{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28666451", "kind": "science-record", "revision": 8, "content_hash": "sha256:25a27d8fc49ad2af30885baa8bb7d3289d42000038900a08dc35d78b4a1ef3c8", "created_at": "2026-11-01T15:40:27Z", "updated_at": "2026-11-01T22:43:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Autologous chondrocyte implantation-derived synovial fluids display distinct responder and non-responder proteomic profiles.", "doi": "10.1186/s13075-017-1336-7", "pmid": "28666451", "authors": ["Charlotte H Hulme", "Emma L Wilson", "Mandy J Peffers", "Sally Roberts", "Deborah M Simpson", "James B Richardson", "Pete Gallacher", "Karina T Wright"], "journal": "Arthritis research & therapy", "year": 2017, "abstract": "BACKGROUND: Autologous chondrocyte implantation (ACI) can be used in the treatment of focal cartilage injuries to prevent the onset of osteoarthritis (OA). However, we are yet to understand fully why some individuals do not respond well to this intervention. Identification of a reliable and accurate biomarker panel that can predict which patients are likely to respond well to ACI is needed in order to assign the patient to the most appropriate therapy. This study aimed to compare the baseline and mid-treatment proteomic profiles of synovial fluids (SFs) obtained from responders and non-responders to ACI.\nMETHODS: SFs were derived from 14 ACI responders (mean Lysholm improvement of 33 (17-54)) and 13 non-responders (mean Lysholm decrease of 14 (4-46)) at the two stages of surgery (cartilage harvest and chondrocyte implantation). Label-free proteome profiling of dynamically compressed SFs was used to identify predictive markers of ACI success or failure and to investigate the biological pathways involved in the clinical response to ACI.\nRESULTS: Only 1 protein displayed a ≥2.0-fold differential abundance in the preclinical SF of ACI responders versus non-responders. However, there is a marked difference between these two groups with regard to their proteome shift in response to cartilage harvest, with 24 and 92 proteins showing ≥2.0-fold differential abundance between Stages I and II in responders and non-responders, respectively. Proteomic data has been uploaded to ProteomeXchange (identifier: PXD005220). We have validated two biologically relevant protein changes associated with this response, demonstrating that matrix metalloproteinase 1 was prominently elevated and S100 calcium binding protein A13 was reduced in response to cartilage harvest in non-responders.\nCONCLUSIONS: The differential proteomic response to cartilage harvest noted in responders versus non-responders is completely novel. Our analyses suggest several pathways which appear to be altered in non-responders that are worthy of further investigation to elucidate the mechanisms of ACI failure. These protein changes highlight many putative biomarkers that may have potential for prediction of ACI treatment success.", "claims": [{"id": "claim-method", "statement": "Statistical analysis was performed using ProgenesisQI™ software; briefly transformed normalised abundances were used for one-way analysis of variance (ANOVA) and all peptides (with p < 0.05) of an identified protein were included.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28666451", "locator": "sections[6] \"Mass spectrometry and label-free quantification\" paragraph 2", "quote": "Statistical analysis was performed using ProgenesisQI™ software; briefly transformed normalised abundances were used for one-way analysis of variance (ANOVA) and all peptides (with p < 0.05) of an identified protein were included."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Proteomic data has been deposited in the PRIDE ProteomeXchange and can be accessed using the identifier PXD005220.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28666451", "locator": "sections[17] \"ack\" paragraph 1", "quote": "Proteomic data has been deposited in the PRIDE ProteomeXchange and can be accessed using the identifier PXD005220."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used Ingenuity pathway analysis with a right-sided Fisher’s exact test and an independent DAVID pathway analysis, while the underlying proteomic source data were deposited in PRIDE ProteomeXchange under identifier PXD005220.", "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:28666451"], "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:PXD005220"], "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:PXD005220"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28666451", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13075-017-1336-7", "sha256": "sha256:c098eae219b4c813614ad855bcebd23e82a42d28d0f8493f76b2eef7501212f2", "bytes": 50158, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13075-017-1336-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5493128", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD005220", "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=PXD005220", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD005220", "version": null, "note": "Proteomic data has been deposited in the PRIDE ProteomeXchange and can be accessed using the identifier PXD005220.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Proteomic data has been deposited in the PRIDE ProteomeXchange and can be accessed using the identifier PXD005220.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic profiles of  synovial fluids derived from autologous chondrocyte implantation surgery", "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:28666451:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bc4afaf837a5d76c20b6ba7a8a43906f9d8bec36a19036c13386050a7233c8ea", "bytes": 1940, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Demographic data for patient participants whose samples from Stage I or Stage II were analysed who responded clinically (responders) or who did not respond (non-responders) to autologous chondrocyte implantation (ACI)", "structure": {"pmcid": "PMC5493128", "section_index": 3, "section_title": "Synovial fluid collection and storage", "row_count": 16, "column_count": 7}, "table": {"label": "Table 1", "caption": "Demographic data for patient participants whose samples from Stage I or Stage II were analysed who responded clinically (responders) or who did not respond (non-responders) to autologous chondrocyte implantation (ACI)", "rows": [["", "Stage I", "Stage II", "p value (A) R v NR SI; (B) R v NR SI", "p value (A) SI v SII R; (B) SI v SII NR"], ["Responders (n = 8)", "Non-responders (n = 7)", "Responders (n = 12)", "Non-responders (n = 12)"], ["Difference in Lysholm Score", "27 (17–38)", "–8 (–4 to –17)", "34 (17–54)", "–11 (–4 to –46)", "(A) 0.0003; (B) <0.0001", "(A) 0.21; (B) 0.55"], ["BMI (kg/m2)", "29 (23–31)", "27 (24–31)", "27 (23–48)", "29 (22–36)", "(A) 0.94; (B) 0.54", "(A) 0.73; (B) 0.68"], ["Age (years)", "32 (17–49)", "40 (25–50)", "40 (17–90)", "43 (25–52)", "(A) 0.28; (B) 0.92", "(A) 0.17; (B) 0.58"], ["Male (n)", "8", "7", "11", "10", "(A) >0.99; (B) >0.99", "(A) >0.99; (B) 0.51"], ["Smoker (n)", "1", "2", "1", "3", "(A) 0.54; (B) 0.59", "(A) >0.99; (B) >0.99"], ["Dilution factor of SF", "5 (3–9)", "4 (2–7)", "4 (1–9)", "3 (2–5)", "(A) 0.48; (B) 0.25", "(A) 0.53; (B) 0.50"], ["Total defect area (cm2)", "14 (0.4–24)", "6 (0.6–12)", "6 (1–20)", "5 (0.6–12)", "(A) 0.74; (B) 0.35", "(A) 0.45; (B) 0.28"], ["Patella defect (n)", "1", "1", "4", "2", "(A) >0.99; (B) 0.64", "(A) 0.60; (B) >0.99"], ["LFC defect (n)", "2", "0", "0", "0", "(A) 0.47; (B) >0.99", "(A) 0.15; (B) >0.99"], ["LTP defect (n)", "1", "0", "0", "0", "(A) >0.99; (B) >0.99", "(A) 0.15; (B) >0.99"], ["MFC defect (n)", "2", "2", "1", "6", "(A) >0.99; (B) 0.07", "(A) 0.54; (B) 0.63"], ["Trochlea defect (n)", "0", "3", "2", "1", "(A) 0.20; (B) >0.99", "(A) 0.49; (B) 0.12"], ["Multiple defects (n)", "1", "0", "1", "1", "(A) >0.99; (B) >0.99", "(A) >0.99; (B) >0.99"], ["Unknown defect location (n)", "1", "1", "4", "2", "(A) >0.99; (B) 0.64", "(A) 0.60; (B) >0.99"]], "row_count": 16, "column_count": 7, "numeric_cells": 88, "header_rows": 2, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:28666451:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:07b8c536a67e4cb2f70a7a828f3e6ff710462df9488e9ff9eba3142c1275cb21", "bytes": 5011, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab2", "version": null, "note": "Fold-change of proteins that are differentially expressed in the synovial fluid collected at Stage I compared to Stage II of the ACI procedure in clinical non-responders. Proteins shown in italic were validated using enzyme linked immunosorbant assay", "structure": {"pmcid": "PMC5493128", "section_index": 11, "section_title": "Differential abundance of proteins after controlled cartilage injury (Stage I versus Stage II)", "row_count": 91, "column_count": 3}, "table": {"label": "Table 2", "caption": "Fold-change of proteins that are differentially expressed in the synovial fluid collected at Stage I compared to Stage II of the ACI procedure in clinical non-responders. Proteins shown in italic were validated using enzyme linked immunosorbant assay", "rows": [["Protein", "Fold change"], ["Description", "Accession"], ["Perilipin-4", "Q96Q06", "–4.3"], ["Syntaxin-7", "O15400", "–3.9"], ["Fermitin family homolog 3", "Q86UX7", "–3.7"], ["Deoxynucleoside triphosphate triphosphohydrolase SAMHD1", "Q9Y3Z3", "–3.7"], ["PDZ and LIM domain protein 1", "O00151", "–3.6"], ["Sorting nexin-5", "Q9Y5X3", "–3.3"], ["Neuroblast differentiation-associated protein AHNAK", "Q09666", "–3.2"], ["Signal recognition particle 14 kDa protein", "P37108", "–3.0"], ["Hyaluronan and proteoglycan link protein 3", "Q96S86", "–3.0"], ["Heterogeneous nuclear ribonucleoprotein K", "P61978", "–2.9"], ["ATP-citrate synthase", "P53396", "–2.9"], ["Fatty acid-binding protein, epidermal", "Q01469", "–2.8"], ["60S ribosomal protein L12", "P30050", "–2.7"], ["Fatty acid-binding protein, adipocyte", "P15090", "–2.6"], ["Insulin-like growth factor-binding protein 6", "P24592", "–2.6"], ["Protein canopy homolog 3", "Q9BT09", "–2.6"], ["Tripeptidyl-peptidase 1", "O14773", "–2.5"], ["PDZ and LIM domain protein 3", "Q53GG5", "–2.5"], ["Cellular nucleic acid-binding protein", "P62633", "–2.5"], ["Bifunctional glutamate/proline-tRNA ligase", "P07814", "–2.5"], ["Protein disulfide-isomerase A3", "P30101", "–2.4"], ["Peroxiredoxin-6", "P30041", "–2.4"], ["Tryptase alpha/beta-1", "Q15661", "–2.4"], ["Endoplasmic reticulum resident protein 29", "P30040", "–2.4"], ["Peroxiredoxin-1", "Q06830", "–2.4"], ["Na(+)/H(+) exchange regulatory cofactor NHE-RF1", "O14745", "–2.4"], ["Mitochondrial import inner membrane translocase subunit TIM14", "Q96DA6", "–2.4"], ["Mortality factor 4-like protein 1", "Q9UBU8", "–2.4"], ["Fructose-bisphosphate aldolase A", "P04075", "–2.3"], ["Microtubule-associated protein RP/EB family member 1", "Q15691", "–2.3"], ["Leucine zipper transcription factor-like protein 1", "Q9NQ48", "–2.3"], ["Transcription elongation factor A protein 1", "P23193", "–2.3"], ["2',3'-cyclic-nucleotide 3'-phosphodiesterase", "P09543", "–2.3"], ["Histamine N-methyltransferase", "P50135", "–2.3"], ["Protein S100-A13", "Q99584", "–2.3"], ["Acrosomal protein SP-10", "P26436", "–2.2"], ["AP-2 complex subunit beta", "P63010", "–2.2"], ["S-phase kinase-associated protein 1", "P63208", "–2.2"], ["High mobility group protein B3", "O15347", "–2.2"], ["Cytokine-like protein 1", "Q9NRR1", "–2.2"], ["Mitochondrial fission 1 protein", "Q9Y3D6", "–2.2"], ["Filamin-A", "P21333", "–2.2"], ["Nuclear migration protein nudC", "Q9Y266", "–2.1"], ["Cathepsin K", "P43235", "–2.1"], ["Prostaglandin E synthase 3", "Q15185", "–2.1"], ["Vinculin", "P18206", "–2.1"], ["Plastin-2", "P13796", "–2.1"], ["Coronin-1C", "Q9ULV4", "–2.1"], ["Ig heavy chain V-I region V35", "P23083", "–2.1"], ["Stress-induced-phosphoprotein 1", "P31948", "–2.1"], ["Putative phospholipase B-like 2", "Q8NHP8", "–2.1"], ["Gelsolin", "P06396", "–2.0"], ["Spectrin beta chain, erythrocytic", "P11277", "–2.0"], ["Stathmin", "P16949", "–2.0"], ["Hsc70-interacting protein", "P50502", "–2.0"], ["40S Ribosomal protein", "P23396", "–2.0"], ["Epidermal growth factor receptor substrate 15", "P42566", "22.5"], ["Hemoglobin subunit theta-1", "P09105", "6.1"], ["C-type lectin domain family 11 member A", "Q9Y240", "5.6"], ["Periostin", "Q15063", "5.1"], ["Collagen alpha-1(I) chain", "P02452", "4.7"], ["Spectrin alpha chain, erythrocytic 1", "P02549", "4.0"], ["Collagen alpha-1(V) chain", "P20908", "3.7"], ["Fibrinogen gamma chain", "P02679", "3.5"], ["Collagen alpha-1(XII) chain", "Q99715", "3.3"], ["Complement C1q tumor necrosis factor-related protein 3", "Q9BXJ4", "3.1"], ["Adiponectin", "Q15848", "3.0"], ["Adipocyte enhancer-binding protein 1", "Q8IUX7", "3.0"], ["Latent-transforming growth factor beta-binding protein 1", "Q14766", "3.0"], ["Fibrinogen beta chain", "P02675", "3.0"], ["Chondroitin sulfate proteoglycan 4", "Q6UVK1", "2.9"], ["Fibrinogen alpha chain", "P02671", "2.8"], ["Interstitial collagenase (MMP1)", "P03956", "2.7"], ["Secreted phosphoprotein 24", "Q13103", "2.7"], ["Collagen alpha-2(V) chain", "P05997", "2.6"], ["Ferritin light chain", "P02792", "2.6"], ["C4b-binding protein alpha chain", "P04003", "2.6"], ["Nucleobindin-1", "Q02818", "2.4"], ["C4b-binding protein beta chain", "P20851", "2.2"], ["Vitamin K-dependent protein S", "P07225", "2.2"], ["Fibronectin", "P02751", "2.2"], ["Prosaposin", "P07602", "2.1"], ["Integrin beta-like protein 1", "O95965", "2.1"], ["Adipocyte plasma membrane-associated protein", "Q9HDC9", "2.1"], ["Cytoplasmic dynein 1 heavy chain 1", "Q14204", "2.0"], ["Soluble scavenger receptor cysteine-rich domain-containing protein SSC5D", "A1L4H1", "2.0"], ["F-actin-capping protein subunit beta", "P47756", "2.0"], ["Mannan-binding lectin serine protease 1", "P48740", "2.0"], ["Thrombospondin-3", "P49746", "2.0"]], "row_count": 91, "column_count": 3, "numeric_cells": 220, "header_rows": 2, "locator": "section[11]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:28666451:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7aa5cdfc8280ec6a4158f1aa502218a473efd4500b5f6ef865567c4299dbb959", "bytes": 1577, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#Tab3", "version": null, "note": "Proteins that are differentially expressed with a ≥2.0-fold-change in the synovial fluid collected at Stage I compared to Stage II of the ACI procedure in clinical responders", "structure": {"pmcid": "PMC5493128", "section_index": 11, "section_title": "Differential abundance of proteins after controlled cartilage injury (Stage I versus Stage II)", "row_count": 26, "column_count": 3}, "table": {"label": "Table 3", "caption": "Proteins that are differentially expressed with a ≥2.0-fold-change in the synovial fluid collected at Stage I compared to Stage II of the ACI procedure in clinical responders", "rows": [["Protein", "Fold change"], ["Description", "Accession"], ["Heat shock protein 75 kDa, mitochondrial", "Q12931", "–470.0"], ["Microtubule-associated protein 1B", "P46821", "–17.2"], ["Adenosylhomocysteinase", "P23526", "–3.7"], ["Complement factor H-related protein 3", "Q02985", "–2.8"], ["Mannose-1-phosphate guanyltransferase beta", "Q9Y5P6", "–2.7"], ["Peroxiredoxin-4", "Q13162", "–2.5"], ["Oxysterol-binding protein 1", "P22059", "–2.4"], ["Protein canopy homolog 3", "Q9BT09", "–2.1"], ["Spermatid perinuclear RNA-binding protein", "Q96SI9", "–2.0"], ["Ferritin light chain", "P02792", "2.2"], ["Secreted phosphoprotein 24", "Q13103", "2.2"], ["Chondroitin sulfate proteoglycan 4", "Q6UVK1", "2.3"], ["Collagen alpha-2(I) chain", "P08123", "2.3"], ["Collagen alpha-1(V) chain", "P20908", "2.5"], ["26S protease regulatory subunit 6A", "P17980", "2.7"], ["Collagen alpha-2(V) chain", "P05997", "2.9"], ["Collagen alpha-1(I) chain", "P02452", "3.3"], ["Spectrin alpha chain, erythrocytic 1", "P02549", "4.1"], ["Histidine triad nucleotide-binding protein 1", "P49773", "4.2"], ["Platelet factor 4", "P02776", "4.2"], ["Alpha-1-acid glycoprotein 2", "P19652", "4.3"], ["Protein 4.1", "P11171", "4.3"], ["Periostin", "Q15063", "4.5"], ["26S proteasome non-ATPase regulatory subunit 13", "Q9UNM6", "4.6"]], "row_count": 26, "column_count": 3, "numeric_cells": 65, "header_rows": 2, "locator": "section[11]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:28666451:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2199179b97fa41a5fd60b7dcf5cfc145981c31f82a8e5150228d816341d5dbaf", "bytes": 2352, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab4", "version": null, "note": "Analysis of upstream regulators of interactome networks generated from protein changes between Stages I (SI) and II (SII) in either responders or non-responders to ACI were identified using Ingenuity Pathway Analysis software", "structure": {"pmcid": "PMC5493128", "section_index": 12, "section_title": "Identification of canonical pathways and protein networks associated with protein changes between Stage I and II", "row_count": 23, "column_count": 5}, "table": {"label": "Table 4", "caption": "Analysis of upstream regulators of interactome networks generated from protein changes between Stages I (SI) and II (SII) in either responders or non-responders to ACI were identified using Ingenuity Pathway Analysis software", "rows": [["Upstream regulators", "Activation z score (SII v SI)", "p value of overlap", "Target molecules in dataset"], ["Non-responders"], ["", "TGFB1", "–1.595", "9.46E–10", "APOB,APOC2,APOE,CD44,COL1A1,COL1A2,COL5A1,COMP,CSPG4,CTSD,ECM1,FETUB,FN1,FTL,GSN,HINT1,HSPG2,HTRA1,IGFBP6,LCAT,MYLK,PCOLCE2,PDXK,POSTN,RAP1A,S100A4,TGFBI"], ["DYSF", "NP", "2.01E–09", "CFD,FN1,FTL,LCP1,LYZ,PROS1,S100-A13,S100A4"], ["MYC", "3.046", "2.20E–09", "ALDOA,ANXA5,CCT3,CD44,COL1A1,COL1A2,COL5A1,CSPG4,CTSD,ECM1,FN1,HSPA9,LYZ,NCL,NUCB1,NUDC,PAM,PTN,RPL22,RPL30,TF"], ["COL9A1", "1.308", "2.79E–09", "COMP,FN1,HSPG2,TGFBI,THBS4"], ["Beta-estradiol", "2.271", "5.01E–09", "ALDOA,APOE,CD44,COL1A1,COL1A2,COMP,CTSD,F7,FN1,GMFB,HSPA2,HSPA8,HSPA9,HTRA1,IGFBP6,LTF,LYZ,MYLK,PAM,PDIA3,QSOX1,RAP1A,RPS13,S100-A13,SLC9A3R1,TF,THBS4"], ["Lipopolysaccharide", "–0.104", "5.96E–09", "ANXA5,APOB,APOC2,APOE,CD44,CFD,COL1A1,COL1A2,COL5A1,CSPG4,FN1,GSN,HDGFRP3,HMGB2,HSPA8,HTRA1,ITIH2,LBP,LTF,LYZ,PARK7,PCOLCE,PCOLCE2,PDIA3,PLG,TF"], ["Dihydrotestosterone", "–1.091", "1.03E–08", "ALDOA,APOE,CCT3,FN1,FTL,GSN,HINT1,LYZ,MYLK,NUCB1,PAM,POSTN,PROS1,RPL30,TF"], ["HRAS", "0.623", "2.52E–08", "CD44,COL1A1,COL1A2,ERP29,FN1,GSN,HSPA8,HTRA1,LYZ,MYH10,PDIA5,PLTP,POSTN,RPL30,S100A4"], ["KRAS", "2.226", "3.99E–08", "ALDOA,CD44,COL1A1,FN1,GBA,GSN,MYLK,PCOLCE,PDIA3,PSMA7,RNASE4,S100A4"], ["SMARCB1", "–1.195", "4.82E–08", "APOC4,CD44,COL1A1,COL1A2,GSN,LBP,POSTN,PTN,RAB14"], ["Responders"], ["", "CEBPB", "–1.067", "2.03E–07", "APOB,CFD,COL1A1,COL1A2,F7,HSPA8,PLG"], ["FLI1", "NP", "3.82E–07", "COL1A1,COL1A2,HSPA8,PF4"], ["S-adenosylhomocysteine", "NP", "1.21E–06", "COL1A1,COL1A2"], ["SCX", "NP", "1.65E–06", "COL1A1,COMP,POSTN"], ["Tgf beta (group)", "–1.454", "5.16E–06", "COL1A1,COL1A2,LCAT,POSTN,TGFBI"], ["ENTPD5", "NP", "1.21E–05", "COL1A1,COL1A2"], ["MKX", "NP", "1.21E–05", "COL1A1,COL1A2"], ["GATA4", "NP", "2.86E–05", "COL1A1,COL1A2,POSTN,TGFBI"], ["Nilotinib", "NP", "3.39E–05", "COL1A1,COL1A2"], ["TBX5", "NP", "5.50E–05", "COL1A1,COL1A2,POSTN"]], "row_count": 23, "column_count": 5, "numeric_cells": 40, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab4"}}], "gaps": ["asset:data:geo:PXD005220 not downloaded", "asset:data:geo:PXD005220 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Statistical analysis was performed using ProgenesisQI™ software; briefly transformed normalised abundances were used for one-way analysis of variance (ANOVA) and all peptides (with p < 0.05) of an identified protein were included."}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "bootstrap_mean_difference", "expected_value": 2.1, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["PXD005220"], "resolved_accessions": ["PXD005220"], "statements": ["Proteomic data has been deposited in the PRIDE ProteomeXchange and can be accessed using the identifier PXD005220."], "basis": "The paper names PXD005220 in PRIDE ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:28666451", "data:geo:PXD005220", "asset:table:pmid:28666451:1", "asset:table:pmid:28666451:2", "asset:table:pmid:28666451:3", "asset:table:pmid:28666451:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD005220"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:28Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 105032, "completion_tokens": 2881, "cached_tokens": 2088}}, "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:28666451", "type": "paper", "label": "pmid:28666451"}, {"id": "source:pmid:28666451", "type": "manuscript", "label": "PMID 28666451 full text"}, {"id": "data:geo:PXD005220", "type": "dataset", "label": "GEO PXD005220"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28666451", "type": "paper", "label": "pmid:28666451"}, {"id": "source:pmid:28666451", "type": "manuscript", "label": "PMID 28666451 full text"}, {"id": "data:geo:PXD005220", "type": "dataset", "label": "GEO PXD005220"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28666451", "type": "extraction", "used": ["source:pmid:28666451"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD005220", "type": "accession_resolution", "used": ["data:geo:PXD005220"], "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:28666451", "parent_hash": "sha256:06d57e8314c43768ce1fa11cdd5e00434978fd45123cab063d0ed06530f36a16", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD005220 licence not read", "asset:data:geo:PXD005220 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Statistical analysis was performed using ProgenesisQI™ software; briefly transformed normalised abundances were used for one-way analysis of variance (ANOVA) and all peptides (with p < 0.05) of an identified protein were included."], "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":"2026-11-04T00:31:27+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}}}