{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38328158", "kind": "science-record", "revision": 3, "content_hash": "sha256:18876ea1f5976ac348c716c3832dec9e4289db3e9196a535a6b5844441954953", "created_at": "2026-11-01T19:20:16Z", "updated_at": "2026-11-01T22:11:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PRRGO: A Tool for Visualizing and Mapping Globally Expressed Genes in Public Gene Expression Omnibus RNA-Sequencing Studies to PageRank-scored Gene Ontology Terms.", "doi": "10.1101/2024.01.21.576540", "pmid": "38328158", "authors": ["Luis E Solano", "Nicholas M D'Sa", "Nikolas Nikolaidis"], "journal": "bioRxiv : the preprint server for biology", "year": 2024, "abstract": "We herein report PageRankeR Gene Ontology (PRRGO), a downloadable web application that can integrate differentially expressed gene (DEG) data from the gene expression omnibus (GEO) GEO2R web tool with the gene ontology (GO) database [1]. Unlike existing tools, PRRGO computes the PageRank for the entire GO network and can generate both interactive GO networks on the web interface and comma-separated values (CSV) files containing the DEG statistics categorized by GO term. These hierarchical and tabular GO-DEG data are especially conducive to hypothesis generation and overlap studies with the use of PageRank data, which can provide a metric of GO term centrality. We verified the tool for accuracy and reliability across nine independent heat shock (HS) studies for which the RNA-seq data was publicly available on GEO and found that the tool produced increasing concordance between study DEGs, GO terms, and select HS-specific GO terms.", "claims": [{"id": "claim-method", "statement": "The networkx package [28] converts the OBO-based GO graph into a network graph, and then computes PageRank scores for that entire network graph via the PageRank function [9, 10].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38328158", "locator": "sections[6] \"DEG Data Integration and Gene Ontology Network Retrieval:\" paragraph 2", "quote": "The networkx package [28] converts the OBO-based GO graph into a network graph, and then computes PageRank scores for that entire network graph via the PageRank function [9, 10]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38328158", "locator": "sections[24] \"Data Availability\" paragraph 2", "quote": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers."}], "state": "complete"}, {"id": "claim-target-result", "statement": "PRRGO was verified across nine public heat-shock RNA-seq studies and showed increasing concordance among study DEGs, GO terms, and selected heat-shock-specific GO terms.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38328158", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We verified the tool for accuracy and reliability across nine independent heat shock (HS) studies for which the RNA-seq data was publicly available on GEO and found that the tool produced increasing concordance between study DEGs, GO terms, and select HS-specific GO terms."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "PRRGO was verified across nine public heat-shock RNA-seq studies and showed increasing concordance among study DEGs, GO terms, and selected heat-shock-specific GO terms.", "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:38328158"], "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:GSE123980"], "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:GSE123980"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38328158", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1101/2024.01.21.576540", "sha256": "sha256:f3edeed26699ad03d47359ce6ec65c64433b405d9e845123f7635e6f5f99306d", "bytes": 44545, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1101/2024.01.21.576540", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10849496", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE123980", "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=GSE123980", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE123980", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3518105", "GSM3518106", "GSM3518107", "GSM3518108", "GSM3518109", "GSM3518110", "GSM3518111", "GSM3518112", "GSM3518113", "GSM3518114", "GSM3518115", "GSM3518116", "GSM3518117", "GSM3518118", "GSM3518119", "GSM3518120", "GSM3518121", "GSM3518122", "GSM3518123", "GSM3518124", "GSM3518125", "GSM3518126", "GSM3518127", "GSM3518128", "GSM3518129", "GSM3518130"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "The pause-initiation limit restricts transcription activation in human cells", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE124510", "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=GSE124510", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE124510", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3535537", "GSM3535538", "GSM3535539", "GSM3535540", "GSM3535541", "GSM3535542", "GSM3535543", "GSM3535544", "GSM3535545", "GSM3535546", "GSM3535547", "GSM3535548", "GSM3535549", "GSM3535550", "GSM3535551", "GSM3535552", "GSM3535553", "GSM3535554", "GSM3535555", "GSM3535556", "GSM3535557", "GSM3535558", "GSM3535559", "GSM3535560", "GSM3535561", "GSM3535562", "GSM3535563", "GSM3535564", "GSM3535565", "GSM3535566", "GSM3535567", "GSM3535568", "GSM3535569", "GSM3535570", "GSM3535571", "GSM3535572", "GSM3535573", "GSM3535574", "GSM3535575", "GSM3535576", "GSM3535577", "GSM3535578", "GSM3535579", "GSM4231704", "GSM4231705", "GSM4231706", "GSM4231707", "GSM4231708", "GSM4231709", "GSM4231710", "GSM4231711", "GSM4231712"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "11154;20301", "taxon": "Homo sapiens", "title": "Proteasome inhibitor-induced modulation reveals the spliceosome as a specific therapeutic vulnerability in multiple myeloma", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE124609", "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=GSE124609", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE124609", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3537582", "GSM3537583", "GSM3537584", "GSM3537585", "GSM3537586", "GSM3537587", "GSM3537588", "GSM3537589", "GSM3537590", "GSM3537591", "GSM3537592", "GSM3537593", "GSM3537594", "GSM3537595", "GSM3537596", "GSM3537597"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Cellular proteostasis collapse in mammalian senescence", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE132447", "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=GSE132447", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE132447", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3864912", "GSM3864913", "GSM3864914", "GSM3864915", "GSM3864916", "GSM3864917", "GSM3864918", "GSM3864919", "GSM3864920", "GSM3864921", "GSM3864922", "GSM3864923", "GSM3864924", "GSM3864925", "GSM3864926", "GSM3864927", "GSM3864928", "GSM3864929", "GSM3864930", "GSM3864931", "GSM3864932", "GSM3864933", "GSM3864934", "GSM3864935", "GSM3864936", "GSM3864937", "GSM3864938", "GSM3864939", "GSM3864940", "GSM3864941", "GSM3864942", "GSM3864943", "GSM3864944", "GSM3864945", "GSM3864946", "GSM3864947", "GSM3864948", "GSM3864949", "GSM3864950", "GSM3864951", "GSM3864952", "GSM3864953"], "sample_count": 42, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Origin of a novel CYP20A1 lncRNA through 23 Alu exaptations in the human lineage creates a potential multi-miRNA sponge", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE159802", "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=GSE159802", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE159802", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4847382", "GSM4847383", "GSM4847384", "GSM4847385", "GSM4847387", "GSM4847388", "GSM4847389", "GSM4847390", "GSM4847392", "GSM4847393", "GSM4847394", "GSM4847395", "GSM4847397", "GSM4847398", "GSM4847399", "GSM4847400", "GSM4847402", "GSM4847403"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "18460", "taxon": "Homo sapiens", "title": "Heat Shock Factor 1 (HSF1) supports the ESR1 action in breast cancer (RNA-seq)", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE164834", "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=GSE164834", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE164834", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5020463", "GSM5020464", "GSM5020465", "GSM5020466", "GSM5020467", "GSM5020468", "GSM5020469", "GSM5020470", "GSM5020471", "GSM5020472", "GSM5020473", "GSM5020474", "GSM5020475", "GSM5020476", "GSM5020477", "GSM5020478", "GSM5020479", "GSM5020480"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Mitochondrial protease Lonp1 localizes to the nucleus in response to heat shock", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE182960", "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=GSE182960", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE182960", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5543727", "GSM5543728", "GSM5543729", "GSM5543730", "GSM5543731", "GSM5543732", "GSM5543733", "GSM5543734", "GSM5543735", "GSM5543736", "GSM5543737", "GSM5543738", "GSM5543739", "GSM5543740", "GSM5543741", "GSM5543742", "GSM5543743", "GSM5543744", "GSM5543745", "GSM5543746", "GSM5543747", "GSM5543748", "GSM5543749", "GSM5543750", "GSM5543751", "GSM5543752", "GSM5543753", "GSM5543754", "GSM5543755", "GSM5543756", "GSM5543757", "GSM5543758", "GSM5543759", "GSM5543760", "GSM5543761", "GSM5543762", "GSM5543763", "GSM5543764", "GSM5543765"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "20301;24676", "taxon": "Homo sapiens", "title": "Cohesin regulates alternative splicing alone or with BRD4", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE66448", "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=GSE66448", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66448", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1622606", "GSM1622607", "GSM1622608", "GSM1622609", "GSM1622610", "GSM1622611", "GSM1622612", "GSM1622613", "GSM1622614", "GSM1622615", "GSM1622616", "GSM1622617", "GSM1622618", "GSM1622619", "GSM1622620", "GSM1622621", "GSM1622622", "GSM1622623", "GSM1622624", "GSM1622625", "GSM1622626", "GSM1622627", "GSM1622628", "GSM1622629", "GSM1622630", "GSM1622631", "GSM1622632", "GSM1622633", "GSM1622634", "GSM1622635", "GSM1622636", "GSM1622637", "GSM1777588", "GSM1777589", "GSM1777590", "GSM1777591", "GSM1777593", "GSM1777594", "GSM1777595", "GSM1777596", "GSM1777597", "GSM1777598", "GSM1777599", "GSM1777601", "GSM1777602", "GSM1777603", "GSM1777604", "GSM1777605", "GSM1777606", "GSM1777608", "GSM1777609", "GSM1777610"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Heat shock-induced changes in chromatin binding of SUMO2/3 modified proteins", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE73471", "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=GSE73471", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73471", "version": null, "note": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1895365", "GSM1895366", "GSM1895367", "GSM1895368", "GSM1895369", "GSM1895370", "GSM1895371", "GSM1895372"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "The bromodomain protein BRD4 regulates splicing during heat shock", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE123980 not downloaded", "asset:data:geo:GSE123980 licence not read", "asset:data:geo:GSE124510 not downloaded", "asset:data:geo:GSE124510 licence not read", "asset:data:geo:GSE124609 not downloaded", "asset:data:geo:GSE124609 licence not read", "asset:data:geo:GSE132447 not downloaded", "asset:data:geo:GSE132447 licence not read", "asset:data:geo:GSE159802 not downloaded", "asset:data:geo:GSE159802 licence not read", "asset:data:geo:GSE164834 not downloaded", "asset:data:geo:GSE164834 licence not read", "asset:data:geo:GSE182960 not downloaded", "asset:data:geo:GSE182960 licence not read", "asset:data:geo:GSE66448 not downloaded", "asset:data:geo:GSE66448 licence not read", "asset:data:geo:GSE73471 not downloaded", "asset:data:geo:GSE73471 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": 0.8, "band": "high", "quote": "DESeq2"}}, {"id": "method-2", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "centrality"}}, {"id": "method-3", "family": null, "specific": null, "label": "PageRank algorithm", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The networkx package [28] converts the OBO-based GO graph into a network graph, and then computes PageRank scores for that entire network graph via the PageRank function [9, 10]."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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: deseq2."}, "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": ["GSE124609", "GSE123980", "GSE73471", "GSE164834", "GSE66448", "GSE124510", "GSE132447", "GSE159802", "GSE182960"], "resolved_accessions": ["GSE124609", "GSE123980", "GSE73471", "GSE164834", "GSE66448", "GSE124510", "GSE132447", "GSE159802", "GSE182960"], "statements": ["PRRGO is publicly available at https://github.com/ndsa23/PRRGO under a GNU Lesser General Public License v2.1. Detailed installation instructions can be found in the README.md in the Github repository. PRRGO is platform-independent and can run on Windows, MacOS, and Linux on all major browsers."], "basis": "The paper names GSE124609, GSE123980, GSE73471, GSE164834, GSE66448, GSE124510, GSE132447, GSE159802, GSE182960 in Gene Expression Omnibus 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:38328158", "data:geo:GSE123980"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE123980"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:07:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12232, "completion_tokens": 2510, "cached_tokens": 128}}, "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:38328158", "type": "paper", "label": "pmid:38328158"}, {"id": "source:pmid:38328158", "type": "manuscript", "label": "PMID 38328158 full text"}, {"id": "data:geo:GSE123980", "type": "dataset", "label": "GEO GSE123980"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38328158", "type": "paper", "label": "pmid:38328158"}, {"id": "source:pmid:38328158", "type": "manuscript", "label": "PMID 38328158 full text"}, {"id": "data:geo:GSE123980", "type": "dataset", "label": "GEO GSE123980"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38328158", "type": "extraction", "used": ["source:pmid:38328158"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE123980", "type": "accession_resolution", "used": ["data:geo:GSE123980"], "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:38328158", "parent_hash": "sha256:1607d26ea71e2794373d242a6151dcf6f9b4e10ddd2f95acad623388394771ed", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE123980 licence not read", "asset:data:geo:GSE123980 not downloaded", "asset:data:geo:GSE124510 licence not read", "asset:data:geo:GSE124510 not downloaded", "asset:data:geo:GSE124609 licence not read", "asset:data:geo:GSE124609 not downloaded", "asset:data:geo:GSE132447 licence not read", "asset:data:geo:GSE132447 not downloaded", "asset:data:geo:GSE159802 licence not read", "asset:data:geo:GSE159802 not downloaded", "asset:data:geo:GSE164834 licence not read", "asset:data:geo:GSE164834 not downloaded", "asset:data:geo:GSE182960 licence not read", "asset:data:geo:GSE182960 not downloaded", "asset:data:geo:GSE66448 licence not read", "asset:data:geo:GSE66448 not downloaded", "asset:data:geo:GSE73471 licence not read", "asset:data:geo:GSE73471 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ssed Genes in Public Gene Expression Omnibus RNA-Sequencing Studies to PageRank-scored Gene Ontology Ter", "endent heat shock (HS) studies for which the RNA-seq data was publicly available on GEO and found", "I DataSets with the query “human heat shock ‘rnaseq counts’[Filter]”. Each returned study was it"], "order_basis": "paper_text_order:56", "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": 0.8, "evidence": ["DESeq2"], "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":"2026-11-04T02:43:48+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}}}