Proteomics data for characterizing Microbacterium oleivorans A9, an uranium-tolerant actinobacterium isolated near the Chernobyl nuclear power plant.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30456224", "kind": "science-record", "revision": 4, "content_hash": "sha256:49e912c58af6846cf74c04e4e048bd620db7b34a2dc3e89aed4fcf69dd38e6d9", "created_at": "2026-11-01T15:40:38Z", "updated_at": "2026-11-01T21:21:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomics data for characterizing Microbacterium oleivorans A9, an uranium-tolerant actinobacterium isolated near the Chernobyl nuclear power plant.", "doi": "10.1016/j.dib.2018.10.136", "pmid": "30456224", "authors": ["Nicolas Gallois", "Laurie Piette", "Philippe Ortet", "Mohamed Barakat", "Justine Long", "Catherine Berthomieu", "Jean Armengaud", "Virginie Chapon", "Béatrice Alpha-Bazin"], "journal": "Data in brief", "year": 2018, "abstract": "Microbacterium oleivorans A9 cells were exposed or not to 10 µM uranyl nitrate as resting cells in sodium chloride solution. Bacteria exposed to U(VI) and controls were harvested after 0.5, 4, and 24 h of toxicant exposure. Bacteria were subjected to high-throughput proteomics analysis using a Q-Exactive HF high resolution tandem mass spectrometer incorporating an ultra-high-field orbitrap analyzer. MS/MS spectra were assigned with a protein sequence database derived from a draft genome obtained by Illumina sequencing and systematic six-reading frame translation of all the contigs. Proteins identified in bacteria exposed to U(VI) and controls at the three time points allow defining the proteome dynamics upon uranium stress. The data reported here are related to a published study regarding the proteome dynamics of M. oleivorans A9 upon uranium stress by Gallois et al. (in press) entitled \"Proteogenomic insights into uranium tolerance of a Chernobyl׳s Microbacterium bacterial isolate\". The data accompanying the manuscript describing the database searches and comparative analysis have been deposited to the ProteomeXchange with identifier PXD005794.", "claims": [{"id": "claim-method", "statement": "The statistical protein variation was compared for each time point between the uranyl exposure and the control conditions using the T-Fold option of PatternLab 2.0 software [8].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30456224", "locator": "sections[7] \"Protein sequence database for proteogenomic MS/MS assignment\" paragraph 2", "quote": "The statistical protein variation was compared for each time point between the uranyl exposure and the control conditions using the T-Fold option of PatternLab 2.0 software [8]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30456224", "locator": "sections[1] \"p\" paragraph 1", "quote": "Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794."}], "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:30456224"], "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:PXD005794"], "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:PXD005794"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30456224", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2018.10.136", "sha256": "sha256:5d4a5c90426ea3c1d2402b00f902e880c6cb5eadc4743b675989f95f5c2091e8", "bytes": 7516, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2018.10.136", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6231083", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD005794", "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=PXD005794", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD005794", "version": null, "note": "Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteogenomics of a Chernobyl's Microbacterium sp. A9 bacterial isolate", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30456224:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:54e5854fac5c39f98f01b7e2dc7418ef1413674d1875aa79a009728afbc62d67", "bytes": 1354, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC6231083", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Environmental microbiology"], ["More specific subject area", "Actinobacteria comparative proteogenomics"], ["Type of data", "Figure, mass spectrometry raw files, Excel tables"], ["How data was acquired", "Data-dependent acquisition of tandem mass spectra using a Q-Exactive HF tandem mass spectrometer (Thermo)."], ["Data format", "Raw and processed"], ["Experimental factors", "Cells, at the exponential growth phase, were harvested and the resulting cell pellets were resuspended in NaCl solution with 0 (control) or 10 µM uranyl nitrate. For each of the three sampling time points, 0.5, 4 and 24 h, four biological replicates were performed."], ["Experimental features", "The 24 proteomes were briefly run on SDS-PAGE, followed by trypsin proteolysis. Tryptic peptides were analyzed by nanoLC-MS/MS and spectra were assigned with a draft genome-derived protein sequence database."], ["Data source location", "CEA-Marcoule, DRF-Li2D, Laboratory “Innovative technologies for Detection and Diagnostics”, BP 17171, F-30200 Bagnols-sur-Cèze, France"], ["Data accessibility", "Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794."]], "row_count": 9, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:30456224:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:54e5854fac5c39f98f01b7e2dc7418ef1413674d1875aa79a009728afbc62d67", "bytes": 1354, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC6231083", "section_index": 2, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Environmental microbiology"], ["More specific subject area", "Actinobacteria comparative proteogenomics"], ["Type of data", "Figure, mass spectrometry raw files, Excel tables"], ["How data was acquired", "Data-dependent acquisition of tandem mass spectra using a Q-Exactive HF tandem mass spectrometer (Thermo)."], ["Data format", "Raw and processed"], ["Experimental factors", "Cells, at the exponential growth phase, were harvested and the resulting cell pellets were resuspended in NaCl solution with 0 (control) or 10 µM uranyl nitrate. For each of the three sampling time points, 0.5, 4 and 24 h, four biological replicates were performed."], ["Experimental features", "The 24 proteomes were briefly run on SDS-PAGE, followed by trypsin proteolysis. Tryptic peptides were analyzed by nanoLC-MS/MS and spectra were assigned with a draft genome-derived protein sequence database."], ["Data source location", "CEA-Marcoule, DRF-Li2D, Laboratory “Innovative technologies for Detection and Diagnostics”, BP 17171, F-30200 Bagnols-sur-Cèze, France"], ["Data accessibility", "Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794."]], "row_count": 9, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:PXD005794 not downloaded", "asset:data:geo:PXD005794 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "T-Fold option of PatternLab 2.0 software", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The statistical protein variation was compared for each time point between the uranyl exposure and the control conditions using the T-Fold option of PatternLab 2.0 software [8]."}}], "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (T-Fold option of PatternLab 2.0 software), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["PXD005794", "PRIDE: PXD005794"], "resolved_accessions": ["PXD005794"], "statements": ["Data are within this article and deposited to the ProteomeXchange via the PRIDE repository with identifier PRIDE: PXD005794."], "basis": "The paper names PXD005794 in ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30456224", "data:geo:PXD005794", "asset:table:pmid:30456224:1", "asset:table:pmid:30456224:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD005794"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:47Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 6944, "completion_tokens": 959, "cached_tokens": 2568}}, "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:30456224", "type": "paper", "label": "pmid:30456224"}, {"id": "source:pmid:30456224", "type": "manuscript", "label": "PMID 30456224 full text"}, {"id": "data:geo:PXD005794", "type": "dataset", "label": "GEO PXD005794"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30456224", "type": "paper", "label": "pmid:30456224"}, {"id": "source:pmid:30456224", "type": "manuscript", "label": "PMID 30456224 full text"}, {"id": "data:geo:PXD005794", "type": "dataset", "label": "GEO PXD005794"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30456224", "type": "extraction", "used": ["source:pmid:30456224"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD005794", "type": "accession_resolution", "used": ["data:geo:PXD005794"], "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:30456224", "parent_hash": "sha256:75d4a6a751715a6385e5126380597a476519338805bd7977c8e2fffeb3899efc", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD005794 licence not read", "asset:data:geo:PXD005794 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}