{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33425911", "kind": "science-record", "revision": 7, "content_hash": "sha256:a09eccae7dd11a050afdd298ffb90738edf3f4a5b31420fea8d9300b66a9cec0", "created_at": "2026-11-01T15:41:22Z", "updated_at": "2026-11-01T22:02:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Clinicopathological Significances of Cancer Stem Cell-Associated HHEX Expression in Breast Cancer.", "doi": "10.3389/fcell.2020.605744", "pmid": "33425911", "authors": ["Kexin Zhang", "Qi Zhao", "Zugui Li", "Fangmei Fu", "Hao Zhang", "Junjie Fu", "Minying Zheng", "Shiwu Zhang"], "journal": "Frontiers in cell and developmental biology", "year": 2020, "abstract": "Aberrant expression of the transcription factor hematopoietic ally expressed homeobox/proline-rich homeodomain (HHEX/PRH) is implicated in numerous cancers. However, the association of HHEX with breast cancer (BC) remains unclear. In this study, HHEX mRNA and protein expression were analyzed using the Oncomine, UALCAN, GEPIA, TCGAportal, and HPA databases. We evaluated the effect of HHEX on clinicopathological parameters using Kaplan-Meier plotter, OncoLnc, TCGAportal, PROGgeneV2, and BC-GenExMiner. Western blotting was performed to compare the level of HHEX in breast samples of Tientsin Albino 2 mice, human breast precancerous lesions, benign breast tumors, and BC. The correlation between HHEX and cancer stem cells was investigated using the GEO (GSE52327 and GSE94865) and GEPIA datasets. Networks between HHEX and survival-related gene marker sets and microRNAs were analyzed using GEPIA, StarBase, and Cytoscape. Results of this study showed that HHEX expression in BC was significantly lower than those in breast precancerous lesions and benign breast tumors at both mRNA and protein levels. BC patients with lower HHEX expression had significantly worse overall survival and disease-free survival. Moreover, HHEX significantly affected the clinicopathology of BC. Specifically, low HHEX expression was correlated with the following groups of patients: age ≤51 years, ER-negative or PR-negative patients, HER-2 positive, triple-negative breast cancer, and basal-like BC. Immunohistochemical analysis of the breast samples showed significant differences of HHEX staining index (P < 0.001) among the three groups. To further investigate the mechanism, we determined the intersection of differentially expressed genes related to BC stem cells and those genes after HHEX expression was altered. This led to the identification of four potentially regulated genes-CXL12, BLNK, PAG1, and LPXN. Using StarBase and km-plotter, the negative regulation of HHEX expression and survival trends, including miR-130b, miR-30e, and miR-301b were joined into miRNA-HHEX-mRNA potential regulatory network. The abilities of proliferation, migration and invasion increased in MDA-MB-231 and BT-549 breast cancer cell lines after HHEX down expression and decreased after HHEX overexpression compared them in the control cells. In conclusion, these data suggest that HHEX expression is downregulated in BC and HHEX may regulate the development of BC through the stem cell-related genes.", "claims": [{"id": "claim-method", "statement": "The Wilcoxon rank sum test was used to assess the significance of the observed differences.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33425911", "locator": "sections[3] \"HHEX Expression Level Analysis\" paragraph 2", "quote": "The Wilcoxon rank sum test was used to assess the significance of the observed differences."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33425911", "locator": "sections[33] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33425911"], "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:GSE52327"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:GSE52327"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33425911", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcell.2020.605744", "sha256": "sha256:d2a3dcb9c171d83296fccc83138bf8bf87fd842a911d140a103902ae0660f174", "bytes": 58354, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcell.2020.605744", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7785851", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE52327", "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=GSE52327", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52327", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1263184", "GSM1263185", "GSM1263186", "GSM1263187", "GSM1263188", "GSM1263189", "GSM1263190", "GSM1263191", "GSM1263192", "GSM1263193", "GSM1263194", "GSM1263195", "GSM1263196", "GSM1263197", "GSM1263198", "GSM1263199"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of ALDH+ breast cancer cells", "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:GSE94865", "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=GSE94865", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE94865", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2486657", "GSM2486658", "GSM2486659", "GSM2486660", "GSM2486661", "GSM2486662", "GSM2486663", "GSM2486664", "GSM2486665", "GSM2486666", "GSM2486667", "GSM2486668"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "18943", "taxon": "Homo sapiens", "title": "Gene expression changes following knockdown or overexpression of HHEX/PRH", "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:33425911:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:41f8f2a261585ac56eaa925bad997cba9273415694c72adf287fad5709682036", "bytes": 2450, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#T1", "version": null, "note": "Summary of databases used in this study.", "structure": {"pmcid": "PMC7785851", "section_index": 18, "section_title": "HHEX Expression Levels in Pan-Cancer and BC Patients", "row_count": 14, "column_count": 4}, "table": {"label": "Table 1", "caption": "Summary of databases used in this study.", "rows": [["Name", "Link", "This study", "Keywords"], ["Oncomine", "https://www.oncomine.org/resource/main.html", "To analyze the HHEX mRNA expression in different cancers", "Gene expression"], ["UALCAN", "http://ualcan.path.uab.edu/", "To analyze the HHEX mRNA expression in different molecular subtypes of BC patients", "Gene expression; 16 cancer types; survival curve; DNA methylation"], ["GEPIA", "http://gepia.cancer-pku.cn/detail.php", "To assess the correlations between genes", "Gene expression; survival curve; isoform details; genes correlation; similar genes detection"], ["TCGAportal", "http://www.tcgaportal.org", "To investigate the expression and survival of HHEX in human tissues", "Gene expression; 28 cancer types; survival curve; DNA methylation; mutation"], ["Human Protein Atlas", "https://www.proteinatlas.org/", "To detect HHEX protein expression and survival", "Proteins distribution; subcellular localization; impact for survival"], ["Kaplan-Meier Plotter", "http://kmplot.com/analysis/index.php?p=background", "To analyzed the correlations between genes and miRNAs expression and RFS as well as OS", "Breast cancer; subtype; survival curve"], ["OncoLnc", "https://www.oncolnc.org/", "To detect HHEX survival", "Breast cancer; survival curve"], ["PROGgeneV2", "http://genomics.jefferson.edu/proggene/", "", "Gene expression; breast cancer; subtype; survival curve"], ["bc-GenExMiner", "http://bcgenex.centregauducheau.fr/BC-GEM/GEM-Accueil.php?js=1", "To compute breast cancer gene-expression correlation analyses, for gene prognostic analyses", "Gene-expression correlation; gene prognostic analyses"], ["cBioportal", "http://www.cbioportal.org/", "To detect HHEX genetic alterations", "Genetic alterations; survival curve"], ["GEO", "https://www.ncbi.nlm.nih.gov/geo/", "To selected data sets related to breast cancer stem cells to explore further mechanisms", "Gene expression; datasets details"], ["STRING", "https://string-db.org/cgi/input.pl", "To obtain the interaction network between HHEX and other important proteins", "Protein details; interactive network; functional enrichment"], ["starBase v3.0", "http://starbase.sysu.edu.cn/index.php", "To predict the miRNAs related to HHEX; To perform miRNAs as well as correlation analysis between miRNAs and HHEX mRNA", "miRNA target; Pan-cancer"]], "row_count": 14, "column_count": 4, "numeric_cells": 4, "header_rows": 1, "locator": "section[18]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33425911:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a6d08e87433f76f4f86ae803e75e11f273a8b431eb9e5205bcfcf80f9a55d52a", "bytes": 524, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#T2A", "version": null, "note": "The differences of HHEX staining index among 53 cases of precancerous lesions (group I), 44 cases of primary BC (group II), and 48 cases of benign breast tumors (group III).", "structure": {"pmcid": "PMC7785851", "section_index": 20, "section_title": "HHEX Expression in Human BC Tissues", "row_count": 4, "column_count": 5}, "table": {"label": "Table 2A", "caption": "The differences of HHEX staining index among 53 cases of precancerous lesions (group I), 44 cases of primary BC (group II), and 48 cases of benign breast tumors (group III).", "rows": [["Group", "n", "Staining index for HHEX", "Value of statistic", "P"], ["Group I", "53", "4.19 ± 2.067", "χ2 = 25.081", "0.001"], ["Group II", "44", "2.11 ± 1.224", "", ""], ["Group III", "48", "4.77 ± 2.363", "", ""]], "row_count": 4, "column_count": 5, "numeric_cells": 8, "header_rows": 1, "locator": "section[20]/table-wrap[1]#T2A"}}, {"id": "asset:table:pmid:33425911:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9384295e149ef99d010a6a3188abb58902d964ad6e967104a357078fdaef9247", "bytes": 422, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[2]#T2B", "version": null, "note": "The difference of HHEX staining index between among 53 cases of precancerous lesions (group I) and 44 cases of primary BC (group II).", "structure": {"pmcid": "PMC7785851", "section_index": 20, "section_title": "HHEX Expression in Human BC Tissues", "row_count": 3, "column_count": 5}, "table": {"label": "Table 2B", "caption": "The difference of HHEX staining index between among 53 cases of precancerous lesions (group I) and 44 cases of primary BC (group II).", "rows": [["Group", "N", "Staining index for HHEX", "Z", "P"], ["Group I", "53", "4.19 ± 2.067", "−4.139", "0.001"], ["Group II", "44", "2.11 ± 1.224", "", ""]], "row_count": 3, "column_count": 5, "numeric_cells": 6, "header_rows": 1, "locator": "section[20]/table-wrap[2]#T2B"}}, {"id": "asset:table:pmid:33425911:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c311282de6e329652655096bcc7b86f164a4a1758e858afda42fe0b23cd53830", "bytes": 420, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[3]#T2C", "version": null, "note": "The difference of HHEX staining index between 44 cases of primary BC (group II) and 48 cases of benign breast tumors (group III).", "structure": {"pmcid": "PMC7785851", "section_index": 20, "section_title": "HHEX Expression in Human BC Tissues", "row_count": 3, "column_count": 5}, "table": {"label": "Table 2C", "caption": "The difference of HHEX staining index between 44 cases of primary BC (group II) and 48 cases of benign breast tumors (group III).", "rows": [["Group", "n", "Staining index for HHEX", "Z", "P"], ["Group II", "44", "2.11 ± 1.224", "−4.641", "0.001"], ["Group III", "48", "4.77 ± 2.363", "", ""]], "row_count": 3, "column_count": 5, "numeric_cells": 6, "header_rows": 1, "locator": "section[20]/table-wrap[3]#T2C"}}, {"id": "asset:table:pmid:33425911:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:343abacc14a657884c47e94e9bbacbae7265b5709c97c17aa4e06ebd36b87690", "bytes": 1424, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#T3", "version": null, "note": "Correlation between HHEX expression and clinicopathological features.", "structure": {"pmcid": "PMC7785851", "section_index": 22, "section_title": "Relationship Between HHEX and Clinicopathological Parameters of BC Patients", "row_count": 21, "column_count": 5}, "table": {"label": "Table 3", "caption": "Correlation between HHEX expression and clinicopathological features.", "rows": [["", "OS", "RFS"], ["Characteristic", "HR (95% CI)", "Log rank P", "HR (95% CI)", "Log rank P"], ["GENE SYMBOL: HHEX, affy id:215933_s_at"], ["ER status", "", "", "", ""], ["ER positive", "0.88(0.62–1.26)", "0.4927", "0.82(0.7–0.97)", "0.0191"], ["ER negative", "0.78(0.49–1.23)", "0.2826", "0.82(0.65–1.02)", "0.0792"], ["HER2 status", "", "", "", ""], ["HER2 positive", "1.52(0.74–3.12)", "0.2518", "0.83(0.54–1.28)", "0.3982"], ["HER2 negative", "1.06(0.45–2.51)", "0.8886", "0.68(0.52–0.88)", "0.0038"], ["Lymph node status", "", "", "", ""], ["Lymph node positive", "0.65(0.44–0.96)", "0.0278", "0.63(0.52–0.77)", "4.00E-06"], ["Lymph node negative", "0.92(0.63–1.33)", "0.6414", "0.75(0.63–0.89)", "0.0009"], ["Grade", "", "", "", ""], ["1", "1.25(0.52–3.02)", "0.6169", "0.86(0.51–1.45)", "0.5758"], ["2", "0.78(0.5–1.2)", "0.2502", "0.73(0.57–0.93)", "0.0094"], ["3", "0.85(0.61–1.18)", "0.3365", "0.9(0.72–1.12)", "0.3396"], ["Intrinsic subtype", "", "", "", ""], ["Basal", "0.8(0.49–1.3)", "0.3599", "0.64(0.5–0.83)", "0.0006"], ["luminal A", "0.72(0.5–1.02)", "0.066", "0.74(0.62–0.88)", "0.0006"], ["luminal B", "0.94(0.65–1.36)", "0.7459", "0.69(0.57–0.84)", "2.00E-04"], ["HER2+", "0.29(0.14–0.6)", "0.0004", "0.56(0.38–0.83)", "0.0033"]], "row_count": 21, "column_count": 5, "numeric_cells": 58, "header_rows": 2, "locator": "section[22]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE52327 not downloaded", "asset:data:geo:GSE52327 licence not read", "asset:data:geo:GSE94865 not downloaded", "asset:data:geo:GSE94865 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The Wilcoxon rank sum test was used to assess the significance of the observed differences."}}, {"id": "method-2", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student's t-test"}}, {"id": "method-3", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-4", "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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-5", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}, {"id": "method-6", "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": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-7", "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": ["method.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE52327", "GSE94865"], "resolved_accessions": ["GSE52327", "GSE94865"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Materials, further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE52327, GSE94865 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33425911", "data:geo:GSE52327", "asset:table:pmid:33425911:1", "asset:table:pmid:33425911:2", "asset:table:pmid:33425911:3", "asset:table:pmid:33425911:4", "asset:table:pmid:33425911:5"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE52327"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:06Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 48245, "completion_tokens": 1934, "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:33425911", "type": "paper", "label": "pmid:33425911"}, {"id": "source:pmid:33425911", "type": "manuscript", "label": "PMID 33425911 full text"}, {"id": "data:geo:GSE52327", "type": "dataset", "label": "GEO GSE52327"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33425911", "type": "paper", "label": "pmid:33425911"}, {"id": "source:pmid:33425911", "type": "manuscript", "label": "PMID 33425911 full text"}, {"id": "data:geo:GSE52327", "type": "dataset", "label": "GEO GSE52327"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33425911", "type": "extraction", "used": ["source:pmid:33425911"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE52327", "type": "accession_resolution", "used": ["data:geo:GSE52327"], "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:33425911", "parent_hash": "sha256:c1aba7d6d3ebad7de8ca1f56274b05db6675b0da234882217854ace8f0912c03", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE52327 licence not read", "asset:data:geo:GSE52327 not downloaded", "asset:data:geo:GSE94865 licence not read", "asset:data:geo:GSE94865 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": [", TCGAportal, PROGgeneV2, and BC-GenExMiner. Western blotting was performed to compare the level of HHEX i", "ls of HHEX. (a) Expression levels of HHEX by western blot analysis in TA2 mice with different numbers"], "order_basis": "paper_text_order:559", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["e-negative breast cancer, and basal-like BC. Immunohistochemical analysis of the breast samples showed signif", "HHEX protein expression in BC, we found that immunohistochemical analysis of HHEX was negative in BC and norm", "ifferent numbers of pregnancies and SBC. (C) Immunohistochemical (IHC) staining of HHEX expression in human b", "regnancies and SBC. (C) Immunohistochemical (IHC) staining of HHEX expression in human breast"], "order_basis": "paper_text_order:1540", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The Wilcoxon rank sum test was used to assess the significance of the observed differences."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:23:01+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}}}