aa6bc3b856b3d628c5afefaa9dc3ac008f0da23412c82834a63be220", "bytes": 589, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[2]#jcmm16655-tbl-0004", "version": null, "note": "The correlation between miRNA‐lncRNA pairs identified by cross‐linking miRNet and MNDR database", "structure": {"pmcid": "PMC8278120", "section_index": 16, "section_title": "Prediction of related non‐coding RNAs (ncRNAs)", "row_count": 7, "column_count": 5}, "table": {"label": "TABLE 4", "caption": "The correlation between miRNA‐lncRNA pairs identified by cross‐linking miRNet and MNDR database", "rows": [["lncRNA ID", "Disease Name", "Scores by MNDR", "Correlated miRNA", "Experiment"], ["H19", "Hepatitis B, Chronic", "0.999141", "hsa‐mir‐106b‐5p", "CLIP‐Seq"], ["hsa‐mir‐17‐5p"], ["hsa‐mir‐20a‐5p"], ["hsa‐mir‐6720‐5p"], ["hsa‐mir‐93‐5p"], ["GAS5", "Hepatitis B", "0.982118", "hsa‐mir‐6720‐5p", "CLIP‐Seq"]], "row_count": 7, "column_count": 5, "numeric_cells": 9, "header_rows": 1, "locator": "section[16]/table-wrap[2]#jcmm16655-tbl-0004"}}], "gaps": ["asset:data:geo:GSE27555 not downloaded", "asset:data:geo:GSE27555 licence not read", "asset:data:geo:GSE54747 not downloaded", "asset:data:geo:GSE54747 licence not read", "asset:data:geo:GSE66698 not downloaded", "asset:data:geo:GSE66698 licence not read", "asset:data:geo:GSE66699 not downloaded", "asset:data:geo:GSE66699 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "GEO2R differential expression analysis with Benjamini–Hochberg P-value adjustment", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The interactive web tool GEO2R (https://www.ncbi.nlm.nih.gov/geo/geo2r), provided by the GEO database, was utilized to screen DEGs. |log2FC| > 1 was set as the cut‐off standards and P < .05 was considered to indicate statistical significance. The adjustment of P‐values and the Benjamini and Hochberg method were applied to optimize the statistical power and control false discovery rate."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (GEO2R differential expression analysis with Benjamini–Hochberg P-value adjustment), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE54747", "GSE27555", "GSE66698", "GSE66699"], "resolved_accessions": ["GSE54747", "GSE27555", "GSE66698", "GSE66699"], "statements": ["Data sets used and analysed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE54747, GSE27555, GSE66698, GSE66699 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": [], "assets": ["source:pmid:34041839", "data:geo:GSE27555", "asset:table:pmid:34041839:1", "asset:table:pmid:34041839:2", "asset:table:pmid:34041839:3", "asset:table:pmid:34041839:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE27555"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 42085, "completion_tokens": 1620, "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:34041839", "type": "paper", "label": "pmid:34041839"}, {"id": "source:pmid:34041839", "type": "manuscript", "label": "PMID 34041839 full text"}, {"id": "data:geo:GSE27555", "type": "dataset", "label": "GEO GSE27555"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34041839", "type": "paper", "label": "pmid:34041839"}, {"id": "source:pmid:34041839", "type": "manuscript", "label": "PMID 34041839 full text"}, {"id": "data:geo:GSE27555", "type": "dataset", "label": "GEO GSE27555"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34041839", "type": "extraction", "used": ["source:pmid:34041839"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE27555", "type": "accession_resolution", "used": ["data:geo:GSE27555"], "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:34041839", "parent_hash": "sha256:20aabd73717934079f595c6e235a3a3a3b9abb1803d611eb93e2e389447eb39e", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE27555 licence not read", "asset:data:geo:GSE27555 not downloaded", "asset:data:geo:GSE54747 licence not read", "asset:data:geo:GSE54747 not downloaded", "asset:data:geo:GSE66698 licence not read", "asset:data:geo:GSE66698 not downloaded", "asset:data:geo:GSE66699 licence not read", "asset:data:geo:GSE66699 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"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":"2026-11-04T01:22:11+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}}}