{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29450146", "kind": "science-record", "revision": 6, "content_hash": "sha256:693c1b8d58394c50ab55f8f42e1689b76321aac872a3dc9d4afb5d49b0b46412", "created_at": "2026-11-01T15:40:31Z", "updated_at": "2026-11-01T21:21:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Novel proteins from proteomic analysis of the trunk disease fungus Lasiodiplodia theobromae (Botryosphaeriaceae).", "doi": "10.1016/j.biopen.2017.03.001", "pmid": "29450146", "authors": ["Carla C Uranga", "Majid Ghassemian", "Rufina Hernández-Martínez"], "journal": "Biochimie open", "year": 2017, "abstract": "Many basic science questions remain regarding protein functions in the pathogen: host interaction, especially in the trunk disease fungi family, the Botryosphaeriaceae, which are a global problem for economically important plants, especially fruiting trees. Proteomics is a highly useful technology for studying protein expression and for discovering novel proteins in unsequenced and poorly annotated organisms. Current fungal proteomics approaches involve 2D SDS-PAGE and extensive, complex, protein extraction methodologies. In this work, a modified Folch extraction was applied to protein extraction to perform both de novo peptide sequencing and peptide fragmentation analysis/protein identification of the plant and human fungal pathogen Lasiodiplodia theobromae. Both bioinformatics approaches yielded novel peptide sequences from proteins produced by L. theobromae in the presence of exogenous triglycerides and glucose. These proteins and the functions they may possess could be targeted for further functional characterization and validation efforts, due to their potential uses in biotechnology and as new paradigms for understanding fungal biochemistry, such as the finding of allergenic enolases, as well as various novel proteases, including zinc metalloproteinases homologous to those found in snake venom. This work contributes to genomic annotation efforts, which, hand in hand with genomic sequencing, will help improve fungal bioinformatics databases for future studies of Botryosphaeriaceae. All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283. This is the first study of its kind in Botryosphaeriaceae.", "claims": [{"id": "claim-method", "statement": "The software Cytoscape [42] with the BiNGO plugin [43] was used for GO and enrichment analysis using up-to-date databases, applying a hypergeometric test with a significance level (p-value) < 0.05, as well as a Benjamini and Hochberg false discovery rate (FDR) correction.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29450146", "locator": "sections[5] \"Protein identification\" paragraph 6", "quote": "The software Cytoscape [42] with the BiNGO plugin [43] was used for GO and enrichment analysis using up-to-date databases, applying a hypergeometric test with a significance level (p-value) < 0.05, as well as a Benjamini and Hochberg false discovery rate (FDR) correction."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29450146", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used a hypergeometric test with Benjamini–Hochberg false-discovery-rate correction for gene-ontology enrichment analysis, and the source data—including raw data—were deposited in ProteomeXchange under identifier PXD005283.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29450146", "locator": "sections[5] \"Protein identification\" paragraph 6", "quote": "Gene ontology (GO) analysis of enriched proteins was done on all those hits obtained from the Uniprot database [33]. The software Cytoscape [42] with the BiNGO plugin [43] was used for GO and enrichment analysis using up-to-date databases, applying a hypergeometric test with a significance level (p-value) < 0.05, as well as a Benjamini and Hochberg false discovery rate (FDR) correction."}, {"asset": "source:pmid:29450146", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used a hypergeometric test with Benjamini–Hochberg false-discovery-rate correction for gene-ontology enrichment analysis, and the source data—including raw data—were deposited in ProteomeXchange under identifier PXD005283.", "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:29450146"], "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:PXD005283"], "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:PXD005283"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29450146", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.biopen.2017.03.001", "sha256": "sha256:f48a6d16699c1c02de76ad7c96b6b3c76b241a440f82f451f3171a6f83ba791d", "bytes": 41024, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.biopen.2017.03.001", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5802045", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD005283", "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=PXD005283", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD005283", "version": null, "note": "All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "A novel protein extraction method for proteomics of the trunk disease fungus Lasiodiplodia theobromae (Botryosphaeriaceae)", "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:29450146:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cd92fd8db37b490cc33c95172e9b83d272cce13bb882a53265a6310f8d14014b", "bytes": 2359, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#tbl1", "version": null, "note": "Proteins identified as “hypothetical” by the MSGF, X! Tandem and OMSSA algorithms, further searched with NCBI BLAST. The top-scoring homologous protein is reported for each search in the last column.", "structure": {"pmcid": "PMC5802045", "section_index": 7, "section_title": "Results and discussion", "row_count": 10, "column_count": 8}, "table": {"label": "Table 1", "caption": "Proteins identified as “hypothetical” by the MSGF, X! Tandem and OMSSA algorithms, further searched with NCBI BLAST. The top-scoring homologous protein is reported for each search in the last column.", "rows": [["Main accession", "Description", "Coverage [%]", "Spectrum counting", "#Validated unique", "Confidence [%]", "Validation", "Homologous protein sequence (BLAST)"], ["407929156", "Hypothetical protein MPH_00684 [Macrophomina phaseolina MS6]", "6.0", "30.1", "2", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative protein mitochondrial targeting protein XM_007580308.1"], ["407928922", "Hypothetical protein MPH_00885 [Macrophomina phaseolina MS6]", "17.1", "228.8", "3", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative phosphotransmitter protein ypd1 protein XM_007584095.1"], ["407927556", "Hypothetical protein MPH_02256 [Macrophomina phaseolina MS6]", "9.1", "124.1", "4", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative nuclear and cytoplasmic polyadenylated rna-binding protein pub1 protein mRNA, XM_007585675.1"], ["407923581", "Hypothetical protein MPH_06104 [Macrophomina phaseolina MS6]", "11.6", "108.6", "2", "100", "Confident", "Sphaerulina musiva SO2202 GTP-binding protein mRNA XM_016910103.1"], ["407922440", "Hypothetical protein MPH_07279 [Macrophomina phaseolina MS6]", "9.9", "242.1", "2", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative fk506-binding protein, XM_007581103.1"], ["407921582", "Hypothetical protein MPH_07998 [Macrophomina phaseolina MS6]", "4.9", "11.8", "2", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative transcription factor (snd1 p100) protein, XM_007582992.1"], ["407921297", "Hypothetical protein MPH_08297 [Macrophomina phaseolina MS6]", "12.3", "74.8", "3", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative g-protein complex beta subunit protein XM_007582859.1"], ["407920925", "Hypothetical protein MPH_08717 [Macrophomina phaseolina MS6]", "23.4", "128.1", "7", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative glycolipid transfer protein het-c2 protein XM_007581974.1"], ["407916430", "Hypothetical protein MPH_13123 [Macrophomina phaseolina MS6]", "21.2", "581.6", "4", "100", "Confident", "Neofusicoccum parvum UCRNP2 putative surface protein 1 protein XM_007588394.1"]], "row_count": 10, "column_count": 8, "numeric_cells": 63, "header_rows": 1, "locator": "section[7]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:29450146:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d42842e756b7ec1f0b1fa31c726e7d63add29dd89a140e47379858fb274bc99f", "bytes": 6728, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#tbl2", "version": null, "note": "Novel de novo peptide sequences from the Novor and PepNovo algorithms and BLASTp search results using an all-Uniprot database of the peptidome from Lasiodiplodia theobromae incubated in 5% grapeseed oil + 5% glucose for 20 days, showing the most probable homolog.", "structure": {"pmcid": "PMC5802045", "section_index": 7, "section_title": "Results and discussion", "row_count": 32, "column_count": 8}, "table": {"label": "Table 2", "caption": "Novel de novo peptide sequences from the Novor and PepNovo algorithms and BLASTp search results using an all-Uniprot database of the peptidome from Lasiodiplodia theobromae incubated in 5% grapeseed oil + 5% glucose for 20 days, showing the most probable homolog.", "rows": [["Query sequence", "Peptide Score", "m/z", "Charge", "E-value", "Uniprot ID", "Organism", "Protein name"], ["ELGFLASLGWNAPPAFPGPELTALDKLSAALSNR", "28.7", "1175.2", "3+", "2", "Q8T9W1", "Dictyostelium discoideum (Slime mold)", "Serine protease/ABC transporter B family protein tagD (EC 3.4.21.-) (Serine protease/ABC transporter tagD)"], ["DDGSMDTCEDDGAGR", "43.1", "808.8", "2+", "8.6", "Q7RTY9", "Homo sapiens (Human)", "Serine protease 41 (EC 3.4.21.-) (Testis serine protease 1) (TESSP-1)"], ["QETSVPGDSQATLDALNEWR", "66.5", "739.7", "3+", "1.6", "Q10749", "Naja mossambica (Mozambique spitting cobra)", "Snake venom metalloproteinase-disintegrin-like mocarhagin (MOC) (Mocarhagin-1) (SVMP) (EC 3.4.24.-) (Zinc metalloproteinase)"], ["LLGTAMHVAGHLCAMMGWYRLTPSLHK", "17.0", "1033.8", "3+", "4.6", "J3RY93", "Crotalus adamanteus", "Snake venom serine proteinase 12 (SVSP) (EC 3.4.21.-)"], ["WLSAKGWAQGVAEGPGDPR", "35.9", "991.5", "2+", "7.7", "P0DL42", "Daboia siamensis (Eastern Russel's viper)", "Snake venom vascular endothelial growth factor toxin VR-1' (svVEGF) (VEGF-F)"], ["DYPPVLEHLLAWEEEQR", "19.0", "708.7", "3+", "7", "B2MVK7", "Rhynchium brunneum (Potter wasp)", "Venom allergen 5 (Antigen 5) (Cysteine-rich venom protein) (CRVP)"], ["VLTVKGSCNLTMLVSFWTFSGNLTNGASTGSHK", "37.4", "1172.3", "3+", "5.7", "C0ITL3", "Pachycondyla chinensis (Asian needle ant)", "Venom allergen 5 (Antigen 5) (Cysteine-rich venom protein) (CRVP) (allergen Pac c 3) (Fragment)"], ["MLPAFLVDVHHSKKVGVPPNYYYQHSK", "15.10", "793.4", "4+", "7.1", "P83370", "Hoplocephalus stephensii (Stephens' banded snake)", "Venom prothrombin activator hopsarin-D (vPA) (EC 3.4.21.6) (Venom coagulation factor Xa-like protease) [Cleaved into: Hopsarin-D light chain; Hopsarin-D heavy chain]"], ["APTPALDGGKLMFVSAK", "38.6", "568.3", "3+", "0.63", "Q5WFT5", "Bacillus clausii (strain KSM-K16)", "Zinc metalloprotease RasP (EC 3.4.24.-) (Regulating alternative sigma factor protease) (Regulating anti-sigma-W factor activity protease)"], ["LASHKPNCFLAPPLGTHDVVPK", "34.5", "800.1", "3+", "6", "B8K1W0", "Daboia russelii (Russel's viper) (Vipera russelii)", "Zinc metalloproteinase-disintegrin-like daborhagin-K (EC 3.4.24.-) (Haemorrhagic metalloproteinase russelysin) (Snake venom metalloproteinase) (SVMP)"], ["VDSDFTVGLAAQWAETDLYK", "49.3", "743.7", "3+", "7", "C5H5D6", "Lachesis muta rhombeata (Bushmaster)", "Zinc metalloproteinase-disintegrin-like lachestatin-2 (EC 3.4.24.-) (Snake venom metalloprotease) (SVMP) (Vascular apoptosis-inducing protein-like) (VAP-like)"], ["YGMKWSLLMLAAGGGR", "54.8", "863.9", "2+", "5.4", "Q5XJ13", "Danio rerio (Zebrafish) (Brachydanio rerio)", "Ankyrin repeat and SAM domain-containing protein 6 (Ankyrin repeat domain-containing protein 14) (SamCystin)"], ["LMAAWGQNPGQAALYVEWNPEVMSAVWK", "37.10", "1054.8", "3+", "1.2", "Q68DC2", "Homo sapiens (Human)", "Ankyrin repeat and SAM domain-containing protein 6 (Ankyrin repeat domain-containing protein 14) (SamCystin)"], ["LGAKWCHHCFAVPMK", "19.9", "929.4", "2+", "0.95", "Q6S8J3", "Homo sapiens (Human)", "POTE ankyrin domain family member E (ANKRD26-like family C member 1A) (Prostate, ovary, testis-expressed protein on chromosome 2) (POTE-2)"], ["ALKGFYLMNPPAPVWWTR", "49.6", "716.4", "3+", "5.6", "B8I4B9", "Clostridium cellulolyticum", "ATP-dependent zinc metalloprotease FtsH (EC 3.4.24.-)"], ["LAAPNPYLWWHDLVPR", "40.5", "974.5", "2+", "6.7", "Q2EEX7", "Helicosporidium sp. subsp. Simulium jonesii", "ATP-dependent zinc metalloprotease FtsH homolog"], ["ELKAKKVGAMDVASSEFYK", "52.7", "701.04", "3+", "1.5", "P30575", "Candida albicans", "Enolase 1 (EC 4.2.1.11) (2-phospho-d-glycerate hydro-lyase) (2-phosphoglycerate dehydratase)"], ["TLVAGFFFLAASLTCLLVPSEAPTFSETTR", "45.0", "812.4", "4+", "1.8", "Q9HDT3", "Alternaria alternata", "Enolase (EC 4.2.1.11) (2-phospho-d-glycerate hydro-lyase) (2-phosphoglycerate dehydratase) (Allergen Alt a 11) (Allergen Alt a 5) (Allergen Alt a XI)"], ["ELGAHTLGFLESNPKFDPGSYEQLADLYK", "53.2", "1080.5", "3+", "1.7", "Q96X30", "Neosartorya fumigata (Aspergillus fumigatus)", "Enolase (EC 4.2.1.11) (2-phospho-d-glycerate hydro-lyase) (2-phosphoglycerate dehydratase) (allergen Asp f 22)"], ["HCLAAVPCMGQSPAAAALLNSSEVQNMAMGFK", "40.4", "1025.5", "2+, 3+, 4+", "1.6", "Q59121", "Arcanobacterium haemolyticum", "Phospholipase D (EC 3.1.4.4) (Choline phosphatase) (PLD-A)"], ["VFRLKDSGNSKPDKAAPPPGPLPR", "29.2", "848.8", "3+", "8.3", "O14939", "Homo sapiens (Human)", "Phospholipase D2 (PLD 2) (hPLD2) (EC 3.1.4.4) (Choline phosphatase 2) (PLD1C) (Phosphatidylcholine-hydrolyzing phospholipase D2)"], ["LHMGTDCAELDCVRSAPK", "33.2", "687.3", "3+", "4.5", "Q9LI83", "Arabidopsis thaliana (Mouse-ear cress)", "Phospholipid-transporting ATPase 10 (AtALA10) (EC 3.6.3.1) (Aminophospholipid flippase 10)"], ["DLADALKAAMGAPKHAVDHVAEPMDVAQLAPGNK", "36.9", "867.7", "4+", "4.2", "P06681", "Homo sapiens (Human)", "Complement C2 (EC 3.4.21.43) (C3/C5 convertase) [Cleaved into: Complement C2b fragment; Complement C2a fragment]"], ["NTLHAPEGTVVHLNAHK", "54.2", "919.5", "2+", "8.7", "P98094", "Eptatretus burgeri (Inshore hagfish)", "Complement C3 [Cleaved into: Complement C3 beta chain; Complement C3 alpha chain; C3a anaphylatoxin; Complement C3 gamma chain] (Fragment)"], ["HNDRCPCMCNCQNDDCRCDTSNVPAK", "16.2", "825.8", "4+", "6.3", "Q00685", "Lethenteron camtschaticum (Japanese lamprey) (Lampetra japonica)", "Complement C3 [Cleaved into: Complement C3 beta chain; Complement C3 alpha chain; C3a anaphylatoxin; Complement C3 gamma chain] (Fragment)"], ["SWFVNVPNCDGALAGMTASFVR", "30.9", "800.4", "3+", "9.7", "P01031", "Homo sapiens (Human)", "Complement C5 (C3 and PZP-like alpha-2-macroglobulin domain-containing protein 4) [Cleaved into: Complement C5 beta chain; Complement C5 alpha chain; C5a anaphylatoxin; Complement C5 alpha chain]"], ["KDLKYLDVYYWRYFWKWRQVDYLVAPAK", "22.6", "928.9", "4+", "4.1", "P15304", "Rattus norvegicus (Rat)", "Hormone-sensitive lipase (HSL) (EC 3.1.1.79)"], ["DPGFLGTLATASGKFGEGDPHAKTSGLNRK", "40.0", "1010.5", "3+", "0.21", "A7L035", "Chironex fleckeri (Box jellyfish)", "Toxin CfTX-1 (Toxin 1)"], ["TLMGYLLAVDGCALGCFFVMPGLGLVAALSK", "28.3", "815.9", "4+", "3.2", "P60262", "Tityus discrepans (Venezuelan scorpion)", "Toxin TdII-3 (Fragment)"], ["SAPDPGTGDEVVMGQMDPR", "37.1", "658.9", "3+", "4.8", "P42211", "Oryza sativa subsp. japonica (Rice)", "Aspartic proteinase (EC 3.4.23.-)"], ["PAYHDLGVVPMADTR", "41.7", "821.4", "2+", "9.2", "Q8VYV9", "Arabidopsis thaliana (Mouse-ear cress)", "Aspartyl protease family protein 1 (EC 3.4.23.-)"]], "row_count": 32, "column_count": 8, "numeric_cells": 172, "header_rows": 1, "locator": "section[7]/table-wrap[2]#tbl2"}}], "gaps": ["asset:data:geo:PXD005283 not downloaded", "asset:data:geo:PXD005283 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Hypergeometric test with Benjamini-Hochberg false discovery rate correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The software Cytoscape [42] with the BiNGO plugin [43] was used for GO and enrichment analysis using up-to-date databases, applying a hypergeometric test with a significance level (p-value) < 0.05, as well as a Benjamini and Hochberg false discovery rate (FDR) correction."}}], "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 (Hypergeometric test with Benjamini-Hochberg false discovery rate correction), 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": ["PXD005283"], "resolved_accessions": ["PXD005283"], "statements": ["All data, including raw data, are available via the ProteomeXchange data repository with identifier PXD005283."], "basis": "The paper names PXD005283 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:29450146", "data:geo:PXD005283", "asset:table:pmid:29450146:1", "asset:table:pmid:29450146:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD005283"]}, "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": "2026-10-31T18:33:40Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 83862, "completion_tokens": 5841, "cached_tokens": 1816}}, "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:29450146", "type": "paper", "label": "pmid:29450146"}, {"id": "source:pmid:29450146", "type": "manuscript", "label": "PMID 29450146 full text"}, {"id": "data:geo:PXD005283", "type": "dataset", "label": "GEO PXD005283"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29450146", "type": "paper", "label": "pmid:29450146"}, {"id": "source:pmid:29450146", "type": "manuscript", "label": "PMID 29450146 full text"}, {"id": "data:geo:PXD005283", "type": "dataset", "label": "GEO PXD005283"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29450146", "type": "extraction", "used": ["source:pmid:29450146"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD005283", "type": "accession_resolution", "used": ["data:geo:PXD005283"], "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:29450146", "parent_hash": "sha256:1bce198570b19f405fb23a6b88d5cea1ced399fd73a209ec4df5bdad7213305a", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD005283 licence not read", "asset:data:geo:PXD005283 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": ["Novel proteins from proteomic analysis of the trunk disease fungus Lasiodi", "important plants, especially fruiting trees. Proteomics is a highly useful technology for studying p", "d poorly annotated organisms. Current fungal proteomics approaches involve 2D SDS-PAGE and extensive", "d to the University of California, San Diego proteomics mass spectrometry department to be processed"], "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":"2026-11-04T02:12:33+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}}}