A multitask multiple kernel learning formulation for discriminating early- and late-stage cancers

Abstract

Motivation Genomic information is increasingly being used in diagnosis, prognosis and treatment of cancer. The severity of the disease is usually measured by the tumor stage. Therefore, identifying pathways playing an important role in progression of the disease stage is of great interest. Given that there are similarities in the underlying mechanisms of different cancers, in addition to the considerable correlation in the genomic data, there is a need for machine learning methods that can take these aspects of genomic data into account. Furthermore, using machine learning for studying multiple cancer cohorts together with a collection of molecular pathways creates an opportunity for knowledge extraction. Results We studied the problem of discriminating early- and late-stage tumors of several cancers using genomic information while enforcing interpretability on the solutions. To this end, we developed a multitask multiple kernel learning (MTMKL) method with a co-clustering step based on a cutting-plane algorithm to identify the relationships between the input tasks and kernels. We tested our algorithm on 15 cancer cohorts and observed that, in most cases, MTMKL outperforms other algorithms (including random forests, support vector machine and single-task multiple kernel learning) in terms of predictive power. Using the aggregate results from multiple replications, we also derived similarity matrices between cancer cohorts, which are, in many cases, in agreement with available relationships reported in the relevant literature. Availability and implementation Our implementations of support vector machine and multiple kernel learning algorithms in R are available at https://github.com/arezourahimi/mtgsbc together with the scripts that replicate the reported experiments. Supplementary information Supplementary data are available at Bioinformatics online.

Explainable artificial intelligence for omics data: a systematic mapping study

“…[ 88 ] iteratively remove low-impact features for improved interpretability while maintaining high predictive performance for cancer risk stratification. Additionally, four articles apply feature relevance to SVMs, for example, by conducting an additional clustering step to assess feature relevance [ 89 ].…”

A Self-Adaptive Multikernel Machine Based on Recursive Least-Squares Applied to Very Short-Term Wind Power Forecasting

“…MKL combines a set of kernels (basis kernels) in a linear, nonlinear or data-dependent way into a composite kernel, where the basis kernels can use different kernel functions or different values for the hyperparameters of a single kernel function [48]. Numerous studies have continuously improved the development of MKL applied in many subjects: classification of hyperspectral images [49], binary classification problems [50], air quality prediction [51], anomaly detection [52], object categorization [53], Alzheimer's disease diagnosis [54], oil painter recognition [55], multiclass classification [56], discriminating early-and late-stage cancers [57], subspace clustering [58], and many others.…”

“…The two regularization terms were introduced to improve the classification ability further. Rahimi and Gönen [57] formulated a multitask MKL method with a coclustering model on gene sets to identify biological processes and learn task-specific classification models simultaneously. Multitask learning, where different tasks are learned simultaneously, allows cohorts (i.e., tasks) with limited data to benefit from other tasks.…”

Diagnostic classification of cancers using DNA methylation of paracancerous tissues

“…Previous studies related to cancer diagnosis mainly focused on molecular data of tumor tissues [3][4][5][6] . Broët et al proposed a new statistic for identifying gene expression features that detected tumor progression 4 .…”