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

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 potent...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongwen Lu, Na An, Shouwei Sheng, Mao Hong, Pin Deng, Junde Wu, Shengji Zhang, Zhaojun Chen
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0328906
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387715904143360
author Zhongwen Lu
Na An
Shouwei Sheng
Mao Hong
Pin Deng
Junde Wu
Shengji Zhang
Zhaojun Chen
author_facet Zhongwen Lu
Na An
Shouwei Sheng
Mao Hong
Pin Deng
Junde Wu
Shengji Zhang
Zhaojun Chen
author_sort Zhongwen Lu
collection DOAJ
description 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.
format Article
id doaj-art-0bca0947166b47a9acf2bc4e4161fa32
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-0bca0947166b47a9acf2bc4e4161fa322025-08-20T03:44:25ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01208e032890610.1371/journal.pone.0328906Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.Zhongwen LuNa AnShouwei ShengMao HongPin DengJunde WuShengji ZhangZhaojun ChenDiabetic 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.https://doi.org/10.1371/journal.pone.0328906
spellingShingle Zhongwen Lu
Na An
Shouwei Sheng
Mao Hong
Pin Deng
Junde Wu
Shengji Zhang
Zhaojun Chen
Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.
PLoS ONE
title Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.
title_full Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.
title_fullStr Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.
title_full_unstemmed Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.
title_short Machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs.
title_sort machine learning combining external validation to explore the immunopathogenesis of diabetic foot ulcer and predict therapeutic drugs
url https://doi.org/10.1371/journal.pone.0328906
work_keys_str_mv AT zhongwenlu machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT naan machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT shouweisheng machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT maohong machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT pindeng machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT jundewu machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT shengjizhang machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs
AT zhaojunchen machinelearningcombiningexternalvalidationtoexploretheimmunopathogenesisofdiabeticfootulcerandpredicttherapeuticdrugs