Multiple-kernel learning for genomic data mining and prediction

Abstract

Background Advances in medical technology have allowed for customized prognosis, diagnosis, and treatment regimens that utilize multiple heterogeneous data sources. Multiple kernel learning (MKL) is well suited for the integration of multiple high throughput data sources. MKL remains to be under-utilized by genomic researchers partly due to the lack of unified guidelines for its use, and benchmark genomic datasets. Results We provide three implementations of MKL in R. These methods are applied to simulated data to illustrate that MKL can select appropriate models. We also apply MKL to combine clinical information with miRNA gene expression data of ovarian cancer study into a single analysis. Lastly, we show that MKL can identify gene sets that are known to play a role in the prognostic prediction of 15 cancer types using gene expression data from The Cancer Genome Atlas, as well as, identify new gene sets for the future research. Conclusion Multiple kernel learning coupled with modern optimization techniques provides a promising learning tool for building predictive models based on multi-source genomic data. MKL also provides an automated scheme for kernel prioritization and parameter tuning. The methods used in the paper are implemented as an R package called RMKL package, which is freely available for download through CRAN at https://CRAN.R-project.org/package=RMKL . Electronic supplementary material The online version of this article (10.1186/s12859-019-2992-1) contains supplementary material, which is available to authorized users.

State of the Field in Multi-Omics Research: From Computational Needs to Data Mining and Sharing

“…Such pattern extraction, selection and representation are often difficult to achieve solely by traditional linear modeling unless coupled with advanced non-linear models. Some methods and tools from the multivariate statistics/ML/DL area that have been developed for multi-omics integration include: (a) Multi-Omics Model and Analytics (MOMA), (b) Multiple Kernel Learning (MKL) ( Wilson et al, 2019 ), (c) DIABLO ( Singh et al, 2019 ), (d) a multi-omics late integration method (MOLI) ( Sharifi-Noghabi et al, 2019 ), (e) multi-omics deep learning method (DCAP) ( Chai et al, 2019 ), and (f) Multi-omics Autoencoder Integration (MAUI) ( Ronen et al, 2019 ). Partly this can be attributed to the reasons described above and partly as described in the following paragraph.…”

Visual-Saliency-Based Abnormality Detection for MRI Brain Images—Alzheimer’s Disease Analysis

“…Kernel prioritization is important for overcoming the problems associated with MKL. The kernels can classify the data and provide boundaries [33].…”

“…The multiple-kernel methods have higher classification accuracies than single-kernel methods [33]. Simple MKL adopts a gradient descent on the support vector machine objective value and updates the kernel weights iteratively.…”

“…AD classification performance depends on clinical and demographic data with respect to patients [33]. It is very difficult to discriminate between patients with very mild AD and those with normal conditions.…”

Synergistic Effects of Different Levels of Genomic Data for the Staging of Lung Adenocarcinoma: An Illustrative Study

“…Dong et al [ 22 ] used a multi-weighted gcForest method to integrate methylation data, RNA-seq, and CNV to predict the staging of LUAD. Many machine learning algorithms are also used in the prediction of clinical outcomes of different types of cancer by analyzing different genetic data types [ 23 , 24 , 25 , 26 , 27 , 28 ]. Recently, Hornung and Wright [ 29 ] designed a method called ‘block forests’ that modifies the split point selection of random forests to incorporate the group structure of multi-omics data.…”