Toward Single Bacterium Proteomics.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37713396", "kind": "science-record", "revision": 3, "content_hash": "sha256:2e27081c59a62afbec7ed73ad6d5ae794918ccddfd10b9c58eff4bbb513f548d", "created_at": "2026-11-01T19:02:32Z", "updated_at": "2026-11-01T21:31:34Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Toward Single Bacterium Proteomics.", "doi": "10.1021/jasms.3c00242", "pmid": "37713396", "authors": ["Ákos Végvári", "Xuepei Zhang", "Roman A Zubarev"], "journal": "Journal of the American Society for Mass Spectrometry", "year": 2023, "abstract": "Bacteria are orders of magnitude smaller than mammalian cells, and while single cell proteomics (SCP) currently detects and quantifies several thousands of proteins per mammalian cell, it is not clear whether conventional SCP methods will be suitable for bacteria. Here we report on the first successful attempt to detect proteins from individual Escherichia coli bacteria, with validation of our findings by comparison with two bacteria samples and bulk proteomics data. Data are available via ProteomeXchange with the identifier PXD043473.", "claims": [{"id": "claim-method", "statement": "Using Percolator for control of FDR ≤ 0.05, 94 PSMs were annotated in the E. coli database, identifying 29 peptides of 19 bacterial proteins across the 96 single/double cells (Tables 1 and 2).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37713396", "locator": "sections[8] \"Single Bacterium Proteomics\" paragraph 4", "quote": "Using Percolator for control of FDR ≤ 0.05, 94 PSMs were annotated in the E. coli database, identifying 29 peptides of 19 bacterial proteins across the 96 single/double cells (Tables 1 and 2)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE23 partner repository with the data set identifier PXD043473.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37713396", "locator": "sections[5] \"RPLC-LC-MS/MS Analysis\" paragraph 5", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE23 partner repository with the data set identifier PXD043473."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Here we report on the first successful attempt to detect proteins from individual Escherichia coli bacteria, with validation of our findings by comparison with two bacteria samples and bulk proteomics data.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37713396", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Here we report on the first successful attempt to detect proteins from individual Escherichia coli bacteria, with validation of our findings by comparison with two bacteria samples and bulk proteomics data."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Here we report on the first successful attempt to detect proteins from individual Escherichia coli bacteria, with validation of our findings by comparison with two bacteria samples and bulk proteomics data.", "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:37713396"], "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:PXD043473"], "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:PXD043473"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37713396", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/jasms.3c00242", "sha256": "sha256:8f54229244a661d48a245c2f0ca899e930660c2358edb9c1dd1cfd7b54f47b20", "bytes": 22954, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/jasms.3c00242", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10557376", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD043473", "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=PXD043473", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD043473", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE23 partner repository with the data set identifier PXD043473.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE23 partner repository with the data set identifier PXD043473.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Towards Single Bacterium Proteomics", "resolution_checked_at": "2026-11-01T19:09:50Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD043473 not downloaded", "asset:data:geo:PXD043473 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Percolator for control of FDR ≤ 0.05", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Using Percolator for control of FDR ≤ 0.05, 94 PSMs were annotated in the E. coli database, identifying 29 peptides of 19 bacterial proteins across the 96 single/double cells (Tables 1 and 2)."}}], "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 (Percolator for control of FDR ≤ 0.05), 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": ["PXD043473"], "resolved_accessions": ["PXD043473"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE23 partner repository with the data set identifier PXD043473."], "basis": "The paper names PXD043473 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:37713396", "data:geo:PXD043473"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD043473"]}, "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": "2026-11-01T18:53:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7716, "completion_tokens": 904, "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:37713396", "type": "paper", "label": "pmid:37713396"}, {"id": "source:pmid:37713396", "type": "manuscript", "label": "PMID 37713396 full text"}, {"id": "data:geo:PXD043473", "type": "dataset", "label": "GEO PXD043473"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37713396", "type": "paper", "label": "pmid:37713396"}, {"id": "source:pmid:37713396", "type": "manuscript", "label": "PMID 37713396 full text"}, {"id": "data:geo:PXD043473", "type": "dataset", "label": "GEO PXD043473"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37713396", "type": "extraction", "used": ["source:pmid:37713396"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD043473", "type": "accession_resolution", "used": ["data:geo:PXD043473"], "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:37713396", "parent_hash": "sha256:32fdd416f5cdd7ed49eb5ceac8300f2495fbc8864106c3b577b159c1d4beee43", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD043473 licence not read", "asset:data:geo:PXD043473 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}