{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23724367", "kind": "science-record", "revision": 3, "content_hash": "sha256:c7fb0b125985ca40e8f3a2806168a083e74bb3b0ef66e479e6d89281e4c63a3f", "created_at": "2026-11-01T15:40:03Z", "updated_at": "2026-11-01T18:46:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A possible approach for gel-based proteomic studies in recalcitrant woody plants.", "doi": "10.1186/2193-1801-2-210", "pmid": "23724367", "authors": ["Mónica Sebastiana", "Andreia Figueiredo", "Filipa Monteiro", "Joana Martins", "Catarina Franco", "Ana Varela Coelho", "Fátima Vaz", "Tânia Simões", "Deborah Penque", "Maria Salomé Pais", "Sílvia Ferreira"], "journal": "SpringerPlus", "year": 2013, "abstract": "Woody plants are particularly difficult to investigate due to high phenolic, resin, and tannin contents and laborious sample preparation. In particular, protein isolation from woody plants for two-dimensional gel electrophoresis (2-DE) is challenging as secondary metabolites negatively interfere with protein extraction and separation. In this study, three protein extraction protocols, using TCA, phenol and ethanol as precipitation or extraction agents, were tested in order to select the more efficient for woody recalcitrant plant gel-based proteomics. Grapevine leaves, pine needles and cork oak ectomycorrhizal roots were used to represent woody plant species and tissues. The phenol protocol produced higher quality 2-DE gels, with increased number of resolved spots, better spot focusing and representation of all molecular mass and isoelectric point ranges tested. In order to test the compatibility of the phenol extracted proteomes with protein identification several spots were excised from the phenol gels and analyzed by mass spectrometry (MALDI-TOF/TOF). Regardless the incomplete genome/protein databases for the plant species under analysis, 49 proteins were identified by Peptide Mass Fingerprint (PMF). Proteomic data have been deposited to the ProteomeXchange with identifier PXD000224. Our results demonstrate the complexity of protein extraction from woody plant tissues and the suitability of the phenol protocol for obtaining high quality protein extracts for efficient 2-DE separation and downstream applications such as protein identification by mass spectrometry.", "claims": [{"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository (Vizcaíno et al., 2013) with the dataset identifier PXD000224.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23724367", "locator": "sections[16] \"MS analysis and protein identification\" paragraph 3", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository (Vizcaíno et al., 2013) with the dataset identifier PXD000224."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The phenol extraction protocol produced the highest-quality 2-DE separation and was compatible with downstream MALDI-TOF/TOF protein identification; the study does not name a statistical method for comparing protocols. The source proteomics data were deposited in ProteomeXchange under identifier PXD000224.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:23724367", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The phenol protocol produced higher quality 2-DE gels, with increased number of resolved spots, better spot focusing and representation of all molecular mass and isoelectric point ranges tested."}, {"asset": "source:pmid:23724367", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Proteomic data have been deposited to the ProteomeXchange with identifier PXD000224."}, {"asset": "source:pmid:23724367", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Our results demonstrate the complexity of protein extraction from woody plant tissues and the suitability of the phenol protocol for obtaining high quality protein extracts for efficient 2-DE separation and downstream applications such as protein identification by mass spectrometry."}, {"asset": "source:pmid:23724367", "locator": "sections[2] \"Results\" paragraph 2", "quote": "In ECM oak roots, both TCA-acetone and ethanol produced a significantly lower amount of spots when compared with the phenol protocol (904), with ethanol producing 111 spots and TCA-acetone only 36 spots."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The phenol extraction protocol produced the highest-quality 2-DE separation and was compatible with downstream MALDI-TOF/TOF protein identification; the study does not name a statistical method for comparing protocols. The source proteomics data were deposited in ProteomeXchange under identifier PXD000224.", "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:23724367"], "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:PXD000224"], "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:PXD000224"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:23724367", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/2193-1801-2-210", "sha256": "sha256:d8f0ee1b504ebc9fd5e3ddeeebea06b9903dd8b6447919870de5b36db49fbf1d", "bytes": 36138, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/2193-1801-2-210", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3663981", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000224", "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=PXD000224", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000224", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository (Vizcaíno et al., 2013) with the dataset identifier PXD000224.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository (Vizcaíno et al., 2013) with the dataset identifier PXD000224.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Protein extraction in recalcitrant plant species", "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:23724367:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f24ca2b37c22a4d8f8600bdf2b0df40a325a006d6f972d911fe33034e2649376", "bytes": 752, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#Tab1", "version": null, "note": "Protein yields and total number of 2-DE protein spots, from grape leaves, pine needles, and cork oak ectomycorrhizal ECM roots after phenol, ethanol and TCA-acetone extraction protocols", "structure": {"pmcid": "PMC3663981", "section_index": 2, "section_title": "Results", "row_count": 10, "column_count": 4}, "table": {"label": "Table 1", "caption": "Protein yields and total number of 2-DE protein spots, from grape leaves, pine needles, and cork oak ectomycorrhizal ECM roots after phenol, ethanol and TCA-acetone extraction protocols", "rows": [["Plant species", "Protocol", "Protein yield (mg/g FW)a", "Total number of spots"], ["Pine", "Phenol", "5.81 ± 0.46", "805"], ["Ethanol", "21.88 ± 4.00", "392"], ["TCA-acetone", "13.86 ± 1.14", "657"], ["Grapevine", "Phenol", "3.78 ± 0.61", "532"], ["Ethanol", "20.55 ± 1.79", "166"], ["TCA-acetone", "16.57 ± 1.31", "362"], ["Oak", "Phenol", "0.61 ± 0.14", "904"], ["Ethanol", "3.57 ± 0.20", "111"], ["", "TCA-acetone", "2.77 ± 0.14", "36"]], "row_count": 10, "column_count": 4, "numeric_cells": 18, "header_rows": 1, "locator": "section[2]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:23724367:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5350cdff8fa9dd229edabc680ea3027db3eeebaf1c5f792d35c7533bada20b1e", "bytes": 8918, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#Tab2", "version": null, "note": "Protein annotation in the grapevine fully developed leaves (V1-V15), cork oak ectomycorrhizal roots (S1-S20) and pine needles (P1-P14) spots excised from 2-DE gels and trypsin-digested", "structure": {"pmcid": "PMC3663981", "section_index": 2, "section_title": "Results", "row_count": 194, "column_count": 7}, "table": {"label": "Table 2", "caption": "Protein annotation in the grapevine fully developed leaves (V1-V15), cork oak ectomycorrhizal roots (S1-S20) and pine needles (P1-P14) spots excised from 2-DE gels and trypsin-digested", "rows": [["Spot", "Protein ID", "Annotation", "Score", "Search engine", "Protein score", "Sequence of the distinct fragmented peptides (p < 0,05)"], ["V1", "8615601", "cyclase [Vitis pseudoreticulata]", "532", "ProteinPilot", "14", "EFESDYAGFTEDGAR"], ["EVILVESLK"], ["KEFESDYAGFTEDGAR"], ["LDDVPAGMYNVHCLHLR"], ["LPGAEGAPIR"], ["SEAYPSAYGSGSCNVELIPVKR"], ["WLVENTDIK"], ["EFESDYAGFTEDGAR"], ["GPALLVDAPR"], ["LPGAEGAPIR"], ["V2", "49388156", "putative chlorophyll a/b-binding protein type III precursor [Oryza sativa Japonica Group]", "270", "ProteinPilot", "10.67", "FQDWANPGSMGK"], ["QGADRPLWFASK"], ["QSLTYLDGSLPGDYGFDPLGLSDPEGTGGFIEPR"], ["QYFLGLEK"], ["WLAYGEVINGR"], ["RFQDWANPGSMGK"], ["LKEVKNGR"], ["QGADRPLWFASK"], ["QYFLGLEK"], ["RFQDWANPGSMGK"], ["WLAYGEVINGR"], ["V3", "225446775", "oxygen-evolving enhancer protein 2, chloroplastic [Vitis vinifera]", "449", "ProteinPilot", "2.13", "SITDYGSPEEFLSK"], ["TNTDFLPYNGEGFK"], ["EFPGQVLR"], ["V4", "73647738", "ascorbate peroxidase [Vitis pseudoreticulata]", "", "ProteinPilot", "9.32", "ALLSDPAFRPLVEK"], ["EDKPEPPPEGR"], ["NCAPIMLR"], ["SYPTVSEEYKK"], ["TGGPFGTMK"], ["EDKPEPPPEGR"], ["NCAPIMLR"], ["V5", "349048", "ribulose-1,5-bisphosphate carboxylase/oxygenase large subunit, partial (chloroplast) [Pogostemon cablin]", "", "MASCOT", "121.49", "TFKGPPHGIQVER"], ["V6", "225460496", "PREDICTED: ATP synthase delta chain, chloroplastic [Vitis vinifera]", "", "MASCOT", "154.41", "LESEHLAQIAK"], ["TAIDPSLVAGFTIR"], ["EIAKEFELVYNR"], ["V7", "225461287", "PREDICTED: cytochrome b6-f complex iron-sulfur subunit, chloroplastic isoform 1 [Vitis vinifera]", "", "MASCOT", "234.97", "GDPTYLVVENDK"], ["DALGNDVIADEWLK"], ["FICPCHGSQYNNQGR"], ["V8", "22797822", "ATP synthase epsilon subunit [Vitis vinifera]", "", "MASCOT", "258.01", "TRVEAINVTS"], ["QIIEANLALR"], ["IGNNEITVLVNDAEK"], ["LNDQWLTMALMGGFAR"], ["V9", "359475330", "PREDICTED: glycine-rich RNA-binding protein GRP1A-like [Vitis vinifera]", "", "MASCOT", "313.75", "DRGYGDGGSR"], ["NITVNEAQSR"], ["AFSQFGEILESK"], ["GGGGGYGGGGGGYGGGSR"], ["GFGFVTFSSEQSMR"], ["CFVGGLAWATDDQSLER"], ["V10", "225468761", "oxygen-evolving enhancer protein 1, chloroplastic [Vitis vinifera]", "610", "MASCOT", "984.17", "VPFLFTIK"], ["RLTYDEIQSK"], ["FGGEFLVPSYR"], ["FCLEPTSFTVK"], ["KFCLEPTSFTVK"], ["DGIDYAAVTVQLPGGER"], ["GTGTANQCPTIDGGVDSFAFK"], ["FEEKDGIDYAAVTVQLPGGER"], ["SKPETGEVIGVFESIQPSDTDLGAK"], ["V11", "225459768", "plastocyanin, chloroplastic isoform 1 [Vitis vinifera]", "331", "MASCOT", "453.18", "GTYSFYCSPHQGAGMVGK"], ["ISMSEEDLLNAPGEVYSVTLTEK"], ["NNAGFPHNVVFDEDEVPSGVDVSK"], ["V12", "30687535", "Quinone reductase family protein [Arabidopsis thaliana]", "393", "MASCOT", "62.96", "AFLDATGGLWR"], ["V13", "225456238", "PREDICTED: glutamine synthetase cytosolic isozyme 1[Vitis vinifera]", "", "MASCOT", "183.79", "VIVEYIWVGGSGMDLR"], ["GNNILVMCDTYTPAGEPIPTNKR"], ["V14", "359473178", "Quinone oxidoreductase-like protein At1g23740, chloroplastic-like [Vitis vinifera]", "612", "MASCOT", "460.41", "VKPVVDPK"], ["LNPYLESGK"], ["KLNPYLESGK"], ["VVAAALNPVDAK"], ["AWVYGDYGGVDVLK"], ["QFGSFAEYTAVEEK"], ["EGGSVVALTGAVTPPGFR"], ["ELKEGDEVYGDINEK"], ["ATDSPLPTVPGYDVAGVVVK"], ["V15", "225432496", "PREDICTED: glutamine synthetase leaf isozyme, chloroplastic [Vitis vinifera]", "", "MASCOT", "349.06", "DISDAHYK"], ["AAEIFGNKK"], ["EHISAYGEGNER"], ["TISKPVEHPSELPK"], ["HKEHISAYGEGNER"], ["HETANINTFSWGVANR"], ["GGNNILVICDSYTPAGEPIPTNKR"], ["S1", "4838443", "symbiosis regulated acidic polypeptide SRAP32-3 [Pisolithus tinctorius]", "", "Protein Pilot", "4", "DKLEAKLDKAAGDYIDGVDI"], ["TDVANSLEFASR"], ["S2", "160897637", "hypothetical protein Daci_2194 [Delftia acidovorans SPH-1]", "", "MASCOT", "59.58", "ERAQSAAAIER"], ["S3", "71659717", "hypothetical protein [Trypanosoma cruzi strain CL Brener]", "", "MASCOT", "58.93", "KDIAEEVLER"], ["S4", "20162432", "AF493154_1 32 kDa-cell wall symbiosis regulated acidic polypeptide [Pisolithus microcarpus]", "", "MASCOT", "80.35", "NDPLYSEAEK"], ["S5", "71659717", "hypothetical protein [Trypanosoma cruzi strain CL Brener]", "", "MASCOT", "57", "KDIAEEVLER"], ["S6", "20162434", "32 kDa-cell wall symbiosis regulated acidic polypeptide precursor [Pisolithus microcarpus]", "358", "MASCOT", "210.62", "ATGDDYAR"], ["NSLEFAAR"], ["FQLAVCSEK"], ["AADKATGDDYAR"], ["S7", "390601324", "cysteine peroxiredoxin [Punctularia strigosozonata HHB-11173SS5]", "391", "MASCOT", "334.84", "NFDEVLR"], ["TVFVIDPK"], ["LTISYPASTGR"], ["VVDSLQLGDKYR"], ["LGSIAPDFEAETTAGPIK"], ["ISTLYDMLDEQDATNR"], ["S8", "225461209", "PREDICTED: flavoprotein wrbA isoform 1 [Vitis vinifera]", "", "MASCOT", "383.52", "GAASVEGVEAK"], ["KGAASVEGVEAK"], ["AFLDATGGLWR"], ["GGSPYGAGTFAGDGSR"], ["VKGGSPYGAGTFAGDGSR"], ["VYIVYYSMYGHVEK"], ["S9", "20097", "jgi|Pisti1|20097|gm1.2716_g", "", "MASCOT", "54.44", "NPDIQAPR"], ["S10", "218533914", "serine proteinase inhibitor [Clitocybe nebularis]", "50.1", "MASCOT", "119.09", "AQEWVIR"], ["YRELQDAYTIVK"], ["S11", "20097", "jgi|Pisti1|20097|gm1.2716_g", "", "MASCOT", "302.72", "VFAVMEGR"], ["LDEPGEIGWIAPTDGSSQIR"], ["RLDEPGEIGWIAPTDGSSQIR"], ["EIPTAPPGQYRPEELYNLAFPLE"], ["S12", "218533914", "serine proteinase inhibitor [Clitocybe nebularis]", "50.1", "MASCOT", "89.1", "AQEWVIR"], ["ELQDAYTIVK"], ["YRELQDAYTIVK"], ["S13", "20097", "jgi|Pisti1|20097|gm1.2716_g", "", "MASCOT", "343.22", "LDEPGEIGWIAPTDGSSQIR"], ["RLDEPGEIGWIAPTDGSSQIR"], ["EIPTAPPGQYRPEELYNLAFPLE"], ["S14", "33323059", "major latex protein [Ficus pumila var. awkeotsang]", "187", "MASCOT", "485.65", "GIDEHITKA"], ["LREDVPAPDK"], ["EKVEYDDANR"], ["SPPEKYYNIFK"], ["SATLIGVDGDIMQEYK"], ["GQAYHVPNAAPDHIQGVDVHEGDWETHGSVK"], ["S15", "3164115", "major latex-like protein [Rubus idaeus]", "", "MASCOT", "68.2", "EKVELDDVNK"], ["S16", "Q9S1X8", "Na(+)/H(+) antiporter NhaA 1/4[Streptomyces coelicolor strain ATCC BAA-471/A3(2)/M145]", "", "MASCOT", "483.67", "NDAYVIAK"], ["EEREEER"], ["GVGWVAPSPENK"], ["VGECTYVISAR"], ["SVTEPPTFNMEK"], ["KSVTEPPTFNMEK"], ["GVGWVAPSPENKEER"], ["S17", "375333787", "lectin 2 [Agrocybe aegerita]", "565", "MASCOT", "647.19", "FLGEATGDGR"], ["FVVDLTGDGR"], ["DFAYSAGGWR"], ["DGFSIQPFVAIK"], ["ADIVGFGDGGVLVSK"], ["SVIDNFTYSAGGWR"], ["FVLNNFGVQQGWQVNK"], ["NTGGGNFSPASLALNDFGYNAGGWR"], ["S18", "392590852", "phosphoglycerate mutase-like protein [Coniophora puteana]", "540", "MASCOT", "431.54", "VYASPEFK"], ["DIGGIGNLPGR"], ["TAQPFFGAIR"], ["LPPTLIEQAR"], ["GPAPEDRDFLR"], ["ADIPLTEFFYR"], ["SVYLSPSSPSYITNMK"], ["S19", "160184939", "Serine protease inhibitor [Lentinula edodes (Shiitake mushroom)]", "58.9", "MASCOT", "106.97", "WCIQYTER"], ["VGDCTYVISAR"], ["S20", "1001331", "jgi|Pisti1|1001331|fgenesh1_kg.33_#_73_#_Locus10529v3rpkm0.40_PRE", "", "MASCOT", "205.69", "YYINYLIER"], ["WIITFVPQPGR"], ["NNLLYEQVTAPQK"], ["P1", "332591479", "phosphoglycerate kinase 1 [Pinus pinaster]", "", "MASCOT", "260.9", "AHASTEGVTK"], ["LTELLGVNVVK"], ["ELDYLVGAVSNPK"], ["ADLNVPLDENQNITDDTR"], ["P2", "396547", "glutamate-ammonia ligase [Pinus sylvestris]", "", "MASCOT", "134.75", "SLSGPVSSVK"], ["VIAEYIWIGGSGMDMR"], ["P3", "218155", "chloroplastic aldolase [Oryza sativa Japonica Group]", "", "MASCOT", "129.98", "EAAWGLAR"], ["AKANSLAQLGK"], ["LASIGLENTEANR"], ["P4", "3415126", "phenylcoumaran benzylic ether reductase [Pinus taeda]", "", "MASCOT", "497.86", "VVILGDGNAR"], ["SLAQAGLTAPPR"], ["ILLIGATGYIGR"], ["DKVVILGDGNAR"], ["ASLDLGHPTFLLVR"], ["FFPSEFGNDVDNVHAVEPAK"], ["GDQTNFEIGPAGVEASQLYPDVK"], ["AIEAEGIPYTYVSSNCFAGYFLR"], ["P5", "413951269", "ferredoxin-NADP reductase, leaf isozyme [Zea mays]", "768", "MASCOT", "388.09", "KDNTYVYMCGLK"], ["RLVYTNDQGEIVK"], ["LYSIASSALGDFGDSK"], ["ITGDDAPGETWHMVFSTEGEIPYR"], ["P6", "359473184", "carbonic anhydrase, chloroplastic-like isoform 2 [Vitis vinifera]", "299", "MASCOT", "109.34", "FMVVACADSR"], ["QTAFIEDWIK"], ["P7", "359473184", "carbonic anhydrase, chloroplastic-like isoform 2 [Vitis vinifera]", "299", "MASCOT", "107.77", "FMVVACADSR"], ["QTAFIEDWIK"], ["P8", "14719331", "putative 3-beta hydroxysteroid dehydrogenase/isomerase protein [Oryza sativa]", "496", "MASCOT", "245.13", "MKPGFDPSK"], ["IGGGDDVFVGDIR"], ["AEQYLADSGLPYTIIR"], ["KAEQYLADSGLPYTIIR"], ["P9", "116790330", "unknown [Picea sitchensis]", "", "MASCOT", "104.32", "TTFLSDSEVK"], ["TTFLSDSEVKR"], ["P10", "116782111", "unknown [Picea sitchensis]", "", "MASCOT", "220.45", "EYYNISVLTR"], ["YEDNGDTVSNVSVMVIPTDKK"], ["P11", "16798638", "AF434186_1 Cu-Zn-superoxide dismutase precursor [Pinus pinaster]", "", "MASCOT", "234.71", "LTHGAPEDDVR"], ["KLTHGAPEDDVR"], ["GGHELSLTTGNAGGR"], ["GNSQVEGVVNLSQEDNGPTTVK"], ["P12", "2911276", "LMW heat shock protein [Fragaria x ananassa]", "103", "MASCOT", "105.95", "QPEPQPPQPK"], ["ASMEDGVLTVTVPK"], ["P13", "413946843", "Putative peptidyl-prolyl cis-trans isomerase family protein [Zea mays]", "307", "MASCOT", "138.86", "TFEDENFK"], ["KLESEETNR"], ["IVLGLFGEDVPK"], ["P14", "20794", "Type III chlorophyll a/b-binding protein [Pinus sylvestris]", "259", "MASCOT", "268.1", "LQDYRNPGSMGK"], ["YLGGSGNPAYPGGPLFNPLGFGK"], ["", "YLGGSGNPAYPGGPLFNPLGFGKDEK"]], "row_count": 194, "column_count": 7, "numeric_cells": 166, "header_rows": 1, "locator": "section[2]/table-wrap[2]#Tab2"}}], "gaps": ["asset:data:geo:PXD000224 not downloaded", "asset:data:geo:PXD000224 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": ["PXD000224"], "resolved_accessions": ["PXD000224"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository (Vizcaíno et al., 2013) with the dataset identifier PXD000224."], "basis": "The paper names PXD000224 in ProteomeXchange Consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:23724367", "data:geo:PXD000224", "asset:table:pmid:23724367:1", "asset:table:pmid:23724367:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000224"]}, "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": "2026-10-31T18:21:24Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 71014, "completion_tokens": 4021, "cached_tokens": 45012}}, "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:23724367", "type": "paper", "label": "pmid:23724367"}, {"id": "source:pmid:23724367", "type": "manuscript", "label": "PMID 23724367 full text"}, {"id": "data:geo:PXD000224", "type": "dataset", "label": "GEO PXD000224"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23724367", "type": "paper", "label": "pmid:23724367"}, {"id": "source:pmid:23724367", "type": "manuscript", "label": "PMID 23724367 full text"}, {"id": "data:geo:PXD000224", "type": "dataset", "label": "GEO PXD000224"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23724367", "type": "extraction", "used": ["source:pmid:23724367"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000224", "type": "accession_resolution", "used": ["data:geo:PXD000224"], "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:23724367", "parent_hash": "sha256:08edba944ac18e8ce3648b922cea27b9cae96afe425a74b7c15a0092e5cbf128", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD000224 licence not read", "asset:data:geo:PXD000224 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": 0.99, "evidence": ["A possible approach for gel-based proteomic studies in recalcitrant woody plants.", "cient for woody recalcitrant plant gel-based proteomics. Grapevine leaves, pine needles and cork oak", "dentified by Peptide Mass Fingerprint (PMF). Proteomic data have been deposited to the ProteomeXcha", "excised from the phenol gels and analyzed by mass spectrometry (MALDI-TOF/TOF). Regardless the incomplete g"], "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":"2026-11-04T03:01:53+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}}}