{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31692674", "kind": "science-record", "revision": 8, "content_hash": "sha256:e7271b5168c6c16ffd6fce74cae5fd5dd6056f622444cf2c7c05c41718ed674f", "created_at": "2026-11-01T15:40:51Z", "updated_at": "2026-11-01T22:44:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset for dose and time-dependent transcriptional response to ionizing radiation exposure.", "doi": "10.1016/j.dib.2019.104624", "pmid": "31692674", "authors": ["Eric C Rouchka", "Robert M Flight", "Bridgitte H Fasciotto", "Rosendo Estrada", "John W Eaton", "Phani K Patibandla", "Sabine J Waigel", "Dazhuo Li", "John K Kirtley", "Palaniappan Sethu", "Robert S Keynton"], "journal": "Data in brief", "year": 2019, "abstract": "Exposure to ionizing radiation associated with highly energetic and charged heavy particles is an inherent risk astronauts face in long duration space missions. We have previously considered the transcriptional effects that three levels of radiation (0.3 Gy, 1.5 Gy, and 3.0 Gy) have at an immediate time point (1 hr) post-exposure [1]. Our analysis of these results suggest effects on transcript levels that could be modulated at lower radiation doses [2]. In addition, a time dependent effect is likely to be present. Therefore, in order to develop a lab-on-a-chip approach for detection of radiation exposure in terms of both radiation level and time since exposure, we developed a time- and dose-course study to determine appropriate sensitive and specific transcript biomarkers that are detectable in blood samples. The data described herein was developed from a study measuring exposure to 0.15 Gy, 0.30 Gy, and 1.5 Gy of radiation at 1 hr, 2 hr, and 6 hr post-exposure using Affymetrix® GeneChip® PrimeView™ microarrays. This report includes raw gene expression data files from the resulting microarray experiments representing typical radiation exposure levels an astronaut may experience as part of a long duration space mission. The data described here is available in NCBI's Gene Expression Omnibus (GEO), accession GSE63952.", "claims": [{"id": "claim-method", "statement": "Differentially expressed genes (DEGs) (defined as Affymetrix® probesets) were determined using Limma [7].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31692674", "locator": "sections[6] \"Data acquisition\" paragraph 4", "quote": "Differentially expressed genes (DEGs) (defined as Affymetrix® probesets) were determined using Limma [7]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw and processed microarray data is available in the Gene Expression Omnibus (GEO) database at NCBI (GSE63952).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31692674", "locator": "sections[2] \"Data\" paragraph 2", "quote": "The raw and processed microarray data is available in the Gene Expression Omnibus (GEO) database at NCBI (GSE63952)."}], "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:31692674"], "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:GSE63952"], "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:GSE63952"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31692674", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104624", "sha256": "sha256:1b56fd6157479a31026c5803ceae61a001f907f28ce761d4e278149e9ae33832", "bytes": 19899, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104624", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6806397", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE63952", "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=GSE63952", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63952", "version": null, "note": "The raw and processed microarray data is available in the Gene Expression Omnibus (GEO) database at NCBI (GSE63952).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw and processed microarray data is available in the Gene Expression Omnibus (GEO) database at NCBI (GSE63952).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1561166", "GSM1561167", "GSM1561168", "GSM1561169", "GSM1561170", "GSM1561171", "GSM1561172", "GSM1561173", "GSM1561174", "GSM1561175", "GSM1561176", "GSM1561177", "GSM1561178", "GSM1561179", "GSM1561180", "GSM1561181", "GSM1561182", "GSM1561183", "GSM1561184", "GSM1561185", "GSM1561186", "GSM1561187", "GSM1561188", "GSM1561189", "GSM1561190", "GSM1561191", "GSM1561192", "GSM1561193", "GSM1561194", "GSM1561195", "GSM1561196", "GSM1561197", "GSM1561198", "GSM1561199", "GSM1561200", "GSM1561201", "GSM1561202", "GSM1561203", "GSM1561204", "GSM1561205", "GSM1561206", "GSM1561207", "GSM1561208", "GSM1561209", "GSM1561210", "GSM1561211", "GSM1561212", "GSM1561213", "GSM1561214", "GSM1561215", "GSM1561216", "GSM1561217", "GSM1561218", "GSM1561219", "GSM1561220", "GSM1561221", "GSM1561222", "GSM1561223", "GSM1561224", "GSM1561225", "GSM1561226", "GSM1561227", "GSM1561228", "GSM1561229", "GSM1561230", "GSM1561231", "GSM1561232", "GSM1561233", "GSM1561234", "GSM1561235", "GSM1561236", "GSM1561237", "GSM1561238", "GSM1561239", "GSM1561240", "GSM1561241", "GSM1561242", "GSM1561243", "GSM1561244", "GSM1561245", "GSM1561246", "GSM1561247", "GSM1561248", "GSM1561249", "GSM1561250", "GSM1561251", "GSM1561252", "GSM1561253", "GSM1561254", "GSM1561255", "GSM1561256", "GSM1561257", "GSM1561258", "GSM1561259", "GSM1561260", "GSM1561261", "GSM1561262", "GSM1561263", "GSM1561264", "GSM1561265"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Early transcriptional changes in response to low dose radiation exposure", "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:31692674:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:53f0b7f5793859f98e04dd56b159e894fcb2400e9d7c4d528e555489833d711c", "bytes": 1786, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications Table", "structure": {"pmcid": "PMC6806397", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": "Specifications Table", "rows": [["Subject", "Biochemistry, Genetics and Molecular Biology"], ["Specific subject area", "Cellular transcriptional response to radiation exposure"], ["Type of data", "Microarray gene expression data"], ["How data were acquired", "Affymetrix® GeneChip® PrimeView™ Arrays"], ["Data format", "Raw; CEL files"], ["Experimental Factors", "0.15 Gy vs. 0.0 Gy at 1 hr post-exposure0.15 Gy vs. 0.0 Gy at 2 hr post-exposure0.15 Gy vs. 0.0 Gy at 6 hr post-exposure0.30 Gy vs. 0.0 Gy at 1 hr post-exposure0.30 Gy vs. 0.0 Gy at 2 hr post-exposure0.30 Gy vs. 0.0 Gy at 6 hr post-exposure1.50 Gy vs. 0.0 Gy at 1 hr post-exposure1.50 Gy vs. 0.0 Gy at 2 hr post-exposure1.50 Gy vs. 0.0 Gy at 6 hr post-exposure0.15 Gy vs. 0.0 Gy (dose-dependent)0.30 Gy vs. 0.0 Gy (dose-dependent)1.50 Gy vs. 0.0 Gy (dose-dependent)2 hr vs. 1 hr (time-dependent)6 hr vs. 1 hr (time-dependent)"], ["Experimental Features", "Gene expression profiling of radiation exposure using:1.0 Gy, 1 hr post-exposure (control; n = 10);1.0 Gy, 2 hr post-exposure (n = 10);1.0 Gy, 6 hr post-exposure (n = 5);0.15 Gy, 1 hr post-exposure (n = 10);0.15 Gy, 2 hr post-exposure (n = 10);0.15 Gy, 6 hr post-exposure (n = 5);0.30 Gy, 1 hr post-exposure (n = 10);0.30 Gy, 2 hr post-exposure (n = 10);0.30 Gy, 6 hr post-exposure (n = 5);1.50 Gy, 1 hr post-exposure (n = 10);1.50 Gy, 2 hr post-exposure (n = 10);1.50 Gy, 6 hr post-exposure (n = 5)."], ["Data source location", "Louisville, Kentucky USA"], ["Data accessibility", "Repository name: Gene Expression Omnibus (GEO)Data identification number: GSE63952Direct URL to data: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE63952"]], "row_count": 9, "column_count": 2, "numeric_cells": 3, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31692674:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cac2ea85db4c3a3e80765ccef8b0b0a6fdb4e75c47fc87954b13f349e8f2f3f4", "bytes": 1309, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6806397", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the Data•Few high-throughput studies regarding ionizing radiation exposure are publicly available. This dataset provides novel time- and dose-dependent transcript abundance data based on typical ionizing radiation exposure faced by astronauts at 0.15 Gy, 0.30 Gy, and 1.50 Gy.•Evaluation of time since exposure is possible with this dataset at immediate time points (1 hr and 2hr post-exposure) as well as an intermediate time point (6 hr post-exposure). Used together, these results allow for the design of appropriate transcript biomarkers used to determine radiation exposure events, the amount of radiation exposed, and the time since the event. As a result, this data can allow for design of appropriate treatment and mitigation.•The determination of appropriate biomarkers for general radiation exposure, dose-dependent markers, and time-dependent markers within blood plasma samples makes it possible to design light-weight, portable, lab-on-a-chip diagnostic tests for measuring radiation exposure. Such diagnostic instrumentation can be incorporated on long-term space flights in order to properly address radiation exposure events."]], "row_count": 1, "column_count": 1, "numeric_cells": 1, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31692674:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a6cd42ae340d1bd244a756833217ba67133d8af9c07f3a6877f4e7c32cc97f1f", "bytes": 5248, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "Sample information.", "structure": {"pmcid": "PMC6806397", "section_index": 2, "section_title": "Data", "row_count": 51, "column_count": 8}, "table": {"label": "Table 1", "caption": "Sample information.", "rows": [["Volunteer", "Time", "Dose", "SampleName", "GEOSample ID", "Dose", "SampleName", "GEOSample ID"], ["1", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-1", "GSM1561166", "0.30 Gy", "SAMPLE_0.30Gy_1h-1", "GSM1561216"], ["2", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-2", "GSM1561167", "0.30 Gy", "SAMPLE_0.30Gy_1h-2", "GSM1561217"], ["3", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-3", "GSM1561168", "0.30 Gy", "SAMPLE_0.30Gy_1h-3", "GSM1561218"], ["4", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-4", "GSM1561169", "0.30 Gy", "SAMPLE_0.30Gy_1h-4", "GSM1561219"], ["5", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-5", "GSM1561170", "0.30 Gy", "SAMPLE_0.30Gy_1h-5", "GSM1561220"], ["6", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-6", "GSM1561171", "0.30 Gy", "SAMPLE_0.30Gy_1h-6", "GSM1561221"], ["7", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-7", "GSM1561172", "0.30 Gy", "SAMPLE_0.30Gy_1h-7", "GSM1561222"], ["8", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-8", "GSM1561173", "0.30 Gy", "SAMPLE_0.30Gy_1h-8", "GSM1561223"], ["9", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-9", "GSM1561174", "0.30 Gy", "SAMPLE_0.30Gy_1h-9", "GSM1561224"], ["10", "1 hr", "0 Gy", "SAMPLE_0.00Gy_1h-10", "GSM1561175", "0.30 Gy", "SAMPLE_0.30Gy_1h-10", "GSM1561225"], ["1", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-1", "GSM1561176", "0.30 Gy", "SAMPLE_0.30Gy_2h-1", "GSM1561226"], ["2", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-2", "GSM1561177", "0.30 Gy", "SAMPLE_0.30Gy_2h-2", "GSM1561227"], ["3", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-3", "GSM1561178", "0.30 Gy", "SAMPLE_0.30Gy_2h-3", "GSM1561228"], ["4", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-4", "GSM1561179", "0.30 Gy", "SAMPLE_0.30Gy_2h-4", "GSM1561229"], ["5", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-5", "GSM1561180", "0.30 Gy", "SAMPLE_0.30Gy_2h-5", "GSM1561230"], ["6", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-6", "GSM1561181", "0.30 Gy", "SAMPLE_0.30Gy_2h-6", "GSM1561231"], ["7", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-7", "GSM1561182", "0.30 Gy", "SAMPLE_0.30Gy_2h-7", "GSM1561232"], ["8", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-8", "GSM1561183", "0.30 Gy", "SAMPLE_0.30Gy_2h-8", "GSM1561233"], ["9", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-9", "GSM1561184", "0.30 Gy", "SAMPLE_0.30Gy_2h-9", "GSM1561234"], ["10", "2 hr", "0 Gy", "SAMPLE_0.00Gy_2h-10", "GSM1561185", "0.30 Gy", "SAMPLE_0.30Gy_2h-10", "GSM1561235"], ["1", "6 hr", "0 Gy", "SAMPLE_0.00Gy_6h-1", "GSM1561186", "0.30 Gy", "SAMPLE_0.30Gy_6h-1", "GSM1561236"], ["2", "6 hr", "0 Gy", "SAMPLE_0.00Gy_6h-2", "GSM1561187", "0.30 Gy", "SAMPLE_0.30Gy_6h-2", "GSM1561237"], ["3", "6 hr", "0 Gy", "SAMPLE_0.00Gy_6h-3", "GSM1561188", "0.30 Gy", "SAMPLE_0.30Gy_6h-3", "GSM1561238"], ["4", "6 hr", "0 Gy", "SAMPLE_0.00Gy_6h-4", "GSM1561189", "0.30 Gy", "SAMPLE_0.30Gy_6h-4", "GSM1561239"], ["7", "6 hr", "0 Gy", "SAMPLE_0.00Gy_6h-7", "GSM1561190", "0.30 Gy", "SAMPLE_0.30Gy_6h-7", "GSM1561240"], ["1", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-1", "GSM1561191", "1.50 Gy", "SAMPLE_1.50Gy_1h-1", "GSM1561241"], ["2", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-2", "GSM1561192", "1.50 Gy", "SAMPLE_1.50Gy_1h-2", "GSM1561242"], ["3", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-3", "GSM1561193", "1.50 Gy", "SAMPLE_1.50Gy_1h-3", "GSM1561243"], ["4", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-4", "GSM1561194", "1.50 Gy", "SAMPLE_1.50Gy_1h-4", "GSM1561244"], ["5", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-5", "GSM1561195", "1.50 Gy", "SAMPLE_1.50Gy_1h-5", "GSM1561245"], ["6", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-6", "GSM1561196", "1.50 Gy", "SAMPLE_1.50Gy_1h-6", "GSM1561246"], ["7", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-7", "GSM1561197", "1.50 Gy", "SAMPLE_1.50Gy_1h-7", "GSM1561247"], ["8", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-8", "GSM1561198", "1.50 Gy", "SAMPLE_1.50Gy_1h-8", "GSM1561248"], ["9", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-9", "GSM1561199", "1.50 Gy", "SAMPLE_1.50Gy_1h-9", "GSM1561249"], ["10", "1 hr", "0.15 Gy", "SAMPLE_0.15Gy_1h-10", "GSM1561200", "1.50 Gy", "SAMPLE_1.50Gy_1h-10", "GSM1561250"], ["1", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-1", "GSM1561201", "1.50 Gy", "SAMPLE_1.50Gy_2h-1", "GSM1561251"], ["2", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-2", "GSM1561202", "1.50 Gy", "SAMPLE_1.50Gy_2h-2", "GSM1561252"], ["3", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-3", "GSM1561203", "1.50 Gy", "SAMPLE_1.50Gy_2h-3", "GSM1561253"], ["4", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-4", "GSM1561204", "1.50 Gy", "SAMPLE_1.50Gy_2h-4", "GSM1561254"], ["5", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-5", "GSM1561205", "1.50 Gy", "SAMPLE_1.50Gy_2h-5", "GSM1561255"], ["6", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-6", "GSM1561206", "1.50 Gy", "SAMPLE_1.50Gy_2h-6", "GSM1561256"], ["7", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-7", "GSM1561207", "1.50 Gy", "SAMPLE_1.50Gy_2h-7", "GSM1561257"], ["8", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-8", "GSM1561208", "1.50 Gy", "SAMPLE_1.50Gy_2h-8", "GSM1561258"], ["9", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-9", "GSM1561209", "1.50 Gy", "SAMPLE_1.50Gy_2h-9", "GSM1561259"], ["10", "2 hr", "0.15 Gy", "SAMPLE_0.15Gy_2h-10", "GSM1561210", "1.50 Gy", "SAMPLE_1.50Gy_2h-10", "GSM1561260"], ["1", "6 hr", "0.15 Gy", "SAMPLE_0.15Gy_6h-1", "GSM1561211", "1.50 Gy", "SAMPLE_1.50Gy_6h-1", "GSM1561261"], ["2", "6 hr", "0.15 Gy", "SAMPLE_0.15Gy_6h-2", "GSM1561212", "1.50 Gy", "SAMPLE_1.50Gy_6h-2", "GSM1561262"], ["3", "6 hr", "0.15 Gy", "SAMPLE_0.15Gy_6h-3", "GSM1561213", "1.50 Gy", "SAMPLE_1.50Gy_6h-3", "GSM1561263"], ["4", "6 hr", "0.15 Gy", "SAMPLE_0.15Gy_6h-4", "GSM1561214", "1.50 Gy", "SAMPLE_1.50Gy_6h-4", "GSM1561264"], ["7", "6 hr", "0.15 Gy", "SAMPLE_0.15Gy_6h-7", "GSM1561215", "1.50 Gy", "SAMPLE_1.50Gy_6h-7", "GSM1561265"]], "row_count": 51, "column_count": 8, "numeric_cells": 400, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:31692674:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f0b8eaa9e16bf2c306fb5eec55aaec163ce343c3de581ca017ea67e43ed4e219", "bytes": 963, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#tbl2", "version": null, "note": "Radiation dependent differentially expressed genes measured as the number of differentially expressed probes detected by Limma at p ≤ 0.05 for low (0.15 Gy vs. 0.0 Gy), mid (0.30 Gy vs. 0.0 Gy) and high (1.5 vs. 0.0 Gy) radiation levels at early (1 hr), mid (2 hr), and late (6 hr) as well as combined time points. Arrows indicate the number of up (↑) or down (↓) regulated probesets.", "structure": {"pmcid": "PMC6806397", "section_index": 2, "section_title": "Data", "row_count": 6, "column_count": 4}, "table": {"label": "Table 2", "caption": "Radiation dependent differentially expressed genes measured as the number of differentially expressed probes detected by Limma at p ≤ 0.05 for low (0.15 Gy vs. 0.0 Gy), mid (0.30 Gy vs. 0.0 Gy) and high (1.5 vs. 0.0 Gy) radiation levels at early (1 hr), mid (2 hr), and late (6 hr) as well as combined time points. Arrows indicate the number of up (↑) or down (↓) regulated probesets.", "rows": [["Time Point", "Comparison"], ["0.15 Gy vs 0 Gy", "0.30 Gy vs 0 Gy", "1.5 Gy vs 0 Gy"], ["Early (1hr)", "879 (635↑, 244↓)", "1462 (898↑, 564↓)", "2278 (1423↑, 855↓)"], ["Mid (2 hr)", "905 (446↑,459↓)", "1521 (763↑,758↓)", "3575 (2115↑,1460↓)"], ["Late (6 hr)", "841 (510↑,331↓)", "1461 (776↑,685↓)", "1884 (1177↑,707↓)"], ["Combined", "805 (496↑,309↓)", "1913 (970↑,943↓)", "3289 (1815↑,1474↓)"]], "row_count": 6, "column_count": 4, "numeric_cells": 18, "header_rows": 2, "locator": "section[2]/table-wrap[2]#tbl2"}}, {"id": "asset:table:pmid:31692674:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:264b968f86efb1428b83437094b0953d89556253ee1eb5087cfd1b7c584226a3", "bytes": 978, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[3]#tbl3", "version": null, "note": "Time dependent differentially expressed genes measured as the number of differentially expressed probesets detected by Limma at p ≤ 0.05 and a log fold-change cutoff of 1 for mid (2 hr vs. 1 hr) and late (6 hr vs. 1 hr) time points measured with no radiation (0 Gy), low radiation (0.15 Gy), mid radiation (0.30 Gy) and high radiation (1.5 Gy) as well as all radiation levels combined. Arrows indicate the number of up (↑) or down (↓) regulated probesets.", "structure": {"pmcid": "PMC6806397", "section_index": 2, "section_title": "Data", "row_count": 7, "column_count": 3}, "table": {"label": "Table 3", "caption": "Time dependent differentially expressed genes measured as the number of differentially expressed probesets detected by Limma at p ≤ 0.05 and a log fold-change cutoff of 1 for mid (2 hr vs. 1 hr) and late (6 hr vs. 1 hr) time points measured with no radiation (0 Gy), low radiation (0.15 Gy), mid radiation (0.30 Gy) and high radiation (1.5 Gy) as well as all radiation levels combined. Arrows indicate the number of up (↑) or down (↓) regulated probesets.", "rows": [["Radiation Level", "Comparison"], ["2 hr vs 1 hr", "6 hr vs 1 hr"], ["No (0 Gy)", "126 (117↑, 9↓)", "1086 (630↑, 456↓)"], ["Low (0.15 Gy)", "194 (170↑,24↓)", "1288 (751↑,537↓)"], ["Mid (0.30 Gy)", "222 (194↑,28↓)", "1367 (771↑,596↓)"], ["High (1.5 Gy)", "272 (236↑,36↓)", "1414 (800↑,614↓)"], ["Combined", "185 (168↑,17↓)", "1285 (723↑, 562↓)"]], "row_count": 7, "column_count": 3, "numeric_cells": 16, "header_rows": 2, "locator": "section[2]/table-wrap[3]#tbl3"}}], "gaps": ["asset:data:geo:GSE63952 not downloaded", "asset:data:geo:GSE63952 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differentially expressed genes (DEGs) (defined as Affymetrix® probesets) were determined using Limma [7]."}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE63952"], "resolved_accessions": ["GSE63952"], "statements": ["The raw and processed microarray data is available in the Gene Expression Omnibus (GEO) database at NCBI (GSE63952)."], "basis": "The paper names GSE63952 in Gene Expression Omnibus (GEO) database at NCBI and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31692674", "data:geo:GSE63952", "asset:table:pmid:31692674:1", "asset:table:pmid:31692674:2", "asset:table:pmid:31692674:3", "asset:table:pmid:31692674:4", "asset:table:pmid:31692674:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE63952"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:39Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 20232, "completion_tokens": 966, "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:31692674", "type": "paper", "label": "pmid:31692674"}, {"id": "source:pmid:31692674", "type": "manuscript", "label": "PMID 31692674 full text"}, {"id": "data:geo:GSE63952", "type": "dataset", "label": "GEO GSE63952"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31692674", "type": "paper", "label": "pmid:31692674"}, {"id": "source:pmid:31692674", "type": "manuscript", "label": "PMID 31692674 full text"}, {"id": "data:geo:GSE63952", "type": "dataset", "label": "GEO GSE63952"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31692674", "type": "extraction", "used": ["source:pmid:31692674"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE63952", "type": "accession_resolution", "used": ["data:geo:GSE63952"], "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:31692674", "parent_hash": "sha256:a7ad84559a408c81a95a532d220bae5149e174dd1a18e3a7ff39a36f645f8d87", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE63952 licence not read", "asset:data:geo:GSE63952 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": ["ene expression data files from the resulting microarray experiments representing typical radiation e", "at 1 hr, 2 hr, and 6 hr post-exposure using Affymetrix® GeneChip® PrimeView™ microarrays. This repo", "pared according to the standard protocol for Affymetrix® 3′ IVT Express Reagent Kit (Affymetrix® Inc", "for Affymetrix® 3′ IVT Express Reagent Kit (Affymetrix® Inc., Santa Clara, CA) from 100 ng total RN"], "order_basis": "paper_text_order:1031", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differentially expressed genes (DEGs) (defined as Affymetrix® probesets) were determined using Limma [7]."], "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":"2026-11-04T02:52:34+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}}}