A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data
PLOS Computational Biology · 10.01.2025 · 21 (1) · e1012739
DOI: 10.1371/journal.pcbi.1012739 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 10.01.2025. Verfasst von Lulu Pan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, School of Public Health, Fudan University, Shanghai, China. Hauptthemen laut MEDLINE: Machine Learning, Gene Expression Profiling. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanghai Rising-Star Program, Shanghai Municipal Natural Science Foundation.
Abstract (Originalsprache)
Transfer learning aims to integrate useful information from multi-source datasets to improve the learning performance of target data. This can be effectively applied in genomics when we learn the gene associations in a target tissue, and data from other tissues can be integrated. However, heavy-tail distribution and outliers are common in genomics data, which poses challenges to the effectiveness of current transfer learning approaches. In this paper, we study the transfer learning problem under high-dimensional linear models with t-distributed error (Trans-PtLR), which aims to improve the estimation and prediction of target data by borrowing information from useful source data and offering robustness to accommodate complex data with heavy tails and outliers. In the oracle case with known transferable source datasets, a transfer learning algorithm based on penalized maximum likelihood and expectation-maximization algorithm is established. To avoid including non-informative sources, we propose to select the transferable sources based on cross-validation. Extensive simulation experiments as well as an application demonstrate that Trans-PtLR demonstrates robustness and better performance of estimation and prediction when heavy-tail and outliers exist compared to transfer learning for linear regression model with normal error distribution. Data integration, Variable selection, T distribution, Expectation maximization algorithm, Genotype-Tissue Expression, Cross validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biostatistics, School of Public Health, Fudan University, Shanghai, China.
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.
- Key Laboratory of Coal Environmental Pathogenicity and Prevention (Shanxi Medical University), Ministry of Education, China.
- Shanghai Institute of Infectious Disease and Biosecurity, Shanghai, China.
- Key Laboratory of Public Health Safety of Ministry of Education, Key Laboratory for Health Technology Assessment, National Commission of Health, Fudan University, Shanghai, China.
ORCID-Profile: Tong Wang
Förderung
- National Natural Science Foundation of China
- Shanghai Rising-Star Program
- Shanghai Municipal Natural Science Foundation
- Shanghai Municipal Science and Technology Major Project
- Fundamental Research Program of Shanxi Province
- Natural Science Foundation of Shanghai Municipality
Zitieren
APA
Pan, L., Gao, Q., Wei, K., Yu, Y., Qin, G., & Wang, T. (2025). A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. PLOS Computational Biology, 21(1), e1012739. https://doi.org/10.1371/journal.pcbi.1012739
Vancouver
Pan L, Gao Q, Wei K, Yu Y, Qin G, Wang T. A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. PLOS Computational Biology. 2025;21(1):e1012739. doi:10.1371/journal.pcbi.1012739
BibTeX
@article{Pan2025,
author = {Pan, Lulu and Gao, Qian and Wei, Kecheng and Yu, Yongfu and Qin, Guoyou and Wang, Tong},
title = {A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data},
journal = {PLOS Computational Biology},
year = {2025},
volume = {21},
number = {1},
pages = {e1012739},
doi = {10.1371/journal.pcbi.1012739}
}
EUVIMED