{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31275533", "kind": "science-record", "revision": 4, "content_hash": "sha256:352091b8d0949765959d8d17ed1044971a15db4aa333b9efacef940e5c9077f1", "created_at": "2026-11-01T15:40:46Z", "updated_at": "2026-11-01T21:22:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Analysis of the Escherichia coli extracellular vesicle proteome identifies markers of purity and culture conditions.", "doi": "10.1080/20013078.2019.1632099", "pmid": "31275533", "authors": ["Jiwon Hong", "Priscila Dauros-Singorenko", "Alana Whitcombe", "Leo Payne", "Cherie Blenkiron", "Anthony Phillips", "Simon Swift"], "journal": "Journal of extracellular vesicles", "year": 2019, "abstract": "Bacteria release nano-sized extracellular vesicles (EVs) into the extracellular milieu. Bacterial EVs contain molecular cargo originating from the parent bacterium and have important roles in bacterial survival and pathogenesis. Using 8-plex iTRAQ approaches, we profiled the EV proteome of two Escherichia coli strains, uropathogenic (UPEC) 536 and probiotic Nissle 1917. For these strains, we compared the proteome of crude input EVs prepared by ultracentrifugation alone with EVs purified by either density gradient centrifugation (DGC) or size exclusion chromatography (SEC). We further compared the proteome of EVs from bacterial cultures that were grown in iron-restricted (R) and iron-supplemented (RF) conditions. Overall, outer membrane components were highly enriched, and bacterial inner membrane components were significantly depleted in both UPEC and Nissle EVs, in keeping with an outer membrane origin. In addition, we found enrichment of ribosome-related Gene Ontology terms in UPEC EVs and proteins involved in glycolytic processes and ligase activity in Nissle EVs. We have identified that three proteins (RbsB of UPEC in R; YoeA of UPEC in RF; BamA of Nissle in R) were consistently enriched in the DGC- and SEC-purified EV samples in comparison to their crude input EV, whereas conversely the 60 kDa chaperonin GroEL was enriched in the crude input EVs for both UPEC and Nissle in R condition. Such proteins may have utility as technical markers for assessing the purity of E. coli EV preparations. Several proteins were changed in their abundance depending on the iron availability in the media. Data are available via ProteomeXchange with identifier PXD011345. In summary, we have undertaken a comprehensive characterization of the protein content of E. coli EVs and found evidence of specific EV cargos for physiological activity and conserved protein cargo that may find utility as markers in the future. Abbreviation: DGC: density gradient centrifugation; DTT: 1,4-dithiothreitol; EV: extracellular vesicles; FDR: false discovery rate; GO: Gene Ontology; R: iron-restricted; RF: iron-supplemented; iTRAQ: isobaric tags for relative and absolute quantitation; OMV: outer membrane vesicle; SWATH-MS: sequential window acquisition of all theoretical mass spectra; SEC: size exclusion chromatography.", "claims": [{"id": "claim-method", "statement": "For the GO analysis, categories with Bonferroni-corrected p value <0.05 were selected.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31275533", "locator": "sections[10] \"Mass spectrometry and protein identification and quantitation\" paragraph 5", "quote": "For the GO analysis, categories with Bonferroni-corrected p value <0.05 were selected."}], "state": "complete"}, {"id": "claim-data-access", "statement": "ProteomeXchange (ID#PXD011345)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31275533", "locator": "sections[30] \"Data deposition\" paragraph 2", "quote": "ProteomeXchange (ID#PXD011345)"}], "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:31275533"], "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:PXD011345"], "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:PXD011345"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31275533", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/20013078.2019.1632099", "sha256": "sha256:4bdb22af5e45b260b1c8bacee71dc5f54155f359895a1ae8a3d7edd02fa840b7", "bytes": 62863, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/20013078.2019.1632099", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6598517", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD011345", "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=PXD011345", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD011345", "version": null, "note": "ProteomeXchange (ID#PXD011345)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "ProteomeXchange (ID#PXD011345)", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Analysis of the Escherichia coli membrane vesicle proteome identifies markers of purity and culture conditions", "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:31275533:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a5da5a4ccfd2f9cf69d4ba2b3baf62389e16126cc0454e6878de2ef487296265", "bytes": 1439, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T0001", "version": null, "note": "Samples used in two 8-plex iTRAQ experiments.", "structure": {"pmcid": "PMC6598517", "section_index": 13, "section_title": "Comparison of overall EV protein profile between UPEC and Nissle", "row_count": 17, "column_count": 6}, "table": {"label": "Table 1.", "caption": "Samples used in two 8-plex iTRAQ experiments.", "rows": [["iTRAQ experiment#", "iTRAQ tag", "E. coli strain", "Growth medium", "EV sample name", "EV preparation description"], ["1", "117", "UPEC", "R", "DGC-crude input", "Crude input before DGC"], ["113", "UPEC", "R", "DGC-purified", "Pooled fractions from DGC purification"], ["119", "UPEC", "R", "SEC-crude input", "Crude input before SEC"], ["115", "UPEC", "R", "SEC-purified", "Pooled fractions from SEC purification"], ["114", "UPEC", "RF", "DGC-crude input", "Crude input before DGC"], ["116", "UPEC", "RF", "DGC-purified", "Pooled fractions from DGC purification"], ["118", "UPEC", "RF", "SEC-crude input", "Crude input before SEC"], ["121", "UPEC", "RF", "SEC-purified", "Pooled fractions from SEC purification"], ["2", "116", "Nissle", "R", "DGC-crude input", "Crude input before DGC"], ["114", "Nissle", "R", "DGC-purified", "Pooled fractions from DGC purification"], ["121", "Nissle", "R", "SEC-crude input", "Crude input before SEC"], ["118", "Nissle", "R", "SEC-purified", "Pooled fractions from SEC purification"], ["117", "Nissle", "RF", "DGC-crude input", "Crude input before DGC"], ["113", "Nissle", "RF", "DGC-purified", "Pooled fractions from DGC purification"], ["119", "Nissle", "RF", "SEC-crude input", "Crude input before SEC"], ["115", "Nissle", "RF", "SEC-purified", "Pooled fractions from SEC purification"]], "row_count": 17, "column_count": 6, "numeric_cells": 18, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T0001"}}, {"id": "asset:table:pmid:31275533:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3873ead682e2269ff4575230ce874c37c93c82b9c0d95363fb28cef9fb25302c", "bytes": 633, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#T0002", "version": null, "note": "Summary of spectra, peptides and proteins identified and quantified in two 8-plex iTRAQ experiments.", "structure": {"pmcid": "PMC6598517", "section_index": 13, "section_title": "Comparison of overall EV protein profile between UPEC and Nissle", "row_count": 3, "column_count": 7}, "table": {"label": "Table 2.", "caption": "Summary of spectra, peptides and proteins identified and quantified in two 8-plex iTRAQ experiments.", "rows": [["Bacteria", "Experiment", "Total spectra", "Identified spectra (99% confidence)", "Identified distinct peptides (99% confidence)", "Identified proteins after grouping (Unused ProtScore >2)", "Quantified proteins (Unused ProtScore >2; with both iTRAQ ratio and p values)"], ["UPEC", "iTRAQ#1", "10,992", "3,387", "2,266", "205", "166"], ["Nissle", "iTRAQ#2", "10,930", "3,067", "1,854", "189", "158"]], "row_count": 3, "column_count": 7, "numeric_cells": 16, "header_rows": 1, "locator": "section[13]/table-wrap[2]#T0002"}}, {"id": "asset:table:pmid:31275533:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:852df3542117253871a46f34650eceae7b3fb919df05e298a6ce40b8c394082c", "bytes": 4474, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T0003", "version": null, "note": "Key findings from iTRAQ#1 experiment on the UPEC EV proteins that compared three EV preparation methods (crude input for DGC or SEC purifications, DGC-purified and SEC-purified) in R (without iron) and RF (with iron) growth conditions. Comparison A) indicates a protein enriched by both DGC and SEC purification methods in iron-restricted condition. Comparison B) indicates proteins depleted by both DGC and SEC purification methods in iron-restricted condition. Comparison C) indicates a protein enriched by both DGC and SEC purification methods in iron-supplemented condition. Comparison D) shows a protein depleted by both DGC and SEC purification methods in iron-supplemented condition. Comparison E) indicates proteins enriched in iron-supplemented condition. Comparison F) indicates proteins enriched in iron-restricted condition. N is the rank of the specified protein relative to all other detected proteins (sorted by Unused ProtScore). The details shown below are based on the winner protein selected by the ProteinPilot software for the specific N.", "structure": {"pmcid": "PMC6598517", "section_index": 14, "section_title": "Effect of purification method on the proteome of UPEC EVs produced under different iron availability conditions", "row_count": 23, "column_count": 6}, "table": {"label": "Table 3.", "caption": "Key findings from iTRAQ#1 experiment on the UPEC EV proteins that compared three EV preparation methods (crude input for DGC or SEC purifications, DGC-purified and SEC-purified) in R (without iron) and RF (with iron) growth conditions. Comparison A) indicates a protein enriched by both DGC and SEC purification methods in iron-restricted condition. Comparison B) indicates proteins depleted by both DGC and SEC purification methods in iron-restricted condition. Comparison C) indicates a protein enriched by both DGC and SEC purification methods in iron-supplemented condition. Comparison D) shows a protein depleted by both DGC and SEC purification methods in iron-supplemented condition. Comparison E) indicates proteins enriched in iron-supplemented condition. Comparison F) indicates proteins enriched in iron-restricted condition. N is the rank of the specified protein relative to all other detected proteins (sorted by Unused ProtScore). The details shown below are based on the winner protein selected by the ProteinPilot software for the specific N.", "rows": [["", "N", "Accession", "Protein Names", "Cellular component", "Biological function"], ["Comparison A)", "R: DGC-crude input < DGC-purified and SEC-crude input < SEC-purified", "", ""], ["", "60", "sp|P02925|RBSB_ECOLI", "Ribose import binding protein RbsB", "Outer membrane-bounded periplasmic space; inner membrane; integral component of membrane", "Monosaccharide transmembrane transporter activity; chemotaxis"], ["Comparison B)", "R: DGC-crude input > DGC-purified and SEC-crude input > SEC-purified", "", ""], ["", "c1", "sp|P09983|HLYAC_ECOLX", "Hemolysin, chromosomal", "Extracellular region; host cell plasma membrane; integral component of membrane", "Calcium ion binding; hemolysis in other organism; pathogenesis"], ["", "a8", "sp|Q0T9P8|CH60_ECOL5", "60 kDa chaperonin (GroEL protein, Protein Cpn60)", "Cytoplasm", "ATP binding; protein refolding"], ["", "12", "sp|P04949|FLIC_ECOLI", "Flagellin", "Extracellular region; bacterial inner membrane; flagellum filament", "Structural molecule activity; bacterial-type flagellum-dependent cell motility; toll-like receptor 5 signaling pathway"], ["", "c22", "sp|Q8XAS6|EFEO_ECO57", "Iron uptake system component EfeO", "Periplasmic space", "Iron-binding and/or electron-transfer component"], ["Comparison C)", "RF: DGC-crude input < DGC-purified and SEC-crude input < SEC-purified", "", ""], ["", "113", "sp|P76356|YOEA_ECOLI", "Putative uncharacterized protein YoeA", "Membrane", "Receptor activity; transport"], ["Comparison D)", "RF: DGC-crude input > DGC-purified and SEC-crude input > SEC-purified", "", ""], ["", "(Not identified)", "", ""], ["Comparison E)", "R < RF in at least 3 samples", "", "", ""], ["", "14", "sp|P09373|PFLB_ECOLI", "Formate acetyltransferase 1 (Pyruvate formate-lyase 1)", "Cytosol", "Formate C-acetyltransferase activity; glucose metabolic process; threonine catabolic process"], ["", "b28", "sp|P02931|OMPF_ECOLI", "Outer membrane protein F (Outer membrane protein 1A, Outer membrane protein B, Outer membrane protein IA, Porin OmpF)", "Cell outer membrane", "Colicin transmembrane transporter activity; drug transmembrane transporter activity; ion transmembrane transporter activity; porin activity"], ["", "39", "sp|P46130|YBHC_ECOLI", "Putative acyl-CoA thioester hydrolase YbhC", "Cell outer membrane", "Aspartyl esterase activity; pectinesterase activity; cell wall modification"], ["", "84", "sp|P37194|SLP_ECOLI", "Outer membrane protein slp", "Cell outer membrane", "Identical protein binding"], ["Comparison F)", "R > RF in 3 samples", "", "", ""], ["", "c1", "sp|P09983|HLYAC_ECOLX", "Hemolysin, chromosomal", "Extracellular region; host cell plasma membrane; integral component of membrane", "Calcium ion binding; hemolysis in other organism; pathogenesis"], ["", "2", "sp|P17315|CIRA_ECOLI", "Colicin I receptor", "Cell outer membrane; integral component of membrane", "Colicin transmembrane transporter activity; receptor activity; siderophore transmembrane transporter activity; iron assimilation"], ["", "21", "sp|P0CK95|ACFD_ECOLI", "Putative lipoprotein AcfD homolog", "Bacterial inner membrane", "(Not known)"], ["", "c,a22", "sp|Q8XAS6|EFEO_ECO57", "Iron uptake system component EfeO", "Periplasmic space", "Iron-binding and/or electron-transfer"], ["", "a27", "sp|Q8X9X2|YNCE_ECO57", "Uncharacterized protein YncE", "(Not known, predicted periplasmic protein)", "(Not known)"]], "row_count": 23, "column_count": 6, "numeric_cells": 33, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T0003"}}, {"id": "asset:table:pmid:31275533:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b17a0d06b02d7eae3d7e4d2e0fd3aad709f3b01c638a6fb415c5f83a712ed116", "bytes": 5410, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T0004", "version": null, "note": "Key findings from iTRAQ#2 experiment on the Nissle EV proteins that compared 3 EV preparation methods (crude input for DGC or SEC purifications, DGC-purified and SEC-purified) in R (without iron) and RF (with iron) growth conditions. Comparison A) indicates a protein enriched by both DGC and SEC purification methods in iron-restricted condition. Comparison B) indicates proteins depleted by both DGC and SEC purification methods in iron-restricted condition. Comparison C) indicates a protein enriched by both DGC and SEC purification methods in iron-supplemented condition. Comparison D) shows a protein depleted by both DGC and SEC purification methods in iron-supplemented condition. Comparison E) indicates proteins enriched in iron-supplemented condition. Comparison F) indicates proteins enriched in iron-restricted condition. N is the rank of the specified protein relative to all other detected proteins (sorted by Unused ProtScore). The details shown below are based on the winner protein selected by the ProteinPilot software for the specific N.", "structure": {"pmcid": "PMC6598517", "section_index": 15, "section_title": "Effect of purification method on the proteome of Nissle EVs produced under different iron availability conditions", "row_count": 30, "column_count": 6}, "table": {"label": "Table 4.", "caption": "Key findings from iTRAQ#2 experiment on the Nissle EV proteins that compared 3 EV preparation methods (crude input for DGC or SEC purifications, DGC-purified and SEC-purified) in R (without iron) and RF (with iron) growth conditions. Comparison A) indicates a protein enriched by both DGC and SEC purification methods in iron-restricted condition. Comparison B) indicates proteins depleted by both DGC and SEC purification methods in iron-restricted condition. Comparison C) indicates a protein enriched by both DGC and SEC purification methods in iron-supplemented condition. Comparison D) shows a protein depleted by both DGC and SEC purification methods in iron-supplemented condition. Comparison E) indicates proteins enriched in iron-supplemented condition. Comparison F) indicates proteins enriched in iron-restricted condition. N is the rank of the specified protein relative to all other detected proteins (sorted by Unused ProtScore). The details shown below are based on the winner protein selected by the ProteinPilot software for the specific N.", "rows": [["", "N", "Accession", "Protein Names", "Cellular component", "Biological function"], ["Comparison A)", "R: DGC-crude input < DGC-purified and SEC-crude input < SEC-purified", "", ""], ["", "23", "sp|Q1RG12|BAMA_ECOUT", "Outer membrane protein assembly factor BamA", "Cell outer membrane; integral component of membrane", "Membrane assembly"], ["Comparison B)", "R: DGC-crude input > DGC-purified and SEC-crude input > SEC-purified", "", ""], ["", "a8", "sp|Q1R3B6|CH60_ECOUT", "60 kDa chaperonin (GroEL protein, Protein Cpn60)", "Cytoplasm", "ATP binding; protein refolding"], ["", "67", "sp|Q8FHC7|MAND_ECOL6", "D-galactonate dehydratase family member RspA", "(Not known)", "Magnesium ion binding; mannonate dehydratase activity; carbohydrate catabolic process; cellular amino acid catabolic process"], ["Comparison C)", "RF: DGC-crude input < DGC-purified and SEC-crude input < SEC-purified", "", ""], ["", "(Not identified)", "", ""], ["Comparison D)", "RF: DGC-crude input > DGC-purified and SEC-crude input > SEC-purified", "", ""], ["", "(Not identified)", "", ""], ["Comparison E)", "R < RF in at least 3 samples", "", "", ""], ["", "3", "sp|Q8FDA1|LPOA_ECOL6", "Penicillin-binding protein activator LpoA", "Cell outer membrane; periplasmic space", "Hydrolase activity, hydrolyzing O-glycosyl compounds; peptidoglycan biosynthetic process; regulation of cell shape"], ["", "b 5", "sp|Q8CVW1|OMPC_ECOL6", "Outer membrane protein C (Outer membrane protein 1B, Porin OmpC)", "Cell outer membrane", "Pore complex; porin activity; ion transport"], ["", "11", "sp|Q8FDW4|SAT_ECOL6", "Serine protease sat autotransporter", "Cell outer membrane; cell surface; extracellular region; integral component of membrane; periplasmic space", "Serine-type endopeptidase activity; pathogenesis"], ["", "14", "sp|P62606|FIM1C_ECOL6", "Type-1 fimbrial protein, C chain (Type-1C pilin)", "Pilus", "Cell adhesion"], ["", "b 21", "sp|P10100|RLPA_ECOLI", "Endolytic peptidoglycan transglycosylase RlpA (Rare lipoprotein A)", "Cell outer membrane; bacterial inner membrane", "Lyase activity; peptidoglycan binding; cell wall organization"], ["", "42", "sp|Q8FJM0|DPS_ECOL6", "DNA protection during starvation protein", "Cytoplasm; nucleoid", "DNA binding; ferric iron binding; oxidoreductase activity, oxidizing metal ions; cellular iron ion homeostasis; chromosome condensation; response to stress"], ["", "b 51", "sp|P21420|NMPC_ECOLI", "Putative outer membrane porin protein NmpC", "Cell outer membrane", "Pore complex; porin activity; ion transport; transport"], ["", "58", "sp|P29744|FLGL_ECOLI", "Flagellar hook-associated protein 3", "Bacterial-type flagellum hook; extracellular region", "Structural molecule activity; bacterial-type flagellum-dependent cell motility"], ["", "76", "sp|P0A913|PAL_ECO57", "Peptidoglycan-associated lipoprotein", "Cell outer membrane; integral component of membrane", "Thought to play a role in bacterial envelope integrity"], ["", "90", "sp|Q8CVU7|FADL_ECOL6", "Long-chain fatty acid transport protein (Outer membrane FadL protein)", "Cell outer membrane; integral component of membrane", "Lipid transport"], ["Comparison F)", "R > RF in at least 3 samples", "", "", ""], ["", "2", "sp|Q1R5Y2|EFTU1_ECOUT", "Elongation factor Tu 1", "Cytoplasm", "GTP binding; GTPase activity; translation elongation factor activity"], ["", "b4", "sp|P23847|DPPA_ECOLI", "Periplasmic dipeptide transport protein", "Periplasmic space", "Chaperone-mediated protein folding; chemotaxis; dipeptide transport; protein transport"], ["", "a,b 10", "sp|Q8X9X2|YNCE_ECO57", "Uncharacterized protein YncE", "(Not known, predicted periplasmic protein)", "(Not known)"], ["", "a 12", "sp|Q8FJ35|EFEO_ECOL6", "Iron uptake system component EfeO", "Periplasmic space", "Iron-binding and/or electron-transfer"], ["", "38", "sp|P65765|FKBA_ECO57", "FKBP-type peptidyl-prolyl cis-trans isomerase FkpA (Rotamase)", "Periplasmic space", "Peptidyl-prolyl cis-trans isomerase activity; protein folding"], ["", "57", "sp|P77717|YBAY_ECOLI", "Uncharacterized lipoprotein YbaY", "Bacterial inner membrane", "(Not known)"], ["", "63", "sp|P0A864|TPX_ECO57", "Thiol peroxidase (Scavengase P20)", "Periplasmic space", "Thioredoxin peroxidase activity; cell redox homeostasis"], ["", "70", "sp|P0A906|SLYB_ECO57", "Outer membrane lipoprotein SlyB", "Cell outer membrane", "(Not known)"]], "row_count": 30, "column_count": 6, "numeric_cells": 41, "header_rows": 1, "locator": "section[15]/table-wrap[1]#T0004"}}], "gaps": ["asset:data:geo:PXD011345 not downloaded", "asset:data:geo:PXD011345 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Bonferroni correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For the GO analysis, categories with Bonferroni-corrected p value <0.05 were selected."}}], "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 (Bonferroni correction), 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": ["PXD011345"], "resolved_accessions": ["PXD011345"], "statements": ["ProteomeXchange (ID#PXD011345)"], "basis": "The paper names PXD011345 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:31275533", "data:geo:PXD011345", "asset:table:pmid:31275533:1", "asset:table:pmid:31275533:2", "asset:table:pmid:31275533:3", "asset:table:pmid:31275533:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD011345"]}, "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": "2026-10-31T18:15:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 46989, "completion_tokens": 1159, "cached_tokens": 792}}, "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:31275533", "type": "paper", "label": "pmid:31275533"}, {"id": "source:pmid:31275533", "type": "manuscript", "label": "PMID 31275533 full text"}, {"id": "data:geo:PXD011345", "type": "dataset", "label": "GEO PXD011345"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31275533", "type": "paper", "label": "pmid:31275533"}, {"id": "source:pmid:31275533", "type": "manuscript", "label": "PMID 31275533 full text"}, {"id": "data:geo:PXD011345", "type": "dataset", "label": "GEO PXD011345"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31275533", "type": "extraction", "used": ["source:pmid:31275533"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD011345", "type": "accession_resolution", "used": ["data:geo:PXD011345"], "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:31275533", "parent_hash": "sha256:72e6e52e74850df9d9ce834a04ae0c3a45f4481ca605f526b23dff90cfa1d700", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD011345 licence not read", "asset:data:geo:PXD011345 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:42:34+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}