Dataset of the proteome of purified outer membrane vesicles from the human pathogen Aggregatibacter actinomycetemcomintans.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28050585", "kind": "science-record", "revision": 5, "content_hash": "sha256:84f4ebcbffb752f465c17b29b9482535382c2c96df880b011741976be60a2d96", "created_at": "2026-11-01T15:40:22Z", "updated_at": "2026-11-01T18:48:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of the proteome of purified outer membrane vesicles from the human pathogen Aggregatibacter actinomycetemcomintans.", "doi": "10.1016/j.dib.2016.12.015", "pmid": "28050585", "authors": ["Thomas Kieselbach", "Jan Oscarsson"], "journal": "Data in brief", "year": 2017, "abstract": "The Gram-negative bacterium Aggregatibacter actinomycetemcomitans is an oral and systemic pathogen, which is linked to aggressive forms of periodontitis and can be associated with endocarditis. The outer membrane vesicles (OMVs) of this species contain effector proteins such as cytolethal distending toxin (CDT) and leukotoxin (LtxA), which they can deliver into human host cells. The OMVs can also activate innate immunity through NOD1- and NOD2-active pathogen-associated molecular patterns. This dataset provides a proteome of highly purified OMVs from A. actinomycetemcomitans serotype e strain 173. The experimental data do not only include the raw data of the LC-MS/MS analysis of four independent preparations of purified OMVs but also the mass lists of the processed data and the Mascot.dat files from the database searches. In total 501 proteins are identified, of which 151 are detected in at least three of four independent preparations. In addition, this dataset contains the COG definitions and the predicted subcellular locations (PSORTb 3.0) for the entire genome of A. actinomycetemcomitans serotype e strain SC1083, which is used for the evaluation of the LC-MS/MS data. These data are deposited in ProteomeXchange in the public dataset PXD002509. In addition, a scientific interpretation of this dataset by Kieselbach et al. (2015) [2] is available at http://dx.doi.org/10.1371/journal.pone.0138591.", "claims": [{"id": "claim-data-access", "statement": "Data is at ProteomeXchange[1]: PXD002509.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28050585", "locator": "sections[2] \"table-wrap\" paragraph 1", "quote": "Data is at ProteomeXchange[1]: PXD002509."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports a qualitative LC-MS/MS dataset rather than a statistical method; it identifies 501 non-redundant OMV proteins, including 151 detected in at least three of four preparations, and provides the raw and processed source data through ProteomeXchange dataset PXD002509.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28050585", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In total 501 proteins are identified, of which 151 are detected in at least three of four independent preparations."}, {"asset": "source:pmid:28050585", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "These data are deposited in ProteomeXchange in the public dataset PXD002509."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper reports a qualitative LC-MS/MS dataset rather than a statistical method; it identifies 501 non-redundant OMV proteins, including 151 detected in at least three of four preparations, and provides the raw and processed source data through ProteomeXchange dataset PXD002509.", "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:28050585"], "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:PXD002509"], "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:PXD002509"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28050585", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2016.12.015", "sha256": "sha256:22b8b0ecea7cbab90ce61293c06b40df704829783d623fb6a95e8fa64273b399", "bytes": 18281, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2016.12.015", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5192097", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002509", "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=PXD002509", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002509", "version": null, "note": "Data is at ProteomeXchange[1]: PXD002509.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data is at ProteomeXchange[1]: PXD002509.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Outer membrane vesicle proteome of Aggregatibacter actinomycetemcomitans serotype e strain 173", "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:PXD002509 not downloaded", "asset:data:geo:PXD002509 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["PXD002509"], "resolved_accessions": ["PXD002509"], "statements": ["Data is at ProteomeXchange[1]: PXD002509."], "basis": "The paper names PXD002509 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:28050585", "data:geo:PXD002509"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002509"]}, "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": "2026-10-31T18:30:18Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 42541, "completion_tokens": 2897, "cached_tokens": 11280}}, "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:28050585", "type": "paper", "label": "pmid:28050585"}, {"id": "source:pmid:28050585", "type": "manuscript", "label": "PMID 28050585 full text"}, {"id": "data:geo:PXD002509", "type": "dataset", "label": "GEO PXD002509"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28050585", "type": "paper", "label": "pmid:28050585"}, {"id": "source:pmid:28050585", "type": "manuscript", "label": "PMID 28050585 full text"}, {"id": "data:geo:PXD002509", "type": "dataset", "label": "GEO PXD002509"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28050585", "type": "extraction", "used": ["source:pmid:28050585"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002509", "type": "accession_resolution", "used": ["data:geo:PXD002509"], "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:28050585", "parent_hash": "sha256:da3ed09d6e3f46f17ac945b05963a3cec6e7b66fd1ce58f4022484c32fc486a3", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PXD002509 licence not read", "asset:data:geo:PXD002509 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["data do not only include the raw data of the LC-MS/MS analysis of four independent preparations of", "083, which is used for the evaluation of the LC-MS/MS data. These data are deposited in ProteomeXc", "ufficient material for a protein analysis by mass spectrometry. However, the high purity of the OMV fractio", "ed using trypsin and then identified through LC-MS/MS (DDA) and bioinformatics. The different step"], "order_basis": "paper_text_order:746", "id": "assay:1"}]}