Transfer learning identifies bacterial signatures for cross‐regional diagnosis of type 2 diabetes and enable stage‐sensitive dietary fiber intervention

DeepMicroFinder is a deep learning framework designed to update the existing disease diagnosis model to generate a transfer model by leveraging region-specific microbiome datasets and transfer learning approach. This framework effectively overcomes the limitation of regional effects in the gut microbiome, enabling accurate cross-regional disease detection. Microbial markers related to type 2 diabetes (T2D) were identified by DeepMicroFinder, and subsequently validated in independent T2D cohorts undergoing dietary fiber interventions.

Authors

Institutions

Publication Details

Journal
iMetaOmics.
Published
2025-05-04
DOI
https://doi.org/10.1002/imo2.70021
Primary Topic
Diet and metabolism studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Transfer learning identifies bacterial signatures for cross‐regional diagnosis of type 2 diabetes and enable stage‐sensitive dietary fiber intervention

Yuan-Tao Liu, Mingyue Cheng, Xiaoli Ma, Chenhong Zhou et al.
iMetaOmics.
Diet and metabolism studies
article

Transfer learning identifies bacterial signatures for cross‐regional diagnosis of type 2 diabetes and enable stage‐sensitive dietary fiber intervention

Yuan-Tao Liu, Mingyue Cheng, Xiaoli Ma, Chenhong Zhou, Qunye Zhang, Kaile Yue, Bin Chen, Zhongchao Wang, Changying Zhao, Minxiu Yao, Kang Ning, Haohong Zhang, Lei Zhang, Chuandi Jin, Dai-Feng Jiang, Yihui Wang, Nan Wang, Haiyan Wang, Jun Wang, Zhe Wang, Yangang Wang, Fanghua Zhang, Liang Gao, Guoping Zhao, Dongming Hu, Zixin Kang, Dashuang Sheng
article en

Abstract

DeepMicroFinder is a deep learning framework designed to update the existing disease diagnosis model to generate a transfer model by leveraging region-specific microbiome datasets and transfer learning approach. This framework effectively overcomes the limitation of regional effects in the gut microbiome, enabling accurate cross-regional disease detection. Microbial markers related to type 2 diabetes (T2D) were identified by DeepMicroFinder, and subsequently validated in independent T2D cohorts undergoing dietary fiber interventions.

iMetaOmics.Vol. 2(2)
Qingdao University (CN), Shandong University (CN), Shanghai Institute of Nutrition and Health (CN), Shandong Provincial Hospital (CN), Affiliated Hospital of Qingdao University (CN), Qingdao Municipal Hospital (CN), Shandong Academy of Sciences (CN), Qilu Hospital of Shandong University (CN), Qingdao Eighth People's Hospital (CN), Shandong First Medical University (CN), University of Chinese Academy of Sciences (CN), State Key Laboratory of Microbial Technology, Huazhong University of Science and Technology (CN)
Shandong University, National Natural Science Foundation of China
Zero hunger
Openalex Percentile: Top 88%
Diet and metabolism studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.