{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26156581", "kind": "science-record", "revision": 3, "content_hash": "sha256:ad7e556eb4ea3592a6a4302849bf8039e1bbe3284555365852175f616a881518", "created_at": "2026-11-01T15:40:09Z", "updated_at": "2026-11-01T18:47:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomic analysis of Artemisia annua--towards elucidating the biosynthetic pathways of the antimalarial pro-drug artemisinin.", "doi": "10.1186/s12870-015-0565-7", "pmid": "26156581", "authors": ["Laura Bryant", "Brian Flatley", "Chhaya Patole", "Geoffrey D Brown", "Rainer Cramer"], "journal": "BMC plant biology", "year": 2015, "abstract": "BACKGROUND: MS-based proteomics was applied to the analysis of the medicinal plant Artemisia annua, exploiting a recently published contig sequence database (Graham et al. (2010) Science 327, 328-331) and other genomic and proteomic sequence databases for comparison. A. annua is the predominant natural source of artemisinin, the precursor for artemisinin-based combination therapies (ACTs), which are the WHO-recommended treatment for P. falciparum malaria.\nRESULTS: The comparison of various databases containing A. annua sequences (NCBInr/viridiplantae, UniProt/viridiplantae, UniProt/A. annua, an A. annua trichome Trinity contig database, the above contig database and another A. annua EST database) revealed significant differences in respect of their suitability for proteomic analysis, showing that an organism-specific database that has undergone extensive curation, leading to longer contig sequences, can greatly increase the number of true positive protein identifications, while reducing the number of false positives. Compared to previously published data an order-of-magnitude more proteins have been identified from trichome-enriched A. annua samples, including proteins which are known to be involved in the biosynthesis of artemisinin, as well as other highly abundant proteins, which suggest additional enzymatic processes occurring within the trichomes that are important for the biosynthesis of artemisinin.\nCONCLUSIONS: The newly gained information allows for the possibility of an enzymatic pathway, utilizing peroxidases, for the less well understood final stages of artemisinin's biosynthesis, as an alternative to the known non-enzymatic in vitro conversion of dihydroartemisinic acid to artemisinin. Data are available via ProteomeXchange with identifier PXD000703.", "claims": [{"id": "claim-data-access", "statement": "The data set supporting the results of this article is available in the PRIDE (Proteomics Identifications Database) partner repository at the European Bioinformatics Institute, PXD000703 (http://www.ebi.ac.uk/pride/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26156581", "locator": "sections[17] \"Availability of supporting data\" paragraph 2", "quote": "The data set supporting the results of this article is available in the PRIDE (Proteomics Identifications Database) partner repository at the European Bioinformatics Institute, PXD000703 (http://www.ebi.ac.uk/pride/)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:26156581"], "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:PXD000703"], "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:PXD000703"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26156581", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12870-015-0565-7", "sha256": "sha256:bc94ef0ed424da2f14b59154f7ba7f7ca4d91ab6d4d0192f646470a3172cd9ed", "bytes": 50814, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12870-015-0565-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4496932", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000703", "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=PXD000703", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000703", "version": null, "note": "The data set supporting the results of this article is available in the PRIDE (Proteomics Identifications Database) partner repository at the European Bioinformatics Institute, PXD000703 (http://www.ebi.ac.uk/pride/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data set supporting the results of this article is available in the PRIDE (Proteomics Identifications Database) partner repository at the European Bioinformatics Institute, PXD000703 (http://www.ebi.ac.uk/pride/).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic Analysis of Artemisia annua", "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:26156581:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:269a4b4597a627500d0e89c4b581201be4426316fa776738b908c24abc2a41af", "bytes": 801, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab1", "version": null, "note": "Protein identification search results from the MS/MS data of trichome-enriched A. annua sample material", "structure": {"pmcid": "PMC4496932", "section_index": 4, "section_title": "LC-MS/MS analysis", "row_count": 6, "column_count": 5}, "table": {"label": "Table 1", "caption": "Protein identification search results from the MS/MS data of trichome-enriched A. annua sample material", "rows": [["Target database", "# of protein family hits", "# of peptides matched above identity threshold in target database", "# of peptides matched above identity threshold in decoy database", "FDR"], ["York Artemis contigs (116,303 sequences)", "671", "3072", "58", "1.9 %"], ["Artemisia trichomeTrinity contigs (150,282 sequences)", "684", "2636", "85", "3.2 %"], ["NCBInr viridiplantae (1,079,491 sequences)", "419", "1286", "60", "4.7 %"], ["UniProt A. annua (118 sequences)", "17", "179", "11", "6.2 %"], ["UniProt viridiplantae (32,329 sequences)", "319", "1271", "112", "8.8 %"]], "row_count": 6, "column_count": 5, "numeric_cells": 25, "header_rows": 1, "locator": "section[4]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:26156581:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c511a70ddcccd9bf61175f40ffeadf7045b6ee74b8567f2b1362458ba2c7c5ee", "bytes": 1414, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab2", "version": null, "note": "Significant protein matches obtained from searching MS/MS data of the trichome-enriched A. annua sample material (against UniProtKB database; taxonomy: A. annua)", "structure": {"pmcid": "PMC4496932", "section_index": 5, "section_title": "The trichome-enriched proteome of Artemisia annua", "row_count": 18, "column_count": 4}, "table": {"label": "Table 2", "caption": "Significant protein matches obtained from searching MS/MS data of the trichome-enriched A. annua sample material (against UniProtKB database; taxonomy: A. annua)", "rows": [["Accession #", "Score", "Mass", "Description"], ["Q84UA9", "1811", "35892", "Peroxidase 1"], ["Q4Q028", "1037", "25593", "Ribulose bisphosphate carboxylase large chain (Fragment)"], ["A5HSG6", "934", "26996", "Chloroplast light-harvesting chlorophyll a/b-binding protein (Fragment)"], ["B2CNV6", "393", "28433", "Actin 1 (Fragment)"], ["A0A3A2", "273", "10794", "Ribulose bisphosphate carboxylase small chain (Fragment)"], ["A5HSG5", "219", "11402", "Histone H4"], ["C5H429", "177", "42705", "Artemisinic aldehyde delta-11(13) reductase"], ["O22036", "84", "16124", "1-aminocyclopropane-1-carboxylate oxidase (Fragment)"], ["D2X5S7", "76", "10971", "Putative ubiquitin-like protein"], ["G0WKM6", "54", "26819", "Allene oxide cyclase"], ["Q9AR04", "45", "64406", "Amorpha-4,11-diene synthase"], ["D2X5N3", "45", "21350", "Glyceraldehyde-3-phosphate dehydrogenase (Fragment)"], ["C0LNV1", "43", "38761", "2-alkenal reductase"], ["A5HSG7", "33", "14862", "Putative ubiquitin-conjugating enzyme"], ["A0A3A1", "24", "24364", "Chitinase-like protein (Fragment)"], ["Q9SWQ3", "13", "62512", "HMG-CoA reductase"], ["Q2EPZ0", "13", "61373", "Putative heme-binding cytochrome P450"]], "row_count": 18, "column_count": 4, "numeric_cells": 47, "header_rows": 1, "locator": "section[5]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:26156581:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b610dd1c086183146947fa47abd8a84fbb1d6d2aeb6ea2deafa0a8fcedff2727", "bytes": 2409, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[2]#Tab3", "version": null, "note": "Highly abundant proteins of the trichome-enriched compared to the trichome-depleted sample material", "structure": {"pmcid": "PMC4496932", "section_index": 5, "section_title": "The trichome-enriched proteome of Artemisia annua", "row_count": 21, "column_count": 6}, "table": {"label": "Table 3", "caption": "Highly abundant proteins of the trichome-enriched compared to the trichome-depleted sample material", "rows": [["Gi number", "EmPAI quotienta", "Access. number (no taxonomy)", "Protein name (no taxonomy)", "Access. number (Tax.: Artemisia)", "Protein name (Tax.: Artemisia)"], ["259726479", "6.42", "ACZ51443.1", "Peroxidase protein [Mikania micrantha]", "AAO45182.1", "Peroxidase 1 [Artemisia annua]"], ["259544254", "5.70", "XP_002285593.1", "Aspartic proteinase nepenthesin-2 [Vitis vinifera]", "", ""], ["259560512", "4.79", "Q9XIV8.1", "Peroxidase N1", "AAO45182.1", "Peroxidase 1 [Artemisia annua]"], ["259867266", "3.86", "XP_004135957.1", "Photosystem II stability/assembly factor HCF136, chloroplastic-like [Cucumis sativus]", "", ""], ["259537187", "3.76", "XP_004251245.1", "Elongation factor 1-beta 1-like [Solanum lycopersicum]", "", ""], ["259859266", "3.73", "XP_003538726.1", "Thylakoid lumenal protein At1g12250, chloroplastic-like [Glycine max]", "", ""], ["259714573", "3.08", "XP_002523024.1", "Amino acid binding protein, putative [Ricinus communis]", "", ""], ["259551155", "2.97", "CAH17986.1", "Peroxidase POA1 [Capsicum annuum]", "AAO45182.1", "Peroxidase 1 [Artemisia annua]"], ["259554365", "2.59", "ABK92641.1", "Unknown [Populus trichocarpa]", "", ""], ["259530226", "2.35", "O04287.1", "Peptidyl-prolyl cis-trans isomerase FKBP12", "", ""], ["259724484", "2.13", "CAA81073.1", "H-protein [Flaveria cronquistii]", "", ""], ["259543684", "2.06", "ABV26711.1", "Cyclophilin [Gerbera hybrid cultivar]", "", ""], ["259527950", "1.89", "AAD11576.1", "Lectin 3 [Helianthus tuberosus]", "AFU82531.1", "CjMDR1 protein, partial [Artemisia tridentata]"], ["259557766", "1.81", "XP_006350796.1", "Thylakoid lumenal 15 kDa protein 1, chloroplastic-like [Solanum tuberosum]", "", ""], ["259561193", "1.81", "AEF01110.1", "Cyclophilin 2 [Tagetes patula]", "", ""], ["259539505", "1.73", "XP_002301776.1", "Predicted protein [Populus trichocarpa]", "", ""], ["259534802", "1.66", "XP_004249062.1", "Macrophage migration inhibitory factor homolog isoform 2 [Solanum lycopersicum]", "", ""], ["259531358", "1.64", "EOY05690.1", "Cysteine synthase [Theobroma cacao]", "", ""], ["259732623", "1.62", "XP_003544567.1", "Fructose-bisphosphate aldolase, cytoplasmic isozyme 1-like [Glycine max]", "", ""], ["259544645", "1.58", "BAD10859.1", "Cysteine protease [Aster tripolium]", "", ""]], "row_count": 21, "column_count": 6, "numeric_cells": 77, "header_rows": 1, "locator": "section[5]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:26156581:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e2db0b2bd8ddda2fc4dddb1ad05f784813c26fcd0e0fa48de9323771ab82c4c4", "bytes": 2688, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[3]#Tab4", "version": null, "note": "Highly abundant proteins of the trichome-depleted compared to the trichome-enriched sample material", "structure": {"pmcid": "PMC4496932", "section_index": 5, "section_title": "The trichome-enriched proteome of Artemisia annua", "row_count": 21, "column_count": 6}, "table": {"label": "Table 4", "caption": "Highly abundant proteins of the trichome-depleted compared to the trichome-enriched sample material", "rows": [["Gi number", "EmPAI quotienta", "Acc. number (no taxonomy)", "Protein name (no taxonomy)", "Acc. number (Tax.: Artemisia)", "Protein name (Tax.: Artemisia)"], ["259558480", "0.14", "CAE82295.1", "Catalase [Homogyne alpina]", "", ""], ["259720159", "0.20", "AFK36692.1", "Unknown [Medicago truncatula]", "", ""], ["259732783", "0.27", "XP_004140097.1", "Ribosome-recycling factor, chloroplastic-like [Cucumis sativus]", "", ""], ["259539861", "0.33", "ADG96009.1", "Beta-1,3-glucanase PR2 [Chrysanthemum x morifolium]", "", ""], ["259732073", "0.34", "YP_007353779.1", "Component of cytochrome b6/f complex (chloroplast) [Chrysanthemum x morifolium]", "YP_007624808.1", "Cytochrome f (chloroplast) [Artemisia frigida]"], ["259542667", "0.35", "P29790.1", "ATP synthase gamma chain, chloroplastic", "", ""], ["259550993", "0.37", "XP_003547929.1", "Ferredoxin--NADP reductase, leaf isozyme, chloroplastic-like isoform 1 [Glycine max]", "AFO64618.1", "Cytochrome P450 reductase [Artemisia annua]"], ["259863294", "0.38", "NP_193769.1", "Putative elongation factor Tu [Arabidopsis thaliana]", "", ""], ["259530332", "0.40", "P00290.1", "Plastocyanin", "", ""], ["259532611", "0.42", "XP_002271791.1", "Photosystem II 10 kDa polypeptide, chloroplastic [Vitis vinifera]", "", ""], ["259544910", "0.43", "ABC41657.1", "Carbonic anhydrase 2 [Flaveria pringlei]", "", ""], ["259533513", "0.43", "AAO42615.1", "Ferredoxin [Helianthus annuus]", "", ""], ["259535874", "0.43", "XP_002299232.1", "Predicted protein [Populus trichocarpa]", "", ""], ["259553333", "0.44", "XP_004228903.1", "Photosystem II CP47 chlorophyll apoprotein-like [Solanum lycopersicum]", "YP_007624821.1", "Photosystem II P680 chlorophyll A apoprotein (chloroplast) [Artemisia frigida]"], ["259529761", "0.44", "BAL14665.1", "Elongation factor 1-alpha [Chrysanthemum seticuspe f. boreale]", "ACP28182.1", "Elongation factor 1-alpha [Artemisia annua]"], ["259529664", "0.49", "ACO35888.1", "Ribulose-1,5-bisphosphate carboxylase/oxygenase small subunit [Ageratina adenophora]", "ABJ74187.1", "Chloroplast ribulose-1,5-bisphosphate carboxylase/oxygenase small subunit [Artemisia annua]"], ["259734867", "0.49", "CBI19198.3", "Unnamed protein product [Vitis vinifera]", "", ""], ["259531744", "0.49", "P46486.1", "Photosystem I reaction center subunit III, chloroplastic", "", ""], ["259542148", "0.53", "BAA04633.1", "PSI-H precursor [Nicotiana sylvestris]", "", ""], ["259563039", "0.54", "ABW80752.1", "Chloroplast ribulose 1,5-bisphosphate carboxylase/oxygenase activase [Flaveria bidentis]", "", ""]], "row_count": 21, "column_count": 6, "numeric_cells": 77, "header_rows": 1, "locator": "section[5]/table-wrap[3]#Tab4"}}, {"id": "asset:table:pmid:26156581:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:540c8136110805aa880842488dcfc46d4d68f8ed7f913ef72a68831f562e800f", "bytes": 1650, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[4]#Tab5", "version": null, "note": "Ten highest abundant proteins detected in the trichome-enriched samples onlya", "structure": {"pmcid": "PMC4496932", "section_index": 5, "section_title": "The trichome-enriched proteome of Artemisia annua", "row_count": 11, "column_count": 5}, "table": {"label": "Table 5", "caption": "Ten highest abundant proteins detected in the trichome-enriched samples onlya", "rows": [["Gi number", "Accesssion number (no taxonomy)", "Protein name (no taxonomy)", "Accession number (Tax.: Artemisia)", "Protein name (Tax.: Artemisia)"], ["259723715", "YP_007624803.1", "Ribulose-1,5-bisphosphate carboxylase/oxygenase large subunit (chloroplast) [Artemisia frigida]", "YP_007624803.1", "Ribulose-1,5-bisphosphate carboxylase/oxygenase large subunit (chloroplast) [Artemisia frigida]"], ["259717416", "XP_004240055.1", "Cationic peroxidase 1-like [Solanum lycopersicum]", "AAO45182.1", "Peroxidase 1 [Artemisia annua]"], ["259711439", "AAM27915.1", "Carbohydrate oxidase [Helianthus annuus]", "", ""], ["259552602", "ACZ74626.1", "Beta-1,3-glucanase form RRII Gln 3 [Hevea brasiliensis]", "", ""], ["259552323", "XP_002514900.1", "Nuclear transport factor, putative [Ricinus communis]", "", ""], ["259732733", "XP_004302854.1", "Chlorophyll a-b binding protein 40, chloroplastic-like [Fragaria vesca subsp. vesca]", "ABQ32304.1", "Chloroplast light-harvesting chlorophyll a/b-binding protein [Artemisia annua]"], ["259737301", "XP_002276749.1", "20 kDa chaperonin, chloroplastic [Vitis vinifera]", "", ""], ["259558851", "XP_004159350.1", "ruBisCO large subunit-binding protein subunit beta, chloroplastic-like [Cucumis sativus]", "", ""], ["259717225", "XP_002283307.1", "psbP domain-containing protein 6, chloroplastic [Vitis vinifera]", "", ""], ["259728302", "XP_002272847.1", "Peroxidase N1 [Vitis vinifera]", "AAO45182.1", "Peroxidase 1 [Artemisia annua]"]], "row_count": 11, "column_count": 5, "numeric_cells": 33, "header_rows": 1, "locator": "section[5]/table-wrap[4]#Tab5"}}, {"id": "asset:table:pmid:26156581:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2f129088cfd5084b585a51de325a5a9c46958f10709a7d5a21193004b7a6f0ad", "bytes": 1562, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[5]#Tab6", "version": null, "note": "Ten highest abundant proteins detected in the trichome-depleted samples onlya", "structure": {"pmcid": "PMC4496932", "section_index": 5, "section_title": "The trichome-enriched proteome of Artemisia annua", "row_count": 11, "column_count": 5}, "table": {"label": "Table 6", "caption": "Ten highest abundant proteins detected in the trichome-depleted samples onlya", "rows": [["Gi number", "Accession number (no taxonomy)", "Protein name (no taxonomy)", "Accession number (Tax.: Artemisia)", "Protein name (Tax.: Artemisia)"], ["259550200", "EOY18549.1", "ATP synthase D chain, mitochondrial [Theobroma cacao]", "", ""], ["259729601", "XP_002965312.1", "Hypothetical protein SELMODRAFT_439163 [Selaginella moellendorffii]", "AFU82552.1", "Heat shock protein, partial [Artemisia tridentata]"], ["259540721", "AAC84136.1", "Ribosomal protein L12 [Cichorium intybus]", "", ""], ["259545610", "XP_003543611.1", "60S ribosomal protein L28-2 [Glycine max]", "", ""], ["259719587", "AET22433.1", "Glutamate synthase [Camellia sinensis]", "", ""], ["259870147", "XP_004503350.1", "40S ribosomal protein S2-3-like [Cicer arietinum]", "ABQ32304.1", "Chloroplast light-harvesting chlorophyll a/b-binding protein [Artemisia annua]"], ["259543403", "CAA65042.1", "Chlorophyll a/b-binding protein CP26 in PS II [Brassica juncea]", "ABQ32304.1", "Chloroplast light-harvesting chlorophyll a/b-binding protein [Artemisia annua]"], ["259736780", "XP_003547929.1", "Ferredoxin--NADP reductase, leaf isozyme, chloroplastic-like isoform 1 [Glycine max]", "AFO64618.1", "Cytochrome P450 reductase [Artemisia annua]"], ["259532505", "AEC10962.1", "40S ribosomal protein s10 [Camellia sinensis]", "", ""], ["259538077", "XP_002301623.1", "Predicted protein [Populus trichocarpa]", "", ""]], "row_count": 11, "column_count": 5, "numeric_cells": 32, "header_rows": 1, "locator": "section[5]/table-wrap[5]#Tab6"}}], "gaps": ["asset:data:geo:PXD000703 not downloaded", "asset:data:geo:PXD000703 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": ["PXD000703"], "resolved_accessions": ["PXD000703"], "statements": ["The data set supporting the results of this article is available in the PRIDE (Proteomics Identifications Database) partner repository at the European Bioinformatics Institute, PXD000703 (http://www.ebi.ac.uk/pride/)."], "basis": "The paper names PXD000703 in ProteomeXchange Consortium via the PRIDE (Proteomics Identifications Database) partner repository at the European Bioinformatics Institute and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26156581", "data:geo:PXD000703", "asset:table:pmid:26156581:1", "asset:table:pmid:26156581:2", "asset:table:pmid:26156581:3", "asset:table:pmid:26156581:4", "asset:table:pmid:26156581:5", "asset:table:pmid:26156581:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000703"]}, "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": "2026-10-31T18:05:11Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 38188, "completion_tokens": 1533, "cached_tokens": 656}}, "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:26156581", "type": "paper", "label": "pmid:26156581"}, {"id": "source:pmid:26156581", "type": "manuscript", "label": "PMID 26156581 full text"}, {"id": "data:geo:PXD000703", "type": "dataset", "label": "GEO PXD000703"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26156581", "type": "paper", "label": "pmid:26156581"}, {"id": "source:pmid:26156581", "type": "manuscript", "label": "PMID 26156581 full text"}, {"id": "data:geo:PXD000703", "type": "dataset", "label": "GEO PXD000703"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26156581", "type": "extraction", "used": ["source:pmid:26156581"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000703", "type": "accession_resolution", "used": ["data:geo:PXD000703"], "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:26156581", "parent_hash": "sha256:6bb9d1f235e6d71a1ee2f00b344c56f7ccec5410a902f20743ed7dd86207dafc", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD000703 licence not read", "asset:data:geo:PXD000703 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"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":"2026-11-04T02:53:50+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}}}