{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31557418", "kind": "science-record", "revision": 7, "content_hash": "sha256:7554a6b6e9925fd8761dc43eb5dda90014b2d93754acacbe322781c491b5f79f", "created_at": "2026-11-01T15:40:50Z", "updated_at": "2026-11-01T22:44:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Elevated hsa-miR-590-3p expression down-regulates HMGB2 expression and contributes to the severity of IgA nephropathy.", "doi": "10.1111/jcmm.14582", "pmid": "31557418", "authors": ["Yaling Zhai", "Yuanyuan Qi", "Xiaoqing Long", "Yanna Dou", "Dong Liu", "Genyang Cheng", "Jing Xiao", "Zhangsuo Liu", "Zhanzheng Zhao"], "journal": "Journal of cellular and molecular medicine", "year": 2019, "abstract": "Peripheral blood mononuclear cells (PBMCs) play important roles in the pathogenesis of IgA nephropathy (IgAN). Our study aimed to provide a deep understanding of IgAN and focused on the dysregulation of hsa-miR-590-3p and its target gene HMGB2 in PBMCs. Three gene expression profile datasets (GSE14795, GSE73953 and GSE25590) were downloaded from the GEO database. The DEGs (differentially expressed genes)-miRNA network that was associated with IgAN was constructed by Cytoscape, and HMGB2 and hsa-miR-590-3p were selected for further exploration. The dual-luciferase reporter system was utilized to verify their interaction. Then, the expression levels of HMGB2 and hsa-miR-590-3p in PBMCs were detected by qPCR in another cohort, and the correlation of their expression levels with the clinical pathological manifestations and serum Gd-IgA1(galactose-deficient IgA1) levels was also investigated. HMGB2 was identified as the target gene of hsa-miR-590-3p. Furtherly, the elderly patients had higher HMGB2 expression levels than the expression levels of the younger patients. As the serum creatinine, serum BUN levels increased, the expression of HMGB2 decreased; Besides, the HMGB2 expression was positively correlated with serum complement 3(C3) levels, and it also had a negative correlation with the diastolic blood pressure, but not reach statistical significance. What is more, both hsa-miR-590-3p and HMGB2 expression had a slight correlation tendency with serum Gd-IgA1 levels in the whole population. In conclusion, HMGB2, the target gene of hsa-miR-590-3p, was identified to correlate with the severity of IgAN, and this provides more clues for the pathogenesis of IgAN.", "claims": [{"id": "claim-method", "statement": "For continuous variables, data with normal distribution were expressed as the mean ± SD and were compared by an independent‐sample t test, and Pearson Correlation was used if need; the other data were expressed as the median (first quartile and third quartile) and were analysed by the Mann‐Whitney U test, and the Spearman Correlation was utilized for the correlation analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31557418", "locator": "sections[10] \"Statistical analysis\" paragraph 2", "quote": "For continuous variables, data with normal distribution were expressed as the mean ± SD and were compared by an independent‐sample t test, and Pearson Correlation was used if need; the other data were expressed as the median (first quartile and third quartile) and were analysed by the Mann‐Whitney U test, and the Spearman Correlation was utilized for the correlation analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31557418", "locator": "sections[23] \"(untitled)\" paragraph 1", "quote": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use."}], "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:31557418"], "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:GSE14795"], "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:GSE14795"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31557418", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/jcmm.14582", "sha256": "sha256:0e1b90f4af17d9ef47e08505df0ac2117c6a3f47fa544398faf152bf60f94a54", "bytes": 36513, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/jcmm.14582", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6815813", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE14795", "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=GSE14795", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE14795", "version": null, "note": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM369302", "GSM369303", "GSM369304", "GSM369305", "GSM369306", "GSM369346", "GSM369347", "GSM369348", "GSM369349", "GSM369350", "GSM369351", "GSM369353", "GSM369354", "GSM369357", "GSM369359", "GSM369894", "GSM369895", "GSM369897", "GSM369898", "GSM369899", "GSM503853", "GSM503855", "GSM503856", "GSM503858", "GSM503859", "GSM503860"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "96;571", "taxon": "Homo sapiens", "title": "Altered modulation of WNT-β-catenin and PI3K/Akt pathways in IgA nephropathy", "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:GSE25590", "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=GSE25590", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25590", "version": null, "note": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM627751", "GSM627779", "GSM627781", "GSM627926", "GSM627964", "GSM627983", "GSM627984", "GSM627998", "GSM627999", "GSM628000", "GSM628001", "GSM628002", "GSM628003", "GSM628004"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "7731", "taxon": "Homo sapiens", "title": "miR-148b modulates the C1GALT1 expression explaining the abnormal glycosylation process in IgA Nephropathy", "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:GSE73953", "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=GSE73953", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73953", "version": null, "note": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1906717", "GSM1906718", "GSM1906719", "GSM1906720", "GSM1906721", "GSM1906722", "GSM1906723", "GSM1906724", "GSM1906725", "GSM1906726", "GSM1906727", "GSM1906728", "GSM1906729", "GSM1906730", "GSM1906731", "GSM1906732", "GSM1906733", "GSM1906734", "GSM1906735", "GSM1906736", "GSM1906737", "GSM1906738", "GSM1906739", "GSM1906740", "GSM1906741"], "sample_count": 25, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Microarray analysis of peripheral blood mononuclear cells (PBMCs) from IgA nephropathy patients, membranous nephropathy patients and healthy controls.", "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:31557418:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:815e69e4a8154d21a67544c077d43ce47daeb67346f5451caec9b4ecce5152cc", "bytes": 632, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#jcmm14582-tbl-0001", "version": null, "note": "Information on the three gene expresssion profile dataset", "structure": {"pmcid": "PMC6815813", "section_index": 3, "section_title": "Microarray data preprocessing", "row_count": 5, "column_count": 6}, "table": {"label": "Table 1", "caption": "Information on the three gene expresssion profile dataset", "rows": [["", "Before nomalization", "After normalization", "Platforms"], ["IgAN sample count", "Control sample count", "IgAN sample count", "Control sample count"], ["GSE14795", "12", "8", "8", "6", "Affymetrix Human Genome U133A Array"], ["GSE73953", "15", "16 (pooled)", "15", "16 (poold)", "Agilent‐014850 Whole Human Genome Microarray 4x44K G4112F"], ["GSE25590", "7", "7", "4", "3", "GPL7731 Agilent‐019118 Human miRNA Microarray 2.0"]], "row_count": 5, "column_count": 6, "numeric_cells": 18, "header_rows": 2, "locator": "section[3]/table-wrap[1]#jcmm14582-tbl-0001"}}, {"id": "asset:table:pmid:31557418:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0d26715ce17b06b85793ef7d459bdb712f7b4b0c53a7c317bc729d981a869d5c", "bytes": 527, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#jcmm14582-tbl-0002", "version": null, "note": "The primer pairs for HMGB2, GAPDH and has‐mir‐590‐3p", "structure": {"pmcid": "PMC6815813", "section_index": 8, "section_title": "Detection of the expression of HMGB2 and hsa‐miR‐590‐3p", "row_count": 7, "column_count": 3}, "table": {"label": "Table 2", "caption": "The primer pairs for HMGB2, GAPDH and has‐mir‐590‐3p", "rows": [["", "Sequence"], ["HMGB2", "F", "5′‐GTGGCCTAGCTCGTCAAGTT‐3′"], ["R", "5′‐GCGTACGAGGACATTTTGCC‐3′"], ["GAPDH", "F", "5′‐GGGAAACTGTGGCGTGAT‐3′"], ["R", "5′‐GAGTGGGTGTCGCTGTTGA‐3′"], ["hsa‐miR‐590‐3p", "F", "5′‐TAATTTTATGTATAAGCTAGT‐3′"], ["R", "5′‐GTGCAGGGTCCGAGGT‐3′"]], "row_count": 7, "column_count": 3, "numeric_cells": 7, "header_rows": 1, "locator": "section[8]/table-wrap[1]#jcmm14582-tbl-0002"}}, {"id": "asset:table:pmid:31557418:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7a37edd39139a0dd78e08e4e2ec8fc70d817acefa7c3c9fdb0760988d903f6a0", "bytes": 1031, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#jcmm14582-tbl-0003", "version": null, "note": "7miRNAs and 19 targeted genes associated with IgAN", "structure": {"pmcid": "PMC6815813", "section_index": 12, "section_title": "Screened miRNAs and target genes associated with IgAN", "row_count": 20, "column_count": 3}, "table": {"label": "Table 3", "caption": "7miRNAs and 19 targeted genes associated with IgAN", "rows": [["Gene symbol", "Fold change (Log2 transformed)", "microRNA"], ["ARID4A", "−1.65", "hsa‐miR‐519c‐3p"], ["CETN3", "−1.75", "hsa‐miR‐520b"], ["CNOT3", "−1.21", "hsa‐miR‐920"], ["GCC2", "−1.29", "hsa‐miR‐590‐3p"], ["HABP4", "−1.76", "hsa‐miR‐519c‐3p"], ["HMGB2", "−1.22", "hsa‐miR‐590‐3p"], ["IFIT5", "−1.13", "hsa‐miR‐384"], ["JMJD1C", "−1.85", "hsa‐miR‐648"], ["MAN1A1", "−1.29", "hsa‐miR‐590‐3p"], ["MAPK6", "−1.37", "hsa‐miR‐384"], ["NAMPT", "−1.12", "hsa‐miR‐590‐3p"], ["NPTN", "−1.29", "hsa‐miR‐873"], ["RAB1A", "−1.57", "hsa‐miR‐648"], ["RASA1", "−1.17", "hsa‐miR‐648"], ["RBM26", "−1.33", "hsa‐miR‐384"], ["TGFA", "−1.65", "hsa‐miR‐384"], ["TMEM57", "−1.29", "hsa‐miR‐384"], ["TUBGCP3", "−1.42", "hsa‐miR‐873"], ["ZFR", "−1.09", "hsa‐miR‐384"]], "row_count": 20, "column_count": 3, "numeric_cells": 40, "header_rows": 1, "locator": "section[12]/table-wrap[1]#jcmm14582-tbl-0003"}}, {"id": "asset:table:pmid:31557418:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0dbdad815c91c7194252ed134695ff3abcfb4cd61fc815701a0cac8a8b292c5d", "bytes": 3796, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#jcmm14582-tbl-0004", "version": null, "note": "GO and KEGG enrichment analysis results for DEGs identified in the three microarray", "structure": {"pmcid": "PMC6815813", "section_index": 12, "section_title": "Screened miRNAs and target genes associated with IgAN", "row_count": 30, "column_count": 4}, "table": {"label": "Table 4", "caption": "GO and KEGG enrichment analysis results for DEGs identified in the three microarray", "rows": [["Description", "gene count", "Pvalue", "Genes"], ["GO terms"], ["GO:0044699‐single‐organism process", "18", "1.00 × 10‐3", "ZFR;TMEM57;MAN1A1;HABP4;IFIT5;TGFA;CETN3;GCC2;JMJD1C;NAMPT;RASA1;MAPK6;RAB1A;ARID4A;TUBGCP3;HMGB2;NPTN;CNOT3"], ["GO:0044707‐single‐multicellular organism process", "13", "4.07 × 10‐6", "ZFR;TMEM5;HABP4;TGFA;JMJD1C;NAMPT;RASA1;MAPK6;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0032501‐multicellular organismal process", "13", "7.82 × 10‐6", "ZFR;TMEM57;HABP4;TGFA;JMJD1C;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0048856‐anatomical structure development", "11", "5.60 × 10‐5", "ZFR;TMEM57;;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0044767‐single‐organism developmental process", "11", "1.13 × 10‐4", "ZFR;TMEM57;TGFA;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0032502‐developmental process", "11", "1.32 × 10‐4", "ZFR;TMEM57;TGFA;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0060255‐regulation of macromolecule metabolic process", "11", "1.57 × 10‐3", "HABP4;TGFA;JMJD1C;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0019222‐regulation of metabolic process", "11", "6.12 × 10‐3", "HABP4;TGFA;JMJD1C;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0007275‐multicellular organism development", "10", "1.02 × 10‐4", "ZFR;TMEM57;TGFA;NAMPT;RASA1;MAPK6 ;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0048518‐positive regulation of biological process", "10", "5.60 × 10‐4", "IFIT5;TGFA;NAMPT;RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0016043‐cellular component organization", "10", "5.45 × 10‐3", "CETN3;GCC2;JMJD1C;RASA1;MAPK6 ;RAB1A;ARID4A;TUBGCP3;HMGB2;NPTN"], ["GO:0080090‐regulation of primary metabolic process", "10", "6.26 × 10‐3", "HABP4;TGFA;JMJD1C;NAMPT;RASA1;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0071840‐cellular component organization or biogenesis", "10", "6.85 × 10‐3", "CETN3;GCC2;JMJD1C;RASA1;MAPK6 ;RAB1A;ARID4A;TUBGCP3;HMGB2;NPTN"], ["GO:0031323‐regulation of cellular metabolic process", "10", "6.93 × 10‐3", "HABP4;TGFA;JMJD1C;NAMPT;RASA1;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0048522‐positive regulation of cellular process", "9", "5.74 × 10‐4", "IFIT5;TGFA;NAMPT;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0048731‐system development", "8", "1.59 × 10‐3", "TMEM57;TGFA;NAMPT;RASA1;MAPK6 ;ARID4A;HMGB2;NPTN"], ["GO:0006996‐organelle organization", "8", "4.66 × 10‐3", "CETN3;GCC2;JMJD1C;RASA1;RAB1A;ARID4A;TUBGCP3;HMGB2"], ["GO:0006464‐cellular protein modification process", "8", "9.25 × 10‐3", "MAN1A1;TGFA;JMJD1C;RASA1;MAPK6 ;RAB1A;ARID4A;NPTN"], ["GO:0036211‐protein modification process", "8", "9.25 × 10‐3", "MAN1A1;TGFA;JMJD1C;RASA1;MAPK6 ;RAB1A;ARID4A;NPTN"], ["GO:0048468‐cell development", "7", "9.85 × 10‐5", "RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:1902589‐single‐organism organelle organization", "7", "2.16 × 10‐3", "CETN3;GCC2;RASA1;RAB1A;ARID4A;TUBGCP3;HMGB2"], ["GO:0009893‐positive regulation of metabolic process", "7", "3.75 × 10‐3", "TGFA;NAMPT;RASA1;RAB1A;ARID4A;HMGB2;NPTN"], ["GO:0030154‐cell differentiation", "7", "3.83 × 10‐3", "RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["GO:0065008‐regulation of biological quality", "7", "4.32 × 10‐3", "HABP4;JMJD1C;RASA1;RAB1A;ARID4A;HMGB2;NPTN"], ["GO:0048869‐cellular developmental process", "7", "7.37 × 10‐3", "RASA1;MAPK6 ;RAB1A;ARID4A;HMGB2;NPTN;CNOT3"], ["KEGG pathways"], ["hsa00760‐Nicotinate and nicotinamide metabolism", "1", "2.94 × 10‐2", "NAMPT"], ["hsa00510‐N‐Glycan biosynthesis", "1", "4.76 × 10‐2", "MAN1A1"]], "row_count": 30, "column_count": 4, "numeric_cells": 88, "header_rows": 1, "locator": "section[12]/table-wrap[2]#jcmm14582-tbl-0004"}}, {"id": "asset:table:pmid:31557418:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d2a17d262ad93785f2a518a62b962647246f8a52efdc4326a6bc5a7a6d428d93", "bytes": 980, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#jcmm14582-tbl-0005", "version": null, "note": "The baseline data of 37 patients with IgAN", "structure": {"pmcid": "PMC6815813", "section_index": 14, "section_title": "Increased hsa‐miR‐590‐3p expression and decreased HMGB2 expression in IgAN", "row_count": 22, "column_count": 2}, "table": {"label": "Table 5", "caption": "The baseline data of 37 patients with IgAN", "rows": [["Characters", "Mean ± SD or median(IQR) or n"], ["Male/female", "23/14"], ["Age (year)", "42.11 ± 14.80"], ["With hypertension (%)", "26(70.27%)"], ["SBP (mmHg)", "135.97 ± 17.61"], ["DBP (mmHg)", "86.00 ± 10.39"], ["24 h proteinuria (g/d)", "1.75 (0.75,4.09)"], ["SCR (μmol/L)", "117 (82,189.50)"], ["BUN (mmol/L)", "6.60 (5.00,11.61)"], ["Uric Acid (μmol/L)", "342.19 ± 82.37"], ["Albumin (g/L)", "35.23 ± 8.98"], ["TCHO (mmol/L)", "4.40 (3.59,5.43)"], ["TG (mmol/L)", "1.93 (1.17, 2.60)"], ["C3 (mg/L)", "1.21 (1.04,1.38)"], ["C4 (mg/L)", "0.30 (0.25, 0.34)"], ["Blood cell count in urine", "24.50 (5.25,48.75)"], ["Oxford classification (n)", ""], ["M score (M0/M1)", "28/9"], ["E score (E0/E1)", "29/8"], ["S score (S0/S1)", "16/21"], ["C score(C0/C1/C2)", "17/18/2"], ["T score (T0/T1/T2)", "20/8/9"]], "row_count": 22, "column_count": 2, "numeric_cells": 21, "header_rows": 1, "locator": "section[14]/table-wrap[1]#jcmm14582-tbl-0005"}}], "gaps": ["asset:data:geo:GSE14795 not downloaded", "asset:data:geo:GSE14795 licence not read", "asset:data:geo:GSE25590 not downloaded", "asset:data:geo:GSE25590 licence not read", "asset:data:geo:GSE73953 not downloaded", "asset:data:geo:GSE73953 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For continuous variables, data with normal distribution were expressed as the mean ± SD and were compared by an independent‐sample t test, and Pearson Correlation was used if need; the other data were expressed as the median (first quartile and third quartile) and were analysed by the Mann‐Whitney U test, and the Spearman Correlation was utilized for the correlation analysis."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman Correlation"}}], "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE14795", "GSE73953", "GSE25590"], "resolved_accessions": ["GSE14795", "GSE73953", "GSE25590"], "statements": ["Raw data used during the current study are available from the corresponding author on reasonable request for non‐commercial use."], "basis": "The paper names GSE14795, GSE73953, GSE25590 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": ["pearson_r"], "assets": ["source:pmid:31557418", "data:geo:GSE14795", "asset:table:pmid:31557418:1", "asset:table:pmid:31557418:2", "asset:table:pmid:31557418:3", "asset:table:pmid:31557418:4", "asset:table:pmid:31557418:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE14795"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 31932, "completion_tokens": 1441, "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:31557418", "type": "paper", "label": "pmid:31557418"}, {"id": "source:pmid:31557418", "type": "manuscript", "label": "PMID 31557418 full text"}, {"id": "data:geo:GSE14795", "type": "dataset", "label": "GEO GSE14795"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31557418", "type": "paper", "label": "pmid:31557418"}, {"id": "source:pmid:31557418", "type": "manuscript", "label": "PMID 31557418 full text"}, {"id": "data:geo:GSE14795", "type": "dataset", "label": "GEO GSE14795"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31557418", "type": "extraction", "used": ["source:pmid:31557418"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE14795", "type": "accession_resolution", "used": ["data:geo:GSE14795"], "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:31557418", "parent_hash": "sha256:5af20e79489e9c2c00a3611b002c6421a814d769ccf3efd7a841280f053e1770", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE14795 licence not read", "asset:data:geo:GSE14795 not downloaded", "asset:data:geo:GSE25590 licence not read", "asset:data:geo:GSE25590 not downloaded", "asset:data:geo:GSE73953 licence not read", "asset:data:geo:GSE73953 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["and hsa-miR-590-3p in PBMCs were detected by qPCR in another cohort, and the correlation of th"], "order_basis": "paper_text_order:784", "id": "assay:1"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For continuous variables, data with normal distribution were expressed as the mean ± SD and were compared by an independent‐sample t test, and Pearson Correlation was used if need; the other data were expressed as the median (first quartile and third quartile) and were analysed by the Mann‐Whitney U test, and the Spearman Correlation was utilized for the correlation analysis."], "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":"2026-11-04T02:54:04+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}}}