CAT-GxD: Centralized access to gene expression datasets.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41092974", "kind": "science-record", "revision": 2, "content_hash": "sha256:ac14dec7c6e3acdc22b1f0bc806e1c3338dc32898c5aa3f5a4496a62bbea48c9", "created_at": "2026-11-01T20:31:09Z", "updated_at": "2026-11-01T21:35:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "CAT-GxD: Centralized access to gene expression datasets.", "doi": "10.1016/j.anaerobe.2025.103005", "pmid": "41092974", "authors": ["Bryan Angelo P Roxas", "Jennifer Lising Roxas", "Jessica S Guo", "David S LeBauer", "Fiona McCarthy", "Gayatri Vedantam", "V K Viswanathan"], "journal": "Anaerobe", "year": 2025, "abstract": "OBJECTIVES: Extensive multi-omic bacterial gene expression datasets are publicly available, but tools that unify these datasets for interpretation and hypothesis-testing are limited. The complexity and requirement of specialized bioinformatics and programming expertise pose significant major barriers for researchers attempting to query and analyze these datasets. Our objective was to develop an integrated search engine that simplifies access to publicly available gene expression data to facilitate comparison and analysis of multi-omics datasets.\nMETHODS: We developed the Centralized Access to Gene Expression Datasets (CAT-GxD) search engine to provide integrated access to, and facilitate analysis of, publicly available transcriptomics and proteomics datasets of the CDC Urgent Threat pathogen Clostridioides difficile. Manual data curation was performed to integrate and standardize all 74 nonredundant transcriptomics and quantitative proteomics datasets available at Gene Expression Omnibus (GEO) database and ProteomeXchange Consortium. The CAT-GxD search engine, developed on open-source R-shiny framework, is available at https://viz.datascience.arizona.edu/catgxd/.\nRESULTS: CAT-GxD successfully consolidated disparate transcriptomics and proteomics datasets, supporting interpretation and hypothesis testing. CAT-GxD provides customizable visualization of gene expression data under different conditions. We demonstrate the utility of CAT-GxD in analyzing the contribution of RNA polymerase, nitrogen-limitation N (RpoN) to C. difficile biology, and highlight the RpoN-dependent regulation of genes treated with succinate and the secondary bile acid deoxycholate.\nCONCLUSIONS: CAT-GxD streamlines the analysis of C. difficile multi-omic data, reducing the complexity and analysis time. It facilitates the generation of novel hypotheses and the identification of anti-infective targets, and can be adapted to incorporate data analysis paradigms for diverse organisms.", "claims": [{"id": "claim-data-access", "statement": "The CAT-GxD platform can be accessed at viz.datascience.arizona.edu/catgxd/. Details about the datasets analyzed in CAT-GxD are provided in Supplemental Table 1. The datasets are accessible via NCBI GEO (https://www.ncbi.nlm.nih.gov/geo/) and ProteomeXchange (https://proteomecentral.proteomexchange.org/cgi/GetDataset).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41092974", "locator": "sections[23] \"Availability of data and materials:\" paragraph 2", "quote": "The CAT-GxD platform can be accessed at viz.datascience.arizona.edu/catgxd/. Details about the datasets analyzed in CAT-GxD are provided in Supplemental Table 1. The datasets are accessible via NCBI GEO (https://www.ncbi.nlm.nih.gov/geo/) and ProteomeXchange (https://proteomecentral.proteomexchange.org/cgi/GetDataset)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "CAT-GxD integrates and standardizes all 74 nonredundant publicly available Clostridioides difficile transcriptomics and quantitative proteomics datasets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41092974", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Manual data curation was performed to integrate and standardize all 74 nonredundant transcriptomics and quantitative proteomics datasets available at Gene Expression Omnibus (GEO) database and ProteomeXchange Consortium."}, {"asset": "source:pmid:41092974", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "CAT-GxD successfully consolidated disparate transcriptomics and proteomics datasets, supporting interpretation and hypothesis testing."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "CAT-GxD integrates and standardizes all 74 nonredundant publicly available Clostridioides difficile transcriptomics and quantitative proteomics datasets.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41092974"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41092974", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.anaerobe.2025.103005", "sha256": "sha256:e87db1dd9631e814b1a2157a4c27d2d7416f36186fc0c0ac468047e59f01ca1f", "bytes": 31981, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.anaerobe.2025.103005", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12704217", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Principal Component Analysis"}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The CAT-GxD platform can be accessed at viz.datascience.arizona.edu/catgxd/. Details about the datasets analyzed in CAT-GxD are provided in Supplemental Table 1. The datasets are accessible via NCBI GEO (https://www.ncbi.nlm.nih.gov/geo/) and ProteomeXchange (https://proteomecentral.proteomexchange.org/cgi/GetDataset)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:41092974"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:03:09Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9130, "completion_tokens": 1719, "cached_tokens": 264}}, "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:41092974", "type": "paper", "label": "pmid:41092974"}, {"id": "source:pmid:41092974", "type": "manuscript", "label": "PMID 41092974 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41092974", "type": "paper", "label": "pmid:41092974"}, {"id": "source:pmid:41092974", "type": "manuscript", "label": "PMID 41092974 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41092974", "type": "extraction", "used": ["source:pmid:41092974"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:41092974", "parent_hash": "sha256:0664aef7176956abe60d8f71b9e4ffd1d12990a6a25b74659df8a982c3a8d0aa", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ative to the parent strain (Soutourina et al microarray dataset [35]).Supplemental Table 3. Selected"], "order_basis": "paper_text_order:5221", "id": "assay:1"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Principal Component Analysis"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}