{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34359700", "kind": "science-record", "revision": 6, "content_hash": "sha256:c8f0d4f8bef5eb22442da58567dac6815911403daebd1d7ecc432a444a05a817", "created_at": "2026-11-01T15:41:47Z", "updated_at": "2026-11-01T21:25:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comprehensive Library Generation for Identification and Quantification of Endometrial Cancer Protein Biomarkers in Cervico-Vaginal Fluid.", "doi": "10.3390/cancers13153804", "pmid": "34359700", "authors": ["Kelechi Njoku", "Davide Chiasserini", "Bethany Geary", "Andrew Pierce", "Eleanor R Jones", "Anthony D Whetton", "Emma J Crosbie"], "journal": "Cancers", "year": 2021, "abstract": "Endometrial cancer is the most common gynaecological malignancy in high-income countries and its incidence is rising. Early detection, aided by highly sensitive and specific biomarkers, has the potential to improve outcomes as treatment can be provided when it is most likely to effect a cure. Sequential window acquisition of all theoretical mass spectra (SWATH-MS), an accurate and reproducible platform for analysing biological samples, offers a technological advance for biomarker discovery due to its reproducibility, sensitivity and potential for data re-interrogation. SWATH-MS requires a spectral library in order to identify and quantify peptides from multiplexed mass spectrometry data. Here we present a bespoke spectral library of 154,206 transitions identifying 19,394 peptides and 2425 proteins in the cervico-vaginal fluid of postmenopausal women with, or at risk of, endometrial cancer. We have combined these data with a library of over 6000 proteins generated based on mass spectrometric analysis of two endometrial cancer cell lines. This unique resource enables the study of protein biomarkers for endometrial cancer detection in cervico-vaginal fluid. Data are available via ProteomeXchange with unique identifier PXD025925.", "claims": [{"id": "claim-method", "statement": "Principal component analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE) plots were then used to assess degree of separation between groups and shown in Figure 10.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34359700", "locator": "sections[19] \"3.3.2. Real World Application of Spectral Library for Biomarker Discovery\" paragraph 4", "quote": "Principal component analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE) plots were then used to assess degree of separation between groups and shown in Figure 10."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All datasets have been deposited in ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org/ (accessed on 26 July 2021)) via the PRIDE partner repository with the dataset identifier PXD025925.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34359700", "locator": "sections[27] \"Data Availability Statement\" paragraph 2", "quote": "All datasets have been deposited in ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org/ (accessed on 26 July 2021)) via the PRIDE partner repository with the dataset identifier PXD025925."}], "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:34359700"], "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:PXD025925"], "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:PXD025925"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34359700", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers13153804", "sha256": "sha256:66704eb3872711fce12f7b3d02cb63235907115631e3d44e830e407a9456d5c0", "bytes": 66738, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers13153804", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8345211", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD025925", "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=PXD025925", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD025925", "version": null, "note": "All datasets have been deposited in ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org/ (accessed on 26 July 2021)) via the PRIDE partner repository with the dataset identifier PXD025925.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets have been deposited in ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org/ (accessed on 26 July 2021)) via the PRIDE partner repository with the dataset identifier PXD025925.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Comprehensive spectral  library generation for identification and quantification of endometrial cancer protein biomarkers in cervico-vaginal fluid", "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:34359700:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d7874e02bb135d41244056e0cc2d9717a86d1dbf9e091cfbcaaad5cc1db08ccf", "bytes": 813, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#cancers-13-03804-t001", "version": null, "note": "Eligibility criteria for case and control selection.", "structure": {"pmcid": "PMC8345211", "section_index": 3, "section_title": "2.1. Research Ethics and Approval", "row_count": 6, "column_count": 2}, "table": {"label": "Table 1", "caption": "Eligibility criteria for case and control selection.", "rows": [["Cases", "Controls"], ["Referred with postmenopausal bleeding", "Referred with postmenopausal bleeding"], ["Biopsy proven AH or EC", "AH and EC excluded following routine diagnostic investigations, including TVS, biopsy and/or hysteroscopy"], ["Able to give informed consent", "Able to give informed consent"], ["Sample taken prior to commencement of any treatment, including surgery, hormone therapy or chemotherapy", "Sample taken prior to commencement of any treatment, including surgery or hormone therapy"], ["", "Can include those with benign pathologies such as benign polyp or atrophic vaginitis"]], "row_count": 6, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[3]/table-wrap[1]#cancers-13-03804-t001"}}, {"id": "asset:table:pmid:34359700:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0354cba511012f06395df2bef7df6050072ce9fef1ad3ac191ac485cb471057a", "bytes": 1464, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#cancers-13-03804-t002", "version": null, "note": "Demographic and clinical characteristics of cases and controls whose samples were used for library generation.", "structure": {"pmcid": "PMC8345211", "section_index": 15, "section_title": "3.1. Descriptive Characteristics of the Study Population", "row_count": 21, "column_count": 6}, "table": {"label": "Table 2", "caption": "Demographic and clinical characteristics of cases and controls whose samples were used for library generation.", "rows": [["Serial Number", "Age(Years)", "BMI(kg/m2)", "Diagnosis", "Grade", "Stage"], ["Library Generation Cohort"], ["1", "57", "38", "Atypical Hyperplasia", "-", "-"], ["2", "78", "45", "Atypical Hyperplasia", "-", "-"], ["3", "61", "37", "Atypical Hyperplasia", "-", "-"], ["4", "65", "27", "Endometrioid Endometrial cancer", "1", "1A"], ["5", "60", "43", "Endometrioid Endometrial cancer", "1", "1A"], ["6", "73", "29", "Endometrioid Endometrial cancer", "2", "1A"], ["7", "52", "30", "Endometrioid Endometrial cancer", "2", "1A"], ["8", "62", "27", "Clear Cell Endometrial cancer", "3", "1A"], ["9", "52", "30", "Serous Endometrial cancer", "3", "1A"], ["10", "74", "27", "Carcinosarcoma", "3", "1B"], ["11", "72", "27", "Mixed (Clear Cell/Endometrioid) cancer", "3", "2"], ["12", "84", "28", "Endometrioid Endometrial cancer", "3", "4B"], ["13", "54", "29", "Control (No endometrial pathology)", "-", "-"], ["14", "81", "24", "Control (No endometrial pathology)", "-", "-"], ["15", "56", "24", "Control (Atrophic vaginitis)", "-", "-"], ["16", "56", "40", "Control (No endometrial pathology)", "-", "-"], ["17", "52", "44", "Control (No endometrial pathology)", "-", "-"], ["18", "50", "24", "Control (No endometrial pathology)", "-", "-"], ["19", "56", "24", "Control (No endometrial pathology)", "-", "-"]], "row_count": 21, "column_count": 6, "numeric_cells": 75, "header_rows": 1, "locator": "section[15]/table-wrap[1]#cancers-13-03804-t002"}}, {"id": "asset:table:pmid:34359700:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86714ae5461f5d13c8f50cc74ccb9e2cd44fc838508611e7b73776f02bc6b36a", "bytes": 714, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#cancers-13-03804-t003", "version": null, "note": "Assay statistics for the consensus cervico-vaginal fluid and endometrial cancer cell-based spectral libraries at a protein FDR of 1%.", "structure": {"pmcid": "PMC8345211", "section_index": 16, "section_title": "3.2. The Spectral Libraries", "row_count": 11, "column_count": 3}, "table": {"label": "Table 3", "caption": "Assay statistics for the consensus cervico-vaginal fluid and endometrial cancer cell-based spectral libraries at a protein FDR of 1%.", "rows": [["Assays", "Proteotypic", "Proteotypic and Shared"], ["Consensus cervico-vaginal fluid spectral library"], ["Proteins", "1836", "2425"], ["Peptides", "18,247", "19,394"], ["Precursors", "22,455", "23,886"], ["Transitions", "144,060", "154,206"], ["Endometrial cancer cell-line based spectral library"], ["Proteins", "5140", "6003"], ["Peptides", "27,972", "29,384"], ["Precursors", "29,509", "30,876"], ["Transitions", "209,988", "221,844"]], "row_count": 11, "column_count": 3, "numeric_cells": 16, "header_rows": 1, "locator": "section[16]/table-wrap[1]#cancers-13-03804-t003"}}, {"id": "asset:table:pmid:34359700:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bc1c5762fbbbf3f58ab7f041b1f98cc10bd681a331ecfeaa7a14011bd57bfcd3", "bytes": 1365, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[2]#cancers-13-03804-t004", "version": null, "note": "Comparative overview of the various studies on the cervico-vaginal (CVF) proteome conducted in non-pregnant women.", "structure": {"pmcid": "PMC8345211", "section_index": 16, "section_title": "3.2. The Spectral Libraries", "row_count": 10, "column_count": 5}, "table": {"label": "Table 4", "caption": "Comparative overview of the various studies on the cervico-vaginal (CVF) proteome conducted in non-pregnant women.", "rows": [["Study Characteristics", "Our CVF Spectral Library", "CVF Proteome by Zegel et al. [23]", "CVF Proteome by Tang et al. [24]", "CVF Proteome by Shaw et al. [25]"], ["Sample size", "19", "7", "29", "5"], ["Age range", "50–67 years", "37–45 years", "24–48 years", "20–40 years"], ["Menopausal status", "Post-menopausal", "Pre-menopausal", "Pre-menopausal", "Pre-menopausal"], ["Clinical diagnoses", "9 EC cases, 3 AH and 7 symptomatic women with no EC", "All had cervical pre-cancer", "Asymptomatic women, 7 had candida", "Healthy female volunteers"], ["Sample collection", "Delphi screener(saline based wash)", "Colposcopy(5% acetic acid wash)", "Syringe(saline based wash)", "Gauze(inserted in vagina for 1 h)"], ["Sample description", "Supernatant and pellets", "Supernatant only", "Supernatant only", "Whole fluid"], ["Sample analysis", "Orbitrap Fusion Lumos Tribrid LC-MS", "MALDI-TOF-TOF MS/MS", "MALDI-TOF-TOF MS/MS", "1D-SDS-PAGE, cation exchange, LS-MS/MS"], ["Protein identification", "X!Tandem", "MASCOT", "MASCOT", "MASCOT & X!Tandem"], ["Spectral library protein count", "2425", "339", "147 (59 unique)", "685"]], "row_count": 10, "column_count": 5, "numeric_cells": 20, "header_rows": 1, "locator": "section[16]/table-wrap[2]#cancers-13-03804-t004"}}, {"id": "asset:table:pmid:34359700:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:968db2c2b0cde85a5dcbf93bc3e8ac651c56f8c63697383f3655ca62bee3bee2", "bytes": 1294, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#cancers-13-03804-t005", "version": null, "note": "Demographic and clinical characteristics of the technical and clinical validation cohorts.", "structure": {"pmcid": "PMC8345211", "section_index": 17, "section_title": "3.3. Spectral Library Validation", "row_count": 18, "column_count": 6}, "table": {"label": "Table 5", "caption": "Demographic and clinical characteristics of the technical and clinical validation cohorts.", "rows": [["Serial Number", "Age(Years)", "BMI(kg/m2)", "Diagnosis", "Grade", "Stage"], ["", "", "", "Technical Validation Cohort", "", ""], ["20", "50", "19", "Control (No endometrial pathology)", "", ""], ["21", "52", "37", "Control (Benign endometrial polyp)", "", ""], ["22", "55", "34", "Control (No endometrial pathology)", "", ""], ["23", "56", "19", "Control (No endometrial pathology)", "", ""], ["24", "56", "37", "Control (No endometrial pathology)", "", ""], ["", "", "", "Clinical Validation Cohort", "", ""], ["25", "58", "36", "Atypical Hyperplasia", "-", "-"], ["26", "67", "30", "Endometrioid endometrial cancer", "1", "1A"], ["27", "55", "34", "Endometrioid endometrial cancer", "1", "1A"], ["28", "50", "54", "Endometrioid endometrial cancer", "1", "1A"], ["29", "62", "27", "Clear cell", "3", "1A"], ["30", "60", "58", "Control (No endometrial pathology)", "-", "-"], ["31", "62", "24", "Control (Atrophic vaginitis)", "-", "-"], ["32", "58", "30", "Control (Benign endometrial polyp)", "-", "-"], ["33", "47", "24", "Control (No endometrial pathology)", "-", "-"], ["34", "52", "33", "Control (No endometrial pathology)", "-", "-"]], "row_count": 18, "column_count": 6, "numeric_cells": 53, "header_rows": 1, "locator": "section[17]/table-wrap[1]#cancers-13-03804-t005"}}, {"id": "asset:table:pmid:34359700:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:230f54630e9267e2c97544ed199fb9b21a07e3c796523784e0776a25bfadb2e4", "bytes": 605, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#cancers-13-03804-t006", "version": null, "note": "Missing values between technical replicates of the same cervico-vaginal fluid samples.", "structure": {"pmcid": "PMC8345211", "section_index": 18, "section_title": "3.3.1. Technical Validation and Applicability for SWATH-MS Data Analysis", "row_count": 6, "column_count": 5}, "table": {"label": "Table 6", "caption": "Missing values between technical replicates of the same cervico-vaginal fluid samples.", "rows": [["Sample", "Protein Count", "Missing Values in Replicate 1", "Missing Values in Replicate 2", "Overall Rate"], ["Sample 1", "410", "21(5.1%)", "32(7.8%)", "12.9%"], ["Sample 2", "389", "25(6.4%)", "28(7.2%)", "13.6%"], ["Sample 3", "308", "37(12.0%)", "30(9.7%)", "21.8%"], ["Sample 4", "378", "29(7.7%)", "33(8.7%)", "16.4%"], ["Sample 5", "426", "25(5.9%)", "35(8.2%)", "14.1%"]], "row_count": 6, "column_count": 5, "numeric_cells": 27, "header_rows": 1, "locator": "section[18]/table-wrap[1]#cancers-13-03804-t006"}}, {"id": "asset:table:pmid:34359700:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:10950a4c49a02a7a10a37813e141af76f3d6f52fa82d77ef655827faafa21625", "bytes": 642, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#cancers-13-03804-t007", "version": null, "note": "Reproducibility of selected biomarker candidates using the consensus cervico-vaginal fluid spectral library.", "structure": {"pmcid": "PMC8345211", "section_index": 19, "section_title": "3.3.2. Real World Application of Spectral Library for Biomarker Discovery", "row_count": 6, "column_count": 4}, "table": {"label": "Table 7", "caption": "Reproducibility of selected biomarker candidates using the consensus cervico-vaginal fluid spectral library.", "rows": [["Biomarker Candidate", "Gene Name", "Intensity Correlation Coefficient", "Coefficient of Variation"], ["Human Epididymis Protein 4", "HE4/WFDC2", "0.99", "3.29"], ["Cancer Associated Antigen 15-3", "MUC-1", "0.99", "4.88"], ["Matrix Metalloproteinase 9", "MMP9", "0.99", "2.01"], ["Fatty Acid Binding Protein-5", "FABP5", "0.99", "0.62"], ["Alpha-1B-Glycoprotein", "AIBG", "0.99", "1.36"]], "row_count": 6, "column_count": 4, "numeric_cells": 16, "header_rows": 1, "locator": "section[19]/table-wrap[1]#cancers-13-03804-t007"}}], "gaps": ["asset:data:geo:PXD025925 not downloaded", "asset:data:geo:PXD025925 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Principal component analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE) plots were then used to assess degree of separation between groups and shown in Figure 10."}}], "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": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["PXD025925"], "resolved_accessions": ["PXD025925"], "statements": ["All datasets have been deposited in ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org/ (accessed on 26 July 2021)) via the PRIDE partner repository with the dataset identifier PXD025925."], "basis": "The paper names PXD025925 in ProteomeXchange Consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:34359700", "data:geo:PXD025925", "asset:table:pmid:34359700:1", "asset:table:pmid:34359700:2", "asset:table:pmid:34359700:3", "asset:table:pmid:34359700:4", "asset:table:pmid:34359700:5", "asset:table:pmid:34359700:6", "asset:table:pmid:34359700:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD025925"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:23Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 51392, "completion_tokens": 1445, "cached_tokens": 784}}, "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:34359700", "type": "paper", "label": "pmid:34359700"}, {"id": "source:pmid:34359700", "type": "manuscript", "label": "PMID 34359700 full text"}, {"id": "data:geo:PXD025925", "type": "dataset", "label": "GEO PXD025925"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34359700", "type": "paper", "label": "pmid:34359700"}, {"id": "source:pmid:34359700", "type": "manuscript", "label": "PMID 34359700 full text"}, {"id": "data:geo:PXD025925", "type": "dataset", "label": "GEO PXD025925"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34359700", "type": "extraction", "used": ["source:pmid:34359700"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD025925", "type": "accession_resolution", "used": ["data:geo:PXD025925"], "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:34359700", "parent_hash": "sha256:d3bdabd2abcf1c151479f245a99d6e51389b37db9dccc049a1a8490eb25cad71", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD025925 licence not read", "asset:data:geo:PXD025925 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ed and tested for Mycoplasma prior to usage. Cell lines were cultured in DMEM growth medium (Gibco Life Technologi", "r Mycoplasma prior to usage. Cell lines were cultured in DMEM growth medium (Gibco Life Technologies;"], "order_basis": "paper_text_order:2518", "id": "assay:1"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Principal component analysis (PCA) and t-distributed stochastic neighbour embedding (t-SNE) plots were then used to assess degree of separation between groups and shown in Figure 10."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:15:11+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}}}