{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27625672", "kind": "science-record", "revision": 6, "content_hash": "sha256:023f5f96650eec70d52996179f485a1ae8c3c6fdb6c8f181a8de91ef066c232b", "created_at": "2026-11-01T15:40:20Z", "updated_at": "2026-11-01T22:42:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomic Studies on the Effects of Lipo-Chitooligosaccharide and Thuricin 17 under Unstressed and Salt Stressed Conditions in Arabidopsis thaliana.", "doi": "10.3389/fpls.2016.01314", "pmid": "27625672", "authors": ["Sowmyalakshmi Subramanian", "Alfred Souleimanov", "Donald L Smith"], "journal": "Frontiers in plant science", "year": 2016, "abstract": "Plants, being sessile organisms, are exposed to widely varying environmental conditions throughout their life cycle. Compatible plant-microbe interactions favor plant growth and development, and help plants deal with these environmental challenges. Microorganisms produce a diverse range of elicitor molecules to establish symbiotic relationships with the plants they associate with, in a given ecological niche. Lipo-chitooligosaccharide (LCO) and Thuricin 17 (Th17) are two such compounds shown to positively influence plant growth of both legumes and non-legumes. Arabidopsis thaliana responded positively to treatment with the bacterial signal compounds LCO and Th17 in the presence of salt stress (up to 250 mM NaCl). Shotgun proteomics of unstressed and 250 mM NaCl stressed A. thaliana rosettes (7 days post stress) in combination with the LCO and Th17 revealed many known, putative, hypothetical, and unknown proteins. Overall, carbon and energy metabolic pathways were affected under both unstressed and salt stressed conditions when treated with these signals. PEP carboxylase, Rubisco-oxygenase large subunit, pyruvate kinase, and proteins of photosystems I and II were some of the noteworthy proteins enhanced by the signals, along with other stress related proteins. These findings suggest that the proteome of A. thaliana rosettes is altered by the bacterial signals tested, and more so under salt stress, thereby imparting a positive effect on plant growth under high salt stress. The roles of the identified proteins are discussed here in relation to salt stress adaptation, which, when translated to field grown crops can be a crucial component and of significant importance in agriculture and global food production. The mass spectrometry proteomics data have been deposited to the ProteomeXchange with identifier PXD004742.", "claims": [{"id": "claim-method", "statement": "The treatment contrasts were then analyzed for fold-change after normalization, and Fisher’s Exact test was used to narrow down the up- and down-regulated proteins, to predict their probable functions at 24 h after signal compound treatment and 7 days after NaCl stress imposition.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27625672", "locator": "sections[14] \"Protein Profiling\" paragraph 2", "quote": "The treatment contrasts were then analyzed for fold-change after normalization, and Fisher’s Exact test was used to narrow down the up- and down-regulated proteins, to predict their probable functions at 24 h after signal compound treatment and 7 days after NaCl stress imposition."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium1 via the PRIDE partner repository (Vizcaino et al., 2013) with the dataset identifier PXD004742.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27625672", "locator": "sections[11] \"Data Analysis\" paragraph 3", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium1 via the PRIDE partner repository (Vizcaino et al., 2013) with the dataset identifier PXD004742."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports that LCO and Th17 affected carbon and energy metabolic pathways under unstressed and salt-stressed conditions. Statistical analysis used fold change and Fisher’s exact test after embedded normalization of spectral quantitative values; the proteomics data were deposited in ProteomeXchange via PRIDE under identifier PXD004742.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:27625672", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Overall, carbon and energy metabolic pathways were affected under both unstressed and salt stressed conditions when treated with these signals."}, {"asset": "source:pmid:27625672", "locator": "sections[11] \"Data Analysis\" paragraph 3", "quote": "Scaffold 4.0 was used for analyzing the proteomics data for fold change and Fisher exact test of the identified proteins after subjecting the quantitative value of the spectra to the embedded normalization."}, {"asset": "source:pmid:27625672", "locator": "sections[11] \"Data Analysis\" paragraph 3", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium1 via the PRIDE partner repository (Vizcaino et al., 2013) with the dataset identifier PXD004742."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper reports that LCO and Th17 affected carbon and energy metabolic pathways under unstressed and salt-stressed conditions. Statistical analysis used fold change and Fisher’s exact test after embedded normalization of spectral quantitative values; the proteomics data were deposited in ProteomeXchange via PRIDE under identifier PXD004742.", "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:27625672"], "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:PXD004742"], "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:PXD004742"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27625672", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fpls.2016.01314", "sha256": "sha256:661aa3de48c31c9c0e4d4a675a1c7c4161bb1343f8f7bf7fac4b6caef466e38b", "bytes": 61077, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fpls.2016.01314", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5003918", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD004742", "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=PXD004742", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD004742", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium1 via the PRIDE partner repository (Vizcaino et al., 2013) with the dataset identifier PXD004742.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium1 via the PRIDE partner repository (Vizcaino et al., 2013) with the dataset identifier PXD004742.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Arabidopsis rosettes proteome in response to LCO and Th17 under salt stress- LC-MS/MS", "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:27625672:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e759a0f5fa252a256a9049a9b767f2ae4dcd5f1cf78b9c1932500336732add6a", "bytes": 698, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T2", "version": null, "note": "Total number of proteins identified at 99% protein probability and total spectra at 95% peptide probability, with two minimum peptides.", "structure": {"pmcid": "PMC5003918", "section_index": 9, "section_title": "Protein Profiling", "row_count": 6, "column_count": 10}, "table": {"label": "Table 2", "caption": "Total number of proteins identified at 99% protein probability and total spectra at 95% peptide probability, with two minimum peptides.", "rows": [["Unstressed", "Control 1", "Control 2", "Control 3", "LCO 1", "LCO 2", "LCO 3", "Th17 1", "Th17 2", "Th17 3"], ["Proteins", "473", "461", "486", "506", "441", "457", "469", "457", "464"], ["Spectra", "5622", "5795", "5598", "5910", "5754", "5623", "5902", "6009", "5717"], ["Stressed at 250 mM NaCl"], ["Proteins", "467", "491", "461", "456", "457", "506", "513", "514", "523"], ["Spectra", "4753", "5125", "4945", "4992", "5098", "5327", "5336", "5379", "5626"]], "row_count": 6, "column_count": 10, "numeric_cells": 46, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:27625672:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e57375518f4b4ac39b106bbbcaf2cc42411401667a1be983ab47babf6424ee12", "bytes": 725, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#T3a", "version": null, "note": "Grouping of proteins in A. thaliana rosettes, that was significant in contrasts based on fold change.", "structure": {"pmcid": "PMC5003918", "section_index": 9, "section_title": "Protein Profiling", "row_count": 6, "column_count": 7}, "table": {"label": "Table 3A", "caption": "Grouping of proteins in A. thaliana rosettes, that was significant in contrasts based on fold change.", "rows": [["Treatment contrasts A. thaliana", "Control vs. LCO", "Control vs. Th17", "LCO vs. Th17", "Control 250 mM NaCl vs. LCO + 250 mM NaCl", "Control 250 mM NaCl vs. Th17 + 250 mM NaCl", "LCO 250 mM NaCl vs. Th17 + 250 mM NaCl"], ["Total significant proteins", "114", "93", "80", "93", "92", "80"], ["Known proteins", "97", "80", "68", "72", "80", "64"], ["Putative proteins", "10", "8", "8", "13", "15", "11"], ["Hypothetical proteins", "3", "1", "2", "1", "-", "1"], ["Unknown proteins", "4", "4", "2", "7", "7", "4"]], "row_count": 6, "column_count": 7, "numeric_cells": 34, "header_rows": 1, "locator": "section[14]/table-wrap[2]#T3a"}}, {"id": "asset:table:pmid:27625672:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cb1a2925f6e5a48f07d17a82768cc5089b7f18024619667d9eedd947fc133322", "bytes": 731, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[3]#T3b", "version": null, "note": "Grouping of proteins in A. thaliana rosettes, that were significant in contrasts based on Fisher’s Exact test.", "structure": {"pmcid": "PMC5003918", "section_index": 9, "section_title": "Protein Profiling", "row_count": 6, "column_count": 7}, "table": {"label": "Table 3B", "caption": "Grouping of proteins in A. thaliana rosettes, that were significant in contrasts based on Fisher’s Exact test.", "rows": [["Treatment contrasts A. thaliana", "Control vs. LCO", "Control vs. Th17", "LCO vs. Th17", "Control 250 mM NaCl vs. LCO + 250 mM NaCl", "Control 250 mM NaCl vs. Th17 + 250 mM NaCl", "LCO 250 mM NaCl vs. Th17 + 250 mM NaCl"], ["Total significant proteins", "63", "42", "26", "25", "40", "25"], ["Known proteins", "55", "33", "22", "21", "34", "20"], ["Putative Proteins", "7", "8", "2", "4", "5", "5"], ["Hypothetical proteins", "1", "1", "1", "-", "-", "-"], ["Unknown proteins", "-", "-", "1", "-", "1", "-"]], "row_count": 6, "column_count": 7, "numeric_cells": 28, "header_rows": 1, "locator": "section[14]/table-wrap[3]#T3b"}}, {"id": "asset:table:pmid:27625672:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e6f2eaffc8c7287158cccc650ff979e7efd6fa2b131bb4c161f0fd74f8833fd0", "bytes": 882, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[4]#T4", "version": null, "note": "Enzyme code distribution in un-stressed and salt stressed groups.", "structure": {"pmcid": "PMC5003918", "section_index": 9, "section_title": "Protein Profiling", "row_count": 7, "column_count": 7}, "table": {"label": "Table 4", "caption": "Enzyme code distribution in un-stressed and salt stressed groups.", "rows": [["Main enzyme classes", "Control", "LCOA", "THA", "250 mM NaCl Control", "LCOA + 250 mM NaCl", "THA + 250 mM NaCl"], ["Oxidoreductases", "204", "191 (↓6.58%)", "197 (↓3.49%)", "242", "248 (↑2.45%)", "269 (↑10.57%)"], ["Transferases", "91", "157 (↑53.22%)", "161 (↑55.55%)", "170", "169 (↓0.59%)", "203 (↑17.7%)"], ["Hydrolases", "107", "129 (↑ 18.64%)", "136 (↑23.87%)", "153", "140 (↓8.87%)", "166 (↑8.15%)"], ["Lyases", "40", "63 (↑44.66%)", "73 (↑58.40%)", "69", "72 (↑4.25%)", "76 (↑9.65%)"], ["Isomerases", "51", "42 (↓19.35%)", "36 (↓34.48%)", "47", "36 (↓26.50%)", "40 (↓16.09%)"], ["Ligases", "24", "52 (↑73.68%)", "51 (↑72%)", "60", "56 (↓6.89%)", "65 (↑8%)"]], "row_count": 7, "column_count": 7, "numeric_cells": 39, "header_rows": 1, "locator": "section[14]/table-wrap[4]#T4"}}, {"id": "asset:table:pmid:27625672:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0269c9053c6d21c5b38ef3d8d07a5a05098d74c1f4a5651e18176f4120afcd8d", "bytes": 796, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T1", "version": null, "note": "Least square means of Arabidopsis thaliana percentage germination – seeds treated with lipo-chitooligosaccharide and Thuricin 17 under optimal conditions.", "structure": {"pmcid": "PMC5003918", "section_index": 13, "section_title": "A. thaliana Seed Germination in Petri Plates and Trays under Unstressed Conditions and in the Presence of Salt Stress Screening, When Treated with LCO and Th17", "row_count": 7, "column_count": 9}, "table": {"label": "Table 1", "caption": "Least square means of Arabidopsis thaliana percentage germination – seeds treated with lipo-chitooligosaccharide and Thuricin 17 under optimal conditions.", "rows": [["Treatments", "24 h", "± SEM", "30 h", "±SEM", "36 h", "±SEM", "48 h", "±SEM"], ["P ≤ 0.05", "", "", "0.1904", "", "0.6972", "", "0.8235", ""], ["Control", "0.00", "0.00", "54.38b", "0.97", "77.49a", "1.15", "86.26a", "1.10"], ["LCOA", "0.00", "0.00", "61.69ab", "0.71", "75.52a", "1.04", "87.83a", "1.11"], ["LCOB", "0.00", "0.00", "57.77ab", "0.70", "72.99a", "1.28", "83.96a", "1.57"], ["THA", "0.00", "0.00", "62.66a", "0.53", "78.87a", "0.77", "87.12a", "0.76"], ["THB", "0.00", "0.00", "61.99ab", "0.97", "75.81a", "1.10", "86.67a", "1.12"]], "row_count": 7, "column_count": 9, "numeric_cells": 48, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:27625672:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e759a0f5fa252a256a9049a9b767f2ae4dcd5f1cf78b9c1932500336732add6a", "bytes": 698, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T2", "version": null, "note": "Total number of proteins identified at 99% protein probability and total spectra at 95% peptide probability, with two minimum peptides.", "structure": {"pmcid": "PMC5003918", "section_index": 14, "section_title": "Protein Profiling", "row_count": 6, "column_count": 10}, "table": {"label": "Table 2", "caption": "Total number of proteins identified at 99% protein probability and total spectra at 95% peptide probability, with two minimum peptides.", "rows": [["Unstressed", "Control 1", "Control 2", "Control 3", "LCO 1", "LCO 2", "LCO 3", "Th17 1", "Th17 2", "Th17 3"], ["Proteins", "473", "461", "486", "506", "441", "457", "469", "457", "464"], ["Spectra", "5622", "5795", "5598", "5910", "5754", "5623", "5902", "6009", "5717"], ["Stressed at 250 mM NaCl"], ["Proteins", "467", "491", "461", "456", "457", "506", "513", "514", "523"], ["Spectra", "4753", "5125", "4945", "4992", "5098", "5327", "5336", "5379", "5626"]], "row_count": 6, "column_count": 10, "numeric_cells": 46, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:27625672:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e57375518f4b4ac39b106bbbcaf2cc42411401667a1be983ab47babf6424ee12", "bytes": 725, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#T3a", "version": null, "note": "Grouping of proteins in A. thaliana rosettes, that was significant in contrasts based on fold change.", "structure": {"pmcid": "PMC5003918", "section_index": 14, "section_title": "Protein Profiling", "row_count": 6, "column_count": 7}, "table": {"label": "Table 3A", "caption": "Grouping of proteins in A. thaliana rosettes, that was significant in contrasts based on fold change.", "rows": [["Treatment contrasts A. thaliana", "Control vs. LCO", "Control vs. Th17", "LCO vs. Th17", "Control 250 mM NaCl vs. LCO + 250 mM NaCl", "Control 250 mM NaCl vs. Th17 + 250 mM NaCl", "LCO 250 mM NaCl vs. Th17 + 250 mM NaCl"], ["Total significant proteins", "114", "93", "80", "93", "92", "80"], ["Known proteins", "97", "80", "68", "72", "80", "64"], ["Putative proteins", "10", "8", "8", "13", "15", "11"], ["Hypothetical proteins", "3", "1", "2", "1", "-", "1"], ["Unknown proteins", "4", "4", "2", "7", "7", "4"]], "row_count": 6, "column_count": 7, "numeric_cells": 34, "header_rows": 1, "locator": "section[14]/table-wrap[2]#T3a"}}, {"id": "asset:table:pmid:27625672:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cb1a2925f6e5a48f07d17a82768cc5089b7f18024619667d9eedd947fc133322", "bytes": 731, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[3]#T3b", "version": null, "note": "Grouping of proteins in A. thaliana rosettes, that were significant in contrasts based on Fisher’s Exact test.", "structure": {"pmcid": "PMC5003918", "section_index": 14, "section_title": "Protein Profiling", "row_count": 6, "column_count": 7}, "table": {"label": "Table 3B", "caption": "Grouping of proteins in A. thaliana rosettes, that were significant in contrasts based on Fisher’s Exact test.", "rows": [["Treatment contrasts A. thaliana", "Control vs. LCO", "Control vs. Th17", "LCO vs. Th17", "Control 250 mM NaCl vs. LCO + 250 mM NaCl", "Control 250 mM NaCl vs. Th17 + 250 mM NaCl", "LCO 250 mM NaCl vs. Th17 + 250 mM NaCl"], ["Total significant proteins", "63", "42", "26", "25", "40", "25"], ["Known proteins", "55", "33", "22", "21", "34", "20"], ["Putative Proteins", "7", "8", "2", "4", "5", "5"], ["Hypothetical proteins", "1", "1", "1", "-", "-", "-"], ["Unknown proteins", "-", "-", "1", "-", "1", "-"]], "row_count": 6, "column_count": 7, "numeric_cells": 28, "header_rows": 1, "locator": "section[14]/table-wrap[3]#T3b"}}, {"id": "asset:table:pmid:27625672:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e6f2eaffc8c7287158cccc650ff979e7efd6fa2b131bb4c161f0fd74f8833fd0", "bytes": 882, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[4]#T4", "version": null, "note": "Enzyme code distribution in un-stressed and salt stressed groups.", "structure": {"pmcid": "PMC5003918", "section_index": 14, "section_title": "Protein Profiling", "row_count": 7, "column_count": 7}, "table": {"label": "Table 4", "caption": "Enzyme code distribution in un-stressed and salt stressed groups.", "rows": [["Main enzyme classes", "Control", "LCOA", "THA", "250 mM NaCl Control", "LCOA + 250 mM NaCl", "THA + 250 mM NaCl"], ["Oxidoreductases", "204", "191 (↓6.58%)", "197 (↓3.49%)", "242", "248 (↑2.45%)", "269 (↑10.57%)"], ["Transferases", "91", "157 (↑53.22%)", "161 (↑55.55%)", "170", "169 (↓0.59%)", "203 (↑17.7%)"], ["Hydrolases", "107", "129 (↑ 18.64%)", "136 (↑23.87%)", "153", "140 (↓8.87%)", "166 (↑8.15%)"], ["Lyases", "40", "63 (↑44.66%)", "73 (↑58.40%)", "69", "72 (↑4.25%)", "76 (↑9.65%)"], ["Isomerases", "51", "42 (↓19.35%)", "36 (↓34.48%)", "47", "36 (↓26.50%)", "40 (↓16.09%)"], ["Ligases", "24", "52 (↑73.68%)", "51 (↑72%)", "60", "56 (↓6.89%)", "65 (↑8%)"]], "row_count": 7, "column_count": 7, "numeric_cells": 39, "header_rows": 1, "locator": "section[14]/table-wrap[4]#T4"}}], "gaps": ["asset:data:geo:PXD004742 not downloaded", "asset:data:geo:PXD004742 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "contingency_analysis", "specific": "fisher_exact", "label": "Categorical (contingency table) analysis", "dsl_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The treatment contrasts were then analyzed for fold-change after normalization, and Fisher’s Exact test was used to narrow down the up- and down-regulated proteins, to predict their probable functions at 24 h after signal compound treatment and 7 days after NaCl stress imposition."}}], "targets": [], "gaps": []}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: fisher_exact."}, "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": ["PXD004742"], "resolved_accessions": ["PXD004742"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium1 via the PRIDE partner repository (Vizcaino et al., 2013) with the dataset identifier PXD004742."], "basis": "The paper names PXD004742 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": ["contingency_table", "chi_square_test"], "assets": ["source:pmid:27625672", "data:geo:PXD004742", "asset:table:pmid:27625672:1", "asset:table:pmid:27625672:2", "asset:table:pmid:27625672:3", "asset:table:pmid:27625672:4", "asset:table:pmid:27625672:5", "asset:table:pmid:27625672:6", "asset:table:pmid:27625672:7", "asset:table:pmid:27625672:8", "asset:table:pmid:27625672:9"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD004742"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:22Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 130095, "completion_tokens": 3421, "cached_tokens": 1560}}, "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:27625672", "type": "paper", "label": "pmid:27625672"}, {"id": "source:pmid:27625672", "type": "manuscript", "label": "PMID 27625672 full text"}, {"id": "data:geo:PXD004742", "type": "dataset", "label": "GEO PXD004742"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27625672", "type": "paper", "label": "pmid:27625672"}, {"id": "source:pmid:27625672", "type": "manuscript", "label": "PMID 27625672 full text"}, {"id": "data:geo:PXD004742", "type": "dataset", "label": "GEO PXD004742"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27625672", "type": "extraction", "used": ["source:pmid:27625672"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD004742", "type": "accession_resolution", "used": ["data:geo:PXD004742"], "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:27625672", "parent_hash": "sha256:8e8901b31f6be8566a04c78d6d8c24250cbe025cee11f4684bc9e2d08d2fd2f2", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD004742 licence not read", "asset:data:geo:PXD004742 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "contingency_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["contingency_table", "chi_square_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The treatment contrasts were then analyzed for fold-change after normalization, and Fisher’s Exact test was used to narrow down the up- and down-regulated proteins, to predict their probable functions at 24 h after signal compound treatment and 7 days after NaCl stress imposition."], "order_basis": "analysis_only", "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":"2026-11-04T02:52:27+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}}}