Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40749079", "kind": "science-record", "revision": 3, "content_hash": "sha256:3ceb4ad7b044fd7d57334875424305c10253283242f0f53d90119f31be6a4575", "created_at": "2026-11-01T20:30:50Z", "updated_at": "2026-11-01T22:14:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.", "doi": "10.1371/journal.pone.0328906", "pmid": "40749079", "authors": ["Zhongwen Lu", "Na An", "Shouwei Sheng", "Mao Hong", "Pin Deng", "Junde Wu", "Shengji Zhang", "Zhaojun Chen"], "journal": "PloS one", "year": 2025, "abstract": "Diabetic foot ulcer (DFU) is a severe complication of diabetes, often leading to amputation due to poor wound healing and infection. The immune-related pathogenesis of DFU remains unclear, and therapeutic drugs are limited. This study aimed to explore the immune mechanisms of DFU and identify potential therapeutic drugs using machine learning and single-cell approaches. Through differential expression analysis of Gene Expression Omnibus (GEO) datasets, we identified 287 differentially expressed genes (DEGs), which were significantly enriched in IL-17 signaling and neutrophil chemotaxis pathways. Weighted gene co-expression network analysis (WGCNA) further pinpointed disease-associated modules containing 1,693 regulatory genes. Machine learning algorithms prioritized seven core genes-CCL20, CXCL13, FGFR2, FGFR3, PI3, PLA2G2A, and S100A8-with validation in an external dataset GSE147890 and single-cell sequencing revealing their predominant expression in neutrophils and keratinocytes. Immune infiltration analysis demonstrated significant dysregulation in DFU patients, characterized by elevated proportions of memory B cells, M0 macrophages, activated mast cells, and neutrophils. Potential therapeutic compounds were identified using the Connectivity Map database and tested through molecular docking and dynamics simulations. The study pinpointed selegiline, L-BSO, flunisolide, PP-30, and fluocinolone as promising therapeutic agents, offering new insights into the pathogenesis of diabetic foot ulcers (DFU) and potential therapeutic strategies.", "claims": [{"id": "claim-method", "statement": "In this study, the “WGCNA” package in R software was employed to construct the co-expression network [15].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40749079", "locator": "sections[6] \"2.4 Weighted gene co-expression network analysis (WGCNA) and identification of core modules\" paragraph 2", "quote": "In this study, the “WGCNA” package in R software was employed to construct the co-expression network [15]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40749079", "locator": "sections[32] \"Data Availability\" paragraph 2", "quote": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Weighted gene co-expression network analysis (WGCNA) further pinpointed disease-associated modules containing 1,693 regulatory genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40749079", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Weighted gene co-expression network analysis (WGCNA) further pinpointed disease-associated modules containing 1,693 regulatory genes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Weighted gene co-expression network analysis (WGCNA) further pinpointed disease-associated modules containing 1,693 regulatory genes.", "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:40749079"], "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": "blocked", "blocked_on": "method:machine_learning_random_forest", "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": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40749079", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0328906", "sha256": "sha256:413a0f675c7c5de289ccfc96a8e9b709ab5b1c44cf5a442759218f1ddc80df5c", "bytes": 64204, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0328906", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12316216", "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": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "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": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "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:GSE199939", "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=GSE199939", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE199939", "version": null, "note": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5994301", "GSM5994302", "GSM5994303", "GSM5994304", "GSM5994305", "GSM5994306", "GSM5994307", "GSM5994308", "GSM5994309", "GSM5994310", "GSM5994311", "GSM5994312", "GSM5994313", "GSM5994314", "GSM5994315", "GSM5994316", "GSM5994317", "GSM5994318", "GSM5994319", "GSM5994320", "GSM5994321"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Comprehensive transcriptomic analysis of immune-related genes in diabetic foot ulcers: New insights into mechanisms and therapeutic targets", "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:GSE248247", "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=GSE248247", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE248247", "version": null, "note": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM7908977", "GSM7908978"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "20301", "taxon": "Homo sapiens", "title": "Characterization of Diabetic and Non-Diabetic Foot Ulcers Using Single-Cell RNA-Sequencing", "resolution_checked_at": "2026-11-01T20:16:08Z", "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:GSE199939 not downloaded", "asset:data:geo:GSE199939 licence not read", "asset:data:geo:GSE248247 not downloaded", "asset:data:geo:GSE248247 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 0.8, "band": "high", "quote": "Random Forest"}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "support vector machine"}}, {"id": "method-3", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "XGBoost"}}, {"id": "method-4", "family": "machine_learning", "specific": "decision_tree", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "decision tree"}}, {"id": "method-5", "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"}}, {"id": "method-6", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-7", "family": "model_calibration", "specific": "decision_curve", "label": "Model calibration / clinical utility", "dsl_operations": ["calibration_bins", "net_benefit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictions_and_outcomes"], "evidence": {"score": 0.8, "band": "high", "quote": "Decision Curve Analysis"}}, {"id": "method-8", "family": null, "specific": null, "label": "Weighted gene co-expression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In this study, the “WGCNA” package in R software was employed to construct the co-expression network [15]."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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", "GSE199939", "GSE147890", "GSE248247"], "resolved_accessions": ["GSE134431", "GSE199939", "GSE147890", "GSE248247"], "statements": ["Our raw datasets can be obtained in the GEO database (https://www.ncbi.nlm.nih.gov/geo/), in this study we use datasets: GSE134431, GSE199939 and GSE147890."], "basis": "The paper names GSE134431, GSE199939, GSE147890, GSE248247 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40749079", "data:geo:GSE134431"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "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": "2026-11-01T19:58:19Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17958, "completion_tokens": 2061, "cached_tokens": 264}}, "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:40749079", "type": "paper", "label": "pmid:40749079"}, {"id": "source:pmid:40749079", "type": "manuscript", "label": "PMID 40749079 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40749079", "type": "paper", "label": "pmid:40749079"}, {"id": "source:pmid:40749079", "type": "manuscript", "label": "PMID 40749079 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40749079", "type": "extraction", "used": ["source:pmid:40749079"], "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:40749079", "parent_hash": "sha256:b3127e53a7a65a99827e537055016f3b231679166dff863743a05531a12deed1", "fork_of": null, "generation": 2}, "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:GSE199939 licence not read", "asset:data:geo:GSE199939 not downloaded", "asset:data:geo:GSE248247 licence not read", "asset:data:geo:GSE248247 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Random Forest"], "order_basis": "analysis_only", "id": "assay:1"}]}