Comparing early and late data fusion methods for gene expression prediction

Uveal melanoma (UM) is a rare cancer that is well characterized at the molecular level. Two to four classes have been identified by the analyses of gene expression (mRNA, ncRNA), DNA copy number, DNA-methylation and somatic mutations yet no factual integration of these data has been reported. We therefore applied novel algorithms for data fusion, joint Singular Value Decomposition (jSVD) and joint Constrained Matrix Factorization (jCMF), as well as similarity network fusion (SNF), for the integration of gene expression, methylation and copy number data that we applied to the Cancer Genome Atlas (TCGA) UM dataset. Variant features that most strongly impact on definition of classes were extracted for biological interpretation of the classes. Data fusion allows for the identification of the two to four classes previously described. Not all of these classes are evident at all levels indicating that integrative analyses add to genomic discrimination power. The classes are also characterized by different frequencies of somatic mutations in putative driver genes (GNAQ, GNA11, SF3B1, BAP1). Innovative data fusion techniques confirm, as expected, the existence of two main types of uveal melanoma mainly characterized by copy number alterations. Subtypes were also confirmed but are somewhat less defined. Data fusion allows for real integration of multi-domain genomic data.

Download Full-text

Adaptive-SFSDAF for Spatiotemporal Image Fusion that Selectively Uses Class Abundance Change Information

Remote Sensing ◽

10.3390/rs12233979 ◽

2020 ◽

Vol 12 (23) ◽

pp. 3979

Author(s):

Shuwei Hou ◽

Wenfang Sun ◽

Baolong Guo ◽

Cheng Li ◽

Xiaobo Li ◽

...

Keyword(s):

Data Fusion ◽

Image Fusion ◽

Temporal Changes ◽

Spectral Unmixing ◽

Spatiotemporal Data ◽

Fusion Method ◽

Fusion Methods ◽

Single Sensor ◽

Primary Contribution ◽

Detection Of Outliers

Many spatiotemporal image fusion methods in remote sensing have been developed to blend highly resolved spatial images and highly resolved temporal images to solve the problem of a trade-off between the spatial and temporal resolution from a single sensor. Yet, none of the spatiotemporal fusion methods considers how the various temporal changes between different pixels affect the performance of the fusion results; to develop an improved fusion method, these temporal changes need to be integrated into one framework. Adaptive-SFSDAF extends the existing fusion method that incorporates sub-pixel class fraction change information in Flexible Spatiotemporal DAta Fusion (SFSDAF) by modifying spectral unmixing to select spectral unmixing adaptively in order to greatly improve the efficiency of the algorithm. Accordingly, the main contributions of the proposed adaptive-SFSDAF method are twofold. One is to address the detection of outliers of temporal change in the image during the period between the origin and prediction dates, as these pixels are the most difficult to estimate and affect the performance of the spatiotemporal fusion methods. The other primary contribution is to establish an adaptive unmixing strategy according to the guided mask map, thus effectively eliminating a great number of insignificant unmixed pixels. The proposed method is compared with the state-of-the-art Flexible Spatiotemporal DAta Fusion (FSDAF), SFSDAF, FIT-FC, and Unmixing-Based Data Fusion (UBDF) methods, and the fusion accuracy is evaluated both quantitatively and visually. The experimental results show that adaptive-SFSDAF achieves outstanding performance in balancing computational efficiency and the accuracy of the fusion results.

Download Full-text

A Survey on Deep Learning for Multimodal Data Fusion

Neural Computation ◽

10.1162/neco_a_01273 ◽

2020 ◽

Vol 32 (5) ◽

pp. 829-864 ◽

Cited By ~ 10

Author(s):

Jing Gao ◽

Peng Li ◽

Zhikui Chen ◽

Jianing Zhang

Keyword(s):

Big Data ◽

Deep Learning ◽

Data Fusion ◽

High Volume ◽

Fusion Method ◽

Learning Models ◽

Multimodal Data ◽

Fusion Methods ◽

Multimodal Data Fusion ◽

Future Topics

With the wide deployments of heterogeneous networks, huge amounts of data with characteristics of high volume, high variety, high velocity, and high veracity are generated. These data, referred to multimodal big data, contain abundant intermodality and cross-modality information and pose vast challenges on traditional data fusion methods. In this review, we present some pioneering deep learning models to fuse these multimodal big data. With the increasing exploration of the multimodal big data, there are still some challenges to be addressed. Thus, this review presents a survey on deep learning for multimodal data fusion to provide readers, regardless of their original community, with the fundamentals of multimodal deep learning fusion method and to motivate new multimodal data fusion techniques of deep learning. Specifically, representative architectures that are widely used are summarized as fundamental to the understanding of multimodal deep learning. Then the current pioneering multimodal data fusion deep learning models are summarized. Finally, some challenges and future topics of multimodal data fusion deep learning models are described.

Download Full-text