{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26793233", "kind": "science-record", "revision": 4, "content_hash": "sha256:7e6d5bd77bdfd82e6b9bde77a60a047412f2c1090a629253b648a00f2257e0d2", "created_at": "2026-11-01T15:40:15Z", "updated_at": "2026-11-01T21:20:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Milk Bottom-Up Proteomics: Method Optimization.", "doi": "10.3389/fgene.2015.00360", "pmid": "26793233", "authors": ["Delphine Vincent", "Vilnis Ezernieks", "Aaron Elkins", "Nga Nguyen", "Peter J Moate", "Benjamin G Cocks", "Simone Rochfort"], "journal": "Frontiers in genetics", "year": 2015, "abstract": "Milk is a complex fluid whose proteome displays a diverse set of proteins of high abundance such as caseins and medium to low abundance whey proteins such as ß-lactoglobulin, lactoferrin, immunoglobulins, glycoproteins, peptide hormones, and enzymes. A sample preparation method that enables high reproducibility and throughput is key in reliably identifying proteins present or proteins responding to conditions such as a diet, health or genetics. Using skim milk samples from Jersey and Holstein-Friesian cows, we compared three extraction procedures which have not previously been applied to samples of cows' milk. Method A (urea) involved a simple dilution of the milk in a urea-based buffer, method B (TCA/acetone) involved a trichloroacetic acid (TCA)/acetone precipitation, and method C (methanol/chloroform) involved a tri-phasic partition method in chloroform/methanol solution. Protein assays, SDS-PAGE profiling, and trypsin digestion followed by nanoHPLC-electrospray ionization-tandem mass spectrometry (nLC-ESI-MS/MS) analyses were performed to assess their efficiency. Replicates were used at each analytical step (extraction, digestion, injection) to assess reproducibility. Mass spectrometry (MS) data are available via ProteomeXchange with identifier PXD002529. Overall 186 unique accessions, major and minor proteins, were identified with a combination of methods. Method C (methanol/chloroform) yielded the best resolved SDS-patterns and highest protein recovery rates, method A (urea) yielded the greatest number of accessions, and, of the three procedures, method B (TCA/acetone) was the least compatible of all with a wide range of downstream analytical procedures. Our results also highlighted breed differences between the proteins in milk of Jersey and Holstein-Friesian cows.", "claims": [{"id": "claim-method", "statement": "Partial Least Squares analyses (PLS) were performed on row means using the cow breed as a response, three latent factors, and 50% valid values.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26793233", "locator": "sections[14] \"Statistical analyses\" paragraph 3", "quote": "Partial Least Squares analyses (PLS) were performed on row means using the cow breed as a response, three latent factors, and 50% valid values."}], "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 dataset identifier PXD002529.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26793233", "locator": "sections[13] \"Database search for protein identification\" paragraph 4", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002529."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using statistical analyses of nLC-ESI-MS/MS data deposited in ProteomeXchange under PXD002529, the study identified 186 unique protein accessions across the combined methods, with urea providing the greatest coverage, methanol/chloroform the best recovery and SDS-PAGE resolution, and TCA/acetone the least suitable downstream performance.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26793233", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Overall 186 unique accessions, major and minor proteins, were identified with a combination of methods."}, {"asset": "source:pmid:26793233", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Mass spectrometry (MS) data are available via ProteomeXchange with identifier PXD002529."}, {"asset": "source:pmid:26793233", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Method C (methanol/chloroform) yielded the best resolved SDS-patterns and highest protein recovery rates, method A (urea) yielded the greatest number of accessions, and, of the three procedures, method B (TCA/acetone) was the least compatible of all with a wide range of downstream analytical procedures."}, {"asset": "source:pmid:26793233", "locator": "sections[1] \"Introduction\" paragraph 5", "quote": "Statistical analyses and gene ontology (GO) classification were employed to further highlight commonalities and differences between the three extraction methods."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using statistical analyses of nLC-ESI-MS/MS data deposited in ProteomeXchange under PXD002529, the study identified 186 unique protein accessions across the combined methods, with urea providing the greatest coverage, methanol/chloroform the best recovery and SDS-PAGE resolution, and TCA/acetone the least suitable downstream performance.", "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:26793233"], "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:PXD002529"], "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:PXD002529"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26793233", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2015.00360", "sha256": "sha256:68cbc25f6513028c626a9ae3b1873c5247960bc6ecfa3beea30adb25749957de", "bytes": 62299, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2015.00360", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4707256", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002529", "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=PXD002529", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002529", "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 dataset identifier PXD002529.", "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 dataset identifier PXD002529.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Milk bottom-up proteomics: method optimisation.", "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:26793233:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b91d760b04635338da2fb86d81003d595a78e13e744d46db38d6ccfad788706a", "bytes": 17969, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T1", "version": null, "note": "List of protein accessions identified in the different milk extracts, along with their description, their coverage (percentage of the database protein sequence covered by matching peptides) across samples, the number of unique peptides (distinct peptide that match to a single protein entry within the search database), the occurrence (%) in the three methods and the two breeds.", "structure": {"pmcid": "PMC4707256", "section_index": 13, "section_title": "Database search for protein identification", "row_count": 187, "column_count": 11}, "table": {"label": "Table 1", "caption": "List of protein accessions identified in the different milk extracts, along with their description, their coverage (percentage of the database protein sequence covered by matching peptides) across samples, the number of unique peptides (distinct peptide that match to a single protein entry within the search database), the occurrence (%) in the three methods and the two breeds.", "rows": [["No", "Description", "gi Accession", "IPI accession", "Σcoverage (%)", "Σ# Unique Peptides", "Occurrencea in method A (%)", "Occurrencea in method B (%)", "Occurrencea in method C (%)", "Occurrencea in breed H (%)", "Occurrencea in breed J (%)"], ["1", "11 kDa protein", "", "IPI00843089.3", "52.3", "22", "100", "100", "100", "100", "100"], ["2", "Actin 1", "4501885", "IPI00698900.1", "16.5", "520", "72", "67", "40", "47", "73"], ["3", "Alpha-1-acid glycoprotein", "94966811", "IPI00691212.1", "33.7", "10", "97", "100", "27", "77", "75"], ["4", "Alpha-1-antiproteinase", "27806941", "IPI00695489.1", "24.5", "10", "97", "94", "85", "98", "87"], ["5", "Alpha-1B-glycoprotein", "114053019", "IPI00692686.1", "13.3", "6", "9", "39", "35", "41", "13"], ["6", "Alpha-2-HS-glycoprotein", "27806751", "IPI00707101.1", "19.2", "8", "86", "74", "65", "90", "62"], ["7", "Alpha-lactabumin", "119393699", "", "30.8", "3", "95", "0", "55", "50", "51"], ["8", "Alpha-lactalbumin", "505782142", "", "9.9", "1", "7", "0", "0", "5", "0"], ["9", "Alpha-lactalbumin", "11036986", "", "18.1", "2", "100", "100", "100", "100", "100"], ["10", "Alpha-lactalbumin", "27805979", "IPI00717424.1", "31.0", "53", "55", "0", "0", "18", "21"], ["11", "Alpha-lactalbumin-like isoform X3", "585153938", "", "12.3", "3", "100", "0", "0", "36", "34"], ["12", "Alpha-S1-casein", "159793227", "", "15.8", "1", "100", "100", "100", "100", "100"], ["13", "Alpha-S1-casein", "299676", "", "64.7", "1", "0", "1", "0", "0", "1"], ["14", "Alpha-S1-casein", "162650", "", "14.0", "1", "22", "12", "17", "22", "11"], ["15", "Alpha-S1-casein isoform X2", "528953236", "", "41.3", "47", "100", "100", "100", "100", "100"], ["16", "Alpha-S1-casein isoform X3", "528953238", "", "42.2", "47", "100", "100", "100", "100", "100"], ["17", "Alpha-S1-casein isoform X6", "528953244", "", "30.2", "5", "100", "100", "100", "100", "100"], ["18", "Alpha-S1-casein isoform X7", "528953246", "", "49.2", "47", "100", "100", "100", "100", "100"], ["19", "Alpha-S2-casein", "27806963", "IPI00698843.1", "59.5", "29", "0", "4", "10", "5", "4"], ["20", "Alpha-S2-casein", "147744646", "", "24.1", "1", "100", "100", "100", "100", "100"], ["21", "Angiogenin-1", "118151356", "IPI00726982.1", "31.8", "5", "76", "39", "74", "69", "57"], ["22", "Antibody Blv5b8", "513137425", "", "9.5", "5", "51", "6", "35", "41", "21"], ["23", "Anti-hiv llama vhh antibody a12", "380258837", "", "6.3", "1", "0", "0", "1", "0", "1"], ["24", "Apolipoprotein A-I preproprotein", "75832056", "IPI00715548.1", "38.1", "56", "99", "0", "99", "67", "63"], ["25", "Apolipoprotein A-II", "114052298", "IPI00688815.2", "16.0", "5", "25", "0", "0", "14", "3"], ["26", "Apolipoprotein A-IV", "82697389", "IPI00695965.1", "18.7", "19", "36", "0", "4", "12", "16"], ["27", "Apolipoprotein E", "27806739", "IPI00712693.1", "7.3", "12", "75", "0", "15", "30", "32"], ["28", "ATP-binding cassette sub-family G member 2", "112817615", "IPI00690408.5", "7.9", "80", "100", "0", "81", "62", "59"], ["29", "Beta-1,4-galactosyltransferase 1", "", "IPI00760476.26", "5.1", "2", "90", "29", "0", "54", "29"], ["30", "Beta-1,4-galactosyltransferase 1", "116241263", "IPI00685910.2", "10.0", "29", "0", "0", "5", "3", "0"], ["31", "Beta-2-microglobulin", "41386683", "IPI00686769.1", "23.7", "22", "100", "82", "97", "96", "90"], ["32", "Beta-casein", "555980347", "IPI00697085.1", "23.7", "8", "0", "0", "81", "27", "23"], ["33", "Beta-casein", "83406093", "", "23.7", "45", "0", "100", "0", "32", "36"], ["34", "Beta-casein variant I", "38231527", "", "35.9", "2", "35", "0", "0", "12", "13"], ["35", "Beta-lactoglobulin", "54037712", "", "37.0", "22", "1", "0", "0", "0", "1"], ["36", "Beta-lactoglobulin", "562890035", "", "30.0", "1", "100", "100", "100", "100", "100"], ["37", "Beta-lactoglobulin", "87196497", "IPI00699698.1", "41.0", "18", "5", "0", "19", "6", "10"], ["38", "Beta-lactoglobulin", "223165", "", "47.5", "19", "100", "0", "100", "68", "64"], ["39", "Beta-lactoglobulin", "49259423", "", "47.5", "15", "100", "0", "0", "36", "34"], ["40", "Beta-lactoglobulin", "378947940", "", "25.8", "1", "100", "100", "0", "68", "70"], ["41", "Beta-lactoglobulin A", "2194088", "", "47.5", "22", "100", "0", "0", "36", "34"], ["42", "Beta-lactoglobulin-like", "593730995", "", "9.4", "1", "22", "0", "0", "2", "13"], ["43", "Butyrophilin subfamily 1 member A1", "3183510", "IPI00708535.1", "28.1", "335", "100", "100", "100", "100", "100"], ["44", "Cathelicidin-1", "27807341", "IPI00718108.1", "10.3", "10", "6", "0", "1", "5", "0"], ["45", "Cathelicidin-4", "27807337", "IPI00686754.1", "11.1", "1", "5", "13", "1", "12", "1"], ["46", "CD5L protein", "", "IPI00867131.2", "14.1", "23", "25", "0", "81", "22", "45"], ["47", "CD81 antigen", "78042548", "IPI00685617.1", "6.8", "9", "89", "8", "0", "37", "31"], ["48", "Cell division control protein 42 homolog isoform 1", "4757952", "IPI00704257.2", "5.2", "76", "19", "0", "33", "19", "15"], ["49", "Chemokine (C-X-C motif) ligand 3", "114050915", "IPI00721750.2", "14.4", "9", "95", "0", "0", "34", "33"], ["50", "Clusterin preproprotein", "27806907", "IPI00694304.1", "18.0", "53", "97", "95", "99", "95", "98"], ["51", "Complement C3", "602697202", "", "7.9", "86", "100", "100", "100", "100", "100"], ["52", "Complement C3", "124056491", "IPI00713505.2", "34.0", "152", "100", "0", "0", "36", "34"], ["53", "Cysteine-rich secretory protein 3", "118601862", "IPI00715999.1", "23.4", "7", "99", "78", "90", "91", "87"], ["54", "dnaJ homolog subfamily B member 9", "300795871", "IPI01000889.1", "17.9", "89", "0", "20", "13", "8", "13"], ["55", "dnaJ homolog subfamily C member 3", "27807457", "IPI00693007.1", "3.4", "14", "0", "0", "1", "1", "0"], ["56", "Dystroglycan", "27806449", "IPI00707359.1", "1.8", "21", "0", "91", "1", "32", "30"], ["57", "Endopin 2B", "38683423", "IPI01017613.1", "16.6", "7", "92", "0", "0", "35", "29"], ["58", "Epididymal secretory protein E1", "27806881", "IPI00711862.1", "32.9", "8", "59", "80", "8", "62", "38"], ["59", "Fab Pgt123 Hiv-1 Neutralizing Antibody", "491668737", "", "5.2", "1", "56", "13", "0", "34", "13"], ["60", "Factor XIIa inhibitor", "27807349", "IPI00710025.1", "15.4", "7", "100", "68", "71", "82", "78"], ["61", "Fatty acid synthase", "426239165", "", "1.2", "11", "8", "0", "0", "1", "5"], ["62", "Fatty acid-binding protein", "507563106", "", "14.3", "40", "99", "40", "100", "94", "64"], ["63", "Fatty acid-binding protein", "27805809", "IPI00691946.2", "47.4", "109", "80", "0", "9", "34", "28"], ["64", "Fibrinogen alpha chain", "75812954", "IPI00691819.1", "8.9", "7", "95", "28", "63", "77", "48"], ["65", "Fibrinogen beta chain", "218931172", "IPI00709763.5", "11.7", "24", "27", "53", "49", "49", "37"], ["66", "Fibroblast growth factor-binding protein 1", "27805911", "IPI00704023.1", "11.5", "5", "94", "40", "92", "87", "63"], ["67", "Fibronectin isoform X10", "528940100", "IPI01028178.1", "0.6", "484", "0", "0", "3", "0", "2"], ["68", "Folate receptor alpha", "330688394", "IPI01017673.1", "9.1", "4", "76", "74", "0", "59", "44"], ["69", "Gelsolin isoform b", "296484315", "IPI01017675.1", "1.8", "190", "0", "11", "0", "2", "5"], ["70", "Glutamyltranspeptidase 1 gamma", "329664306", "IPI00705565.2", "6.7", "4", "10", "2", "0", "2", "7"], ["71", "Glycosylation-dependent cell adhesion molecule 1", "27807339", "IPI00716366.1", "50.3", "39", "100", "100", "100", "100", "100"], ["72", "GTP binding protein Rab1a", "15281851", "IPI00883580.1", "17.0", "118", "0", "1", "37", "16", "8"], ["73", "hCG1791766 isoform CRA_a", "119626014", "", "13.7", "2", "0", "18", "47", "22", "20"], ["74", "Heat shock cognate 71 kDa protein", "548494982", "IPI00708526.2", "5.9", "656", "14", "0", "0", "4", "6"], ["75", "Heat shock-related 70 kDa protein 2", "148887197", "IPI00710052.1", "1.7", "1", "0", "1", "19", "8", "5"], ["76", "Hedgehog interacting protein-like 2-like", "76669880", "IPI00700055.2", "11.5", "10", "0", "80", "96", "60", "54"], ["77", "Hemopexin", "77736171", "IPI00690198.4", "3.5", "6", "2", "0", "0", "2", "0"], ["78", "Heparin cofactor 2", "157280001", "IPI00688367.1", "2.6", "6", "0", "5", "0", "1", "2"], ["79", "Histatherin", "242347807", "IPI00944405.1", "39.7", "2", "13", "12", "88", "44", "28"], ["80", "Hornerin", "28557150", "", "4.1", "6", "0", "0", "1", "0", "1"], ["81", "Ig anti-HIV-1", "612405504", "", "12.6", "1", "1", "0", "59", "13", "25"], ["82", "Ig J chain", "32401410", "IPI00701295.1", "29.9", "20", "99", "100", "99", "98", "100"], ["83", "Ig lambda light chain", "15088675", "", "21.3", "10", "100", "0", "100", "68", "64"], ["84", "Ig lambda light chain constant region 2 allotypic variant IGLC2b", "343197004", "", "30.2", "1", "98", "100", "0", "67", "69"], ["85", "Ig lambda light chain constant region 3 allotypic variant IGLC3c", "343197026", "", "52.8", "3", "100", "100", "100", "100", "100"], ["86", "Ig lambda-1 variable region", "42759882", "", "13.9", "2", "0", "0", "19", "1", "11"], ["87", "Ig lambda-like polypeptide 1-like", "", "IPI01002118.1", "23.3", "8", "100", "0", "100", "68", "64"], ["88", "Ig light chain", "310893433", "", "16.7", "3", "91", "62", "77", "80", "74"], ["89", "Ig light chain", "310893435", "", "61.4", "16", "100", "0", "100", "68", "64"], ["90", "Ig light chain variable region", "5802436", "", "11.5", "1", "100", "100", "100", "100", "100"], ["91", "Ig light chain variable region", "2323400", "", "41.8", "12", "0", "4", "3", "4", "0"], ["92", "Ig light chain variable region", "482673169", "", "9.4", "15", "16", "6", "0", "10", "6"], ["93", "Ig light chain, lambda gene cluster", "92096965", "IPI00867205.1", "20.1", "1", "0", "100", "0", "32", "36"], ["94", "IgG1 heavy chain constant region", "7547266", "", "16.4", "9", "98", "95", "99", "98", "97"], ["95", "IgG2a heavy chain constant region", "1699167", "", "12.9", "2", "48", "5", "45", "42", "23"], ["96", "IGK protein", "115545495", "IPI00724838.2", "10.0", "10", "0", "2", "99", "34", "29"], ["97", "IgM heavy chain constant region", "2232299", "", "22.7", "53", "100", "100", "100", "100", "100"], ["98", "Inhibitor of carbonic anhydrase-like", "470655576", "", "5.2", "7", "0", "6", "0", "3", "1"], ["99", "Isocitrate dehydrogenase cytoplasmic", "75056526", "IPI00702781.2", "12.1", "5", "0", "0", "14", "6", "2"], ["100", "Isocitrate dehydrogenase cytoplasmic", "75832090", "IPI01028293.1", "25.9", "148", "77", "0", "0", "28", "26"], ["101", "Kappa-casein", "8099324", "", "40.6", "33", "1", "6", "13", "5", "8"], ["102", "Kappa-casein", "162807", "", "42.4", "42", "100", "100", "100", "100", "100"], ["103", "Kappa-casein", "1705608", "", "24.0", "135", "100", "100", "100", "100", "100"], ["104", "Kappa-casein", "284027124", "", "17.3", "133", "100", "54", "100", "88", "81"], ["105", "Kappa-casein", "315143016", "", "36.8", "67", "58", "26", "24", "32", "41"], ["106", "Kappa-casein", "428755215", "", "13.6", "2", "100", "100", "100", "100", "100"], ["107", "Kappa-casein", "428755219", "", "33.3", "66", "99", "100", "100", "99", "100"], ["108", "Kappa-casein", "284626", "", "58.5", "1", "100", "100", "100", "100", "100"], ["109", "Kappa-casein", "2493514", "", "20.5", "10", "100", "100", "100", "100", "100"], ["110", "Kappa-casein", "251198", "", "100.0", "1", "100", "100", "100", "100", "100"], ["111", "Kappa-casein", "1594249", "", "9.0", "2", "100", "100", "0", "68", "70"], ["112", "Kappa-casein A", "229416", "", "57.1", "33", "100", "100", "100", "100", "100"], ["113", "Kininogen-1", "125505", "IPI00701166.1", "11.6", "13", "99", "0", "26", "50", "36"], ["114", "Kininogen-2", "490", "IPI00718535.1", "10.4", "4", "0", "53", "0", "29", "7"], ["115", "Kininogen-2 isoform X1", "528936694", "", "14.7", "17", "99", "0", "0", "35", "34"], ["116", "Lactadherin", "2494285", "IPI00689035.1", "33.3", "55", "100", "62", "100", "100", "75"], ["117", "Lactoperoxidase", "27806851", "IPI00716157.1", "26.1", "144", "36", "0", "36", "23", "25"], ["118", "Lactoperoxidase", "16740670", "", "5.1", "12", "100", "100", "100", "100", "100"], ["119", "Lactotransferrin", "589925430", "", "4.0", "24", "100", "100", "100", "100", "100"], ["120", "Lactotransferrin", "30794292", "IPI00710664.1", "53.1", "134", "98", "0", "0", "35", "33"], ["121", "Lethal(3)malignant brain tumor-like protein 4", "505792423", "", "2.5", "1", "1", "0", "1", "2", "0"], ["122", "Leucine proline-enriched proteoglycan (leprecan) 1", "507937306", "", "1.9", "1", "1", "0", "1", "1", "1"], ["123", "Lipopolysaccharide-binding protein", "84579853", "IPI00730056.1", "2.3", "5", "2", "0", "0", "1", "1"], ["124", "Lipoprotein lipase", "115497164", "IPI00692291.3", "22.0", "152", "100", "99", "100", "100", "99"], ["125", "Lymphocyte antigen 96", "114051704", "IPI00689371.2", "6.3", "9", "3", "0", "0", "1", "2"], ["126", "Lymphocyte-specific protein 1 isoform X6", "587003867", "", "5.8", "4", "3", "0", "0", "1", "2"], ["127", "Mammaglobin-A", "155372309", "IPI00711254.1", "14.1", "1", "10", "0", "0", "7", "0"], ["128", "Mammary serum amyloid A3.2", "347300329", "IPI01017597.1", "9.2", "11", "17", "1", "0", "0", "13"], ["129", "Monocyte differentiation antigen CD14 isoform X1", "528956860", "IPI00686931.2", "22.7", "25", "82", "0", "68", "47", "52"], ["130", "Mucin-1", "41386778", "IPI00706283.1", "3.1", "13", "100", "7", "8", "43", "37"], ["131", "Mucin-15", "41386723", "IPI00716220.1", "7.3", "10", "99", "100", "94", "97", "98"], ["132", "Myristoylated alanine-rich C-kinase substrate", "148872484", "IPI00760436.1", "6.0", "6", "0", "9", "0", "6", "0"], ["133", "Neutrophil gelatinase-associated lipocalin isoform X3", "528912092", "IPI00685784.3", "30.5", "11", "28", "95", "74", "65", "66"], ["134", "Nucleobindin-1", "115497814", "IPI00722271.2", "28.1", "117", "100", "0", "38", "48", "46"], ["135", "Nucleobindin-2", "115496067", "IPI00696729.2", "15.2", "73", "0", "100", "0", "32", "36"], ["136", "Olfactory receptor 2S2-like", "724801196", "", "2.2", "1", "0", "4", "1", "2", "1"], ["137", "Osteopontin isoform X1", "528952550", "IPI00691887.2", "31.7", "71", "99", "100", "100", "99", "100"], ["138", "Pancreatic elastase inhibitor", "861514", "", "66.7", "1", "10", "0", "0", "1", "6"], ["139", "Pancreatic secretory granule membrane major glycoprotein GP2", "341572597", "", "23.0", "84", "100", "96", "100", "100", "98"], ["140", "Peptidoglycan recognition protein 1", "27808640", "IPI00701640.1", "13.7", "5", "0", "15", "63", "37", "13"], ["141", "Peptidyl-prolyl cis-trans isomerase A", "47523764", "IPI00697285.3", "16.5", "101", "6", "2", "8", "4", "6"], ["142", "Peptidyl-prolyl cis-trans isomerase B", "555965067", "IPI00702098.4", "6.0", "85", "31", "0", "0", "14", "8"], ["143", "Peptidyl-prolyl cis-trans isomerase FKBP1A", "78365305", "IPI00698916.2", "25.0", "98", "7", "0", "0", "2", "2"], ["144", "Perilipin-2 isoform X2", "528958213", "IPI01017444.1", "38.0", "96", "100", "100", "100", "100", "100"], ["145", "Platelet glycoprotein 4", "521258696", "IPI00710204.3", "15.5", "106", "100", "100", "100", "100", "100"], ["146", "Polymeric immunoglobulin receptor", "3914346", "IPI00696714.1", "30.0", "28", "100", "0", "100", "68", "64"], ["147", "Polymeric immunoglobulin receptor", "296479365", "", "23.9", "21", "100", "100", "100", "100", "100"], ["148", "Polyubiquitin", "2627129", "", "21.0", "380", "0", "79", "0", "24", "29"], ["149", "Prosaposin", "27806447", "IPI00718311.3", "5.0", "54", "25", "0", "0", "11", "6"], ["150", "Prostaglandin-H2 D-isomerase", "27807521", "IPI00709683.1", "7.3", "6", "65", "94", "100", "85", "87"], ["151", "Protein CREG1", "115495283", "IPI00702458.2", "20.4", "11", "78", "0", "13", "30", "33"], ["152", "Protein HP-25 homolog 1", "114050753", "IPI00724799.2", "7.1", "3", "1", "0", "0", "1", "0"], ["153", "Protein HP-25 homolog 2", "114052108", "IPI00700655.3", "14.9", "3", "7", "2", "40", "27", "4"], ["154", "Protein inturned", "617602241", "", "1.3", "1", "1", "0", "0", "1", "0"], ["155", "Protein OS-9", "77735409", "IPI00706896.1", "4.5", "2", "5", "0", "1", "2", "2"], ["156", "Prothrombin", "135806", "IPI00710799.1", "2.2", "7", "6", "1", "0", "2", "3"], ["157", "Ras-related protein Rab-11A", "84000297", "IPI00695221.3", "11.1", "82", "1", "0", "0", "1", "0"], ["158", "Ras-related protein Rab-18", "115495023", "IPI00691826.3", "7.3", "123", "3", "0", "0", "1", "2"], ["159", "Rhophilin-2-like protein RHPN2P1", "190360225", "", "2.4", "2", "0", "1", "0", "1", "0"], ["160", "Ribonuclease 4", "32363484", "IPI00697112.1", "9.2", "1", "0", "81", "0", "30", "25"], ["161", "Ribonuclease 4", "95006989", "IPI00760446.1", "28.6", "4", "31", "0", "3", "12", "11"], ["162", "Ribonuclease pancreatic", "133210", "", "10.5", "100", "0", "19", "0", "3", "10"], ["163", "Secretoglobin family 1D member", "118150406", "IPI00824879.1", "21.6", "4", "100", "100", "100", "100", "100"], ["164", "Selenium-binding protein 1", "", "IPI00718529.1", "1.7", "1", "8", "0", "3", "3", "4"], ["165", "Selenoprotein", "148680082", "", "13.0", "69", "45", "0", "9", "23", "14"], ["166", "Serotransferrin", "2501351", "IPI00690534.1", "45.5", "61", "100", "95", "100", "100", "97"], ["167", "Serpin A3-1", "160332365", "IPI00700622.4", "12.9", "32", "100", "0", "77", "67", "51"], ["168", "Serum albumin", "1351907", "IPI01028455.1", "65.1", "40", "100", "61", "100", "83", "90"], ["169", "Sodium-dependent phosphate transport protein 2B", "27807195", "IPI00703813.1", "5.9", "7", "92", "0", "0", "35", "29"], ["170", "Sulfhydryl oxidase 1", "156120795", "IPI00867237.1", "19.1", "11", "98", "27", "97", "75", "72"], ["171", "Superoxide dismutase", "134289051", "IPI00847121.1", "11.8", "73", "0", "1", "0", "0", "1"], ["172", "Sushi repeat-containing protein SRPX", "507969850", "", "3.9", "3", "0", "2", "6", "2", "4"], ["173", "Tetranectin", "114051137", "IPI00717369.1", "6.9", "5", "89", "0", "1", "34", "29"], ["174", "Transforming protein RhoA", "10835049", "IPI00688998.3", "6.2", "49", "0", "0", "1", "1", "0"], ["175", "Transthyretin", "27806789", "IPI00689362.1", "34.7", "24", "0", "91", "77", "59", "50"], ["176", "Uncharacterized proteinb (P02666 Beta-casein 71% ident.)", "", "IPI00712994.3", "33.5", "5", "18", "0", "0", "7", "6"], ["177", "Uncharacterized proteinb (F1MGU7 Fibrinogen gamma-B chain 100% ident.)", "", "IPI00843209.1", "17.2", "16", "99", "0", "0", "35", "34"], ["178", "Uncharacterized proteinb (A5PK72 Uncharacterized protein 92% ident.)", "IPI01017618.1", "20.6", "10", "42", "0", "0", "10", "20"], ["179", "Uncharacterized proteinb (A0A0A0MP92 Serpin A3-7 98% ident.)", "", "IPI00971595.1", "21.1", "4", "1", "0", "6", "5", "0"], ["180", "Uncharacterized proteinb (Q2HJI6 Granulin 99% ident.)", "", "IPI00904166.1", "6.3", "99", "98", "0", "41", "57", "37"], ["181", "Uncharacterized proteinb (F1MLW7 Uncharacterized protein 97% ident.)", "", "IPI00838162.2", "20.9", "1", "0", "100", "0", "32", "36"], ["182", "Uncharacterized protein LOC524810b (A5D7Q2 Uncharacterized protein 100% ident.)", "326937675", "IPI00852509.1", "10.9", "6", "100", "100", "100", "100", "100"], ["183", "Vitamin D-binding protein", "78369364", "IPI00823795.1", "8.0", "20", "38", "0", "0", "21", "6"], ["184", "Xanthine dehydrogenase/oxidase", "296482686", "", "15.6", "16", "0", "100", "0", "32", "36"], ["185", "Xanthine dehydrogenase/oxidase", "109940048", "IPI00695367.3", "14.1", "16", "100", "0", "100", "68", "64"], ["186", "Zinc-alpha-2-glycoprotein", "77735615", "IPI00698993.1", "11.4", "2", "1", "100", "100", "64", "67"]], "row_count": 187, "column_count": 11, "numeric_cells": 1852, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:26793233:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3b6ddd77b345ef91757e644ed03ee61deb5dc5d9939bb120086bfb69eac7ce55", "bytes": 5847, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#T2", "version": null, "note": "List of protein accessions identified in the combined protein standards, along with their description, their score, coverage, the number of peptides identified per protein, the number of peptide spectrum matches (PSM), the size of the protein (AA and MW) and their theoretical isoelectric point (calc. pI).", "structure": {"pmcid": "PMC4707256", "section_index": 21, "section_title": "Protein validation", "row_count": 52, "column_count": 10}, "table": {"label": "Table 2", "caption": "List of protein accessions identified in the combined protein standards, along with their description, their score, coverage, the number of peptides identified per protein, the number of peptide spectrum matches (PSM), the size of the protein (AA and MW) and their theoretical isoelectric point (calc. pI).", "rows": [["No.", "Accession", "Description", "Score", "Coverage (%)", "# Peptides", "# PSM", "# AAs", "MW [kDa]", "calc. pI"], ["1", "IPI00843089.3", "11 kDa protein", "124.2", "29.0", "2", "2", "107", "11.1", "7.99"], ["2", "306440544", "Actin", "746.4", "28.6", "9", "21", "371", "41.3", "5.22"], ["3", "74267962", "Albumin ALB protein [Bos taurus]", "1905.6", "51.7", "29", "60", "607", "69.2", "6.25"], ["4", "IPI00691212.1", "Alpha-1-acid glycoprotein", "84.3", "15.4", "3", "3", "202", "23.2", "5.87"], ["5", "11036998", "Alpha-lactalbumin [Physeter catodon]", "94.0", "12.0", "1", "2", "92", "10.4", "4.59"], ["6", "27805979; IPI00717424.1", "Alpha-lactalbumin precursor [Bos taurus]", "858.8", "31.0", "18", "51", "142", "16.2", "5.14"], ["7", "528953238", "Alpha-S1-casein isoform X3 [Bos taurus]", "1009.1", "40.8", "8", "37", "206", "23.6", "5.19"], ["8", "528953244", "Alpha-S1-casein isoform X6 [Bos taurus]", "639.0", "30.2", "5", "22", "199", "22.6", "4.79"], ["9", "528953246", "Alpha-S1-casein isoform X7 [Bos taurus]", "1011.8", "47.5", "8", "37", "177", "20.2", "5.41"], ["10", "159793227", "Alpha-S1-casein, partial [Bos taurus]", "154.4", "15.8", "2", "3", "95", "10.9", "4.56"], ["11", "27806963; IPI00698843.1", "Alpha-S2-casein precursor [Bos taurus]", "650.6", "38.7", "19", "64", "222", "26.0", "8.43"], ["12", "513137422", "Antibody Blv1h12", "221.5", "23.2", "3", "5", "216", "22.5", "6.11"], ["13", "114052298; IPI00688815.2", "Apolipoprotein A-II precursor [Bos taurus]", "73.4", "16.0", "2", "2", "100", "11.2", "8.10"], ["14", "47564119; IPI00689034.1", "APOLIPOPROTEIN C-III precursor [Bos taurus]", "108.3", "16.7", "2", "4", "96", "10.7", "5.11"], ["15", "41386683; IPI00686769.1", "Beta-2-microglobulin precursor [Bos taurus]", "148.9", "18.6", "6", "9", "118", "13.7", "8.00"], ["16", "223165", "Beta-lactoglobulin", "736.4", "48.2", "9", "26", "162", "18.3", "4.92"], ["17", "87196497; IPI00699698.1", "Beta-lactoglobulin precursor [Bos taurus]", "1112.4", "38.8", "17", "79", "178", "19.9", "5.02"], ["18", "593730995", "Beta-lactoglobulin-like [Physeter catodon]", "65.6", "9.4", "2", "2", "180", "20.3", "5.94"], ["19", "1351907; IPI01028455.1", "Bovine serum albumin", "3415.0", "69.4", "78", "207", "607", "69.2", "6.18"], ["20", "124056491; IPI00713505.2", "Complement C3", "179.6", "4.5", "10", "10", "1661", "187.1", "6.84"], ["21", "6980814", "Fibrinogen", "908.6", "32.6", "11", "21", "390", "42.7", "7.97"], ["22", "75812954; IPI00691819.1", "Fibrinogen alpha chain precursor [Bos taurus]", "1601.7", "41.1", "40", "80", "615", "67.0", "7.17"], ["23", "1346006", "Fibrinogen beta chain", "741.2", "37.6", "13", "20", "468", "53.3", "8.19"], ["24", "488508027", "Fibrinogen beta chain isoform 2 [Dasypus novemcinctus]", "126.4", "8.8", "3", "3", "433", "50.0", "7.39"], ["25", "229156", "Fibrinopeptide B", "152.4", "71.4", "1", "4", "21", "2.4", "4.44"], ["26", "528940100; IPI01028178.1", "Fibronectin isoform X10 [Bos taurus]", "292.9", "5.0", "14", "14", "2268", "249.0", "5.63"], ["27", "113912055; IPI00695142.3", "Glycoprotein 2 (zymogen granule membrane) [Bos taurus]", "81.7", "2.8", "2", "2", "534", "59.2", "4.82"], ["28", "343197008", "Immunoglobulin lambda light chain IGLC2c [Bos taurus]", "160.6", "42.5", "3", "4", "106", "11.4", "8.59"], ["29", "310893435", "Immunoglobulin light chain [Bos taurus]", "118.9", "30.7", "2", "2", "101", "10.4", "6.48"], ["30", "1705608", "Kappa-casein", "472.7", "22.4", "4", "25", "192", "21.5", "5.81"], ["31", "284626", "Kappa-casein–bovine", "171.6", "24.5", "2", "13", "53", "6.0", "5.11"], ["32", "315143016", "Kappa-casein [Bos indicus]", "2183.5", "36.8", "5", "90", "144", "15.9", "6.77"], ["33", "284027124", "Kappa-casein [Ovis vignei]", "464.0", "15.4", "4", "32", "162", "18.0", "6.15"], ["34", "229416", "Kappa-casein para kappaA", "2020.9", "46.7", "4", "79", "105", "12.3", "8.78"], ["35", "162807", "Kappa-casein precursor, partial [Bos taurus]", "589.3", "42.4", "4", "28", "99", "10.6", "5.24"], ["36", "146386372", "Kininogen [Oryctolagus cuniculus]", "104.6", "3.6", "1", "3", "302", "33.3", "6.52"], ["37", "27806851; IPI00716157.1", "Lactoperoxidase precursor [Bos taurus]", "58.8", "1.5", "2", "2", "712", "80.6", "8.54"], ["38", "586476652", "Lactotransferrin [Chrysochloris asiatica]", "233.3", "4.1", "2", "6", "708", "78.0", "8.51"], ["39", "30794292; IPI00710664.1", "Lactotransferrin precursor [Bos taurus]", "2949.1", "57.2", "88", "179", "708", "78.0", "8.32"], ["40", "528912092; IPI00685784.3", "Neutrophil gelatinase-associated lipocalin isoform X3 [Bos taurus]", "168.8", "16.0", "4", "6", "200", "23.0", "9.17"], ["41", "528961411; IPI00866916.1", "Plasminogen isoform X3 [Bos taurus]", "103.2", "4.6", "3", "4", "724", "81.5", "7.96"], ["42", "3914346; IPI00696714.1", "Polymeric immunoglobulin receptor", "130.9", "5.9", "5", "5", "757", "82.4", "7.27"], ["43", "95006989; IPI00760446.1", "Ribonuclease 4 precursor [Bos taurus]", "122.2", "28.6", "6", "6", "147", "16.9", "8.85"], ["44", "118150406; IPI00824879.1", "Secretoglobin family 1D member precursor [Bos taurus]", "83.1", "21.6", "4", "4", "102", "11.3", "8.73"], ["45", "2501351; IPI00690534.1", "Serotransferrin", "117.9", "7.7", "6", "6", "704", "77.7", "7.08"], ["46", "554537890", "Serotransferrin [Myotis brandtii]", "70.8", "4.1", "2", "2", "713", "77.9", "7.05"], ["47", "24119203; IPI00714405.3", "Tropomyosin alpha-3 chain isoform 2 [Homo sapiens]", "51.4", "4.0", "2", "2", "248", "29.0", "4.78"], ["48", "999627", "Trypsin", "77.5", "22.0", "2", "3", "82", "8.8", "7.30"], ["49", "IPI00843209.1", "Uncharacterized protein", "228.2", "18.7", "7", "7", "443", "50.2", "5.72"], ["50", "IPI00712994.3", "Uncharacterized protein", "532.4", "29.2", "6", "23", "161", "18.3", "5.19"], ["51", "556760750", "Uncharacterized protein LOC102338350 [Pantholops hodgsonii]", "60.0", "4.1", "1", "4", "245", "28.1", "9.70"]], "row_count": 52, "column_count": 10, "numeric_cells": 470, "header_rows": 1, "locator": "section[21]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:PXD002529 not downloaded", "asset:data:geo:PXD002529 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Partial Least Squares (PLS) analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Partial Least Squares analyses (PLS) were performed on row means using the cow breed as a response, three latent factors, and 50% valid values."}}], "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 (Partial Least Squares (PLS) analysis), 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": ["PXD002529"], "resolved_accessions": ["PXD002529"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (Vizcaíno et al., 2014) via the PRIDE partner repository with the dataset identifier PXD002529."], "basis": "The paper names PXD002529 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:26793233", "data:geo:PXD002529", "asset:table:pmid:26793233:1", "asset:table:pmid:26793233:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002529"]}, "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": "2026-10-31T18:27:08Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 120880, "completion_tokens": 4032, "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:26793233", "type": "paper", "label": "pmid:26793233"}, {"id": "source:pmid:26793233", "type": "manuscript", "label": "PMID 26793233 full text"}, {"id": "data:geo:PXD002529", "type": "dataset", "label": "GEO PXD002529"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26793233", "type": "paper", "label": "pmid:26793233"}, {"id": "source:pmid:26793233", "type": "manuscript", "label": "PMID 26793233 full text"}, {"id": "data:geo:PXD002529", "type": "dataset", "label": "GEO PXD002529"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26793233", "type": "extraction", "used": ["source:pmid:26793233"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002529", "type": "accession_resolution", "used": ["data:geo:PXD002529"], "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:26793233", "parent_hash": "sha256:65ee7b02cc5d0f5d246d7aa72803aaf17d6a18886bc9183e3d265db2464fd236", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD002529 licence not read", "asset:data:geo:PXD002529 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": ["Milk Bottom-Up Proteomics: Method Optimization.", "d by nanoHPLC-electrospray ionization-tandem mass spectrometry (nLC-ESI-MS/MS) analyses were performed to a", "stion, injection) to assess reproducibility. Mass spectrometry (MS) data are available via ProteomeXchange", "ray ionization-tandem mass spectrometry (nLC-ESI-MS/MS) analyses were performed to assess their"], "order_basis": "paper_text_order:0", "id": "assay:1"}]},"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":"2026-11-04T01:48:48+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}}}