{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26862565", "kind": "science-record", "revision": 3, "content_hash": "sha256:fb7ab4e0fd5ccc016446f23d6957ed9df80db6698f8d0d80c4920114431a235b", "created_at": "2026-11-01T15:40:15Z", "updated_at": "2026-11-01T18:47:57Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Time-course investigation of Phytophthora infestans infection of potato leaf from three cultivars by quantitative proteomics.", "doi": "10.1016/j.dib.2015.11.069", "pmid": "26862565", "authors": ["Mia Kruse Guldstrand Larsen", "Malene Møller Jørgensen", "Tue Bjerg Bennike", "Allan Stensballe"], "journal": "Data in brief", "year": 2016, "abstract": "Potato late blight is one the most important crop diseases worldwide. Even though potato has been studied for many years, the potato disease late blight still has a vast negative effect on the potato production [1], [2], [3]. Late blight is caused by the pathogen Phytophthora infestans (P. infestans), which initiates infection through leaves. However, the biological activities during different stages of infection are poorly described, and could enable novel or improved ways of defeating late blight infection [4]. Therefore, we investigated the interactions between P. infestans (mixed strain culture) and potato (Solanum tuberosum). Three commercially available field potato cultivars of different resistance to late blight infection; Kuras (moderate), Sarpo Mira (highly resistant) and Bintje (very susceptable) were grown under controlled green house conditions and inoculated with a diversity of P. infestans populations. We used label-free quantitative proteomics to investigate the infection with P. infestans in a time-course study over 258 h. Several key issues limits proteome analysis of potato leaf tissue [5], [6], [7]. Firstly, the immense complexity of the plant proteome, which is further complicated by the presence of highly abundant proteins, such as ribulose bisphosphate carboxylase/oxygenase (RuBisCO). Secondly, plant leaf and potato, in particular, contain abundant levels amounts of phenols and polyphenols, which hinder or completely prevent a successful protein extraction. Hitherto, protein profiling of potato leaf tissues have been limited to few proteome studies and only 1484 proteins have been extracted and comprehensively described [5], [8], [9]. We here present the detailed methods and raw data by optimized gel-enhanced label free quantitative approach. The methodology enabled us to detect and quantify between 3248 and 3529 unique proteins from each cultivar, and up to 758 P. infestans derived proteins. The complete dataset is available via ProteomeXchange, with the identifier PXD002767.", "claims": [{"id": "claim-data-access", "statement": "The proteomics raw data and MaxQuant result-files from the analysis have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD0002767 [11], [12], [13], [14], and can be downloaded directly (http://www.ebi.ac.uk/pride/archive/projects/PXD002767).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26862565", "locator": "sections[10] \"Data\" paragraph 2", "quote": "The proteomics raw data and MaxQuant result-files from the analysis have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD0002767 [11], [12], [13], [14], and can be downloaded directly (http://www.ebi.ac.uk/pride/archive/projects/PXD002767)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used MaxQuant-based label-free quantitative proteomics, with statistical analysis based on the search-output files deposited in the ProteomeXchange/PRIDE repository under dataset identifier PXD002767; the methodology detected and quantified 3,248–3,529 unique proteins per cultivar and up to 758 P. infestans-derived proteins.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26862565", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The methodology enabled us to detect and quantify between 3248 and 3529 unique proteins from each cultivar, and up to 758 P. infestans derived proteins."}, {"asset": "source:pmid:26862565", "locator": "sections[9] \"Proteomic data analysis\" paragraph 2", "quote": "This enables statistical analysis based on the search output files as provided in the ProteomXchange and described in detail in Table 2."}, {"asset": "source:pmid:26862565", "locator": "sections[10] \"Data\" paragraph 2", "quote": "The proteomics raw data and MaxQuant result-files from the analysis have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD0002767 [11], [12], [13], [14], and can be downloaded directly (http://www.ebi.ac.uk/pride/archive/projects/PXD002767)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used MaxQuant-based label-free quantitative proteomics, with statistical analysis based on the search-output files deposited in the ProteomeXchange/PRIDE repository under dataset identifier PXD002767; the methodology detected and quantified 3,248–3,529 unique proteins per cultivar and up to 758 P. infestans-derived proteins.", "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:26862565"], "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:PXD002767"], "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:PXD002767"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26862565", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2015.11.069", "sha256": "sha256:fdf4efdf317785fff6a00e095479ee872cb24c0ff6ee3b09a3161f9ecad92e08", "bytes": 19654, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2015.11.069", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4707178", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002767", "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=PXD002767", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002767", "version": null, "note": "The proteomics raw data and MaxQuant result-files from the analysis have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD0002767 [11], [12], [13], [14], and can be downloaded directly (http://www.ebi.ac.uk/pride/archive/projects/PXD002767).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The proteomics raw data and MaxQuant result-files from the analysis have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD0002767 [11], [12], [13], [14], and can be downloaded directly (http://www.ebi.ac.uk/pride/archive/projects/PXD002767).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Time-course Investigation of Phytophthora infestans infection of potato leaf from three cultivars by quantitative proteomics", "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:26862565:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:563a13bad1d72b94bc95f7ddc3d8c223f8a9910fcf95c3011041d9b9ecfa502b", "bytes": 1839, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t0005", "version": null, "note": "Description of search file-names in the ProteomeXchange repository PXD002767 based on MaxQuant [11]. Each zip contains a range of files where the four most relevant are described above.", "structure": {"pmcid": "PMC4707178", "section_index": 9, "section_title": "Proteomic data analysis", "row_count": 9, "column_count": 2}, "table": {"label": "Table 2", "caption": "Description of search file-names in the ProteomeXchange repository PXD002767 based on MaxQuant [11]. Each zip contains a range of files where the four most relevant are described above.", "rows": [["Search Files Filename", "Description of content"], ["MQ_Search_Kuras.zip", "MaxQuant result folder “txt” of Q Exactive GelMS potato leaf samples, search against the Uniprot reference proteome databases for potato (AUP000011115) and late blight (AUP000006643)."], ["MQ_Search_Bintje.zip", "MaxQuant result folder “txt” of Q Exactive GelMS potato leaf samples, search against the Uniprot reference proteome databases for potato (AUP000011115) and late blight (AUP000006643)."], ["MQ_Search_Sarpomira.zip", "MaxQuant result folder “txt” of Q Exactive GelMS potato leaf samples, search against the Uniprot reference proteome databases for potato (AUP000011115) and late blight (AUP000006643)."], ["MQ_Search_all_cultivars.zip", "MaxQuant result folder “txt” of Q Exactive GelMS potato leaf samples from all cultivars, search against the Uniprot reference proteome databases for potato (AUP000011115) and late blight (AUP000006643)."], ["The MaxQuant output in folder \"txt\" contains a range of files containing important search information. Below files are the most commonly used for post-identification analysis and quantitative analysis."], ["tables.pdf", "A summary of all the definitions and files used for the MaxQuant search."], ["proteinGroups.txt", "File containing all proteins with corresponding label free quantitative information to be imported into the Perseus post-analysis program [15]."], ["summary.txt parameters.txt", "Detailed description of all settings used for the MaxQuant search."]], "row_count": 9, "column_count": 2, "numeric_cells": 5, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:26862565:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0cfaa28c3553a0bc88987b90c196de51066f8ed1976e32d33c6934dcea11f4fc", "bytes": 9093, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t0010", "version": null, "note": "Description of file-names in the ProteomeXchange repository PXD002767. MS files were searched using using MaxQuant [10]. Combining fractions of GelMS (1top-4bottom) gel lanes. The number of identified proteins after filtration of typical contaminants and Phytophthora infestans is reported.", "structure": {"pmcid": "PMC4707178", "section_index": 10, "section_title": "Data", "row_count": 309, "column_count": 6}, "table": {"label": "Table 1", "caption": "Description of file-names in the ProteomeXchange repository PXD002767. MS files were searched using using MaxQuant [10]. Combining fractions of GelMS (1top-4bottom) gel lanes. The number of identified proteins after filtration of typical contaminants and Phytophthora infestans is reported.", "rows": [["File", "Sample", "Cultivar", "Digestion", "MS system", "# ID proteins"], [""], ["Bin_K4_1.raw", "Control,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "2894"], ["Bin_K4_1b.raw", "4 h"], ["Bin_K4_2.raw", "(Pooled control leafs (n=3) at 4 h)"], ["Bin_K4_2b.raw"], ["Bin_K4_3.raw"], ["Bin_K4_3b.raw"], ["Bin_K4_4.raw"], ["Bin_K4_4b.raw"], ["Bin_K16_1.raw", "Control,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "2831"], ["Bin_K16_1b.raw", "16 h"], ["Bin_K16_2.raw"], ["Bin_K16_2b.raw"], ["Bin_K16_3.raw"], ["Bin_K16_3b.raw"], ["Bin_K16_4.raw"], ["Bin_K16_4b.raw"], ["Bin_K65_1.raw", "Control,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "2841"], ["Bin_K65_1b.raw", "65 h"], ["Bin_K65_2.raw"], ["Bin_K65_2b.raw"], ["Bin_K65_3.raw"], ["Bin_K65_3b.raw"], ["Bin_K65_4.raw"], ["Bin_K65_4b.raw"], ["Bin_K120_1.raw", "Control,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "2889"], ["Bin_K120_1b.raw", "120 h"], ["Bin_K120_2.raw"], ["Bin_K120_2b.raw"], ["Bin_K120_3.raw"], ["Bin_K120_3b.raw"], ["Bin_K120_4.raw"], ["Bin_K120_4b.raw"], ["BIn_K258_1.raw", "Control,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "2784"], ["258 h"], ["BIn_K258_1b.raw"], ["BIn_K258_2.raw"], ["BIn_K258_2b.raw"], ["BIn_K258_3.raw"], ["BIn_K258_3b.raw"], ["BIn_K258_4.raw"], ["BIn_K258_4b.raw"], ["Bin_S4_2207_1.raw", "P. infestans infect,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "3057"], ["Bin_S4_2207_2.raw", "4 h"], ["Bin_S4_2207_3.raw", "(sampling leaf #2207,2208, 2209)"], ["Bin_S4_2207_4.raw"], ["Bin_S4_2208_1.raw"], ["Bin_S4_2208_2.raw"], ["Bin_S4_2208_3.raw"], ["Bin_S4_2208_4.raw"], ["Bin_S4_2209_1.raw"], ["Bin_S4_2209_2.raw"], ["Bin_S4_2209_3.raw"], ["Bin_S4_2209_4.raw"], ["Bin_S16_2258_1.raw", "P. infestans infect,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "3065"], ["Bin_S16_2258_2.raw"], ["16 h"], ["Bin_S16_2258_3.raw"], ["Bin_S16_2258_4.raw"], ["Bin_S16_2259_1.raw"], ["Bin_S16_2259_2.raw"], ["Bin_S16_2259_3.raw"], ["Bin_S16_2259_4.raw"], ["Bin_S16_2260_1.raw"], ["Bin_S16_2260_2.raw"], ["Bin_S16_2260_3.raw"], ["Bin_S16_2260_4.raw"], ["Bin_S65_2309_1.raw", "P. Infestans infect,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "3099"], ["Bin_S65_2309_2.raw"], ["65 h"], ["Bin_S65_2309_3.raw"], ["Bin_S65_2309_4.raw"], ["Bin_S65_2310_1.raw"], ["Bin_S65_2310_2.raw"], ["Bin_S65_2310_3.raw"], ["Bin_S65_2310_4.raw"], ["Bin_S65_2311_1.raw"], ["Bin_S65_2311_2.raw"], ["Bin_S65_2311_3.raw"], ["Bin_S65_2311_4.raw"], ["Bin_S120_2360_1.raw", "P. Infestans infect,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "3149"], ["Bin_S120_2360_2.raw"], ["120 h"], ["Bin_S120_2360_3.raw"], ["Bin_S120_2360_4.raw"], ["Bin_S120_2361_1.raw"], ["Bin_S120_2361_2.raw"], ["Bin_S120_2361_3.raw"], ["Bin_S120_2361_4.raw"], ["Bin_S120_2362_1.raw"], ["Bin_S120_2362_2.raw"], ["Bin_S120_2362_3.raw"], ["Bin_S120_2362_4.raw"], ["Bin_S258_2411_1.raw", "P. Infestans infect,", "Bintje", "GelMS (4 lanes)", "Q Exactive", "3097"], ["Bin_S258_2411_2.raw", "258 h"], ["Bin_S258_2411_3.raw"], ["Bin_S258_2411_4.raw"], ["Bin_S258_2412_1.raw"], ["Bin_S258_2412_2.raw"], ["Bin_S258_2412_3.raw"], ["Bin_S258_2412_4.raw"], ["Kur_K4_1.raw", "Control,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3006"], ["Kur_K4_1b.raw", "4 h"], ["Kur_K4_2.raw"], ["Kur_K4_2b.raw"], ["Kur_K4_3.raw"], ["Kur_K4_3b.raw"], ["Kur_K4_4.raw"], ["Kur_K4_4b.raw"], ["Kur_K16_1.raw", "Control,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3004"], ["Kur_K16_1b.raw", "16 h"], ["Kur_K16_2.raw"], ["Kur_K16_2b.raw"], ["Kur_K16_3.raw"], ["Kur_K16_3b.raw"], ["Kur_K16_4.raw"], ["Kur_K16_4b.raw"], ["Kur_K65_1.raw", "Control,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3177"], ["Kur_K65_1b.raw", "65 h"], ["Kur_K65_2.raw"], ["Kur_K65_2b.raw"], ["Kur_K65_3.raw"], ["Kur_K65_3b.raw"], ["Kur_K65_4.raw"], ["Kur_K65_4b.raw"], ["Kur_K120_1.raw", "Control,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3144"], ["Kur_K120_1b.raw", "120 h"], ["Kur_K120_2.raw"], ["Kur_K120_2b.raw"], ["Kur_K120_3.raw"], ["Kur_K120_3b.raw"], ["Kur_K120_4.raw"], ["Kur_K120_4b.raw"], ["Kur_K258_1.raw", "Control,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3122"], ["Kur_K258_1b.raw", "258 h"], ["Kur_K258_2.raw"], ["Kur_K258_2b.raw"], ["Kur_K258_3.raw"], ["Kur_K258_3b.raw"], ["Kur_K258_4.raw"], ["Kur_K258_4b.raw"], ["Kur_S4_2231_1.raw", "P. Infestans infect,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3346"], ["Kur_S4_2231_2.raw"], ["Kur_S4_2231_3.raw", "4 h"], ["Kur_S4_2231_4.raw"], ["Kur_S4_2232_1.raw"], ["Kur_S4_2232_2.raw"], ["Kur_S4_2232_3.raw"], ["Kur_S4_2232_4.raw"], ["Kur_S4_2233_1.raw"], ["Kur_S4_2233_2.raw"], ["Kur_S4_2233_3.raw"], ["Kur_S4_2233_4.raw"], ["Kur_S16_2282_1.raw", "P. Infestans Infect,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3261"], ["Kur_S16_2282_2.raw"], ["16 h"], ["Kur_S16_2282_3.raw"], ["Kur_S16_2282_4.raw"], ["Kur_S16_2283_1.raw"], ["Kur_S16_2283_2.raw"], ["Kur_S16_2283_3.raw"], ["Kur_S16_2283_4.raw"], ["Kur_S16_2284_1.raw"], ["Kur_S16_2284_2.raw"], ["Kur_S16_2284_3.raw"], ["Kur_S16_2284_4.raw"], ["Kur_S65_2333_1.raw", "P. Infestans infect,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3370"], ["65 h"], ["Kur_S65_2333_2.raw"], ["Kur_S65_2333_3.raw"], ["Kur_S65_2333_4.raw"], ["Kur_S65_2334_1.raw"], ["Kur_S65_2334_2.raw"], ["Kur_S65_2334_3.raw"], ["Kur_S65_2334_4.raw"], ["Kur_S65_2335_1.raw"], ["Kur_S65_2335_2.raw"], ["Kur_S65_2335_3.raw"], ["Kur_S65_2335_4.raw"], ["Kur_S120_2384_1.raw", "P. Infestans infect,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3406"], ["120 h"], ["Kur_S120_2384_2.raw"], ["Kur_S120_2384_3.raw"], ["Kur_S120_2384_4.raw"], ["Kur_S120_2385_1.raw"], ["Kur_S120_2385_2.raw"], ["Kur_S120_2385_3.raw"], ["Kur_S120_2385_4.raw"], ["Kur_S120_2386_1.raw"], ["Kur_S120_2386_2.raw"], ["Kur_S120_2386_3.raw"], ["Kur_S120_2386_4.raw"], ["Kur_S258_2435_1.raw", "P. Infestans infect,", "Kuras", "GelMS (4 lanes)", "Q Exactive", "3414"], ["Kur_S258_2435_2.raw", "258 h"], ["Kur_S258_2435_3.raw"], ["Kur_S258_2435_4.raw"], ["Kur_S258_2436_1.raw"], ["Kur_S258_2436_2.raw"], ["Kur_S258_2436_3.raw"], ["Kur_S258_2436_4.raw"], ["Kur_S258_2437_1.raw"], ["Kur_S258_2437_2.raw"], ["Kur_S258_2437_3.raw"], ["Kur_S258_2437_4.raw"], ["Sar_K4_1.raw", "Control,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3096"], ["Sar_K4_1b.raw", "4 h"], ["Sar_K4_2.raw"], ["Sar_K4_2b.raw"], ["Sar_K4_3.raw"], ["Sar_K4_3b.raw"], ["Sar_K4_4.raw"], ["Sar_K4_4b.raw"], ["Sar_K16_1.raw", "Control,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "2880"], ["Sar_K16_1b.raw", "16 h"], ["Sar_K16_2.raw"], ["Sar_K16_2b.raw"], ["Sar_K16_3.raw"], ["Sar_K16_3b.raw"], ["Sar_K16_4.raw"], ["Sar_K16_4b.raw"], ["Sar_K65_1.raw", "Control,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3099"], ["Sar_K65_1b.raw", "65 h"], ["Sar_K65_2.raw"], ["Sar_K65_2b.raw"], ["Sar_K65_3.raw"], ["Sar_K65_3b.raw"], ["Sar_K65_4.raw"], ["Sar_K65_4b.raw"], ["Sar_K120_1.raw", "Control,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3092"], ["Sar_K120_1b.raw", "120 h"], ["Sar_K120_2.raw"], ["Sar_K120_2b.raw"], ["Sar_K120_3.raw"], ["Sar_K120_3b.raw"], ["Sar_K120_4.raw"], ["Sar_K120_4b.raw"], ["Sar_K258_1.raw", "Control,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3124"], ["Sar_K258_1b.raw", "258 h"], ["Sar_K258_2.raw"], ["Sar_K258_2b.raw"], ["Sar_K258_3.raw"], ["Sar_K258_3b.raw"], ["Sar_K258_4.raw"], ["Sar_K258_4b.raw"], ["Sar_S4_2240_1.raw", "P. Infestans infect,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3363"], ["Sar_S4_2240_2.raw"], ["4 h"], ["Sar_S4_2240_3.raw"], ["Sar_S4_2240_4.raw"], ["Sar_S4_2441_1.raw"], ["Sar_S4_2241_2.raw"], ["Sar_S4_2241_3.raw"], ["Sar_S4_2241_4.raw"], ["Sar_S4_2242_2.raw"], ["Sar_S4_2242_3.raw"], ["Sar_S4_2242_4.raw"], ["Sar_S4_2442_1.raw"], ["Sar_S16_2291_1.raw", "P. Infestans infect,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3361"], ["Sar_S16_2291_2.raw"], ["16 h"], ["Sar_S16_2291_3.raw"], ["Sar_S16_2291_4.raw"], ["Sar_S16_2292_1.raw"], ["Sar_S16_2292_2.raw"], ["Sar_S16_2292_3.raw"], ["Sar_S16_2292_4.raw"], ["Sar_S16_2293_1.raw"], ["Sar_S16_2293_2.raw"], ["Sar_S16_2293_3.raw"], ["Sar_S16_2293_4.raw"], ["Sar_S65_2342_1.raw", "P. Infestans infect,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3326"], ["Sar_S65_2342_2.raw", "65 h"], ["Sar_S65_2342_3.raw"], ["Sar_S65_2342_4.raw"], ["Sar_S65_2343_1.raw"], ["Sar_S65_2343_2.raw"], ["Sar_S65_2343_3.raw"], ["Sar_S65_2343_4.raw"], ["Sar_S65_2344_1.raw"], ["Sar_S65_2344_2.raw"], ["Sar_S65_2344_3.raw"], ["Sar_S65_2344_4.raw"], ["Sar_S120_2393_1.raw", "P. Infestans infect,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3389"], ["Sar_S120_2393_2.raw"], ["120 h"], ["Sar_S120_2393_3.raw"], ["Sar_S120_2393_4.raw"], ["Sar_S120_2394_1.raw"], ["Sar_S120_2394_2.raw"], ["Sar_S120_2394_3.raw"], ["Sar_S120_2394_4.raw"], ["Sar_S120_2395_1.raw"], ["Sar_S120_2395_2.raw"], ["Sar_S120_2395_3.raw"], ["Sar_S120_2395_4.raw"], ["Sar_S258_2444_1.raw", "P. Infestans infect,", "SarpoMira", "GelMS (4 lanes)", "Q Exactive", "3348"], ["Sar_S258_2444_2.raw"], ["258 h"], ["Sar_S258_2444_3.raw"], ["Sar_S258_2444_4.raw"], ["Sar_S258_2445_1.raw"], ["Sar_S258_2445_2.raw"], ["Sar_S258_2445_3.raw"], ["Sar_S258_2445_4.raw"], ["Sar_S258_2446_1.raw"], ["Sar_S258_2446_2.raw"], ["Sar_S258_2446_3.raw"], ["Sar_S258_2446_4.raw"]], "row_count": 309, "column_count": 6, "numeric_cells": 388, "header_rows": 0, "locator": "section[10]/table-wrap[1]#t0010"}}], "gaps": ["asset:data:geo:PXD002767 not downloaded", "asset:data:geo:PXD002767 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["PXD002767"], "resolved_accessions": ["PXD002767"], "statements": ["The proteomics raw data and MaxQuant result-files from the analysis have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD0002767 [11], [12], [13], [14], and can be downloaded directly (http://www.ebi.ac.uk/pride/archive/projects/PXD002767)."], "basis": "The paper names PXD002767 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:26862565", "data:geo:PXD002767", "asset:table:pmid:26862565:1", "asset:table:pmid:26862565:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002767"]}, "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": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 45016, "completion_tokens": 3221, "cached_tokens": 1808}}, "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:26862565", "type": "paper", "label": "pmid:26862565"}, {"id": "source:pmid:26862565", "type": "manuscript", "label": "PMID 26862565 full text"}, {"id": "data:geo:PXD002767", "type": "dataset", "label": "GEO PXD002767"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26862565", "type": "paper", "label": "pmid:26862565"}, {"id": "source:pmid:26862565", "type": "manuscript", "label": "PMID 26862565 full text"}, {"id": "data:geo:PXD002767", "type": "dataset", "label": "GEO PXD002767"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26862565", "type": "extraction", "used": ["source:pmid:26862565"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002767", "type": "accession_resolution", "used": ["data:geo:PXD002767"], "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:26862565", "parent_hash": "sha256:4291c91cae9cbab9ed1669b0f7ce9b9458c5179b2e61ee1f9d97e39377085207", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD002767 licence not read", "asset:data:geo:PXD002767 not downloaded", "execution.not_run", "method", "operations", "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": 0.83, "evidence": ["to leaf from three cultivars by quantitative proteomics.", "populations. We used label-free quantitative proteomics to investigate the infection with P. infesta"], "order_basis": "paper_text_order:69", "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":"2026-11-04T01:33:51+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}}}