Yang Li, Xiaonan Ren, Haochen Yu, Tao Sun, Shuangge Ma
{"title":"A penalized integrative deep neural network for variable selection among multiple omics datasets","authors":"Yang Li, Xiaonan Ren, Haochen Yu, Tao Sun, Shuangge Ma","doi":"10.1002/qub2.51","DOIUrl":null,"url":null,"abstract":"Deep learning has been increasingly popular in omics data analysis. Recent works incorporating variable selection into deep learning have greatly enhanced the model’s interpretability. However, because deep learning desires a large sample size, the existing methods may result in uncertain findings when the dataset has a small sample size, commonly seen in omics data analysis. With the explosion and availability of omics data from multiple populations/studies, the existing methods naively pool them into one dataset to enhance the sample size while ignoring that variable structures can differ across datasets, which might lead to inaccurate variable selection results. We propose a penalized integrative deep neural network (PIN) to simultaneously select important variables from multiple datasets. PIN directly aggregates multiple datasets as input and considers both homogeneity and heterogeneity situations among multiple datasets in an integrative analysis framework. Results from extensive simulation studies and applications of PIN to gene expression datasets from elders with different cognitive statuses or ovarian cancer patients at different stages demonstrate that PIN outperforms existing methods with considerably improved performance among multiple datasets. The source code is freely available on Github (rucliyang/PINFunc). We speculate that the proposed PIN method will promote the identification of disease‐related important variables based on multiple studies/datasets from diverse origins.","PeriodicalId":45660,"journal":{"name":"Quantitative Biology","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quantitative Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1002/qub2.51","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Deep learning has been increasingly popular in omics data analysis. Recent works incorporating variable selection into deep learning have greatly enhanced the model’s interpretability. However, because deep learning desires a large sample size, the existing methods may result in uncertain findings when the dataset has a small sample size, commonly seen in omics data analysis. With the explosion and availability of omics data from multiple populations/studies, the existing methods naively pool them into one dataset to enhance the sample size while ignoring that variable structures can differ across datasets, which might lead to inaccurate variable selection results. We propose a penalized integrative deep neural network (PIN) to simultaneously select important variables from multiple datasets. PIN directly aggregates multiple datasets as input and considers both homogeneity and heterogeneity situations among multiple datasets in an integrative analysis framework. Results from extensive simulation studies and applications of PIN to gene expression datasets from elders with different cognitive statuses or ovarian cancer patients at different stages demonstrate that PIN outperforms existing methods with considerably improved performance among multiple datasets. The source code is freely available on Github (rucliyang/PINFunc). We speculate that the proposed PIN method will promote the identification of disease‐related important variables based on multiple studies/datasets from diverse origins.
期刊介绍:
Quantitative Biology is an interdisciplinary journal that focuses on original research that uses quantitative approaches and technologies to analyze and integrate biological systems, construct and model engineered life systems, and gain a deeper understanding of the life sciences. It aims to provide a platform for not only the analysis but also the integration and construction of biological systems. It is a quarterly journal seeking to provide an inter- and multi-disciplinary forum for a broad blend of peer-reviewed academic papers in order to promote rapid communication and exchange between scientists in the East and the West. The content of Quantitative Biology will mainly focus on the two broad and related areas: ·bioinformatics and computational biology, which focuses on dealing with information technologies and computational methodologies that can efficiently and accurately manipulate –omics data and transform molecular information into biological knowledge. ·systems and synthetic biology, which focuses on complex interactions in biological systems and the emergent functional properties, and on the design and construction of new biological functions and systems. Its goal is to reflect the significant advances made in quantitatively investigating and modeling both natural and engineered life systems at the molecular and higher levels. The journal particularly encourages original papers that link novel theory with cutting-edge experiments, especially in the newly emerging and multi-disciplinary areas of research. The journal also welcomes high-quality reviews and perspective articles.