Priority-Lasso: a simple hierarchical approach to the prediction of clinical outcome using multi-omics data

Abstract

BackgroundThe inclusion of high-dimensional omics data in prediction models has become a well-studied topic in the last decades. Although most of these methods do not account for possibly different types of variables in the set of covariates available in the same dataset, there are many such scenarios where the variables can be structured in blocks of different types, e.g., clinical, transcriptomic, and methylation data. To date, there exist a few computationally intensive approaches that make use of block structures of this kind.ResultsIn this paper we present priority-Lasso, an intuitive and practical analysis strategy for building prediction models based on Lasso that takes such block structures into account. It requires the definition of a priority order of blocks of data. Lasso models are calculated successively for every block and the fitted values of every step are included as an offset in the fit of the next step. We apply priority-Lasso in different settings on an acute myeloid leukemia (AML) dataset consisting of clinical variables, cytogenetics, gene mutations and expression variables, and compare its performance on an independent validation dataset to the performance of standard Lasso models.ConclusionThe results show that priority-Lasso is able to keep pace with Lasso in terms of prediction accuracy. Variables of blocks with higher priorities are favored over variables of blocks with lower priority, which results in easily usable and transportable models for clinical practice.Electronic supplementary materialThe online version of this article (10.1186/s12859-018-2344-6) contains supplementary material, which is available to authorized users.

Structured Penalized Regression for Drug Sensitivity Prediction

“…Klau et al . () presented the priority lasso to construct blocks of multiomics data sources and to regress on each source of data sequentially. It needs a priority sequence for regressing the multiple sources of data.…”

Block Forests: random forests for blocks of clinical and omics covariate data

“…In addition to the approach mentioned above, Fuchs et al [10] also consider performing variable selection separately for each block and then learning a single classifier using all blocks. Klau et al [11] present the priority-Lasso, a lasso-type prediction method for multi-omics data that differs from the approaches described above in that its main focus is not prediction accuracy but applicability from a practical point of view: with this method the user has to provide a priority order of the blocks that is for example motivated by the costs of generating each type of data. Blocks of low priority are likely to be automatically excluded by this method, which should frequently lead to prediction rules that are easy to apply in practice and, at the same time, feature a high prediction accuracy.…”

A role for the immune system in advanced laryngeal cancer

“…The second analysis was carried out considering as main endpoint time to relapse. Priority-LASSO Cox model (hierarchical approach) was applied to select genes able to predict the survival endpoint 23 , 24 . Disease-free survival (DFS) was defined as the interval in years, from the surgery to the first recurrence or last follow-up.…”