A proteomic dataset of secreted proteins by three Staphylococcus saprophyticus strains.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30456272", "kind": "science-record", "revision": 3, "content_hash": "sha256:d189c0da6d6dcae679e36ab2ce8000cd37aad867521c36a5dd84ff7d481c99a2", "created_at": "2026-11-01T15:40:39Z", "updated_at": "2026-11-01T21:21:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A proteomic dataset of secreted proteins by three Staphylococcus saprophyticus strains.", "doi": "10.1016/j.dib.2018.10.122", "pmid": "30456272", "authors": ["Andrea Santana de Oliveira", "Isabella Inês Rodrigues Rosa", "Evandro Novaes", "Lucas Silva de Oliveira", "Lilian Cristiane Baeza", "Clayton Luiz Borges", "Lennart Marlinghaus", "Célia Maria de Almeida Soares", "Marcia Giambiagi-deMarval", "Juliana Alves Parente-Rocha"], "journal": "Data in brief", "year": 2018, "abstract": "This article presents a proteomic dataset generated from a comparative analysis of the exoproteome of Staphylococcus saprophyticus, ATCC 15305, 7108 and 9325 strains. The extract of secreted proteins were obtained after incubation of stationary phase cells in BHI medium. All samples were submitted to nano-ESI-UPLC-MSE, and the spectrum obtained was processed and analyzed by ProteinLynx Global Server (PLGS), Uniprot and Pedant databases, for identification, annotation and functional classification of proteins. Fold changes and protein relative abundances were properly reported. This report is related to the research article entitled \"The exoproteome profiles of three Staphylococcus saprophyticus strains reveal diversity in protein secretion contents\" (Oliveira et al., 2018). The proteomic data generated have been deposited to the ProteomeXchange Consortium, via the PRIDE partner repository, with a project number PXD008643, https://www.ebi.ac.uk/pride/archive/projects/PXD008643.", "claims": [{"id": "claim-data-access", "statement": "The analyzed data in excel format are available in this article, and raw data are accessible in ProteomeXchange Consortium[1], via the PRIDE partner repository, under Project number PXD008643 [https://www.ebi.ac.uk/pride/archive/projects/PXD008643]", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30456272", "locator": "sections[2] \"table-wrap\" paragraph 1", "quote": "The analyzed data in excel format are available in this article, and raw data are accessible in ProteomeXchange Consortium[1], via the PRIDE partner repository, under Project number PXD008643 [https://www.ebi.ac.uk/pride/archive/projects/PXD008643]"}], "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:30456272"], "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:PXD008643"], "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:PXD008643"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30456272", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2018.10.122", "sha256": "sha256:1c638ccbe8322a710155e07320e954e2b21774007fe591753239e2462a1f0d36", "bytes": 9804, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2018.10.122", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6234272", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD008643", "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=PXD008643", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD008643", "version": null, "note": "The analyzed data in excel format are available in this article, and raw data are accessible in ProteomeXchange Consortium[1], via the PRIDE partner repository, under Project number PXD008643 [https://www.ebi.ac.uk/pride/archive/projects/PXD008643]", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed data in excel format are available in this article, and raw data are accessible in ProteomeXchange Consortium[1], via the PRIDE partner repository, under Project number PXD008643 [https://www.ebi.ac.uk/pride/archive/projects/PXD008643]", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "THE EXOPROTEOME PROFILES OF THREE STAPHYLOCOCCUS SAPROPHYTICUS STRAINS REVEAL DIVERSITY IN PROTEIN SECRETION CONTENT", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD008643 not downloaded", "asset:data:geo:PXD008643 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Statistical tools from R software, using a 0.05 false discovery threshold", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“The data showed in this article were generated by a comparative proteomic analysis performed using statistical tools from R software.” “Proteins were described as differentially expressed using a threshold of 0.05 false discovery.”"}}], "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 (Statistical tools from R software, using a 0.05 false discovery threshold), 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": ["PXD008643"], "resolved_accessions": ["PXD008643"], "statements": ["The analyzed data in excel format are available in this article, and raw data are accessible in ProteomeXchange Consortium[1], via the PRIDE partner repository, under Project number PXD008643 [https://www.ebi.ac.uk/pride/archive/projects/PXD008643]"], "basis": "The paper names PXD008643 in ProteomeXchange Consortium, via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30456272", "data:geo:PXD008643"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD008643"]}, "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": "2026-10-31T18:12:54Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 8862, "completion_tokens": 2018, "cached_tokens": 648}}, "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:30456272", "type": "paper", "label": "pmid:30456272"}, {"id": "source:pmid:30456272", "type": "manuscript", "label": "PMID 30456272 full text"}, {"id": "data:geo:PXD008643", "type": "dataset", "label": "GEO PXD008643"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30456272", "type": "paper", "label": "pmid:30456272"}, {"id": "source:pmid:30456272", "type": "manuscript", "label": "PMID 30456272 full text"}, {"id": "data:geo:PXD008643", "type": "dataset", "label": "GEO PXD008643"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30456272", "type": "extraction", "used": ["source:pmid:30456272"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD008643", "type": "accession_resolution", "used": ["data:geo:PXD008643"], "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:30456272", "parent_hash": "sha256:351d1a50aaa6d5e8e014f0f45463c150d06719b94d297edf190d99dcdb4768dd", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD008643 licence not read", "asset:data:geo:PXD008643 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}