OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data

SIMPLE SUMMARY: OmiEmbed is a unified multi-task deep learning framework for multi-omics data, supporting dimensionality reduction, multi-omics integration, tumour type classification, phenotypic feature reconstruction and survival prediction. The framework is comprised of deep embedding and downstream task modules to capture biomedical information from high-dimensional omics data. OmiEmbed outperformed state-of-the-art methods on all three types of downstream tasks: classification, regression and survival prediction. Better performance was achieved using the multi-task training strategy compared to training each downstream task individually. With the multi-task strategy, OmiEmbed learnt a comprehensive omics embedding containing information from multiple tasks. OmiEmbed is open source, well-organised and convenient to be extended to other customised input data, network structures and downstream tasks, which has promising potential to facilitate more accurate and personalised clinical decision making. ABSTRACT: High-dimensional omics data contain intrinsic biomedical information that is crucial for personalised medicine. Nevertheless, it is challenging to capture them from the genome-wide data, due to the large number of molecular features and small number of available samples, which is also called “the curse of dimensionality” in machine learning. To tackle this problem and pave the way for machine learning-aided precision medicine, we proposed a unified multi-task deep learning framework named OmiEmbed to capture biomedical information from high-dimensional omics data with the deep embedding and downstream task modules. The deep embedding module learnt an omics embedding that mapped multiple omics data types into a latent space with lower dimensionality. Based on the new representation of multi-omics data, different downstream task modules were trained simultaneously and efficiently with the multi-task strategy to predict the comprehensive phenotype profile of each sample. OmiEmbed supports multiple tasks for omics data including dimensionality reduction, tumour type classification, multi-omics integration, demographic and clinical feature reconstruction, and survival prediction. The framework outperformed other methods on all three types of downstream tasks and achieved better performance with the multi-task strategy compared to training them individually. OmiEmbed is a powerful and unified framework that can be widely adapted to various applications of high-dimensional omics data and has great potential to facilitate more accurate and personalised clinical decision making.