{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26990150", "kind": "science-record", "revision": 7, "content_hash": "sha256:c4793808a59a0d23189b944d24353c077fa735322f0f97b85bc41ce7e76441c6", "created_at": "2026-11-01T15:40:17Z", "updated_at": "2026-11-01T21:58:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Longitudinal quantification of the gingival crevicular fluid proteome during progression from gingivitis to periodontitis in a canine model.", "doi": "10.1111/jcpe.12548", "pmid": "26990150", "authors": ["Ian J Davis", "Andrew W Jones", "Andrew J Creese", "Ruth Staunton", "Jujhar Atwal", "Iain L C Chapple", "Stephen Harris", "Melissa M Grant"], "journal": "Journal of clinical periodontology", "year": 2016, "abstract": "AIM: Inflammatory periodontal disease is widespread in dogs. This study evaluated site-specific changes in the canine gingival crevicular fluid (GCF) proteome during longitudinal progression from very mild gingivitis to mild periodontitis. Periodontitis diagnosis in dogs requires general anaesthesia with associated risks and costs; our ultimate aim was to develop a periodontitis diagnostic for application in conscious dogs. The objective of this work was to identify potential biomarkers of periodontal disease progression in dogs.\nMATERIAL AND METHODS: Gingival crevicular fluid was sampled from a total of 10 teeth in eight dogs at three different stages of health/disease and samples prepared for quantitative mass spectrometry (data available via ProteomeXchange; identifier PXD003337). A univariate mixed model analysis determined significantly altered proteins between health states and six were evaluated by ELISA.\nRESULTS: Four hundred and six proteins were identified with 84 present in all samples. The prevalence of 40 proteins was found to be significantly changed in periodontitis relative to gingivitis. ELISA measurements confirmed that haptoglobin was significantly increased.\nCONCLUSIONS: This study demonstrates for the first time that proteins detected by mass spectrometry have potential to identify novel biomarkers for canine periodontal disease. Further work is required to validate additional biomarkers for a periodontitis diagnostic.", "claims": [{"id": "claim-method", "statement": "To investigate which proteins changed significantly between disease states, a univariate mixed model analysis of these proteins was employed.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26990150", "locator": "sections[13] \"Proteomic analysis of GCF samples\" paragraph 8", "quote": "To investigate which proteins changed significantly between disease states, a univariate mixed model analysis of these proteins was employed."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al. 2014) via the PRIDE partner repository with the data set identifier PXD003337.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26990150", "locator": "sections[9] \"Mass spectrometry data processing and annotation\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al. 2014) via the PRIDE partner repository with the data set identifier PXD003337."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Using a univariate mixed model on mass-spectrometry data deposited in ProteomeXchange under PXD003337, the study found 40 proteins significantly changed in periodontitis relative to gingivitis, with ELISA confirming a significant increase in haptoglobin.", "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:26990150"], "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:PXD003337"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:regression_modelling_mixed_effects", "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:PXD003337"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:regression_modelling_mixed_effects"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26990150", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/jcpe.12548", "sha256": "sha256:b8316360390671d8192d30c92fd4c7ad1d1117332cd19686ebf363d96bc2e595", "bytes": 46432, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/jcpe.12548", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5089638", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD003337", "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=PXD003337", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD003337", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al. 2014) via the PRIDE partner repository with the data set identifier PXD003337.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al. 2014) via the PRIDE partner repository with the data set identifier PXD003337.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Longitudinal quantification of the GCF proteome during progression from gingivitis to periodontitis in a canine model", "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:26990150:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2fd67d1757d4be968fb5015a41a1ea2140631d0c3d80d734bd18b718fb55b28b", "bytes": 741, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#jcpe12548-tbl-0001", "version": null, "note": "Disease scoring system adapted from Marshall et al. 2014 to show the stages used in this study. G1: very mild gingivitis; G3: moderate gingivitis; PD1 mild periodontitis", "structure": {"pmcid": "PMC5089638", "section_index": 6, "section_title": "Longitudinal trial design and scoring criteria", "row_count": 4, "column_count": 4}, "table": {"label": "Table 1", "caption": "Disease scoring system adapted from Marshall et al. 2014 to show the stages used in this study. G1: very mild gingivitis; G3: moderate gingivitis; PD1 mild periodontitis", "rows": [["Score", "Gingivitis", "Periodontal probing depth (mm)", "Gingival recession (mm)"], ["G1", "Very mild gingivitis (red, swollen but no bleeding on probing)", "≥1 to 2", "0"], ["G3", "Moderate gingivitis (red, swollen and immediate bleeding on probing)", "≥1 to 2", "0"], ["PD1", "Gingivitis must be present (i.e. active periodontitis)", ">2 (>3 on canine teeth) to 4 (6 on canine teeth)", ">0 to 2 (3 on canine teeth)"]], "row_count": 4, "column_count": 4, "numeric_cells": 6, "header_rows": 1, "locator": "section[6]/table-wrap[1]#jcpe12548-tbl-0001"}}, {"id": "asset:table:pmid:26990150:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:15c07100872578d845ba989d7645f17e7970b1248c1c39fbfb39104f6a093499", "bytes": 1224, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[2]#jcpe12548-tbl-0002", "version": null, "note": "A summary of the 30 samples used for proteomic discovery. Table shows the unique dog identification number, tooth sampled, age at start of study, gender and the week when the respective sample was taken. G1 represents very mild gingivitis, G3 moderate gingivitis and PD1 mild periodontitis. Teeth are labelled by quadrant (where the first number represents the FDI notation for that quadrant) and position in the quadrant (second and third numbers 03 incisor, 04 canine, 07 premolar, 08 premolar and 09 molar)", "structure": {"pmcid": "PMC5089638", "section_index": 6, "section_title": "Longitudinal trial design and scoring criteria", "row_count": 12, "column_count": 7}, "table": {"label": "Table 2", "caption": "A summary of the 30 samples used for proteomic discovery. Table shows the unique dog identification number, tooth sampled, age at start of study, gender and the week when the respective sample was taken. G1 represents very mild gingivitis, G3 moderate gingivitis and PD1 mild periodontitis. Teeth are labelled by quadrant (where the first number represents the FDI notation for that quadrant) and position in the quadrant (second and third numbers 03 incisor, 04 canine, 07 premolar, 08 premolar and 09 molar)", "rows": [["Dog ID", "Tooth", "Sex", "Age (years)", "Sampling week"], ["G1 sample", "G3 sample", "PD1 sample"], ["MS05164", "207", "Male", "1.3", "6", "18", "42"], ["MS05159", "409", "Female", "1.3", "0", "24", "54"], ["MS04713", "104", "Male", "4.7", "0", "6", "24"], ["MS04713", "304", "Male", "4.7", "0", "18", "24"], ["MS04707", "408", "Female", "4.8", "0", "18", "24"], ["MS04651", "208", "Female", "5.8", "0", "12", "18"], ["MS05027", "103", "Male", "2.4", "0", "30", "42"], ["MS05029", "209", "Female", "2.5", "0", "6", "12"], ["MS05028", "108", "Male", "2.3", "18", "30", "42"], ["MS05028", "209", "Male", "2.3", "0", "18", "42"]], "row_count": 12, "column_count": 7, "numeric_cells": 60, "header_rows": 2, "locator": "section[6]/table-wrap[2]#jcpe12548-tbl-0002"}}, {"id": "asset:table:pmid:26990150:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a78232950678a95998ab03d3e8aaf9fcd7e61ba1fdf0b908c32d059f089e9e4", "bytes": 7495, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#jcpe12548-tbl-0003", "version": null, "note": "Results of the univariate mixed model analysis comparing each health state, showing the 41 proteins with significant changes at adjusted p < 0.05. For each health state comparison, the fold change and 95% confidence intervals are shown along with adjusted p‐values. G1 represents very mild gingivitis, G3 moderate gingivitis and PD1 mild periodontitis", "structure": {"pmcid": "PMC5089638", "section_index": 13, "section_title": "Proteomic analysis of GCF samples", "row_count": 41, "column_count": 7}, "table": {"label": "Table 3", "caption": "Results of the univariate mixed model analysis comparing each health state, showing the 41 proteins with significant changes at adjusted p < 0.05. For each health state comparison, the fold change and 95% confidence intervals are shown along with adjusted p‐values. G1 represents very mild gingivitis, G3 moderate gingivitis and PD1 mild periodontitis", "rows": [["Accession", "UniProt annotation", "Putative group", "Putative function", "PD1/G1 Fold change (CI) & adjusted p‐value", "PD1/G3 Fold change (CI) & adjusted p‐value", "G3/G1 Fold change (CI) & adjusted p‐value"], ["F1PQM1", "Purine nucleoside phosphorylase", "Biosynthesis", "Nucleotide synth – Adenosine to A, Guanosine to G", "1.59 (1.12, 2.26) 0.0362", "1.55 (1.09, 2.21) 0.0438", "1.03 (0.72, 1.46) 1.0000"], ["P19006", "Haptoglobin", "Blood constituent", "Plasma – binds free haemoglobin, inhibits oxidative activity", "2.48 (1.32, 4.66) 0.0358", "2.42 (1.29, 4.56) 0.0358", "1.02 (0.54, 1.92) 1.0000"], ["E2R0T6", "Heat‐shock 70 kDa protein 8", "House keeping", "Multiple including chaperone protein & regulator of apoptosis", "1.55 (1.11, 2.16) 0.0364", "1.48 (1.06, 2.07) 0.0571", "1.05 (0.75, 1.46) 1.0000"], ["E2RAL0", "Rho GDP dissociation inhibitor (GDI) beta", "House keeping", "Cell signalling, proliferation, cytoskeletal organization and secretion", "1.81 (1.16, 2.83) 0.0358", "1.87 (1.20, 2.92) 0.0358", "0.97 (0.62, 1.51) 1.0000"], ["F1PBZ4", "NAD(P)H:quinone oxidoreductase‐1", "House keeping", "Response to oxidative stress", "1.68 (1.15, 2.45) 0.0358", "1.41 (0.96, 2.05) 0.1732", "1.19 (0.82, 1.74) 0.7978"], ["F1PKW7", "14‐3‐3 protein beta/alpha", "House keeping", "Adapter protein", "2.00 (1.32, 3.02) 0.0142", "1.75 (1.16, 2.63) 0.0358", "1.15 (0.76, 1.73) 0.9630"], ["C0LQL0", "S100 calcium‐binding protein A8", "Immunity & inflammation", "Subunit of Calprotectin – Putative inflammatory regulator", "2.28 (1.30, 3.99) 0.0358", "1.55 (0.89, 2.72) 0.2866", "1.47 (0.84, 2.57) 0.4270"], ["J9P732", "S100 calcium‐binding protein A9", "Immunity & inflammation", "Subunit of Calprotectin – Putative inflammatory regulator", "1.90 (1.17, 3.07) 0.0358", "1.62 (1.00, 2.61) 0.1124", "1.17 (0.73, 1.90) 0.9620"], ["J9PAQ5", "S100 calcium‐binding protein A12", "Immunity & inflammation", "Putative anti‐inflammatory and cell signalling", "2.15 (1.24, 3.71) 0.0358", "1.84 (1.07, 3.18) 0.0733", "1.17 (0.67, 2.02) 1.0000"], ["E2RCI8", "Annexin A6", "Immunity & inflammation", "Structural or anti‐inflammatory", "1.81 (1.18, 2.78) 0.0358", "1.43 (0.93, 2.19) 0.2420", "1.27 (0.83, 1.95) 0.6282"], ["F1P6B7", "Annexin A1", "Immunity & inflammation", "Glucocorticoid anti‐inflammatory", "1.64 (1.22, 2.21) 0.0142", "1.36 (1.01, 1.84) 0.0929", "1.21 (0.89, 1.62) 0.5154"], ["F1PIC7", "Heat‐shock protein 5 (HSPA5)", "Immunity & inflammation", "ER overload response", "1.74 (1.14, 2.66) 0.0387", "1.60 (1.05, 2.45) 0.0738", "1.09 (0.71, 1.66) 1.0000"], ["J9NWJ5", "Thioredoxin", "Immunity & inflammation", "Redox signalling and oxidative stress", "1.64 (1.15, 2.34) 0.0358", "1.56 (1.10, 2.23) 0.0438", "1.05 (0.74, 1.50) 1.0000"], ["J9P0R6", "Myeloperoxidase", "Immunity & inflammation", "Neutrophil respiratory burst", "1.7 (1.16, 2.51) 0.0358", "1.64 (1.11, 2.42) 0.0425", "1.04 (0.70, 1.53) 1.0000"], ["J9P969", "Neuroblast differentiation‐associated protein AHNAK", "Immunity & inflammation", "Interaction with S100 B protein", "1.78 (1.21, 2.62) 0.0329", "1.57 (1.07, 2.31) 0.0622", "1.13 (0.77, 1.67) 0.9657"], ["P81709", "Lysozyme C", "Immunity & inflammation", "Bacterial peptidoglcyan destruction", "1.65 (1.16, 2.35) 0.0358", "1.61 (1.13, 2.29) 0.0358", "1.03 (0.72, 1.47) 1.0000"], ["Q8MJD1", "Neutrophil elastase", "Immunity & inflammation", "Neutrophil/macrophages secreted", "1.65 (1.13, 2.40) 0.0376", "1.59 (1.09, 2.32) 0.0497", "1.04 (0.71, 1.51) 1.0000"], ["E2R2C3", "Glucose‐6‐phosphate isomerase", "Metabolic", "Glycolysis", "1.78 (1.36, 2.32) 0.0005", "1.61 (1.23, 2.11) 0.0114", "1.10 (0.84, 1.44) 0.9393"], ["F1PE09", "6‐Phosphogluconate dehydrogenase", "Metabolic", "Pentose phosphate pathway", "1.63 (1.14, 2.33) 0.0358", "1.54 (1.08, 2.21) 0.0521", "1.05 (0.74, 1.51) 1.0000"], ["F1PE28", "Transketolase", "Metabolic", "Pentose phosphate pathway", "1.86 (1.27, 2.71) 0.0142", "1.63 (1.12, 2.38) 0.0387", "1.14 (0.78, 1.66) 0.9525"], ["H9GW87", "Transaldolase", "Metabolic", "Links the pentose phosphate pathway to glycolysis", "1.67 (1.13, 2.48) 0.0387", "1.70 (1.15, 2.51) 0.0358", "0.99 (0.67, 1.46) 1.0000"], ["E2QZK2", "Uncharacterized protein", "NA", "Uncharacterized putative gelsolin‐like protein", "1.62 (1.10, 2.36) 0.0438", "1.51 (1.03, 2.21) 0.0816", "1.07 (0.73, 1.57) 1.0000"], ["F1PBL1", "Uncharacterized protein", "NA", "Uncharacterized poly(A) RNA‐binding protein", "1.57 (1.09, 2.27) 0.0447", "1.51 (1.05, 2.17) 0.0733", "1.04 (0.73, 1.50) 1.0000"], ["F1PJ65", "Uncharacterized protein", "NA", "Uncharacterized putative GTPase protein", "1.47 (1.06, 2.06) 0.0645", "1.54 (1.10, 2.15) 0.0410", "0.96 (0.69, 1.34) 1.0000"], ["F1PNY2", "Uncharacterized protein", "NA", "Uncharacterized protein – Ig‐like domain", "1.97 (1.30, 2.99) 0.0142", "1.77 (1.17, 2.68) 0.0358", "1.11 (0.73, 1.69) 1.0000"], ["F1PR54", "Uncharacterized protein", "NA", "Uncharacterized transferrin‐like protein", "1.62 (1.10, 2.39) 0.0465", "1.60 (1.08, 2.37) 0.0525", "1.01 (0.68, 1.49) 1.0000"], ["J9NYW7", "Uncharacterized protein", "NA", "Uncharacterized protein – Ig‐like domain", "2.38 (1.33, 4.27) 0.0329", "2.08 (1.16, 3.73) 0.0438", "1.14 (0.64, 2.05) 1.0000"], ["J9P127", "Uncharacterized protein", "NA", "Uncharacterized poly(A) RNA‐binding protein", "1.57 (1.02, 2.41) 0.0927", "1.93 (1.25, 2.97) 0.0301", "0.81 (0.53, 1.25) 0.7693"], ["E2QUU4", "Keratin, type II cytoskeletal 4", "Structural", "Cytoskeletal protein", "1.86 (1.16, 3.01) 0.0387", "1.71 (1.06, 2.76) 0.0733", "1.09 (0.68, 1.76) 1.0000"], ["F1PYU9", "Keratin, type I cytoskeletal 10", "Structural", "Cytoskeletal protein", "1.51 (1.09, 2.10) 0.0438", "1.25 (0.90, 1.73) 0.4321", "1.21 (0.87, 1.68) 0.5839"], ["E2R4B0", "Keratin 78", "Structural", "Cytoskeletal protein", "1.87 (1.28, 2.73) 0.0142", "1.62 (1.11, 2.37) 0.0425", "1.15 (0.79, 1.68) 0.9355"], ["E2R7U2", "Keratin 13", "Structural", "Cytoskeletal protein", "1.69 (1.20, 2.38) 0.0301", "1.45 (1.03, 2.05) 0.0780", "1.16 (0.83, 1.64) 0.8273"], ["E2R8Z5", "Keratin 5", "Structural", "Cytoskeletal protein", "1.57 (1.11, 2.23) 0.0405", "1.55 (1.09, 2.20) 0.0438", "1.01 (0.71, 1.44) 1.0000"], ["E2RB38", "Tropomyosin 1", "Structural", "Actin binding", "1.75 (1.17, 2.63) 0.0358", "1.66 (1.11, 2.49) 0.0445", "1.06 (0.70, 1.58) 1.0000"], ["F1PLS4", "Vimentin", "Structural", "Type III intermediate filament", "1.51 (0.99, 2.31) 0.1312", "1.78 (1.16, 2.73) 0.0358", "0.85 (0.55, 1.29) 0.8977"], ["H9GWE2", "Uridine phosphorylase 1", "Structural", "Interacts with vimentin", "1.62 (1.13, 2.32) 0.0358", "1.62 (1.13, 2.33) 0.0358", "1.00 (0.70, 1.43) 1.0000"], ["E2QWN7", "Lymphocyte cytosolic protein 1", "Structural", "Actin binding", "1.83 (1.18, 2.81) 0.0358", "1.79 (1.16, 2.76) 0.0358", "1.02 (0.66, 1.57) 1.0000"], ["H9GWB1", "Histone H2B", "Structural", "DNA packaging", "1.69 (1.17, 2.44) 0.0358", "1.43 (0.99, 2.06) 0.1262", "1.18 (0.82, 1.70) 0.8201"], ["J9P2B7", "Histone H2A", "Structural", "DNA packaging", "1.54 (1.03, 2.31) 0.0816", "1.67 (1.12, 2.50) 0.0428", "0.92 (0.62, 1.38) 1.0000"], ["L7N0L3", "Histone H4", "Structural", "DNA packaging", "1.42 (0.97, 2.09) 0.1644", "1.65 (1.12, 2.42) 0.0387", "0.86 (0.59, 1.27) 0.9123"]], "row_count": 41, "column_count": 7, "numeric_cells": 149, "header_rows": 1, "locator": "section[13]/table-wrap[1]#jcpe12548-tbl-0003"}}], "gaps": ["asset:data:geo:PXD003337 not downloaded", "asset:data:geo:PXD003337 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "mixed_effects", "label": "Regression modelling", "dsl_operations": [], "missing_operations": ["regression_modelling_mixed_effects"], "expressible": false, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To investigate which proteins changed significantly between disease states, a univariate mixed model analysis of these proteins was employed."}}, {"id": "method-2", "family": "meta_analysis", "specific": "random_effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": ["random_effects_pool"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 0.8, "band": "high", "quote": "random effect"}}, {"id": "method-3", "family": "meta_analysis", "specific": "fixed_effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": [], "missing_operations": ["fixed_effects_pool"], "expressible": false, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 0.8, "band": "high", "quote": "fixed effect"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor", "method.regression_modelling_mixed_effects"]}, "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": false, "required_operations": [], "missing_operations": ["regression_modelling_mixed_effects"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: mixed_effects."}, "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": ["PXD003337"], "resolved_accessions": ["PXD003337"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al. 2014) via the PRIDE partner repository with the data set identifier PXD003337."], "basis": "The paper names PXD003337 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:26990150", "data:geo:PXD003337", "asset:table:pmid:26990150:1", "asset:table:pmid:26990150:2", "asset:table:pmid:26990150:3"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "regression_modelling_mixed_effects", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD003337"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:59Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 95228, "completion_tokens": 2703, "cached_tokens": 1824}}, "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:26990150", "type": "paper", "label": "pmid:26990150"}, {"id": "source:pmid:26990150", "type": "manuscript", "label": "PMID 26990150 full text"}, {"id": "data:geo:PXD003337", "type": "dataset", "label": "GEO PXD003337"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26990150", "type": "paper", "label": "pmid:26990150"}, {"id": "source:pmid:26990150", "type": "manuscript", "label": "PMID 26990150 full text"}, {"id": "data:geo:PXD003337", "type": "dataset", "label": "GEO PXD003337"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26990150", "type": "extraction", "used": ["source:pmid:26990150"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD003337", "type": "accession_resolution", "used": ["data:geo:PXD003337"], "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:26990150", "parent_hash": "sha256:9ea3d62210d0635711122607978e342c820c2f07ef1e1f6d358e8ad295860ef9", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD003337 licence not read", "asset:data:geo:PXD003337 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "method.regression_modelling_mixed_effects", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:regression_modelling_mixed_effects"], "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": ["isease and samples prepared for quantitative mass spectrometry (data available via ProteomeXchange; identif", "for the first time that proteins detected by mass spectrometry have potential to identify novel biomarkers", "suspended in formic acid (20 μl, 0.1 (v/v)). Mass spectrometry data processing and annotation The data were", "ch contained unique peptides were used). The mass spectrometry proteomics data have been deposited to the P"], "order_basis": "paper_text_order:813", "id": "assay:1"}, {"role": "data_generation", "definition_id": "elisa", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ween health states and six were evaluated by ELISA. RESULTS: Four hundred and six proteins were", "ged in periodontitis relative to gingivitis. ELISA measurements confirmed that haptoglobin was", "tory with the data set identifier PXD003337. ELISA methodology In an attempt to corroborate the", "om the same tooth was screened with a single ELISA. Samples from 10 dogs were screened on each"], "order_basis": "paper_text_order:1015", "id": "assay:2"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To investigate which proteins changed significantly between disease states, a univariate mixed model analysis of these proteins was employed."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T02:46:32+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}}}