CustOmics: A versatile deep-learning based strategy for multi-omics integration
Recent advances in high-throughput sequencing technologies have enabled the extraction of multiple features that depict patient samples at diverse and complementary molecular levels. The generation of such data has led to new challenges in computational biology regarding the integration of high-dimensional and heterogeneous datasets that capture the interrelationships between multiple genes and their functions. Thanks to their versatility and ability to learn synthetic latent representations of complex data, deep learning methods offer promising perspectives for integrating multi-omics data. These methods have led to the conception of many original architectures that are primarily based on autoencoder models. However, due to the difficulty of the task, the integration strategy is fundamental to take full advantage of the sources' particularities without losing the global trends. This paper presents a novel strategy to build a customizable autoencoder model that adapts to the dataset used in the case of high-dimensional multi-source integration. We will assess the impact of integration strategies on the latent representation and combine the best strategies to propose a new method, CustOmics (https://github.com/HakimBenkirane/CustOmics). We focus here on the integration of data from multiple omics sources and demonstrate the performance of the proposed method on test cases for several tasks such as classification and survival analysis.
Code (1)
Tasks
Survival AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration
Advances in single-cell sequencing have enabled high-resolution profiling of diverse molecular modalities, while integrating unpaired multi-omics single-cell data remains challenging. Existing approaches either rely on p…
Stacked Autoencoder Based Multi-Omics Data Integration for Cancer Survival Prediction
Cancer survival prediction is important for developing personalized treatments and inducing disease-causing mechanisms. Multi-omics data integration is attracting widespread interest in cancer research for providing info…
Data IntegrationDimensionality ReductionPredictionSurvival PredictionSTProtein: predicting spatial protein expression from multi-omics data
The integration of spatial multi-omics data from single tissues is crucial for advancing biological research. However, a significant data imbalance impedes progress: while spatial transcriptomics data is relatively abund…
Multi-Task LearningscpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
The integration of single-cell proteomic data is often hindered by the fragmented nature of targeted antibody panels. To address this limitation, we introduce scpFormer, a transformer-based foundation model designed for …
Drug Response PredictionGROVER: Graph-guided Representation of Omics and Vision with Expert Regulation for Adaptive Spatial Multi-omics Fusion
Effectively modeling multimodal spatial omics data is critical for understanding tissue complexity and underlying biological mechanisms. While spatial transcriptomics, proteomics, and epigenomics capture molecular featur…
Contrastive Learning