{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29085871", "kind": "science-record", "revision": 5, "content_hash": "sha256:a90ea5451717c58bf76db2a76b4381abf62b8f6483044c4797eeac27d856ff87", "created_at": "2026-11-01T15:40:29Z", "updated_at": "2026-11-01T18:49:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomics dataset: The colon mucosa from inflammatory bowel disease patients, gastrointestinal asymptomic rheumatoid arthritis patients, and controls.", "doi": "10.1016/j.dib.2017.09.059", "pmid": "29085871", "authors": ["Tue Bjerg Bennike", "Thomas Gelsing Carlsen", "Torkell Ellingsen", "Ole Kristian Bonderup", "Henning Glerup", "Martin Bøgsted", "Gunna Christiansen", "Svend Birkelund", "Vibeke Andersen", "Allan Stensballe"], "journal": "Data in brief", "year": 2017, "abstract": "The datasets presented in this article are related to the research articles entitled \"Neutrophil Extracellular Traps in Ulcerative Colitis: A Proteome Analysis of Intestinal Biopsies\" (Bennike et al., 2015 [1]), and \"Proteome Analysis of Rheumatoid Arthritis Gut Mucosa\" (Bennike et al., 2017 [2]). The colon mucosa represents the main interacting surface of the gut microbiota and the immune system. Studies have found an altered composition of the gut microbiota in rheumatoid arthritis patients (Zhang et al., 2015; Vaahtovuo et al., 2008; Hazenberg et al., 1992) [5], [6], [7] and inflammatory bowel disease patients (Morgan et al., 2012; Abraham and Medzhitov, 2011; Bennike, 2014) [8], [9], [10]. Therefore, we characterized the proteome of colon mucosa biopsies from 10 inflammatory bowel disease ulcerative colitis (UC) patients, 11 gastrointestinal healthy rheumatoid arthritis (RA) patients, and 10 controls. We conducted the sample preparation and liquid chromatography mass spectrometry (LC-MS/MS) analysis of all samples in one batch, enabling label-free comparison between all biopsies. The datasets are made publicly available to enable critical or extended analyses. The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples.", "claims": [{"id": "claim-data-access", "statement": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29085871", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used label-free LC-MS/MS comparison across all biopsy samples, and the source data are available through PRIDE via ProteomeXchange under PXD001608 and PXD003082; no numerical statistical result is reported for this target.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29085871", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We conducted the sample preparation and liquid chromatography mass spectrometry (LC-MS/MS) analysis of all samples in one batch, enabling label-free comparison between all biopsies."}, {"asset": "source:pmid:29085871", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used label-free LC-MS/MS comparison across all biopsy samples, and the source data are available through PRIDE via ProteomeXchange under PXD001608 and PXD003082; no numerical statistical result is reported for this target.", "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:29085871"], "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:PXD001608"], "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:PXD001608"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29085871", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2017.09.059", "sha256": "sha256:0ce5a39782dda7c6842bc75f3def981cfeec2e2ea3ce42b6197feb6a2164078d", "bytes": 14245, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2017.09.059", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5650644", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD001608", "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=PXD001608", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001608", "version": null, "note": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Human colon biopsies (healthy and Ulcerative Colitis) 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": "data:geo:PXD003082", "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=PXD003082", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD003082", "version": null, "note": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "A proteome analysis by LC-MS/MS of human colon mucosal biopsies from gastrointestinal healthy rheumatoid arthritis patients", "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:29085871:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:79e6d0f422f4cfedd5a75152f74539ab670248eb781acf1dfb145552d9e8e288", "bytes": 1693, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0015", "version": null, "note": null, "structure": {"pmcid": "PMC5650644", "section_index": 1, "section_title": "p", "row_count": 14, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Characterization of the proteome of the colon mucosa of ulcerative colitis patients, gastrointestinal healthy rheumatoid arthritis patients, and controls."], ["Type of data", "Raw- mass spectrometry files and text/excel files"], ["How data was acquired", "Mass Spectrometry Liquid Chromatography"], ["Data was acquired using a high-resolution/high-accuracy Q Exactive plus (Thermo Scientific) mass spectrometer."], ["Data format", "Raw- and analyzed data."], ["Experimental factors", "Human colon mucosal biopsies from ulcerative colitis patients, gastrointestinal healthy rheumatoid arthritis patients, and controls."], ["Experimental features", "Biopsies were extracted by colonoscopy and immediately snap-frozen with liquid nitrogen. The biopsies were tryptic digested and analyzed by electrospray ionization liquid chromatography mass spectrometry."], ["Data source location", "The Laboratory for Medical Mass Spectrometry, Department of Health Science and Technology, Aalborg University, Fredrik Bajers Vej 7E, 9220 Aalborg East, Denmark"], ["Data accessibility", "The proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository, [13], [14], [15], [16] with dataset identifiers:"], ["PXD001608 – Ulcerative colitis patients, and controls."], ["PXD003082 – Gastrointestinal healthy rheumatoid arthritis patients."], ["Direct download links: http://www.ebi.ac.uk/pride/archive/projects/PXD001608"], ["http://www.ebi.ac.uk/pride/archive/projects/PXD003082"]], "row_count": 14, "column_count": 2, "numeric_cells": 6, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0015"}}, {"id": "asset:table:pmid:29085871:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:79e6d0f422f4cfedd5a75152f74539ab670248eb781acf1dfb145552d9e8e288", "bytes": 1693, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0015", "version": null, "note": null, "structure": {"pmcid": "PMC5650644", "section_index": 2, "section_title": "p", "row_count": 14, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Characterization of the proteome of the colon mucosa of ulcerative colitis patients, gastrointestinal healthy rheumatoid arthritis patients, and controls."], ["Type of data", "Raw- mass spectrometry files and text/excel files"], ["How data was acquired", "Mass Spectrometry Liquid Chromatography"], ["Data was acquired using a high-resolution/high-accuracy Q Exactive plus (Thermo Scientific) mass spectrometer."], ["Data format", "Raw- and analyzed data."], ["Experimental factors", "Human colon mucosal biopsies from ulcerative colitis patients, gastrointestinal healthy rheumatoid arthritis patients, and controls."], ["Experimental features", "Biopsies were extracted by colonoscopy and immediately snap-frozen with liquid nitrogen. The biopsies were tryptic digested and analyzed by electrospray ionization liquid chromatography mass spectrometry."], ["Data source location", "The Laboratory for Medical Mass Spectrometry, Department of Health Science and Technology, Aalborg University, Fredrik Bajers Vej 7E, 9220 Aalborg East, Denmark"], ["Data accessibility", "The proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository, [13], [14], [15], [16] with dataset identifiers:"], ["PXD001608 – Ulcerative colitis patients, and controls."], ["PXD003082 – Gastrointestinal healthy rheumatoid arthritis patients."], ["Direct download links: http://www.ebi.ac.uk/pride/archive/projects/PXD001608"], ["http://www.ebi.ac.uk/pride/archive/projects/PXD003082"]], "row_count": 14, "column_count": 2, "numeric_cells": 6, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0015"}}, {"id": "asset:table:pmid:29085871:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ad7c5686dd3bc49a6247b95b8986856262239a1137f0990daed2667f6adf7917", "bytes": 3046, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t0005", "version": null, "note": "Raw-datafiles in PXD001608 and PXD003082. All samples were analyzed in technical triplicates, and all raw-files are named accordingly (e.g. Ctrl_10_3 is the third repeat of control 10). “Poor R” signifies a Pearson's correlation coefficient R<0.95 between the technical repeats, and additional data validation is recommended for studies including these datafiles. The number of identified proteins in each replicate is given, wo/w the MaxQuant match between runs feature which transfer MS/MS information between different LC-MS/MS analysis. RA: Rheumatoid arthritis, UC: ulcerative colitis, NA: Not available.", "structure": {"pmcid": "PMC5650644", "section_index": 3, "section_title": "Data", "row_count": 32, "column_count": 6}, "table": {"label": "Table 1", "caption": "Raw-datafiles in PXD001608 and PXD003082. All samples were analyzed in technical triplicates, and all raw-files are named accordingly (e.g. Ctrl_10_3 is the third repeat of control 10). “Poor R” signifies a Pearson's correlation coefficient R<0.95 between the technical repeats, and additional data validation is recommended for studies including these datafiles. The number of identified proteins in each replicate is given, wo/w the MaxQuant match between runs feature which transfer MS/MS information between different LC-MS/MS analysis. RA: Rheumatoid arthritis, UC: ulcerative colitis, NA: Not available.", "rows": [["Filename", "Sample", "#Proteins matching OFF", "#Proteins matching ON", "Dataset ID", "Comment"], ["Ctrl_1", "Control", "4362, 4279, 4241", "5967, 5903, 5897", "PXD001608", ""], ["Ctrl_2", "Control", "3613, 3607, 3595", "5657, 5664, 5723", "PXD001608", ""], ["Ctrl_3", "Control", "4203, 4203, 4188", "5936, 5952, 5939", "PXD001608", ""], ["Ctrl_4", "Control", "4245, 4268, 4191", "5863, 5865, 5849", "PXD001608", ""], ["Ctrl_5", "Control", "3961, 3881, 3903", "5694, 5683, 5632", "PXD001608", ""], ["Ctrl_6", "Control", "4290, 4281, 4242", "5966, 5959, 5932", "PXD001608", ""], ["Ctrl_7", "Control", "4080, 4099, 4097", "5856, 5822, 5817", "PXD001608", ""], ["Ctrl_8", "Control", "4269, 4325, 4336", "5968, 5986, 5966", "PXD001608", ""], ["Ctrl_9", "Control", "4560, 4549, 3974", "6103, 6126, 6103", "PXD001608", ""], ["Ctrl_10", "Control", "3974, 3993, 3972", "5781, 5817, 5779", "PXD001608", ""], ["UC_1", "UC", "4290, 4229, 4363", "5870, 5852, 5907", "PXD001608", ""], ["UC_2", "UC", "3328, 3285, 3328", "5148, 5101, 5139", "PXD001608", ""], ["UC_3", "UC", "4455, 4472, 4482", "6068, 6082, 6041", "PXD001608", ""], ["UC_4", "UC", "4236, 4005, NA", "5685, 5773, NA", "PXD001608", "UC_4_3 poor R"], ["UC_5", "UC", "3097, 3174, NA", "5051, 5017, NA", "PXD001608", "UC_5_3 poor R"], ["UC_6", "UC", "4458, 4424, 4482", "6118, 6108, 6115", "PXD001608", ""], ["UC_7", "UC", "3657, 3686, 3693", "5647, 5626, 5575", "PXD001608", ""], ["UC_8", "UC", "3356, 3288, 3303", "5237, 5207, 5164", "PXD001608", ""], ["UC_9", "UC", "4681, 4700, 4703", "6220, 6233, 6223", "PXD001608", ""], ["UC_10", "UC", "3762, 3688, 3674", "5587, 5557, 5562", "PXD001608", ""], ["RA_1", "RA", "3900, 3789, 3755", "5658, 5644, 5632", "PXD003082", ""], ["RA_2", "RA", "4347, 4141, 4285", "6023, 5997, 5973", "PXD003082", ""], ["RA_3", "RA", "4654, 4678, 4629", "6204, 6179, 6180", "PXD003082", ""], ["RA_4", "RA", "4298, 4287, 4267", "5933, 5925, 5899", "PXD003082", ""], ["RA_5", "RA", "3472, 3521, 3491", "5402, 5390, 5344", "PXD003082", ""], ["RA_6", "RA", "3545, 3485, 3526", "5735, 5742, 5728", "PXD003082", ""], ["RA_7", "RA", "4538, 4476, 4459", "6057, 6062, 6071", "PXD003082", ""], ["RA_8", "RA", "3619, 3439 NA", "5317, 5310, NA", "PXD003082", "RA_8_3 poor R"], ["RA_9", "RA", "3361, NA, 3427,", "5256, NA, 5187", "PXD003082", "RA_9_2 poor R"], ["RA_10", "RA", "4417, 4354, 4361", "5991, 6010, 6023", "PXD003082", ""], ["RA_11", "RA", "3094, 3055, 3051", "5005, 5050, 5006", "PXD003082", ""]], "row_count": 32, "column_count": 6, "numeric_cells": 128, "header_rows": 1, "locator": "section[3]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:29085871:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7c7f92c46bd92c21acbec1119a2a79d5f6957502f8169e3b82d1427cfa823a19", "bytes": 1153, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#t0010", "version": null, "note": "Additional submitted Search and FASTA files in PXD001608 and PXD003082. RA: Rheumatoid arthritis, UC: ulcerative colitis.", "structure": {"pmcid": "PMC5650644", "section_index": 3, "section_title": "Data", "row_count": 6, "column_count": 4}, "table": {"label": "Table 2", "caption": "Additional submitted Search and FASTA files in PXD001608 and PXD003082. RA: Rheumatoid arthritis, UC: ulcerative colitis.", "rows": [["Filename", "Dataset ID", "Content", "Description"], ["CombinedTxtFiles.zip", "PXD001608", "Zipped MaxQuant combined txt folder.", "Result of the label-free quantitative analysis of UC and controls in MaxQuant. The content of each file is described in “tables.pdf”."], ["131008_Swissprot_Human_Ref_ proteome.fasta", "PXD001608", "Protein FASTA database file.", "Protein database used for the UC and controls analysis."], ["MaxQuantOutput.zip", "PXD003082", "Zipped MaxQuant combined txt folder.", "Result of the label-free quantitative analysis of UC, RA, and controls in MaxQuant. The content of each file is described in “tables.pdf”."], ["UniprotHumanProteome P000005640Isoforms.fasta", "PXD003082", "Protein FASTA database file.", "Protein database used for the UC, RA, and controls analysis."], ["FASTA file parameters.txt", "PXD003082", "FASTA info.", "Information regarding the database."]], "row_count": 6, "column_count": 4, "numeric_cells": 7, "header_rows": 1, "locator": "section[3]/table-wrap[2]#t0010"}}], "gaps": ["asset:data:geo:PXD001608 not downloaded", "asset:data:geo:PXD001608 licence not read", "asset:data:geo:PXD003082 not downloaded", "asset:data:geo:PXD003082 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": ["PXD001608", "PXD003082"], "resolved_accessions": ["PXD001608", "PXD003082"], "statements": ["The proteomics data and search results, have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD001608 for ulcerative colitis and control samples, and PXD003082 for rheumatoid arthritis samples."], "basis": "The paper names PXD001608, PXD003082 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:29085871", "data:geo:PXD001608", "asset:table:pmid:29085871:1", "asset:table:pmid:29085871:2", "asset:table:pmid:29085871:3", "asset:table:pmid:29085871:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD001608"]}, "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": "2026-10-31T18:32:37Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 34235, "completion_tokens": 3297, "cached_tokens": 2089}}, "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:29085871", "type": "paper", "label": "pmid:29085871"}, {"id": "source:pmid:29085871", "type": "manuscript", "label": "PMID 29085871 full text"}, {"id": "data:geo:PXD001608", "type": "dataset", "label": "GEO PXD001608"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29085871", "type": "paper", "label": "pmid:29085871"}, {"id": "source:pmid:29085871", "type": "manuscript", "label": "PMID 29085871 full text"}, {"id": "data:geo:PXD001608", "type": "dataset", "label": "GEO PXD001608"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29085871", "type": "extraction", "used": ["source:pmid:29085871"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD001608", "type": "accession_resolution", "used": ["data:geo:PXD001608"], "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:29085871", "parent_hash": "sha256:fb2b66a78c04b9c53bf3339eb8f639573f085e8f745758385fd6d98b7a26402e", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PXD001608 licence not read", "asset:data:geo:PXD001608 not downloaded", "asset:data:geo:PXD003082 licence not read", "asset:data:geo:PXD003082 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Proteomics dataset: The colon mucosa from inflammatory", "to enable critical or extended analyses. The proteomics data and search results, have been deposited", "gen followed by storage at minus 80 °C until proteomics sample preparation. All participants had giv", "Danish Data Protection Agency (2008-58-035). Proteomic sample preparation The biopsies were randomi"], "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":"2026-11-04T02:36:11+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}}}