Cargando…
DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks
Understanding the immune cell abundance of cancer and other disease-related tissues has an important role in guiding disease treatments. Computational cell type proportion estimation methods have been previously developed to derive such information from bulk RNA sequencing data. Unfortunately, our r...
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058910/ https://www.ncbi.nlm.nih.gov/pubmed/35510186 http://dx.doi.org/10.1016/j.patter.2022.100440 |
_version_ | 1784698213680283648 |
---|---|
author | Lin, Yating Li, Haojun Xiao, Xu Zhang, Lei Wang, Kejia Zhao, Jingbo Wang, Minshu Zheng, Frank Zhang, Minwei Yang, Wenxian Han, Jiahuai Yu, Rongshan |
author_facet | Lin, Yating Li, Haojun Xiao, Xu Zhang, Lei Wang, Kejia Zhao, Jingbo Wang, Minshu Zheng, Frank Zhang, Minwei Yang, Wenxian Han, Jiahuai Yu, Rongshan |
author_sort | Lin, Yating |
collection | PubMed |
description | Understanding the immune cell abundance of cancer and other disease-related tissues has an important role in guiding disease treatments. Computational cell type proportion estimation methods have been previously developed to derive such information from bulk RNA sequencing data. Unfortunately, our results show that the performance of these methods can be seriously plagued by the mismatch between training data and real-world data. To tackle this issue, we propose the DAISM-DNN(XMBD) (XMBD: Xiamen Big Data, a biomedical open software initiative in the National Institute for Data Science in Health and Medicine, Xiamen University, China.) (denoted as DAISM-DNN) pipeline that trains a deep neural network (DNN) with dataset-specific training data populated from a certain amount of calibrated samples using DAISM, a novel data augmentation method with an in silico mixing strategy. The evaluation results demonstrate that the DAISM-DNN pipeline outperforms other existing methods consistently and substantially for all the cell types under evaluation in real-world datasets. |
format | Online Article Text |
id | pubmed-9058910 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-90589102022-05-03 DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks Lin, Yating Li, Haojun Xiao, Xu Zhang, Lei Wang, Kejia Zhao, Jingbo Wang, Minshu Zheng, Frank Zhang, Minwei Yang, Wenxian Han, Jiahuai Yu, Rongshan Patterns (N Y) Article Understanding the immune cell abundance of cancer and other disease-related tissues has an important role in guiding disease treatments. Computational cell type proportion estimation methods have been previously developed to derive such information from bulk RNA sequencing data. Unfortunately, our results show that the performance of these methods can be seriously plagued by the mismatch between training data and real-world data. To tackle this issue, we propose the DAISM-DNN(XMBD) (XMBD: Xiamen Big Data, a biomedical open software initiative in the National Institute for Data Science in Health and Medicine, Xiamen University, China.) (denoted as DAISM-DNN) pipeline that trains a deep neural network (DNN) with dataset-specific training data populated from a certain amount of calibrated samples using DAISM, a novel data augmentation method with an in silico mixing strategy. The evaluation results demonstrate that the DAISM-DNN pipeline outperforms other existing methods consistently and substantially for all the cell types under evaluation in real-world datasets. Elsevier 2022-02-03 /pmc/articles/PMC9058910/ /pubmed/35510186 http://dx.doi.org/10.1016/j.patter.2022.100440 Text en © 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Article Lin, Yating Li, Haojun Xiao, Xu Zhang, Lei Wang, Kejia Zhao, Jingbo Wang, Minshu Zheng, Frank Zhang, Minwei Yang, Wenxian Han, Jiahuai Yu, Rongshan DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
title | DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
title_full | DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
title_fullStr | DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
title_full_unstemmed | DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
title_short | DAISM-DNN(XMBD): Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
title_sort | daism-dnn(xmbd): highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058910/ https://www.ncbi.nlm.nih.gov/pubmed/35510186 http://dx.doi.org/10.1016/j.patter.2022.100440 |
work_keys_str_mv | AT linyating daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT lihaojun daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT xiaoxu daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT zhanglei daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT wangkejia daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT zhaojingbo daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT wangminshu daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT zhengfrank daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT zhangminwei daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT yangwenxian daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT hanjiahuai daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks AT yurongshan daismdnnxmbdhighlyaccuratecelltypeproportionestimationwithinsilicodataaugmentationanddeepneuralnetworks |