A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data.
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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1012739 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540334167425024 |
|---|---|
| author | Lulu Pan Qian Gao Kecheng Wei Yongfu Yu Guoyou Qin Tong Wang |
| author_facet | Lulu Pan Qian Gao Kecheng Wei Yongfu Yu Guoyou Qin Tong Wang |
| author_sort | Lulu Pan |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-8cae2cfb58c949e89c7a5b260eae588d |
| institution | Kabale University |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-8cae2cfb58c949e89c7a5b260eae588d2025-02-05T05:30:38ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-01-01211e101273910.1371/journal.pcbi.1012739A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data.Lulu PanQian GaoKecheng WeiYongfu YuGuoyou QinTong WangTransfer 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.https://doi.org/10.1371/journal.pcbi.1012739 |
| spellingShingle | Lulu Pan Qian Gao Kecheng Wei Yongfu Yu Guoyou Qin Tong Wang A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. PLoS Computational Biology |
| title | A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. |
| title_full | A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. |
| title_fullStr | A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. |
| title_full_unstemmed | A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. |
| title_short | A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data. |
| title_sort | robust transfer learning approach for high dimensional linear regression to support integration of multi source gene expression data |
| url | https://doi.org/10.1371/journal.pcbi.1012739 |
| work_keys_str_mv | AT lulupan arobusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT qiangao arobusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT kechengwei arobusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT yongfuyu arobusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT guoyouqin arobusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT tongwang arobusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT lulupan robusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT qiangao robusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT kechengwei robusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT yongfuyu robusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT guoyouqin robusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata AT tongwang robusttransferlearningapproachforhighdimensionallinearregressiontosupportintegrationofmultisourcegeneexpressiondata |