Dataset Information

JDSNMF: Joint Deep Semi-Non-Negative Matrix Factorization for Learning Integrative Representation of Molecular Signals in Alzheimer's Disease.

ABSTRACT: High dimensional multi-omics data integration can enhance our understanding of the complex biological interactions in human diseases. However, most studies involving unsupervised integration of multi-omics data focus on linear integration methods. In this study, we propose a joint deep semi-non-negative matrix factorization (JDSNMF) model, which uses a hierarchical non-linear feature extraction approach that can capture shared latent features from the complex multi-omics data. The extracted latent features obtained from JDSNMF enabled a variety of downstream tasks, including prediction of disease and module analysis. The proposed model is applicable not only to sample-matched multiple data (e.g., multi-omics data from one cohort) but also to feature-matched multiple data (e.g., omics data from multiple cohorts), and therefore it can be flexibly applied to various cases. We demonstrate the capabilities of JDSNMF using sample-matched simulated data and feature-matched multi-omics data from Alzheimer's disease cohorts, evaluating the feature extraction performance in the context of classification. In a test application, we identify AD- and age-related modules from the latent matrices using an explainable artificial intelligence and regression model. These results show that the JDSNMF model is effective in identifying latent features having a complex interplay of potential biological signatures.

SUBMITTER: Moon S

PROVIDER: S-EPMC8400727 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background:Matrix factorization is a well established pattern discovery tool that has seen numerous applications in biomedical data analytics, such as gene expression co-clustering, patient stratification, and gene-disease association mining. Matrix factorization learns a latent data model that takes a data matrix and transforms it into a latent feature space enabling generalization, noise removal and feature discovery. However, factorization algorithms are numerically intensive, and hence there is a pressing challenge to scale current algorithms to work with large datasets. Our focus in this paper is matrix tri-factorization, a popular method that is not limited by the assumption of standard matrix factorization about data residing in one latent space. Matrix tri-factorization solves this by inferring a separate latent space for each dimension in a data matrix, and a latent mapping of interactions between the inferred spaces, making the approach particularly suitable for biomedical data mining. Results:We developed a block-wise approach for latent factor learning in matrix tri-factorization. The approach partitions a data matrix into disjoint submatrices that are treated independently and fed into a parallel factorization system. An appealing property of the proposed approach is its mathematical equivalence with serial matrix tri-factorization. In a study on large biomedical datasets we show that our approach scales well on multi-processor and multi-GPU architectures. On a four-GPU system we demonstrate that our approach can be more than 100-times faster than its single-processor counterpart. Conclusions:A general approach for scaling non-negative matrix tri-factorization is proposed. The approach is especially useful parallel matrix factorization implemented in a multi-GPU environment. We expect the new approach will be useful in emerging procedures for latent factor analysis, notably for data integration, where many large data matrices need to be collectively factorized.

Dataset Information

JDSNMF: Joint Deep Semi-Non-Negative Matrix Factorization for Learning Integrative Representation of Molecular Signals in Alzheimer's Disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets