{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28588348", "kind": "science-record", "revision": 9, "content_hash": "sha256:3fced6a4ecdfef356413be7535ba7b4dd7945b5e507e5ed211c1bad024960106", "created_at": "2026-11-01T15:40:26Z", "updated_at": "2026-11-01T22:43:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Analysis of Microarray-Identified Genes and MicroRNAs Associated with Idiopathic Pulmonary Fibrosis.", "doi": "10.1155/2017/1804240", "pmid": "28588348", "authors": ["Lichao Fan", "Xiaoting Yu", "Ziling Huang", "Shaoqiang Zheng", "Yongxin Zhou", "Hanjing Lv", "Yu Zeng", "Jin-Fu Xu", "Xuyou Zhu", "Xianghua Yi"], "journal": "Mediators of inflammation", "year": 2017, "abstract": "The aim of this study was to identify potential microRNAs and genes associated with idiopathic pulmonary fibrosis (IPF) through web-available microarrays. The microRNA microarray dataset GSE32538 and the mRNA datasets GSE32537, GSE53845, and GSE10667 were downloaded from the Gene Expression Omnibus (GEO) database. Differentially expressed miRNAs (DE-miRNAs)/genes (DEGs) were screened with GEO2R, and their associations with IPF were analyzed by comprehensive bioinformatic analyses. A total of 45 DE-microRNAs were identified between IPF and control tissues, whereas 67 common DEGs were determined to exhibit the same expression trends in all three microarrays. Furthermore, functional analysis indicated that microRNAs in cancer and ECM-receptor interaction were the most significant pathways and were enriched by the 45 DE-miRNAs and 67 common DEGs. Finally, we predicted potential microRNA-target interactions between 17 DE-miRNAs and 17 DEGs by using at least three online programs. A microRNA-mediated regulatory network among the DE-miRNAs and DEGs was constructed that might shed new light on potential biomarkers for the prediction of IPF progression.", "claims": [{"id": "claim-method", "statement": "This tool is based on a t-test (ANOVA) or analysis of variance, and it is useful for comparing two or more groups of samples across the same experimental conditions to characterize differentially expressed microRNAs or genes.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28588348", "locator": "sections[4] \"2.2. Inclusion Criteria for Differentially Expressed MicroRNAs and Genes\" paragraph 2", "quote": "This tool is based on a t-test (ANOVA) or analysis of variance, and it is useful for comparing two or more groups of samples across the same experimental conditions to characterize differentially expressed microRNAs or genes."}], "state": "complete"}, {"id": "claim-data-access", "statement": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28588348", "locator": "sections[3] \"2.1. Acquisition and Analysis of Datasets\" paragraph 2", "quote": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]."}, {"asset": "source:pmid:28588348", "locator": "sections[6] \"3.1. Microarray Datasets That Met the Inclusion Criteria\" paragraph 2", "quote": "The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used GEO2R to screen microarrays downloaded from GEO, identifying 45 DE-miRNAs in IPF and 67 common DEGs across three mRNA datasets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28588348", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The microRNA microarray dataset GSE32538 and the mRNA datasets GSE32537, GSE53845, and GSE10667 were downloaded from the Gene Expression Omnibus (GEO) database. Differentially expressed miRNAs (DE-miRNAs)/genes (DEGs) were screened with GEO2R, and their associations with IPF were analyzed by comprehensive bioinformatic analyses."}, {"asset": "source:pmid:28588348", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 45 DE-microRNAs were identified between IPF and control tissues, whereas 67 common DEGs were determined to exhibit the same expression trends in all three microarrays."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used GEO2R to screen microarrays downloaded from GEO, identifying 45 DE-miRNAs in IPF and 67 common DEGs across three mRNA datasets.", "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:28588348"], "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:GSE10667"], "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:GSE10667"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28588348", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2017/1804240", "sha256": "sha256:702bd8559a84b16306f762db2ee102297ebb47b19104ece1b88f953843f763c6", "bytes": 32935, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2017/1804240", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5446886", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10667", "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=GSE10667", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10667", "version": null, "note": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM269749", "GSM269750", "GSM269751", "GSM269752", "GSM269753", "GSM269754", "GSM269755", "GSM269756", "GSM269757", "GSM269758", "GSM269759", "GSM269760", "GSM269761", "GSM269762", "GSM269763", "GSM269764", "GSM269765", "GSM269766", "GSM269767", "GSM269768", "GSM269769", "GSM269770", "GSM269771", "GSM269772", "GSM269773", "GSM269774", "GSM269775", "GSM269776", "GSM269777", "GSM269778", "GSM269779", "GSM269780", "GSM269781", "GSM269782", "GSM269783", "GSM269784", "GSM269785", "GSM269786", "GSM373881", "GSM373882", "GSM373883", "GSM373884", "GSM373885", "GSM373886", "GSM373887", "GSM373888"], "sample_count": 46, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "MMP1 and MMP7 as potential peripheral blood biomarkers in Idiopathic Pulmonary Fibrosis ", "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:GSE32537", "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=GSE32537", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32537", "version": null, "note": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM806204", "GSM806205", "GSM806206", "GSM806207", "GSM806208", "GSM806209", "GSM806210", "GSM806211", "GSM806212", "GSM806213", "GSM806214", "GSM806215", "GSM806216", "GSM806217", "GSM806218", "GSM806219", "GSM806220", "GSM806221", "GSM806222", "GSM806223", "GSM806224", "GSM806225", "GSM806226", "GSM806227", "GSM806228", "GSM806229", "GSM806230", "GSM806231", "GSM806232", "GSM806233", "GSM806234", "GSM806235", "GSM806236", "GSM806237", "GSM806238", "GSM806239", "GSM806240", "GSM806241", "GSM806242", "GSM806243", "GSM806244", "GSM806245", "GSM806246", "GSM806247", "GSM806248", "GSM806249", "GSM806250", "GSM806251", "GSM806252", "GSM806253", "GSM806254", "GSM806255", "GSM806256", "GSM806257", "GSM806258", "GSM806259", "GSM806260", "GSM806261", "GSM806262", "GSM806263", "GSM806264", "GSM806265", "GSM806266", "GSM806267", "GSM806268", "GSM806269", "GSM806270", "GSM806271", "GSM806272", "GSM806273", "GSM806274", "GSM806275", "GSM806276", "GSM806277", "GSM806278", "GSM806279", "GSM806280", "GSM806281", "GSM806282", "GSM806283", "GSM806284", "GSM806285", "GSM806286", "GSM806287", "GSM806288", "GSM806289", "GSM806290", "GSM806291", "GSM806292", "GSM806293", "GSM806294", "GSM806295", "GSM806296", "GSM806297", "GSM806298", "GSM806299", "GSM806300", "GSM806301", "GSM806302", "GSM806303", "GSM806304", "GSM806305", "GSM806306", "GSM806307", "GSM806308", "GSM806309", "GSM806310", "GSM806311", "GSM806312", "GSM806313", "GSM806314", "GSM806315", "GSM806316", "GSM806317", "GSM806318", "GSM806319", "GSM806320", "GSM806321", "GSM806322", "GSM806323", "GSM806324", "GSM806325", "GSM806326", "GSM806327", "GSM806328", "GSM806329", "GSM806330", "GSM806331", "GSM806332", "GSM806333", "GSM806334", "GSM806335", "GSM806336", "GSM806337", "GSM806338", "GSM806339", "GSM806340", "GSM806341", "GSM806342", "GSM806343", "GSM806344", "GSM806345", "GSM806346", "GSM806347", "GSM806348", "GSM806349", "GSM806350", "GSM806351", "GSM806352", "GSM806353", "GSM806354", "GSM806355", "GSM806356", "GSM806357", "GSM806358", "GSM806359", "GSM806360", "GSM806361", "GSM806362", "GSM806363", "GSM806364", "GSM806365", "GSM806366", "GSM806367", "GSM806368", "GSM806369", "GSM806370", "GSM806371", "GSM806372", "GSM806373", "GSM806374", "GSM806375", "GSM806376", "GSM806377", "GSM806378", "GSM806379", "GSM806380", "GSM806381", "GSM806382", "GSM806383", "GSM806384", "GSM806385", "GSM806386", "GSM806387", "GSM806388", "GSM806389", "GSM806390", "GSM806391", "GSM806392", "GSM806393", "GSM806394", "GSM806395", "GSM806396", "GSM806397", "GSM806398", "GSM806399", "GSM806400", "GSM806401", "GSM806402", "GSM806403", "GSM806404", "GSM806405", "GSM806406", "GSM806407", "GSM806408", "GSM806409", "GSM806410", "GSM806411", "GSM806412", "GSM806413", "GSM806414", "GSM806415", "GSM806416", "GSM806417", "GSM806418", "GSM806419", "GSM806420"], "sample_count": 217, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Molecular phenotyping of the idiopathic interstitial pneumonias [mRNA]", "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:GSE32538", "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=GSE32538", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32538", "version": null, "note": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM806421", "GSM806422", "GSM806423", "GSM806424", "GSM806425", "GSM806426", "GSM806427", "GSM806428", "GSM806429", "GSM806430", "GSM806431", "GSM806432", "GSM806433", "GSM806434", "GSM806435", "GSM806436", "GSM806437", "GSM806438", "GSM806439", "GSM806440", "GSM806441", "GSM806442", "GSM806443", "GSM806444", "GSM806445", "GSM806446", "GSM806447", "GSM806448", "GSM806449", "GSM806450", "GSM806451", "GSM806452", "GSM806453", "GSM806454", "GSM806455", "GSM806456", "GSM806457", "GSM806458", "GSM806459", "GSM806460", "GSM806461", "GSM806462", "GSM806463", "GSM806464", "GSM806465", "GSM806466", "GSM806467", "GSM806468", "GSM806469", "GSM806470", "GSM806471", "GSM806472", "GSM806473", "GSM806474", "GSM806475", "GSM806476", "GSM806477", "GSM806478", "GSM806479", "GSM806480", "GSM806481", "GSM806482", "GSM806483", "GSM806484", "GSM806485", "GSM806486", "GSM806487", "GSM806488", "GSM806489", "GSM806490", "GSM806491", "GSM806492", "GSM806493", "GSM806494", "GSM806495", "GSM806496", "GSM806497", "GSM806498", "GSM806499", "GSM806500", "GSM806501", "GSM806502", "GSM806503", "GSM806504", "GSM806505", "GSM806506", "GSM806507", "GSM806508", "GSM806509", "GSM806510", "GSM806511", "GSM806512", "GSM806513", "GSM806514", "GSM806515", "GSM806516", "GSM806517", "GSM806518", "GSM806519", "GSM806520", "GSM806521", "GSM806522", "GSM806523", "GSM806524", "GSM806525", "GSM806526", "GSM806527", "GSM806528", "GSM806529", "GSM806530", "GSM806531", "GSM806532", "GSM806533", "GSM806534", "GSM806535", "GSM806536", "GSM806537", "GSM806538", "GSM806539", "GSM806540", "GSM806541", "GSM806542", "GSM806543", "GSM806544", "GSM806545", "GSM806546", "GSM806547", "GSM806548", "GSM806549", "GSM806550", "GSM806551", "GSM806552", "GSM806553", "GSM806554", "GSM806555", "GSM806556", "GSM806557", "GSM806558", "GSM806559", "GSM806560", "GSM806561", "GSM806562", "GSM806563", "GSM806564", "GSM806565", "GSM806566", "GSM806567", "GSM806568", "GSM806569", "GSM806570", "GSM806571", "GSM806572", "GSM806573", "GSM806574", "GSM806575", "GSM806576", "GSM806577", "GSM806578", "GSM806579", "GSM806580", "GSM806581", "GSM806582", "GSM806583", "GSM806584", "GSM806585", "GSM806586", "GSM806587", "GSM806588", "GSM806589", "GSM806590", "GSM806591", "GSM806592", "GSM806593", "GSM806594", "GSM806595", "GSM806596", "GSM806597", "GSM806598", "GSM806599", "GSM806600", "GSM806601", "GSM806602", "GSM806603", "GSM806604", "GSM806605", "GSM806606", "GSM806607", "GSM806608", "GSM806609", "GSM806610", "GSM806611", "GSM806612"], "sample_count": 192, "group_sizes": null, "group_sizes_basis": null, "platform": "8786", "taxon": "Homo sapiens; synthetic construct", "title": "Molecular phenotyping of the idiopathic interstitial pneumonias [miRNA]", "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:GSE53845", "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=GSE53845", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53845", "version": null, "note": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1302033", "GSM1302034", "GSM1302035", "GSM1302036", "GSM1302037", "GSM1302038", "GSM1302039", "GSM1302040", "GSM1302041", "GSM1302042", "GSM1302043", "GSM1302044", "GSM1302045", "GSM1302046", "GSM1302047", "GSM1302048", "GSM1302049", "GSM1302050", "GSM1302051", "GSM1302052", "GSM1302053", "GSM1302054", "GSM1302055", "GSM1302056", "GSM1302057", "GSM1302058", "GSM1302059", "GSM1302060", "GSM1302061", "GSM1302062", "GSM1302063", "GSM1302064", "GSM1302065", "GSM1302066", "GSM1302067", "GSM1302068", "GSM1302069", "GSM1302070", "GSM1302071", "GSM1302072", "GSM1302073", "GSM1302074", "GSM1302075", "GSM1302076", "GSM1302077", "GSM1302078", "GSM1302079", "GSM1302080"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "40 IPF patients and 8 healthy controls", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28588348:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4608f639ac6cadb3c0b767c3dc6c0afddf0f9e6b91a00268c706b6a7668e717e", "bytes": 952, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#tab1", "version": null, "note": "microRNA and gene expression microarray datasets related to idiopathic pulmonary fibrosis.", "structure": {"pmcid": "PMC5446886", "section_index": 6, "section_title": "3.1. Microarray Datasets That Met the Inclusion Criteria", "row_count": 6, "column_count": 9}, "table": {"label": "Table 1", "caption": "microRNA and gene expression microarray datasets related to idiopathic pulmonary fibrosis.", "rows": [["", "Accession number of the dataset", "Organization name", "Platform", "Status", "Organism", "Experiment type", "Disease type"], ["IPF", "Control"], ["MicroRNA", "GSE32538 [14]", "University of Colorado", "GPL8786", "Public on June 21, 2013", "Homo sapiens", "Noncoding RNA profiling by array", "106", "50"], ["mRNA", "GSE32537 [14]", "University of Colorado", "GPL6244", "Public on June 21, 2013", "Homo sapiens", "Expression profiling by array", "119", "50"], ["", "GSE53845 [15]", "Genentech, Inc.", "GPL6480", "Public on Oct. 14, 2014", "Homo sapiens", "Expression profiling by array", "40", "8"], ["", "GSE10667 [16–18]", "University of Pittsburgh", "GPL4133", "Public on Feb. 20, 2009", "Homo sapiens", "Expression profiling by array", "23", "15"]], "row_count": 6, "column_count": 9, "numeric_cells": 20, "header_rows": 2, "locator": "section[6]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:28588348:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:63a817a740f5982086cb5256ea53895e4a52966c21acbfcffdd1c8e7f542fbc8", "bytes": 736, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#tab2", "version": null, "note": "Top 10 logFc of differentially expressed miRNAs obtained from the GSE32538 dataset.", "structure": {"pmcid": "PMC5446886", "section_index": 7, "section_title": "3.2. Differentially Expressed MicroRNAs and Pathway Enrichment", "row_count": 12, "column_count": 4}, "table": {"label": "Table 2", "caption": "Top 10 logFc of differentially expressed miRNAs obtained from the GSE32538 dataset.", "rows": [["Dysfunction", "miRNA", "logFc", "adj. p value"], ["Upregulated", "hsa-miR-205", "1.8093192", "2.79E-08"], ["hsa-miR-34c-3p", "2.2856359", "1.91E-08"], ["hsa-miR-34c-5p", "2.3310863", "3.36E-07"], ["hsa-miR-31", "2.3422275", "1.28E-08"], [""], ["Downregulated", "hsa-miR-532-5p", "−1.9021268", "5.03E-18"], ["hsa-miR-652", "−1.8713939", "8.44E-15"], ["hsa-miR-130a", "−1.6770333", "5.48E-11"], ["hsa-miR-210", "−1.6699558", "5.39E-11"], ["hsa-miR-500", "−1.6698889", "3.16E-15"], ["hsa-miR-193a-5p", "−1.6402524", "4.57E-15"]], "row_count": 12, "column_count": 4, "numeric_cells": 30, "header_rows": 1, "locator": "section[7]/table-wrap[1]#tab2"}}], "gaps": ["asset:data:geo:GSE10667 not downloaded", "asset:data:geo:GSE10667 licence not read", "asset:data:geo:GSE32537 not downloaded", "asset:data:geo:GSE32537 licence not read", "asset:data:geo:GSE32538 not downloaded", "asset:data:geo:GSE32538 licence not read", "asset:data:geo:GSE53845 not downloaded", "asset:data:geo:GSE53845 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "This tool is based on a t-test (ANOVA) or analysis of variance, and it is useful for comparing two or more groups of samples across the same experimental conditions to characterize differentially expressed microRNAs or genes."}}, {"id": "method-2", "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-3", "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": []}, "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE32538", "GSE32537", "GSE53845", "GSE10667"], "resolved_accessions": ["GSE32538", "GSE32537", "GSE53845", "GSE10667"], "statements": ["We downloaded the microRNA expression microarray dataset GSE32538 [14] and the mRNA expression microarray datasets GSE32537 [14], GSE53845 [15], and GSE10667 [16–18]. The samples used to generate the GSE32538 dataset were lung tissues from 167 subjects with IIP and 50 nondiseased controls."], "basis": "The paper names GSE32538, GSE32537, GSE53845, GSE10667 in National Center for Biotechnology Information Gene Expression Omnibus (NCBI GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:28588348", "data:geo:GSE10667", "asset:table:pmid:28588348:1", "asset:table:pmid:28588348:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10667"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:19Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 73287, "completion_tokens": 3617, "cached_tokens": 2080}}, "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:28588348", "type": "paper", "label": "pmid:28588348"}, {"id": "source:pmid:28588348", "type": "manuscript", "label": "PMID 28588348 full text"}, {"id": "data:geo:GSE10667", "type": "dataset", "label": "GEO GSE10667"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28588348", "type": "paper", "label": "pmid:28588348"}, {"id": "source:pmid:28588348", "type": "manuscript", "label": "PMID 28588348 full text"}, {"id": "data:geo:GSE10667", "type": "dataset", "label": "GEO GSE10667"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28588348", "type": "extraction", "used": ["source:pmid:28588348"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10667", "type": "accession_resolution", "used": ["data:geo:GSE10667"], "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:28588348", "parent_hash": "sha256:03e3c3dc50c24a6d5960c7c82a80078e77a003b5abbd4e6a463037a35072b196", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE10667 licence not read", "asset:data:geo:GSE10667 not downloaded", "asset:data:geo:GSE32537 licence not read", "asset:data:geo:GSE32537 not downloaded", "asset:data:geo:GSE32538 licence not read", "asset:data:geo:GSE32538 not downloaded", "asset:data:geo:GSE53845 licence not read", "asset:data:geo:GSE53845 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["Analysis of Microarray-Identified Genes and MicroRNAs Associated wi", "ough web-available microarrays. The microRNA microarray dataset GSE32538 and the mRNA datasets GSE32", "ds 2.1. Acquisition and Analysis of Datasets Microarray data from IPF-related microRNA and mRNA expr", "ctly the same expression trends in all three microarray sets (the list of the 67 differentially expr"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"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": ["r, extracellular matrix, cell migration, and apoptosis are shown in Figure 4(b). All of the above b"], "order_basis": "paper_text_order:5556", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["This tool is based on a t-test (ANOVA) or analysis of variance, and it is useful for comparing two or more groups of samples across the same experimental conditions to characterize differentially expressed microRNAs or genes."], "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":"2026-11-04T01:20:41+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}}}