{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40796870", "kind": "science-record", "revision": 4, "content_hash": "sha256:abd57436ebc1b2b9790bdba6c7889e67726dfcc21ebc14b371d07347aa642803", "created_at": "2026-11-01T20:30:53Z", "updated_at": "2026-11-01T22:57:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "FGFR2 identified as a NETs-associated biomarker and therapeutic target in diabetic foot ulcers.", "doi": "10.1186/s40001-025-03012-5", "pmid": "40796870", "authors": ["Linrui Dai", "Shunli Rui", "Mengling Yang", "Shiyan Yu", "Qingqing Chen", "Hongyan Wang", "Bo Deng", "Liling Deng", "Wei Hao", "Xiaohua Wu", "David G Armstrong", "Zhidong Cao", "Xiaodong Duan", "Wuquan Deng"], "journal": "European journal of medical research", "year": 2025, "abstract": "BACKGROUND: Diabetic foot ulcer (DFU) is characterized by impaired wound healing and chronic inflammation, partly driven by the excessive formation of neutrophil extracellular traps (NETs). However, the molecular mediators linking NETs to failed tissue regeneration remain poorly understood. This study aimed to identify and validate novel NETs-associated biomarkers in DFU using an integrative bioinformatics and machine learning approach.\nMETHODS: Differentially expressed genes (DEGs) were identified from the GEO dataset GSE134431. These DEGs were intersected with a NETs-related gene set to identify NETs-associated DEGs (NETDEGs). LASSO logistic regression and Random Forest algorithms were applied to the NETDEGs to select key feature genes. The top candidate, Fibroblast Growth Factor Receptor 2 (FGFR2), was validated in two independent datasets (GSE7014 and GSE147890). Its expression was further confirmed in human DFU tissues and diabetic mouse models using qPCR and immunohistochemistry. The effect of a high-glucose environment on FGFR2 expression in neutrophils was assessed in vitro. Finally, molecular docking technique was used to screen for existing drugs targeting FGFR2, with top candidates validated at the cellular level.\nRESULTS: Our analysis identified FGFR2 as a key downregulated gene at the intersection of DFU pathology and NETs-related pathways. FGFR2 expression was significantly reduced in DFU tissues across all datasets and in our experimental models, where its downregulation correlated with increased NETs accumulation. FGFR2 demonstrated strong diagnostic potential, with an AUC of 1.00 in the training set. In vitro, high glucose conditions suppressed FGFR2 expression in neutrophils. From 32 glucose-lowering drugs, Canagliflozin and Gliquidone were found to significantly upregulate FGFR2 protein expression in neutrophils, suggesting a potential modulatory effect.\nCONCLUSIONS: FGFR2 is a promising potential biomarker associated with NET-driven inflammation in DFU. Its downregulation in the diabetic wound microenvironment and its modulation by existing pharmacological agents suggest that targeting the FGFR2 pathway may be a viable future therapeutic strategy for improving DFU healing outcomes. Further preclinical validation is warranted.", "claims": [{"id": "claim-method", "statement": "The R package limma (version 3.40.6) was used for differential expression analysis between DFU and control groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40796870", "locator": "sections[4] \"Data processing and differentially expressed gene screening\" paragraph 2", "quote": "The R package limma (version 3.40.6) was used for differential expression analysis between DFU and control groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40796870", "locator": "sections[35] \"Availability of data and materials\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Our analysis identified FGFR2 as a key downregulated gene at the intersection of DFU pathology and NETs-related pathways.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40796870", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Our analysis identified FGFR2 as a key downregulated gene at the intersection of DFU pathology and NETs-related pathways."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Our analysis identified FGFR2 as a key downregulated gene at the intersection of DFU pathology and NETs-related pathways.", "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:40796870"], "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:GSE134431"], "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:GSE134431"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40796870", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s40001-025-03012-5", "sha256": "sha256:76c2d892db32e5268a236620f34b2eef33d04a6a79338274d192d0b376d7ab61", "bytes": 56222, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s40001-025-03012-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12344841", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE134431", "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=GSE134431", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE134431", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3946485", "GSM3946486", "GSM3946487", "GSM3946488", "GSM3946489", "GSM3946490", "GSM3946491", "GSM3946492", "GSM3946493", "GSM3946494", "GSM3946495", "GSM3946496", "GSM3946497", "GSM3946498", "GSM3946499", "GSM3946500", "GSM3946501", "GSM3946502", "GSM3946503", "GSM3946504", "GSM3946505"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Deregulated immune signature orchestrated by FOXM1 impairs human diabetic wound healing", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE147890", "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=GSE147890", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE147890", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4448280", "GSM4448281", "GSM4448282", "GSM4448283", "GSM4448284", "GSM4448285", "GSM4448286", "GSM4448287", "GSM4448288", "GSM4448289", "GSM4448290", "GSM4448291", "GSM4448292", "GSM4448293", "GSM4448294", "GSM4448295", "GSM4448296", "GSM4448297", "GSM4448298", "GSM4448299", "GSM4448300", "GSM4448301", "GSM4448302", "GSM4448303", "GSM4448304", "GSM4448305"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Transcriptomic characterization of the delayed wound healing response in a diabetic skin humanized mice model", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE23006", "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=GSE23006", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE23006", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM567618", "GSM567619", "GSM567620", "GSM567621", "GSM567622", "GSM567623", "GSM567624", "GSM567625", "GSM567626", "GSM567627", "GSM567628", "GSM567629", "GSM567630", "GSM567631", "GSM567632", "GSM567633", "GSM567634", "GSM567635", "GSM567636", "GSM567637", "GSM567638", "GSM567639", "GSM567640", "GSM567641", "GSM567642", "GSM567643", "GSM567644", "GSM567645", "GSM567646", "GSM567647", "GSM567648", "GSM567649", "GSM567650", "GSM567651", "GSM567652", "GSM567653", "GSM567654", "GSM567655", "GSM567656", "GSM567657", "GSM567658", "GSM567659", "GSM567660", "GSM567661", "GSM567662", "GSM567663", "GSM567664", "GSM567665"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Transcriptional profiling of a  wound healing process in skin and oral mucosa", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE7014", "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=GSE7014", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7014", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM161935", "GSM161936", "GSM161937", "GSM161938", "GSM161939", "GSM161940", "GSM161941", "GSM161942", "GSM161943", "GSM161944", "GSM161945", "GSM161946", "GSM161948", "GSM161949", "GSM161950", "GSM161951", "GSM161952", "GSM161953", "GSM161954", "GSM161955", "GSM161956", "GSM161957", "GSM161958", "GSM161959", "GSM161960", "GSM161961", "GSM161962", "GSM161963", "GSM161964", "GSM161965", "GSM161966", "GSM161967", "GSM161968", "GSM161969", "GSM161970", "GSM161971"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from DM1, DM2 and Normal Adult Skeletal Muscle Biopsies", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE134431 not downloaded", "asset:data:geo:GSE134431 licence not read", "asset:data:geo:GSE147890 not downloaded", "asset:data:geo:GSE147890 licence not read", "asset:data:geo:GSE23006 not downloaded", "asset:data:geo:GSE23006 licence not read", "asset:data:geo:GSE7014 not downloaded", "asset:data:geo:GSE7014 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The R package limma (version 3.40.6) was used for differential expression analysis between DFU and control groups."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"id": "method-3", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "logistic regression"}}, {"id": "method-4", "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": "GO enrichment"}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE134431", "GSE7014", "GSE147890", "GSE23006"], "resolved_accessions": ["GSE134431", "GSE7014", "GSE147890", "GSE23006"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/."], "basis": "The paper names GSE134431, GSE7014, GSE147890, GSE23006 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:40796870", "data:geo:GSE134431"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE134431"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:59:04Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15953, "completion_tokens": 2029, "cached_tokens": 128}}, "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:40796870", "type": "paper", "label": "pmid:40796870"}, {"id": "source:pmid:40796870", "type": "manuscript", "label": "PMID 40796870 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40796870", "type": "paper", "label": "pmid:40796870"}, {"id": "source:pmid:40796870", "type": "manuscript", "label": "PMID 40796870 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40796870", "type": "extraction", "used": ["source:pmid:40796870"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE134431", "type": "accession_resolution", "used": ["data:geo:GSE134431"], "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:40796870", "parent_hash": "sha256:90b126ba1777d0b35a384fb19553f8183fd289abc424f32acbc0fca717093632", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE134431 licence not read", "asset:data:geo:GSE134431 not downloaded", "asset:data:geo:GSE147890 licence not read", "asset:data:geo:GSE147890 not downloaded", "asset:data:geo:GSE23006 licence not read", "asset:data:geo:GSE23006 not downloaded", "asset:data:geo:GSE7014 licence not read", "asset:data:geo:GSE7014 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["confirmed in human DFU tissues and diabetic mouse models using qPCR and immunohistochemistry.", "reduced neutrophil FGFR2 expression, and the in vivo observations in DFU. Availability of data an", "with our hypothesis, the expression of Ly6G (in mice) and CD15 (in humans) was significantly upre", "FGFR2 during wound healing using the public mouse transcriptomic dataset GSE23006 [50]. This a"], "order_basis": "paper_text_order:1003", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["DFU tissues and diabetic mouse models using qPCR and immunohistochemistry. The effect of a hi", "FR2 in DFUs and the controls was analyzed by qPCR (N = 3); c IF of FGFR2 (green) in skin tissu", "med these findings in human DFU tissues. Our qPCR analysis showed significantly lower FGFR2 mR"], "order_basis": "paper_text_order:1022", "id": "assay:2"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ues and diabetic mouse models using qPCR and immunohistochemistry. The effect of a high-glucose environment on", "n-diabetic controls (Fig. 7b). Additionally, immunofluorescence staining corroborated this downregulation. F"], "order_basis": "paper_text_order:1030", "id": "assay:3"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["(TPM) for expression quantification. For the microarray datasets, raw data were processed and normal"], "order_basis": "paper_text_order:2538", "id": "assay:4"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["(Shanghai) Biotechnology Development Co. and cultured in T25 flasks using DMEM high-glucose medium (G"], "order_basis": "paper_text_order:3548", "id": "assay:5"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["3); i, j Quantification of ly6G and CD15; k Flow cytometry validation of ly6G-labeled neutrophil ratio", "wing confirmation of neutrophil purity using flow cytometry (Fig. 7k), Western blot analysis revealed th"], "order_basis": "paper_text_order:6065", "id": "assay:6"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["of ly6G-labeled neutrophil ratio (N = 3); l Western blot validates the effect of a high glucose model", "el on neutrophil FGFR2 expression (N = 3); m Western blot statistics. Experiments were performed at le", "ophil purity using flow cytometry (Fig. 7k), Western blot analysis revealed that neutrophils cultured"], "order_basis": "paper_text_order:6135", "id": "assay:7"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The R package limma (version 3.40.6) was used for differential expression analysis between DFU and control groups."], "order_basis": "consumes_earlier_output", "id": "assay:8"}]},"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":"2026-11-04T02:36:40+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}}}