Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes

Abstract Background Pancreatic cellular heterogeneity is fundamental to systemic metabolic regulation, yet its pathological remodeling in diabetes remains poorly characterized. Methods We integrated single-cell RNA sequencing with machine learning frameworks to decode pancreatic heterogeneity. Novel...

Full description

Saved in:
Bibliographic Details
Main Authors: Xueqin Xie, Changchun Wu, Yuhe Yang, Wei Su, Fuying Dao, Jian Huang, Zheng Shi, Hao Lyu, Hao Lin
Format: Article
Language:English
Published: BMC 2025-07-01
Series:Cardiovascular Diabetology
Subjects:
Online Access:https://doi.org/10.1186/s12933-025-02865-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849767046367150080
author Xueqin Xie
Changchun Wu
Yuhe Yang
Wei Su
Fuying Dao
Jian Huang
Zheng Shi
Hao Lyu
Hao Lin
author_facet Xueqin Xie
Changchun Wu
Yuhe Yang
Wei Su
Fuying Dao
Jian Huang
Zheng Shi
Hao Lyu
Hao Lin
author_sort Xueqin Xie
collection DOAJ
description Abstract Background Pancreatic cellular heterogeneity is fundamental to systemic metabolic regulation, yet its pathological remodeling in diabetes remains poorly characterized. Methods We integrated single-cell RNA sequencing with machine learning frameworks to decode pancreatic heterogeneity. Novel tools included PanSubPred (two-stage feature selection/XGBoost classifier) for multi-lineage annotation and PSC-Stat (XGBoost/Gini optimization) for stellate cell activation analysis. Results By establishing PanSubPred, we systematically decoded pancreatic cellular diversity, identifying 64 cell-type-specific markers (38 novel) that maintained cross-dataset accuracy (AUC > 0.970) even after excluding known canonical markers. Building on this annotation precision, we developed PSC-Stat to quantify stellate cell activation dynamics, revealing their progressive activation from diabetes to pancreatic cancer (activated/quiescent ratio: control: 1.44 ± 1.02, diabetes: 4.72 ± 4.01, pancreatic cancer: 18.67 ± 18.70). Diabetes reorganized intercellular communication into ductal-centric hubs via FGF7-FGFR2/3, EFNB3-EPHB2/4/6 and EFNA5-EPHA2 axes, from which we derived a 15-gene signature for diabetic ductal cells (AUC = 0.846). Beta cell heterogeneity analysis uncovered diabetes-associated depletion of mature insulin-secretory clusters (INS + NKX6-1+), expansion of immature (CD81 + RBP4+) and endoplasmic reticulum stress-adapted subtypes (DDIT3 + HSPA5+). Moreover, non-beta lineages exhibited parallel dysfunction: acinar cells shifted toward inflammatory states (CCL2 + CXCL17+), while ductal cells adopted secretory phenotypes (MUC1 + CFTR+). Conclusions This study presents a machine learning-based single-cell framework that systematically maps pancreatic cellular alterations in diabetes. The identified novel signatures, stellate activation dynamics, and beta cell maturation trajectories may serve as potential targets for diabetic management and pancreatic cancer risk stratification. Graphical abstract
format Article
id doaj-art-2c5ab9b452cd414da7248b8611f310ef
institution DOAJ
issn 1475-2840
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series Cardiovascular Diabetology
spelling doaj-art-2c5ab9b452cd414da7248b8611f310ef2025-08-20T03:04:22ZengBMCCardiovascular Diabetology1475-28402025-07-0124111810.1186/s12933-025-02865-8Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetesXueqin Xie0Changchun Wu1Yuhe Yang2Wei Su3Fuying Dao4Jian Huang5Zheng Shi6Hao Lyu7Hao Lin8Department of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaSchool of Biological Sciences, Nanyang Technological UniversityDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaClinical Genetics Laboratory, Clinical Medical College & Affiliated Hospital, Chengdu UniversityDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaDepartment of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Life Science and Technology, University of Electronic Science and Technology of ChinaAbstract Background Pancreatic cellular heterogeneity is fundamental to systemic metabolic regulation, yet its pathological remodeling in diabetes remains poorly characterized. Methods We integrated single-cell RNA sequencing with machine learning frameworks to decode pancreatic heterogeneity. Novel tools included PanSubPred (two-stage feature selection/XGBoost classifier) for multi-lineage annotation and PSC-Stat (XGBoost/Gini optimization) for stellate cell activation analysis. Results By establishing PanSubPred, we systematically decoded pancreatic cellular diversity, identifying 64 cell-type-specific markers (38 novel) that maintained cross-dataset accuracy (AUC > 0.970) even after excluding known canonical markers. Building on this annotation precision, we developed PSC-Stat to quantify stellate cell activation dynamics, revealing their progressive activation from diabetes to pancreatic cancer (activated/quiescent ratio: control: 1.44 ± 1.02, diabetes: 4.72 ± 4.01, pancreatic cancer: 18.67 ± 18.70). Diabetes reorganized intercellular communication into ductal-centric hubs via FGF7-FGFR2/3, EFNB3-EPHB2/4/6 and EFNA5-EPHA2 axes, from which we derived a 15-gene signature for diabetic ductal cells (AUC = 0.846). Beta cell heterogeneity analysis uncovered diabetes-associated depletion of mature insulin-secretory clusters (INS + NKX6-1+), expansion of immature (CD81 + RBP4+) and endoplasmic reticulum stress-adapted subtypes (DDIT3 + HSPA5+). Moreover, non-beta lineages exhibited parallel dysfunction: acinar cells shifted toward inflammatory states (CCL2 + CXCL17+), while ductal cells adopted secretory phenotypes (MUC1 + CFTR+). Conclusions This study presents a machine learning-based single-cell framework that systematically maps pancreatic cellular alterations in diabetes. The identified novel signatures, stellate activation dynamics, and beta cell maturation trajectories may serve as potential targets for diabetic management and pancreatic cancer risk stratification. Graphical abstracthttps://doi.org/10.1186/s12933-025-02865-8Pancreatic cellular heterogeneitySingle-cell transcriptomicsMachine learningType 2 diabetesStellate cell activationBeta cell dysfunction
spellingShingle Xueqin Xie
Changchun Wu
Yuhe Yang
Wei Su
Fuying Dao
Jian Huang
Zheng Shi
Hao Lyu
Hao Lin
Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
Cardiovascular Diabetology
Pancreatic cellular heterogeneity
Single-cell transcriptomics
Machine learning
Type 2 diabetes
Stellate cell activation
Beta cell dysfunction
title Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
title_full Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
title_fullStr Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
title_full_unstemmed Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
title_short Interpretable machine learning-guided single-cell mapping deciphers multi-lineage pancreatic dysregulation in type 2 diabetes
title_sort interpretable machine learning guided single cell mapping deciphers multi lineage pancreatic dysregulation in type 2 diabetes
topic Pancreatic cellular heterogeneity
Single-cell transcriptomics
Machine learning
Type 2 diabetes
Stellate cell activation
Beta cell dysfunction
url https://doi.org/10.1186/s12933-025-02865-8
work_keys_str_mv AT xueqinxie interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT changchunwu interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT yuheyang interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT weisu interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT fuyingdao interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT jianhuang interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT zhengshi interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT haolyu interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes
AT haolin interpretablemachinelearningguidedsinglecellmappingdeciphersmultilineagepancreaticdysregulationintype2diabetes