{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29137293", "kind": "science-record", "revision": 5, "content_hash": "sha256:3ee853d5f8da3ffc2f8dc8304068189c69346aba05df7ecfd3e5bc9d1a8c7b45", "created_at": "2026-11-01T11:44:20Z", "updated_at": "2026-11-03T11:16:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "pilot-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of novel genetic regulations associated with airway epithelial homeostasis using next-generation sequencing data and bioinformatics approaches", "doi": "10.18632/oncotarget.19752", "pmid": "29137293", "authors": ["Chau-Chyun Sheu", "Ming-Ju Tsai", "Feng-Wei Chen", "Kuo-Feng Chang", "Wei-An Chang", "Inn-Wen Chong", "Po-Lin Kuo", "Ya-Ling Hsu"], "journal": "Oncotarget", "year": 2017, "abstract": "Airway epithelial cells play important roles in airway remodeling. Understanding gene regulations in airway epithelial homeostasis may provide new insights into pathogenesis and treatment of asthma. This study aimed to combine gene expression (GE) microarray, next generation sequencing (NGS), and bioinformatics to explore genetic regulations associated with airway epithelial homeostasis. We analyzed expression profiles of mRNAs (GE microarray) and microRNAs (NGS) in normal and asthmatic bronchial epithelial cells, and identified 9 genes with potential microRNA-mRNA interactions. Of these 9 dysregulated genes, downregulation of MEF2C and MDGA1 were validated in a representative microarray (GSE43696) from the gene expression omnibus (GEO) database. Our findings suggested that upregulated mir-203a may repress MEF2C, a transcription factor, leading to decreased cellular proliferation. In addition, upregulated mir-3065-3p may repress MDGA1, a cell membrane anchor protein, resulting in suppression of cell-cell adhesion. We also found that KCNJ2, a potassium channel, was downregulated in severe asthma and may promote epithelial cell apoptosis. We proposed that aberrant regulations of mir-203a-MEF2C and mir-3065-3p-MDGA1, as well as downregulation of KCNJ2, play important roles in airway epithelial homeostasis in asthma. These findings provide new perspectives on diagnostic or therapeutic strategies targeting bronchial epithelium for asthma. The approach in this study also provides a new aspect of studying asthma.", "claims": [{"id": "claim-method", "statement": "The raw data extracted from GEO database were statistically analyzed using one-way ANOVA with Tukey post hoc test by GraphPad Prism 5 software (GraphPad Software, La Jolla, CA, USA).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29137293", "locator": "sections[15] \"Statistical analysis\" paragraph 2", "quote": "The raw data extracted from GEO database were statistically analyzed using one-way ANOVA with Tukey post hoc test by GraphPad Prism 5 software (GraphPad Software, La Jolla, CA, USA)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Our findings suggested that upregulated mir-203a may repress MEF2C, a transcription factor, leading to decreased cellular proliferation.", "kind": "qualitative", "target": {"value": null, "unit": null, "tolerance": null, "source": "Our findings suggested that upregulated mir-203a may repress MEF2C, a transcription factor, leading to decreased cellular proliferation."}, "evidence": [{"asset": "source:pmid:29137293", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Our findings suggested that upregulated mir-203a may repress MEF2C, a transcription factor, leading to decreased cellular proliferation."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray of accession number GSE43696 published in 2014 [61] was used in this study. This microarray contains gene expression information of clinical bronchial epithelial cells from 108 patients, including normal control (n = 20, 9 males and 11 females), mild-moderate asthma (n = 50, 15 males and 35 females), and severe asthma (n = 38, 10 males and 28 females). The raw data were extracted and re-plotted by GraphPad prism 5 software (GraphPad Software, La Jolla, CA, USA).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29137293", "locator": "sections[14] \"Gene expression omnibus (GEO) database analysis\" paragraph 2", "quote": "The microarray of accession number GSE43696 published in 2014 [61] was used in this study. This microarray contains gene expression information of clinical bronchial epithelial cells from 108 patients, including normal control (n = 20, 9 males and 11 females), mild-moderate asthma (n = 50, 15 males and 35 females), and severe asthma (n = 38, 10 males and 28 females). The raw data were extracted and re-plotted by GraphPad prism 5 software (GraphPad Software, La Jolla, CA, USA)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The paper used one-way ANOVA with a Tukey post hoc test to analyze raw gene-expression data extracted from the GEO database (GSE43696). No numerical result was reported for the registered target.", "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:29137293"], "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:GSE43696"], "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:post_hoc_tukey", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {"design": "one-way ANOVA", "post_hoc": "Tukey", "software": "GraphPad Prism 5"}, "inputs": ["data:geo:GSE43696"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:post_hoc_tukey"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29137293", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/oncotarget.19752", "sha256": "sha256:d48a0333cf809363edd89b2ae22bc8b01cade0d4bd77b7d6d7837f951a33e51d", "bytes": 29763, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/oncotarget.19752", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5669919", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE43696", "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=GSE43696", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43696", "version": null, "note": "The microarray of accession number GSE43696 published in 2014 [61] was used in this study. This microarray contains gene expression information of clinical bronchial epithelial cells from 108 patients, including normal control (n = 20, 9 males and 11 females), mild-moderate asthma (n = 50, 15 males and 35 females), and severe asthma (n = 38, 10 males and 28 females). The raw data were extracted and re-plotted by GraphPad prism 5 software (GraphPad Software, La Jolla, CA, USA).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray of accession number GSE43696 published in 2014 [61] was used in this study. This microarray contains gene expression information of clinical bronchial epithelial cells from 108 patients, including normal control (n = 20, 9 males and 11 females), mild-moderate asthma (n = 50, 15 males and 35 females), and severe asthma (n = 38, 10 males and 28 females). The raw data were extracted and re-plotted by GraphPad prism 5 software (GraphPad Software, La Jolla, CA, USA).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1068458", "GSM1068459", "GSM1068460", "GSM1068461", "GSM1068462", "GSM1068463", "GSM1068464", "GSM1068465", "GSM1068466", "GSM1068467", "GSM1068468", "GSM1068469", "GSM1068470", "GSM1068471", "GSM1068472", "GSM1068473", "GSM1068474", "GSM1068475", "GSM1068476", "GSM1068477", "GSM1068478", "GSM1068479", "GSM1068480", "GSM1068481", "GSM1068482", "GSM1068483", "GSM1068484", "GSM1068485", "GSM1068486", "GSM1068487", "GSM1068488", "GSM1068489", "GSM1068490", "GSM1068491", "GSM1068492", "GSM1068493", "GSM1068494", "GSM1068495", "GSM1068496", "GSM1068497", "GSM1068498", "GSM1068499", "GSM1068500", "GSM1068501", "GSM1068502", "GSM1068503", "GSM1068504", "GSM1068505", "GSM1068506", "GSM1068507", "GSM1068508", "GSM1068509", "GSM1068510", "GSM1068511", "GSM1068512", "GSM1068513", "GSM1068514", "GSM1068515", "GSM1068516", "GSM1068517", "GSM1068518", "GSM1068519", "GSM1068520", "GSM1068521", "GSM1068522", "GSM1068523", "GSM1068524", "GSM1068525", "GSM1068526", "GSM1068527", "GSM1068528", "GSM1068529", "GSM1068530", "GSM1068531", "GSM1068532", "GSM1068533", "GSM1068534", "GSM1068535", "GSM1068536", "GSM1068537", "GSM1068538", "GSM1068539", "GSM1068540", "GSM1068541", "GSM1068542", "GSM1068543", "GSM1068544", "GSM1068545", "GSM1068546", "GSM1068547", "GSM1068548", "GSM1068549", "GSM1068550", "GSM1068551", "GSM1068552", "GSM1068553", "GSM1068554", "GSM1068555", "GSM1068556", "GSM1068557", "GSM1068558", "GSM1068559", "GSM1068560", "GSM1068561", "GSM1068562", "GSM1068563", "GSM1068564", "GSM1068565"], "sample_count": 108, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Asthma", "resolution_checked_at": "2026-11-01T11:38:18Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29137293:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:532a40829aebc72881d3525ce8455e68ea6e47ffac5d2a363ffe0ae314542c3a", "bytes": 3785, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "MicroRNAs with significant change in asthmatic bronchial epithelial cells versus normal bronchial epithelial cells", "structure": {"pmcid": "PMC5669919", "section_index": 3, "section_title": "Identification of potential microRNA-mRNA interactions in asthmatic bronchial epithelial cells", "row_count": 57, "column_count": 6}, "table": {"label": "Table 1", "caption": "MicroRNAs with significant change in asthmatic bronchial epithelial cells versus normal bronchial epithelial cells", "rows": [["#miRNA", "Precursor", "Asthmatic HBE", "Normal HBE", "Fold change", "Up/down"], ["Seq (norm)", "Seq (norm)"], ["hsa-miR-190a", "hsa-mir-190a", "6.06", "1.29", "4.70", "UP"], ["hsa-miR-3065-5p", "hsa-mir-3065", "24.4", "5.49", "4.44", "UP"], ["hsa-miR-10a-5p", "hsa-mir-10a", "6937.77", "2251.48", "3.08", "UP"], ["hsa-miR-146a-5p", "hsa-mir-146a", "157.81", "53.57", "2.95", "UP"], ["hsa-miR-218-5p", "hsa-mir-218-1", "55.02", "18.72", "2.94", "UP"], ["hsa-miR-218-5p", "hsa-mir-218-2", "53.98", "18.72", "2.88", "UP"], ["hsa-miR-3935", "hsa-mir-3935", "11.09", "3.87", "2.87", "UP"], ["hsa-miR-3065-3p", "hsa-mir-3065", "15.23", "5.32", "2.86", "UP"], ["hsa-miR-486-5p", "hsa-mir-486", "248.91", "93.91", "2.65", "UP"], ["hsa-miR-19a-3p", "hsa-mir-19a", "117.14", "45.67", "2.56", "UP"], ["hsa-miR-3661", "hsa-mir-3661", "5.77", "2.26", "2.55", "UP"], ["hsa-miR-10a-3p", "hsa-mir-10a", "6.51", "2.58", "2.52", "UP"], ["hsa-miR-19b-3p", "hsa-mir-19b-2", "409.83", "164.11", "2.50", "UP"], ["hsa-miR-19b-3p", "hsa-mir-19b-1", "404.95", "162.17", "2.50", "UP"], ["hsa-miR-4521", "hsa-mir-4521", "12.87", "5.16", "2.49", "UP"], ["hsa-miR-203a", "hsa-mir-203a", "2852.52", "1184.56", "2.41", "UP"], ["hsa-miR-29c-5p", "hsa-mir-29c", "9.91", "4.36", "2.27", "UP"], ["hsa-miR-548d-5p", "hsa-mir-548d-1", "5.47", "2.42", "2.26", "UP"], ["hsa-miR-3613-5p", "hsa-mir-3613", "3.85", "1.77", "2.18", "UP"], ["hsa-miR-221-5p", "hsa-mir-221", "415.59", "191.86", "2.17", "UP"], ["hsa-miR-7-5p", "hsa-mir-7-2", "35.94", "16.78", "2.14", "UP"], ["hsa-miR-7-5p", "hsa-mir-7-3", "35.94", "16.78", "2.14", "UP"], ["hsa-miR-7-5p", "hsa-mir-7-1", "36.53", "17.1", "2.14", "UP"], ["hsa-miR-147b", "hsa-mir-147b", "4.14", "1.94", "2.13", "UP"], ["hsa-miR-140-5p", "hsa-mir-140", "9.17", "4.36", "2.10", "UP"], ["hsa-miR-548au-5p", "hsa-mir-548au", "2.37", "1.13", "2.10", "UP"], ["hsa-miR-548o-3p", "hsa-mir-548o", "27.66", "13.23", "2.09", "UP"], ["hsa-miR-548o-3p", "hsa-mir-548o-2", "27.66", "13.23", "2.09", "UP"], ["hsa-miR-4517", "hsa-mir-4517", "3.7", "1.77", "2.09", "UP"], ["hsa-miR-548d-5p", "hsa-mir-548d-2", "7.69", "3.71", "2.07", "UP"], ["hsa-miR-29b-1-5p", "hsa-mir-29b-1", "27.66", "13.39", "2.07", "UP"], ["hsa-miR-29a-5p", "hsa-mir-29a", "11.83", "5.81", "2.04", "UP"], ["hsa-miR-942", "hsa-mir-942", "9.17", "4.52", "2.03", "UP"], ["hsa-miR-365a-5p", "hsa-mir-365a", "5.18", "2.58", "2.01", "UP"], ["hsa-miR-122-5p", "hsa-mir-122", "1.04", "2.1", "-2.02", "Down"], ["hsa-miR-664a-5p", "hsa-mir-664a", "1.18", "2.42", "-2.05", "Down"], ["hsa-miR-424-3p", "hsa-mir-424", "127.49", "265.6", "-2.08", "Down"], ["hsa-miR-323a-3p", "hsa-mir-323a", "1.33", "2.9", "-2.18", "Down"], ["hsa-miR-483-5p", "hsa-mir-483", "1.48", "3.39", "-2.29", "Down"], ["hsa-miR-24-1-5p", "hsa-mir-24-1", "1.18", "2.74", "-2.32", "Down"], ["hsa-miR-424-5p", "hsa-mir-424", "142.13", "349.19", "-2.46", "Down"], ["hsa-miR-665", "hsa-mir-665", "1.04", "2.58", "-2.48", "Down"], ["hsa-miR-487a", "hsa-mir-487a", "1.04", "2.74", "-2.63", "Down"], ["hsa-miR-33b-5p", "hsa-mir-33b", "12.87", "34.53", "-2.68", "Down"], ["hsa-miR-4792", "hsa-mir-4792", "6.95", "19.69", "-2.83", "Down"], ["hsa-miR-548h-5p", "hsa-mir-548h-1", "1.18", "3.55", "-3.01", "Down"], ["hsa-miR-548h-5p", "hsa-mir-548h-2", "1.18", "3.55", "-3.01", "Down"], ["hsa-miR-548h-5p", "hsa-mir-548h-3", "1.18", "3.55", "-3.01", "Down"], ["hsa-miR-548h-5p", "hsa-mir-548h-4", "1.18", "3.55", "-3.01", "Down"], ["hsa-miR-548h-5p", "hsa-mir-548h-5", "1.18", "3.55", "-3.01", "Down"], ["hsa-miR-3177-3p", "hsa-mir-3177", "1.04", "3.39", "-3.26", "Down"], ["hsa-miR-212-3p", "hsa-mir-212", "1.48", "5.32", "-3.59", "Down"], ["hsa-miR-873-5p", "hsa-mir-873", "1.63", "9.84", "-6.04", "Down"], ["hsa-miR-3176", "hsa-mir-3176", "5.18", "39.37", "-7.60", "Down"], ["hsa-miR-6499-5p", "hsa-mir-6499", "5.62", "78.74", "-14.01", "Down"]], "row_count": 57, "column_count": 6, "numeric_cells": 275, "header_rows": 2, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:29137293:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d9426fc65babec185ceeda8e6057c959e89cdec14c3b6dbe6446b7d49aedf60c", "bytes": 1080, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#T2", "version": null, "note": "Genes selected by intersection between GE array candidates and microRNA putative targets", "structure": {"pmcid": "PMC5669919", "section_index": 3, "section_title": "Identification of potential microRNA-mRNA interactions in asthmatic bronchial epithelial cells", "row_count": 10, "column_count": 5}, "table": {"label": "Table 2", "caption": "Genes selected by intersection between GE array candidates and microRNA putative targets", "rows": [["Official gene symbol", "Gene name", "Species", "Fold change(Asthma/normal)", "Expression"], ["FGF2", "fibroblast growth factor 2 (FGF2)", "Homo sapiens", "2.08", "Up"], ["IRAK3", "interleukin 1 receptor associated kinase 3 (IRAK3)", "Homo sapiens", "0.48", "Down"], ["LOX", "lysyl oxidase (LOX)", "Homo sapiens", "0.13", "Down"], ["MDGA1", "MAM domain containing glycosylphosphatidylinositol anchor 1 (MDGA1)", "Homo sapiens", "0.21", "Down"], ["MEF2C", "myocyte enhancer factor 2C (MEF2C)", "Homo sapiens", "0.48", "Down"], ["NAIP", "NLR family apoptosis inhibitory protein (NAIP)", "Homo sapiens", "0.3", "Down"], ["TFPI", "tissue factor pathway inhibitor (TFPI)", "Homo sapiens", "0.42", "Down"], ["TP53I11", "tumor protein p53 inducible protein 11 (TP53I11)", "Homo sapiens", "3.52", "Up"], ["NEURL1", "neuralized E3 ubiquitin protein ligase 1 (NEURL1)", "Homo sapiens", "0.38", "Down"]], "row_count": 10, "column_count": 5, "numeric_cells": 16, "header_rows": 1, "locator": "section[3]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:29137293:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e174d87a3fdd738de13d8d9f1b63d2d17e27098d0d9b5757bb6995434147b5de", "bytes": 361, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T3", "version": null, "note": "KEGG pathway analysis of 9 genes with potential microRNA-mRNA interaction", "structure": {"pmcid": "PMC5669919", "section_index": 4, "section_title": "Downregulation of MEF2C and MDGA1 may be involved in the homeostasis of asthmatic airway epithelium", "row_count": 2, "column_count": 6}, "table": {"label": "Table 3", "caption": "KEGG pathway analysis of 9 genes with potential microRNA-mRNA interaction", "rows": [["KEGG pathway", "Count", "P-value", "Genes up", "Genes down", "Fold enrichment"], ["MAPK signaling pathway", "2", "1.40E-01", "FGF2", "MEF2C", "10.84"]], "row_count": 2, "column_count": 6, "numeric_cells": 3, "header_rows": 1, "locator": "section[4]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:29137293:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:856cbc05b6f1f91f156033037e222121787641ba2d96d960f3bf017ac019ca53", "bytes": 470, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[2]#T4", "version": null, "note": "MicroRNAs and the corresponding predicted targets", "structure": {"pmcid": "PMC5669919", "section_index": 4, "section_title": "Downregulation of MEF2C and MDGA1 may be involved in the homeostasis of asthmatic airway epithelium", "row_count": 4, "column_count": 7}, "table": {"label": "Table 4", "caption": "MicroRNAs and the corresponding predicted targets", "rows": [["miRNA", "Precursor", "Asthmatic HBE", "Normal HBE", "Fold change", "Log2 (ratio)", "Predicted targets"], ["Seq (norm)", "Seq (norm)"], ["Hsa-miR-203a", "hsa-mir-203a", "2852.52", "1184.56", "2.41", "1.27", "MEF2C"], ["hsa-miR-3065-3p", "hsa-miR-3065", "15.23", "5.32", "2.86", "1.52", "MDGA1"]], "row_count": 4, "column_count": 7, "numeric_cells": 12, "header_rows": 2, "locator": "section[4]/table-wrap[2]#T4"}}, {"id": "asset:table:pmid:29137293:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d9ad102ce13f34f0b420906fc81fb64d4e31fca8f30fb9f54e49d5e63e6dbf7e", "bytes": 1880, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T5", "version": null, "note": "KEGG pathway analysis of dysregulated genes identified from GE microarray", "structure": {"pmcid": "PMC5669919", "section_index": 5, "section_title": "Downregulation of KCNJ2 may be associated with severity of asthma", "row_count": 15, "column_count": 6}, "table": {"label": "Table 5", "caption": "KEGG pathway analysis of dysregulated genes identified from GE microarray", "rows": [["KEGG pathways", "Count", "P-value", "Genes up", "Genes down", "Fold enrichment"], ["Cell adhesion molecules (CAMs)", "10", "1.08E-02", "OCLN, NLGN4X, CLDN1", "HLA-DQB1, NTNG1, CNTN1, ITGB2, ITGA4, CLDN20, HLA-F", "2.72"], ["Glycosaminoglycan biosynthesis - heparan sulfate / heparin", "4", "2.29E-02", "XYLT1", "HS3ST3A1, HS3ST2, HS3ST3B1", "6.43"], ["ECM-receptor interaction", "7", "2.43E-02", "COL5A1", "LAMA1, COL4A2, COL1A2, COL6A1, ITGA4, FN1", "3.11"], ["Pathways in cancer", "18", "2.43E-02", "FZD10, FGFR3, MMP9, FGF2", "LAMA1, FOS, PTGER1, COL4A2, RAC2, RAC3, RASGRP2, EGLN3, FGF13, HHIP, FZD2, GLI2, MMP1, FN1", "1.77"], ["Regulation of actin cytoskeleton", "11", "4.55E-02", "FGFR3, SCIN, FGF2", "CHRM4, RAC2, RAC3, FGF13, ITGB2, ITGA4, MYLK, FN1", "2.01"], ["Focal adhesion", "10", "8.41E-02", "COL5A1", "LAMA1, COL4A2, RAC2, RAC3, COL1A2, COL6A1, ITGA4, MYLK, FN1", "1.87"], ["MAPK signaling pathway", "10", "2.11E-01", "FGFR3, FGF2, CACNA1A", "MEF2C, FOS, RAC2, RAC3, RASGRP2, DUSP10, FGF13", "1.51"], ["cGMP-PKG signaling pathway", "7", "2.56E-01", "RGS2", "MEF2C, KCNMB4, ATP1A4, ATP1A1, ADRA2C, MYLK", "1.63"], ["Transcriptional misregulation in cancer", "7", "2.65E-01", "LMO2, UTY, MMP9", "MEF2C, FLI1, NGFR, MMP3", "1.61"], ["PI3K-Akt signaling pathway", "12", "2.75E-01", "FGFR3, FGF2, COL5A1", "LAMA1, COL4A2, COL1A2, COL6A1, FGF13, TLR4, NGFR, ITGA4, FN1", "1.34"], ["Oxytocin signaling pathway", "6", "3.85E-01", "RGS2", "MEF2C, FOS, KCNJ12, KCNJ2, MYLK", "1.47"], ["cAMP signaling pathway", "7", "4.01E-01", "", "FOS, RAC2, RAC3, ATP1A4, ATP1A1, HHIP, HTR1F", "1.36"], ["Adherens junction", "3", "5.50E-01", "", "PTPRB, RAC2, RAC3", "1.63"], ["Tight junction", "4", "6.91E-01", "EPB41L3, OCLN, CLDN1", "CLDN20", "1.13"]], "row_count": 15, "column_count": 6, "numeric_cells": 51, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T5"}}], "gaps": ["asset:data:geo:GSE43696 not downloaded", "asset:data:geo:GSE43696 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "One-way ANOVA with Tukey post hoc test", "label": "One-way analysis of variance", "dsl_operations": ["group_comparison_anova"], "missing_operations": ["post_hoc_tukey"], "expressible": false, "parameters": {"design": "one-way ANOVA", "post_hoc": "Tukey", "software": "GraphPad Prism 5"}, "data_shapes": ["grouped numeric gene-expression measurements"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The raw data extracted from GEO database were statistically analyzed using one-way ANOVA with Tukey post hoc test by GraphPad Prism 5 software (GraphPad Software, La Jolla, CA, USA)."}}], "targets": [{"id": "target-mir-203a-fold-change", "claim_id": "claim-target-result", "operation": "differential_expression_fit", "expected_value": 2.41, "unit": "fold change (asthma/normal)", "tolerance": null, "state": "complete", "note": "Table 4: hsa-miR-203a 2852.52 versus 1184.56, log2 ratio 1.27, predicted target MEF2C. The GSE43696 ANOVA/Tukey estimates themselves are shown graphically in the paper and are not serialised as numerical table cells."}], "gaps": ["method.post_hoc_tukey"]}, "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:post_hoc_tukey", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": ["group_comparison_anova"], "missing_operations": ["post_hoc_tukey"], "basis": "The DSL catalogue has no operation for: post_hoc_tukey."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The corpus capability table owns computational analysis."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE43696"], "statements": ["The microarray of accession number GSE43696 published in 2014 [61] was used in this study. This microarray contains gene expression information of clinical bronchial epithelial cells from 108 patients, including normal control (n = 20, 9 males and 11 females), mild-moderate asthma (n = 50, 15 males and 35 females), and severe asthma (n = 38, 10 males and 28 females). The raw data were extracted and re-plotted by GraphPad prism 5 software (GraphPad Software, La Jolla, CA, USA)."], "basis": "The GEO series resolves and its sample accessions are listed. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_comparison_anova"], "assets": ["source:pmid:29137293", "data:geo:GSE43696", "asset:table:pmid:29137293:1", "asset:table:pmid:29137293:2", "asset:table:pmid:29137293:3", "asset:table:pmid:29137293:4", "asset:table:pmid:29137293:5"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "post_hoc_tukey", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE43696"]}, "gaps": ["method:post_hoc_tukey"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:46Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 37525, "completion_tokens": 1838, "cached_tokens": 1313}}, "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:29137293", "type": "paper", "label": "pmid:29137293"}, {"id": "source:pmid:29137293", "type": "manuscript", "label": "PMID 29137293 full text"}, {"id": "data:geo:GSE43696", "type": "dataset", "label": "GEO GSE43696"}], "activities": [{"id": "activity-pilot-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29137293", "type": "paper", "label": "pmid:29137293"}, {"id": "source:pmid:29137293", "type": "manuscript", "label": "PMID 29137293 full text"}, {"id": "data:geo:GSE43696", "type": "dataset", "label": "GEO GSE43696"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29137293", "type": "extraction", "used": ["source:pmid:29137293"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE43696", "type": "accession_resolution", "used": ["data:geo:GSE43696"], "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": "pilot-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:29137293", "parent_hash": "sha256:60d395ecbd1fac3829ec8b98a7001974c8ccba114200aa461145183541022e48", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE43696 licence not read", "asset:data:geo:GSE43696 not downloaded", "execution.not_run", "method.post_hoc_tukey", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:post_hoc_tukey"], "assays": [{"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ted with airway epithelial homeostasis using next-generation sequencing data and bioinformatics approaches", "(GE) microarray, next generation sequencing (NGS), and bioinformatics to explore genetic regu", "iles of mRNAs (GE microarray) and microRNAs (NGS) in normal and asthmatic bronchial epithelia", "izing solution, and HEPES buffered solution. Next-generation sequencing (NGS) The expression profile of microRNAs wa"], "order_basis": "paper_text_order:51", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["study aimed to combine gene expression (GE) microarray, next generation sequencing (NGS), and bioin", "We analyzed expression profiles of mRNAs (GE microarray) and microRNAs (NGS) in normal and asthmatic", "and MDGA1 were validated in a representative microarray (GSE43696) from the gene expression omnibus", "change > 2, and reads per million (RPM) > 1. Microarray analysis Total RNA of bronchial epithelial c"], "order_basis": "paper_text_order:362", "id": "assay:2"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["evere asthma and may promote epithelial cell apoptosis. We proposed that aberrant regulations of mi"], "order_basis": "paper_text_order:1257", "id": "assay:3"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["maintained at 37°C in 5% CO2 incubator, and passaged with ReagentPack™ (Lonza; Clonetics, San Die"], "order_basis": "paper_text_order:2251", "id": "assay:4"}, {"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["with the Illumina software. To analyze small RNA sequencing, the sequences were applied to go through a"], "order_basis": "paper_text_order:3740", "id": "assay:5"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_comparison_anova"], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The raw data extracted from GEO database were statistically analyzed using one-way ANOVA with Tukey post hoc test by GraphPad Prism 5 software (GraphPad Software, La Jolla, CA, USA)."], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T01:18:34+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}}}