Sparse kernel canonical correlation analysis for discovery of nonlinear interactions in high-dimensional data

By Kosuke Yoshida, Junichiro Yoshimoto, Kenji Doya. 2017

37 citations recorded by the source corpus.

Advance in high-throughput technologies in genomics, transcriptomics, and metabolomics has created demand for bioinformatics tools to integrate high-dimensional data from different sources. Canonical correlation analysis (CCA) is a statistical tool for finding linear associations between different types of information. Previous extensions of CCA used to capture nonlinear associations, such as kernel CCA, did not allow feature selection or capturing of multiple canonical components. Here we propose a novel method, two-stage kernel CCA (TSKCCA) to select appropriate kernels in the framework of multiple kernel learning. TSKCCA first selects relevant kernels based on the HSIC criterion in the multiple kernel learning framework. Weights are then derived by non-negative matrix decomposition with L1 regularization. Using artificial datasets and nutrigenomic datasets, we show that TSKCCA can extract multiple, nonlinear associations among high-dimensional data and multiplicative interactions among variables. TSKCCA can identify nonlinear associations among high-dimensional data more reliably than previous nonlinear CCA methods.

Subfields: Computational Mathematics, Molecular Biology, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mathematics

1. Bin Yu
2. Martin J. Wainwright

In Molecular Biology

1. Bin Yu
2. Karl Kumbier
3. James B. Brown
4. Sumanta Basu
5. Jing Lei

In Statistics and Probability

1. Bin Yu
2. Karl Kumbier
3. Sumanta Basu
4. James B. Brown
5. Francis R. Bach
6. Tong Zhang
7. Martin J. Wainwright
8. Peter Buhlmann

Citations in the corpus

• Iterative random forests to discover predictive and stable high-order interactions (2017, methodology): “While several methods have been developed to identify interactions in large genomics datasets, for example (Zhou and Troyanskaya, 2014; Lundberg et al., 2016; Yoshida et al., 2017), these approaches either focus on pairwise relationships or require explicit enumeration of higher-order interactions, ”