Bayesian multi-tensor factorization

Omics in a Digital World: The Role of Bioinformatics in Providing New Insights Into Human Aging

Background

Aging is a complex phenotype influenced by a combination of genetic and environmental factors. Although many studies addressed its cellular and physiological age-related changes, the molecular causes of aging remain undetermined. Considering the biological complexity and heterogeneity of the aging process, it is now clear that full understanding of mechanisms underlying aging can only be achieved through the integration of different data types and sources, and with new computational methods capable to achieve such integration.

Recent Advances

In this review, we show that an omics vision of the age-dependent changes occurring as the individual ages can provide researchers with new opportunities to understand the mechanisms of aging. Combining results from single-cell analysis with systems biology tools would allow building interaction networks and investigate how these networks are perturbed during aging and disease. The development of high-throughput technologies such as next-generation sequencing, proteomics, metabolomics, able to investigate different biological markers and to monitor them simultaneously during the aging process with high accuracy and specificity, represents a unique opportunity offered to biogerontologists today.

Critical Issues

Although the capacity to produce big data drastically increased over the years, integration, interpretation and sharing of high-throughput data remain major challenges. In this paper we present a survey of the emerging omics approaches in aging research and provide a large collection of datasets and databases as a useful resource for the scientific community to identify causes of aging. We discuss their peculiarities, emphasizing the need for the development of methods focused on the integration of different data types.

Future Directions

We critically review the contribution of bioinformatics into the omics of aging research, and we propose a few recommendations to boost collaborations and produce new insights. We believe that significant advancements can be achieved by following major developments in bioinformatics, investing in diversity, data sharing and community-driven portable bioinformatics methods. We also argue in favor of more engagement and participation, and we highlight the benefits of new collaborations along these lines. This review aims at being a useful resource for many researchers in the field, and a call for new partnerships in aging research.

Bayesian Low-Tubal-Rank Robust Tensor Factorization with Multi-Rank Determination

Robust tensor factorization is a fundamental problem in machine learning and computer vision, which aims at decomposing tensors into low-rank and sparse components. However, existing methods either suffer from limited modeling power in preserving low-rank structures, or have difficulties in determining the target tensor rank and the trade-off between the low-rank and sparse components. To address these problems, we propose a fully Bayesian treatment of robust tensor factorization along with a generalized sparsity-inducing prior. By adapting the recently proposed low-tubal-rank model in a generative manner, our method is effective in preserving low-rank structures. Moreover, benefiting from the proposed prior and the Bayesian framework, the proposed method can automatically determine the tensor rank while inferring the trade-off between the low-rank and sparse components. For model estimation, we develop a variational inference algorithm, and further improve its efficiency by reformulating the variational updates in the frequency domain. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed method in multi-rank determination as well as its superiority in image denoising and background modeling over state-of-the-art approaches.

An integrative machine learning approach to discovering multi-level molecular mechanisms of obesity using data from monozygotic twin pairs

We combined clinical, cytokine, genomic, methylation and dietary data from 43 young adult monozygotic twin pairs (aged 22-36 years, 53% female), where 25 of the twin pairs were substantially weight discordant (delta body mass index > 3 kg m^-2). These measurements were originally taken as part of the TwinFat study, a substudy of The Finnish Twin Cohort study. These five large multivariate datasets (comprising 42, 71, 1587, 1605 and 63 variables, respectively) were jointly analysed using an integrative machine learning method called group factor analysis (GFA) to offer new hypotheses into the multi-molecular-level interactions associated with the development of obesity. New potential links between cytokines and weight gain are identified, as well as associations between dietary, inflammatory and epigenetic factors. This encouraging case study aims to enthuse the research community to boldly attempt new machine learning approaches which have the potential to yield novel and unintuitive hypotheses. The source code of the GFA method is publically available as the R package GFA.

Tightly integrated genomic and epigenomic data mining using tensor decomposition

Motivation

Complex diseases such as cancers often involve multiple types of genomic and/or epigenomic abnormalities. Rapid accumulation of multiple types of omics data demands methods for integrating the multidimensional data in order to elucidate complex relationships among different types of genomic and epigenomic abnormalities.

Results

In the present study, we propose a tightly integrated approach based on tensor decomposition. Multiple types of data, including mRNA, methylation, copy number variations and somatic mutations, are merged into a high-order tensor which is used to develop predictive models for overall survival. The weight tensors of the models are constrained using CANDECOMP/PARAFAC (CP) tensor decomposition and learned using support tensor machine regression (STR) and ridge tensor regression (RTR). The results demonstrate that the tensor decomposition based approaches can achieve better performance than the models based individual data type and the concatenation approach.

Supplementary information

Supplementary data are available at Bioinformatics online.

S3CMTF: Fast, accurate, and scalable method for incomplete coupled matrix-tensor factorization

How can we extract hidden relations from a tensor and a matrix data simultaneously in a fast, accurate, and scalable way? Coupled matrix-tensor factorization (CMTF) is an important tool for this purpose. Designing an accurate and efficient CMTF method has become more crucial as the size and dimension of real-world data are growing explosively. However, existing methods for CMTF suffer from lack of accuracy, slow running time, and limited scalability. In this paper, we propose S³CMTF, a fast, accurate, and scalable CMTF method. In contrast to previous methods which do not handle large sparse tensors and are not parallelizable, S³CMTF provides parallel sparse CMTF by carefully deriving gradient update rules. S³CMTF asynchronously updates partial gradients without expensive locking. We show that our method is guaranteed to converge to a quality solution theoretically and empirically. S³CMTF further boosts the performance by carefully storing intermediate computation and reusing them. We theoretically and empirically show that S³CMTF is the fastest, outperforming existing methods. Experimental results show that S³CMTF is up to 930× faster than existing methods while providing the best accuracy. S³CMTF shows linear scalability on the number of data entries and the number of cores. In addition, we apply S³CMTF to Yelp rating tensor data coupled with 3 additional matrices to discover interesting patterns.

A review of drug knowledge discovery using BioNLP and tensor or matrix decomposition

Prediction of the relations among drug and other molecular or social entities is the main knowledge discovery pattern for the purpose of drug-related knowledge discovery. Computational approaches have combined the information from different sources and levels for drug-related knowledge discovery, which provides a sophisticated comprehension of the relationship among drugs, targets, diseases, and targeted genes, at the molecular level, or relationships among drugs, usage, side effect, safety, and user preference, at a social level. In this research, previous work from the BioNLP community and matrix or matrix decomposition was reviewed, compared, and concluded, and eventually, the BioNLP open-shared task was introduced as a promising case study representing this area.

A Sequentially Truncated Higher Order Singular Value Decomposition-Based Algorithm for Tensor Completion

The problem of recovering missing data of an incomplete tensor has drawn more and more attentions in the fields of pattern recognition, machine learning, data mining, computer vision, and signal processing. Researches on this problem usually share a common assumption that the original tensor is of low-rank. One of the important ways to capture the low-rank structure of the incomplete tensor is based on tensor factorization. For the traditional tensor factorization algorithms, the tensor ranks should be specified ahead, which is not reasonable in real applications. To overcome this drawback, an adaptive algorithm is first presented based on sequentially truncated higher order singular value decomposition (ST-HOSVD) for fast low-rank approximation of complete tensor, in which the tensor ranks can be obtained adaptively. Then for tensor with missing data, we use adaptive ST-HOSVD and the average operator of low-rank approximation to improve the accuracy of the fulfilled tensor. Convergence analysis of the proposed algorithm is also given in this paper. The experimental results on 14 image datasets and three video datasets show that the proposed method outperforms the state-of-the-art methods in terms of running time and the accuracy.

Patient similarity by joint matrix trifactorization to identify subgroups in acute myeloid leukemia

Objective

Computing patients’ similarity is of great interest in precision oncology since it supports clustering and subgroup identification, eventually leading to tailored therapies. The availability of large amounts of biomedical data, characterized by large feature sets and sparse content, motivates the development of new methods to compute patient similarities able to fuse heterogeneous data sources with the available knowledge.

Materials and Methods

In this work, we developed a data integration approach based on matrix trifactorization to compute patient similarities by integrating several sources of data and knowledge. We assess the accuracy of the proposed method: (1) on several synthetic data sets which similarity structures are affected by increasing levels of noise and data sparsity, and (2) on a real data set coming from an acute myeloid leukemia (AML) study. The results obtained are finally compared with the ones of traditional similarity calculation methods.

Results

In the analysis of the synthetic data set, where the ground truth is known, we measured the capability of reconstructing the correct clusters, while in the AML study we evaluated the Kaplan-Meier curves obtained with the different clusters and measured their statistical difference by means of the log-rank test. In presence of noise and sparse data, our data integration method outperform other techniques, both in the synthetic and in the AML data.

Discussion

In case of multiple heterogeneous data sources, a matrix trifactorization technique can successfully fuse all the information in a joint model. We demonstrated how this approach can be efficiently applied to discover meaningful patient similarities and therefore may be considered a reliable data driven strategy for the definition of new research hypothesis for precision oncology.

Conclusion

The better performance of the proposed approach presents an advantage over previous methods to provide accurate patient similarities supporting precision medicine.

Integrated 'omics analysis reveals new drug-induced mitochondrial perturbations in human hepatocytes

We performed a multiple 'omics study by integrating data on epigenomic, transcriptomic, and proteomic perturbations associated with mitochondrial dysfunction in primary human hepatocytes caused by the liver toxicant valproic acid (VPA), to deeper understand downstream events following epigenetic alterations in the mitochondrial genome. Furthermore, we investigated persistence of cross-omics changes after terminating drug treatment. Upon transient methylation changes of mitochondrial genes during VPA-treatment, increasing complexities of gene-interaction networks across time were demonstrated, which normalized during washout. Furthermore, co-expression between genes and their corresponding proteins increased across time. Additionally, in relation to persistently decreased ATP production, we observed decreased expression of mitochondrial complex I and III-V genes. Persistent transcripts and proteins were related to citric acid cycle and β-oxidation. In particular, we identified a potential novel mitochondrial-nuclear signaling axis, MT-CO2-FN1-MYC-CPT1. In summary, this cross-omics study revealed dynamic responses of the mitochondrial epigenome to an impulse toxicant challenge resulting in persistent mitochondrial dysfunctioning. Moreover, this approach allowed for discriminating between the toxic effect of VPA and adaptation.

Identification of candidate drugs using tensor-decomposition-based unsupervised feature extraction in integrated analysis of gene expression between diseases and DrugMatrix datasets

Identifying drug target genes in gene expression profiles is not straightforward. Because a drug targets proteins and not mRNAs, the mRNA expression of drug target genes is not always altered. In addition, the interaction between a drug and protein can be context dependent; this means that simple drug incubation experiments on cell lines do not always reflect the real situation during active disease. In this paper, I applied tensor-decomposition-based unsupervised feature extraction to the integrated analysis using a mathematical product of gene expression in various diseases and gene expression in the DrugMatrix dataset, where comprehensive data on gene expression during various drug treatments of rats are reported. I found that this strategy, in a fully unsupervised manner, enables researchers to identify a combined set of genes and compounds that significantly overlap with gene and drug interactions identified in the past. As an example illustrating the usefulness of this strategy in drug discovery experiments, I considered cirrhosis, for which no effective drugs have ever been proposed. The present strategy identified two promising therapeutic-target genes, CYPOR and HNFA4; for their protein products, bezafibrate was identified as a promising candidate drug, supported by in silico docking analysis.

Systematic identification of feature combinations for predicting drug response with Bayesian multi-view multi-task linear regression

MOTIVATION

A prime challenge in precision cancer medicine is to identify genomic and molecular features that are predictive of drug treatment responses in cancer cells. Although there are several computational models for accurate drug response prediction, these often lack the ability to infer which feature combinations are the most predictive, particularly for high-dimensional molecular datasets. As increasing amounts of diverse genome-wide data sources are becoming available, there is a need to build new computational models that can effectively combine these data sources and identify maximally predictive feature combinations.

RESULTS

We present a novel approach that leverages on systematic integration of data sources to identify response predictive features of multiple drugs. To solve the modeling task we implement a Bayesian linear regression method. To further improve the usefulness of the proposed model, we exploit the known human cancer kinome for identifying biologically relevant feature combinations. In case studies with a synthetic dataset and two publicly available cancer cell line datasets, we demonstrate the improved accuracy of our method compared to the widely used approaches in drug response analysis. As key examples, our model identifies meaningful combinations of features for the well known EGFR, ALK, PLK and PDGFR inhibitors.

AVAILABILITY AND IMPLEMENTATION

The source code of the method is available at https://github.com/suleimank/mvlr .

CONTACT

muhammad.ammad-ud-din@helsinki.fi or suleiman.khan@helsinki.fi.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.