{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26746581", "kind": "science-record", "revision": 6, "content_hash": "sha256:f0fdf44563bdd992ae66cac8c447e9c7b0e35a4e0b34624946ac760a82ffee8a", "created_at": "2026-11-01T15:40:15Z", "updated_at": "2026-11-01T21:20:22Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Quantitative proteomic analysis of Shigella flexneri and Shigella sonnei Generalized Modules for Membrane Antigens (GMMA) reveals highly pure preparations.", "doi": "10.1016/j.ijmm.2015.12.003", "pmid": "26746581", "authors": ["Luana Maggiore", "Lu Yu", "Ulrich Omasits", "Omar Rossi", "Gordon Dougan", "Nicholas R Thomson", "Allan Saul", "Jyoti S Choudhary", "Christiane Gerke"], "journal": "International journal of medical microbiology : IJMM", "year": 2016, "abstract": "Outer membrane blebs are naturally shed by Gram-negative bacteria and are candidates of interest for vaccines development. Genetic modification of bacteria to induce hyperblebbing greatly increases the yield of blebs, called Generalized Modules for Membrane Antigens (GMMA). The composition of the GMMA from hyperblebbing mutants of Shigella flexneri 2a and Shigella sonnei were quantitatively analyzed using high-sensitivity mass spectrometry with the label-free iBAQ procedure and compared to the composition of the solubilized cells of the GMMA-producing strains. There were 2306 proteins identified, 659 in GMMA and 2239 in bacteria, of which 290 (GMMA) and 1696 (bacteria) were common to both S. flexneri 2a and S. sonnei. Predicted outer membrane and periplasmic proteins constituted 95.7% and 98.7% of the protein mass of S. flexneri 2a and S. sonnei GMMA, respectively. Among the remaining proteins, small quantities of ribosomal proteins collectively accounted for more than half of the predicted cytoplasmic protein impurities in the GMMA. In GMMA, the outer membrane and periplasmic proteins were enriched 13.3-fold (S. flexneri 2a) and 8.3-fold (S. sonnei) compared to their abundance in the parent bacteria. Both periplasmic and outer membrane proteins were enriched similarly, suggesting that GMMA have a similar surface to volume ratio as the surface to periplasmic volume ratio in these mutant bacteria. Results in S. flexneri 2a and S. sonnei showed high reproducibility indicating a robust GMMA-producing process and the low contamination by cytoplasmic proteins support the use of GMMA for vaccines. Data are available via ProteomeXchange with identifier PXD002517.", "claims": [{"id": "claim-method", "statement": "There was no statistically significant difference in the enrichment of membrane proteins compared to periplasmic proteins in either the Sf2a or Ss preparations (p = 0.94 and 0.85 by t test, for Sf2a and Ss, respectively).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26746581", "locator": "sections[12] \"Composition of predicted outer membrane and periplasmic proteins in GMMA\" paragraph 9", "quote": "There was no statistically significant difference in the enrichment of membrane proteins compared to periplasmic proteins in either the Sf2a or Ss preparations (p = 0.94 and 0.85 by t test, for Sf2a and Ss, respectively)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaino et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002517.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26746581", "locator": "sections[10] \"Bioinformatics\" paragraph 4", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaino et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002517."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper used label-free iBAQ quantitative proteomics to compare GMMA with solubilized bacterial cells, and its source data are available through ProteomeXchange under identifier PXD002517.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26746581", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "The composition of the GMMA from hyperblebbing mutants of Shigella flexneri 2a and Shigella sonnei were quantitatively analyzed using high-sensitivity mass spectrometry with the label-free iBAQ procedure and compared to the composition of the solubilized cells of the GMMA-producing strains."}, {"asset": "source:pmid:26746581", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Data are available via ProteomeXchange with identifier PXD002517."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper used label-free iBAQ quantitative proteomics to compare GMMA with solubilized bacterial cells, and its source data are available through ProteomeXchange under identifier PXD002517.", "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:26746581"], "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:PXD002517"], "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:PXD002517"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26746581", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.ijmm.2015.12.003", "sha256": "sha256:7ed4a5c24747b09aee20b24fa92c200eb76678561165f842979f0d3a5fd1d594", "bytes": 57108, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.ijmm.2015.12.003", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4820968", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002517", "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=PXD002517", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002517", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaino et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002517.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaino et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002517.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative proteomic analysis of Shigella flexneri and Shigella sonnei Generalized Modules for Membrane Antigens (GMMA) reveals highly pure preparations.", "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:26746581:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:52495dce3527cbd9a2621a3479c4f067d158a91b732cbae0444a6e8ca4a5a039", "bytes": 1376, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tbl0005", "version": null, "note": "Predicted location of proteins found in Sf2a and Ss GMMA and Lysates.", "structure": {"pmcid": "PMC4820968", "section_index": 12, "section_title": "Composition of predicted outer membrane and periplasmic proteins in GMMA", "row_count": 19, "column_count": 9}, "table": {"label": "Table 1", "caption": "Predicted location of proteins found in Sf2a and Ss GMMA and Lysates.", "rows": [["Predicted location", "GMMA", "Lysates"], ["", "% mass", "Number of proteins", "% mass", "Number of proteins"], ["", "Sf2a", "Ss", "Sf2a", "Ss", "Sf2a", "Ss", "Sf2a", "Ss"], ["Outer membrane"], ["Outer membrane integral proteins (OM)", "47.85", "48.12", "33", "39", "3.37", "5.04", "22", "33"], ["Outer membrane lipoprotein (OM lipo)", "28.00", "32.34", "66", "75", "2.72", "4.05", "52", "59"], ["Periplasmic", "19.86", "18.25", "105", "133", "2.2", "2.28", "90", "127"], ["Total predicted outer membrane/periplasmic", "95.70", "98.71", "204", "247", "8.29", "11.37", "164", "219"], ["Cytoplasmic"], ["Ribosomal", "0.86", "0.28", "43", "35", "15.03", "15.08", "53", "53"], ["Other cytoplasmic", "0.63", "0.20", "177", "93", "65.08", "61.30", "1137", "1198"], ["Cytoplasmic membrane"], ["Tail-specific protease", "1.15", "0.21", "1", "1", "0.03", "0.02", "1", "1"], ["Other cytoplasmic membrane", "0.24", "0.13", "53", "29", "7.00", "6.44", "291", "346"], ["Extracellular", "0.00", "–", "1", "0", "0.02", "0.01", "5", "4"], ["Unknown"], ["YajG", "1.28", "0.34", "1", "1", "0.04", "0.05", "1", "1"], ["Other unknown", "0.13", "0.13", "35", "28", "4.51", "5.72", "216", "245"], ["Total predicted non-OM/periplasmic", "4.30", "1.29", "311", "187", "91.71", "88.63", "1704", "1848"]], "row_count": 19, "column_count": 9, "numeric_cells": 95, "header_rows": 3, "locator": "section[12]/table-wrap[1]#tbl0005"}}, {"id": "asset:table:pmid:26746581:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7895e552d6c23c3a597d9b9f879832c7a20f6bd18ca63c7f48d398c9ca9dffc7", "bytes": 4032, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#tbl0010", "version": null, "note": "40 most abundant proteins found in GMMA (by average % mass in Sf2a and Ss GMMA).", "structure": {"pmcid": "PMC4820968", "section_index": 12, "section_title": "Composition of predicted outer membrane and periplasmic proteins in GMMA", "row_count": 41, "column_count": 7}, "table": {"label": "Table 2", "caption": "40 most abundant proteins found in GMMA (by average % mass in Sf2a and Ss GMMA).", "rows": [["Gene name", "Location", "Protein name", "Uniprot name", "Average % mass in GMMA", "% mass in Sf2a GMMA", "% mass in Ss GMMA"], ["SF2457T_0298", "OM", "Outer membrane protein C", "E3XX60_SHIFL", "13.411", "14.619", "12.203"], ["SF2457T_0799", "OM", "Outer membrane protein A", "E3XYK2_SHIFL", "11.943", "10.615", "13.271"], ["SS53G_3941", "OM", "Outer membrane protein X", "E9UMG3_SHISO", "8.506", "11.829", "5.183"], ["SS53G_0415", "OM lipo", "Repeated sequence found in lipoLPP family prot.", "E7JU63_SHISO", "7.261", "9.955", "4.566"], ["SF2457T_4977", "PP", "Protease Do (HtrA)", "E3YA49_SHIFL", "4.604", "7.366", "1.842"], ["SS53G_2965", "OM lipo", "Entericidin B", "E7K193_SHISO", "4.257", "0.101", "8.413"], ["SS53G_0370", "OM lipo", "Outer membrane lipoprotein pcp", "E7JU20_SHISO", "3.528", "4.570", "2.485"], ["tolB", "PP", "Protein tolB", "TOLB_SHISS", "2.859", "2.637", "3.080"], ["SS53G_0760", "OM", "Outer membrane porin protein LC", "E7JV54_SHISO", "2.419", "0.479", "4.358"], ["SF2457T_3748", "OM", "Outer membrane protein", "E3Y6Q5_SHIFL", "2.145", "2.654", "1.636"], ["yaeT", "OM", "Outer membrane protein assembly factor yaeT", "YAET_SHISS", "1.646", "2.258", "1.035"], ["lpoA", "OM lipo", "Penicillin-binding protein activator LpoA", "LPOA_SHIF8", "1.595", "1.679", "1.510"], ["SF2457T_0832", "OM", "Outer membrane protein F", "E3XYN5_SHIFL", "1.471", "1.036", "1.905"], ["SGF_01778", "OM lipo", "Glycoprotein-polysaccharide metabolism", "E7TB57_SHIFL", "1.465", "0.280", "2.650"], ["SS53G_1454", "OM lipo", "Osmotically inducible lipoprotein B", "E7JX36_SHISO", "1.256", "1.692", "0.820"], ["lamB", "OM", "Maltoporin", "LAMB_SHISS", "1.156", "0", "2.312"], ["slp", "OM lipo", "OM protein induced after carbon starvation", "Q3YWI0_SHISS", "1.151", "0.014", "2.288"], ["SGF_00427", "OM", "Aerobactin siderophore receptor IutA", "E7T7F9_SHIFL", "0.977", "1.486", "0.468"], ["SF2457T_4357", "PP", "Peptidyl-prolyl cis-trans isomerase", "E3Y8E7_SHIFL", "0.932", "0.968", "0.896"], ["pal", "OM lipo", "Peptidoglycan-associated lipoprotein", "E7K8X6_SHISO", "0.873", "0.930", "0.816"], ["SS53G_1748", "PP", "Putative uncharacterized protein", "E7JXX8_SHISO", "0.869", "1.080", "0.658"], ["SS53G_0544", "OM lipo", "SmpA/OmlA family protein", "E7JUJ2_SHISO", "0.829", "0.170", "1.489"], ["yajG", "Unknown", "Putative polymerase/proteinase", "Q3Z4W9_SHISS", "0.808", "1.276", "0.340"], ["SF2457T_2094", "PP", "Periplasmic oligopeptide-binding protein", "E3Y260_SHIFL", "0.769", "1.065", "0.473"], ["SF2457T_2279", "CytoM", "Tail-specific protease", "E3Y2N8_SHIFL", "0.679", "1.152", "0.206"], ["surA", "PP", "Chaperone surA", "SURA_SHISS", "0.623", "0.787", "0.458"], ["SF2457T_0435", "OM", "Long-chain fatty acid outer membrane transporter", "E3XXF4_SHIFL", "0.622", "0.062", "1.181"], ["SS53G_1935", "OM lipo", "SmpA/OmlA family protein", "E7JYG3_SHISO", "0.611", "0.858", "0.364"], ["degQ", "PP", "Serine endoprotease", "Q3YX14_SHISS", "0.592", "0.053", "1.132"], ["SS53G_3947", "PP", "Putative uncharacterized protein", "E9UMG9_SHISO", "0.540", "0.816", "0.265"], ["SF2457T_3200", "OM lipo", "Pectinesterase B", "E3Y553_SHIFL", "0.532", "0.651", "0.414"], ["SF2457T_3582", "OM lipo", "Peptidase family M48 family protein", "E3Y5Y2_SHIFL", "0.530", "0.555", "0.504"], ["livJ", "PP", "High-affinity amino acid transport system", "Q3YW68_SHISS", "0.521", "0.264", "0.777"], ["yeaF", "OM", "Putative uncharacterized protein yeaF", "Q3Z2C1_SHISS", "0.507", "0.479", "0.535"], ["SS53G_4569", "OM lipo", "Putative phospholipid-binding domain protein", "E7K576_SHISO", "0.468", "0.535", "0.401"], ["SF2457T_4988", "OM", "Ferrichrome-iron receptor", "E3YA60_SHIFL", "0.435", "0.816", "0.053"], ["SF2457T_4129", "PP", "PP dipeptide transport protein", "E3Y7S0_SHIFL", "0.434", "0.401", "0.467"], ["ybjP", "OM lipo", "Putative enzyme", "Q0T8Q3_SHIF8", "0.414", "0.429", "0.400"], ["SF2457T_3629", "OM", "Serine protease eatA", "E3Y628_SHIFL", "0.410", "0.115", "0.705"], ["yfgL", "OM-Lipo", "Outer membrane assembly lipoprotein YfgL", "E7JUN3_SHISO", "0.409", "0.571", "0.246"]], "row_count": 41, "column_count": 7, "numeric_cells": 163, "header_rows": 1, "locator": "section[12]/table-wrap[2]#tbl0010"}}, {"id": "asset:table:pmid:26746581:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6b55adce4c45496c243278380b9ba8c4f96ab09ac8fdee5b5e1bee7a705c2d7d", "bytes": 3633, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tbl0015", "version": null, "note": "Proteins preferentially found in Ss GMMA.", "structure": {"pmcid": "PMC4820968", "section_index": 13, "section_title": "Comparative analysis of Sf2a and Ss GMMA and lysates", "row_count": 38, "column_count": 7}, "table": {"label": "Table 3", "caption": "Proteins preferentially found in Ss GMMA.", "rows": [["Gene name", "Location", "Protein name", "Uniprot name", "% mass in Ss GMMA", "Ratio", "Theoretically present in Sf2a*"], ["Predicted outer membrane and periplasmic localized proteins with at least 0.01% mass in Ss GMMA not found in Sf2a GMMA"], ["SS53G_2461", "PP", "Maltose-binding periplasmic protein", "E7JZV4_SHISO", "0.799", "−**", "+"], ["SS53G_0290", "OM lipo", "TonB-dependent Receptor Plug domain protein", "E7JTU0_SHISO", "0.732", "−", "−"], ["SS53G_3463", "OM", "Iron(III) dicitrate transport protein fecA", "E7K2N5_SHISO", "0.589", "−", "−"], ["cirA", "OM", "OM receptor for iron-regulated colicin I receptor", "Q3Z051_SHISS", "0.430", "−", "−"], ["exc", "OM lipo", "Entry exclusion protein 2", "A4SH43_SHISS", "0.423", "−", "−"], ["SS53G_3761", "OM", "Ferrichrome-iron receptor", "E7K3K6_SHISO", "0.396", "−", "−"], ["SS53G_2464", "PP", "Maltose operon periplasmic protein", "E7JZV7_SHISO", "0.337", "−", "+"], ["ycdO", "PP", "UPF0409 protein ycdO", "YCDO_SHISS", "0.276", "−", "+"], ["SS53G_0127", "OM", "Putative tonB-dependent receptor yncD", "E7JTC8_SHISO", "0.159", "−", "−"], ["hdeA", "PP", "Putative uncharacterized protein hdeA", "Q3YWI4_SHISS", "0.140", "−", "+"], ["mdoG", "PP", "Glucans biosynthesis protein G", "OPGG_SHISS", "0.106", "−", "+"], ["SS53G_2146", "PP", "Putative uncharacterized protein", "E7JZ10_SHISO", "0.064", "−", "−"], ["SS53G_0128", "PP", "PQQ enzyme repeat family protein", "E7JTC9_SHISO", "0.058", "−", "−"], ["SS53G_5268", "OM", "TonB-dependent Receptor Plug domain protein", "E7K7A5_SHISO", "0.053", "−", "+"], ["SS53G_2796", "OM lipo", "Inner membrane lipoprotein yiaD", "E7K0S5_SHISO", "0.051", "−", "+"], ["SSON_1625", "PP", "Putative sulfatase", "Q3Z1P2_SHISS", "0.047", "−", "−"], ["SS53G_0368", "OM lipo", "Putative uncharacterized protein", "E7JU18_SHISO", "0.036", "−", "−"], ["SS53G_4157", "PP", "Putative uncharacterized protein", "E7K461_SHISO", "0.032", "−", "+"], ["yehZ", "PP", "Putative transport system permease protein", "Q3Z073_SHISS", "0.026", "−", "+"], ["SS53G_4973", "PP", "Acid-resistance protein", "E7K6I7_SHISO", "0.025", "−", "+"], ["SS53G_0106", "PP", "Bacterial extracellular solute-binding family protein", "E7JTA7_SHISO", "0.024", "−", "−"], ["SSON_1637", "PP", "Putative hemin-binding lipoprotein", "Q3Z1N0_SHISS", "0.022", "−", "−"], ["tauA", "PP", "Taurine transport system periplasmic protein", "Q3Z543_SHISS", "0.019", "−", "−"], ["SS53G_3203", "OM lipo", "Putative uncharacterized protein", "E7K1X5_SHISO", "0.015", "−", "+"], [""], ["Predicted outer membrane and periplasmic localized proteins highly enriched in Ss GMMA compared to Sf2a GMMA***"], ["lamB", "OM", "Maltoporin", "LAMB_SHISS", "2.312", "6017", ""], ["slp", "OM lipo", "Outer membrane protein induced after carbon starvation", "Q3YWI0_SHISS", "2.288", "163", ""], ["glpQ", "PP", "Glycerophosphodiester phosphodiesterase, periplasmic", "Q3YZW7_SHISS", "0.609", "193", ""], ["SS53G_4155", "OM lipo", "Putative polysaccharide export protein gfcE", "E7K459_SHISO", "0.313", "170", ""], ["SS53G_3546", "PP", "Putative phospholipid-binding domain protein", "E7K2W6_SHISO", "0.249", "321", ""], ["SS53G_4156", "OM", "Putative uncharacterized protein", "E7K460_SHISO", "0.216", "239", ""], ["SS53G_5756", "PP", "Glutamate/aspartate periplasmic-binding protein", "E7K8P1_SHISO", "0.105", "230", ""], ["ycdB", "PP", "Peroxidase ycdB (Deferrochelatase/peroxidase EfeB)", "YCDB_SHISS", "0.091", "246", ""], ["ymcC", "OM lipo", "Putative regulator", "Q3Z3D5_SHISS", "0.052", "376", ""], ["blc", "OM lipo", "Outer membrane lipoprotein", "Q3YUI9_SHISS", "0.051", "329", ""]], "row_count": 38, "column_count": 7, "numeric_cells": 77, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tbl0015"}}, {"id": "asset:table:pmid:26746581:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0b6e1f4bde4a1308209d55f86e7328021af1ec2dbedabff52a2f11c3dc36634b", "bytes": 718, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#tbl0020", "version": null, "note": "Proteins preferentially found in Sf2a GMMA.", "structure": {"pmcid": "PMC4820968", "section_index": 13, "section_title": "Comparative analysis of Sf2a and Ss GMMA and lysates", "row_count": 6, "column_count": 6}, "table": {"label": "Table 4", "caption": "Proteins preferentially found in Sf2a GMMA.", "rows": [["Gene name", "Location", "Protein name", "Uniprot name", "% mass in Sf2a GMMA", "Theoretically present in Ss*"], ["Predicted outer membrane and periplasmic localized proteins with at least 0.01% mass in Sf2a GMMA not found in Ss GMMA"], ["SF2457T_1008", "OM lipo", "Uncharacterized lipoprotein ydcL", "E3XZ64_SHIFL", "0.035", "−"], ["SF2457T_0155", "OM lipo", "Lipoprotein", "E3XWR9_SHIFL", "0.035", "−"], ["sitA", "PP", "Iron transport protein", "Q3Z1C5_SHISS", "0.024", "+"], ["SF2457T_3658", "OM", "Antigen 43", "E3Y656_SHIFL", "0.014", "−"]], "row_count": 6, "column_count": 6, "numeric_cells": 11, "header_rows": 1, "locator": "section[13]/table-wrap[2]#tbl0020"}}], "gaps": ["asset:data:geo:PXD002517 not downloaded", "asset:data:geo:PXD002517 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-2", "family": null, "specific": null, "label": "t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "There was no statistically significant difference in the enrichment of membrane proteins compared to periplasmic proteins in either the Sf2a or Ss preparations (p = 0.94 and 0.85 by t test, for Sf2a and Ss, respectively)."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["PXD002517"], "resolved_accessions": ["PXD002517"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaino et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002517."], "basis": "The paper names PXD002517 in ProteomeXchange Consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:26746581", "data:geo:PXD002517", "asset:table:pmid:26746581:1", "asset:table:pmid:26746581:2", "asset:table:pmid:26746581:3", "asset:table:pmid:26746581:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002517"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:01Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 125462, "completion_tokens": 4282, "cached_tokens": 16664}}, "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:26746581", "type": "paper", "label": "pmid:26746581"}, {"id": "source:pmid:26746581", "type": "manuscript", "label": "PMID 26746581 full text"}, {"id": "data:geo:PXD002517", "type": "dataset", "label": "GEO PXD002517"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26746581", "type": "paper", "label": "pmid:26746581"}, {"id": "source:pmid:26746581", "type": "manuscript", "label": "PMID 26746581 full text"}, {"id": "data:geo:PXD002517", "type": "dataset", "label": "GEO PXD002517"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26746581", "type": "extraction", "used": ["source:pmid:26746581"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002517", "type": "accession_resolution", "used": ["data:geo:PXD002517"], "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:26746581", "parent_hash": "sha256:e23d04f6d41a3525266dc4fee9fa1e62375c572bea80dae71eb658126813d404", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD002517 licence not read", "asset:data:geo:PXD002517 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["Quantitative proteomic analysis of Shigella flexneri and Shigella s", "antitatively analyzed using high-sensitivity mass spectrometry with the label-free iBAQ procedure and compa"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Pearson correlation"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T01:43:43+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}}}