PRRGO: A Tool for Visualizing and Mapping Globally Expressed Genes in Public Gene Expression Omnibus RNA-Sequencing Studies to PageRank-scored Gene Ontology Terms.

{"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"}]}