Dataset Information

Novel Collaborative Weighted Non-negative Matrix Factorization Improves Prediction of Disease-Associated Human Microbes.

ABSTRACT: Extensive clinical and biomedical studies have shown that microbiome plays a prominent role in human health. Identifying potential microbe-disease associations (MDAs) can help reveal the pathological mechanism of human diseases and be useful for the prevention, diagnosis, and treatment of human diseases. Therefore, it is necessary to develop effective computational models and reduce the cost and time of biological experiments. Here, we developed a novel machine learning-based joint framework called CWNMF-GLapRLS for human MDA prediction using the proposed collaborative weighted non-negative matrix factorization (CWNMF) technique and graph Laplacian regularized least squares. Especially, to fuse more similarity information, we calculated the functional similarity of microbes. To deal with missing values and effectively overcome the data sparsity problem, we proposed a collaborative weighted NMF technique to reconstruct the original association matrix. In addition, we developed a graph Laplacian regularized least-squares method for prediction. The experimental results of fivefold and leave-one-out cross-validation demonstrated that our method achieved the best performance by comparing it with 5 state-of-the-art methods on the benchmark dataset. Case studies further showed that the proposed method is an effective tool to predict potential MDAs and can provide more help for biomedical researchers.

SUBMITTER: Xu D

PROVIDER: S-EPMC8965656 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Novel Collaborative Weighted Non-negative Matrix Factorization Improves Prediction of Disease-Associated Human Microbes.

Xu Da D Xu Hanxiao H Zhang Yusen Y Gao Rui R

Frontiers in microbiology 20220310

Extensive clinical and biomedical studies have shown that microbiome plays a prominent role in human health. Identifying potential microbe-disease associations (MDAs) can help reveal the pathological mechanism of human diseases and be useful for the prevention, diagnosis, and treatment of human diseases. Therefore, it is necessary to develop effective computational models and reduce the cost and time of biological experiments. Here, we developed a novel machine learning-based joint framework cal ...[more]

PMID: 35369503

Similar Datasets

Project description:The direct "metagenomic" sequencing of genomic material from complex assemblages of bacteria, archaea, viruses and microeukaryotes has yielded new insights into the structure of microbial communities. For example, analysis of metagenomic data has revealed the existence of previously unknown microbial taxa whose spatial distributions are limited by environmental conditions, ecological competition, and dispersal mechanisms. However, differences in genotypes that might lead biologists to designate two microbes as taxonomically distinct need not necessarily imply differences in ecological function. Hence, there is a growing need for large-scale analysis of the distribution of microbial function across habitats. Here, we present a framework for investigating the biogeography of microbial function by analyzing the distribution of protein families inferred from environmental sequence data across a global collection of sites. We map over 6,000,000 protein sequences from unassembled reads from the Global Ocean Survey dataset to [Formula: see text] protein families, generating a protein family relative abundance matrix that describes the distribution of each protein family across sites. We then use non-negative matrix factorization (NMF) to approximate these protein family profiles as linear combinations of a small number of ecological components. Each component has a characteristic functional profile and site profile. Our approach identifies common functional signatures within several of the components. We use our method as a filter to estimate functional distance between sites, and find that an NMF-filtered measure of functional distance is more strongly correlated with environmental distance than a comparable PCA-filtered measure. We also find that functional distance is more strongly correlated with environmental distance than with geographic distance, in agreement with prior studies. We identify similar protein functions in several components and suggest that functional co-occurrence across metagenomic samples could lead to future methods for de-novo functional prediction. We conclude by discussing how NMF, and other dimension reduction methods, can help enable a macroscopic functional description of marine ecosystems.

Project description:BackgroundMatrix 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.ResultsWe 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.ConclusionsA 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.

Project description:The relationship between grey matter volume (GMV) patterns and age can be captured by multivariate pattern analysis, allowing prediction of individuals' age based on structural imaging. Raw data, voxel-wise GMV and non-sparse factorization (with Principal Component Analysis, PCA) show good performance but do not promote relatively localized brain components for post-hoc examinations. Here we evaluated a non-negative matrix factorization (NNMF) approach to provide a reduced, but also interpretable representation of GMV data in age prediction frameworks in healthy and clinical populations. This examination was performed using three datasets: a multi-site cohort of life-span healthy adults, a single site cohort of older adults and clinical samples from the ADNI dataset with healthy subjects, participants with Mild Cognitive Impairment and patients with Alzheimer's disease (AD) subsamples. T1-weighted images were preprocessed with VBM8 standard settings to compute GMV values after normalization, segmentation and modulation for non-linear transformations only. Non-negative matrix factorization was computed on the GM voxel-wise values for a range of granularities (50-690 components) and LASSO (Least Absolute Shrinkage and Selection Operator) regression were used for age prediction. First, we compared the performance of our data compression procedure (i.e., NNMF) to various other approaches (i.e., uncompressed VBM data, PCA-based factorization and parcellation-based compression). We then investigated the impact of the granularity on the accuracy of age prediction, as well as the transferability of the factorization and model generalization across datasets. We finally validated our framework by examining age prediction in ADNI samples. Our results showed that our framework favorably compares with other approaches. They also demonstrated that the NNMF based factorization derived from one dataset could be efficiently applied to compress VBM data of another dataset and that granularities between 300 and 500 components give an optimal representation for age prediction. In addition to the good performance in healthy subjects our framework provided relatively localized brain regions as the features contributing to the prediction, thereby offering further insights into structural changes due to brain aging. Finally, our validation in clinical populations showed that our framework is sensitive to deviance from normal structural variations in pathological aging.

Dataset Information

Novel Collaborative Weighted Non-negative Matrix Factorization Improves Prediction of Disease-Associated Human Microbes.

Publications

Novel Collaborative Weighted Non-negative Matrix Factorization Improves Prediction of Disease-Associated Human Microbes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets