Dataset Information

The Incremental Multiresolution Matrix Factorization Algorithm.

ABSTRACT: Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric matrices - an important aspect in the success of many vision problems. Our new algorithm, the incremental multiresolution matrix factorization, uncovers such structure one feature at a time, and hence scales well to large matrices. We describe how this multiscale analysis goes much farther than what a direct "global" factorization of the data can identify. We evaluate the efficacy of the resulting factorizations for relative leveraging within regression tasks using medical imaging data. We also use the factorization on representations learned by popular deep networks, providing evidence of their ability to infer semantic relationships even when they are not explicitly trained to do so. We show that this algorithm can be used as an exploratory tool to improve the network architecture, and within numerous other settings in vision.

SUBMITTER: Ithapu VK

PROVIDER: S-EPMC5798492 | biostudies-literature | 2017 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The Incremental Multiresolution Matrix Factorization Algorithm.

Ithapu Vamsi K VK Kondor Risi R Johnson Sterling C SC Singh Vikas V

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 20170701

Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric matrices - an important aspect in the success of many vision problems. Our new algorithm, the incremental multiresolution matrix factorization, uncovers such structure one feature at a time, and hence scales well to large matrices. We describe how this multisca ...[more]

PMID: 29416293

Similar Datasets

Project description:The amounts and types of available multimodal tumor data are rapidly increasing, and their integration is critical for fully understanding the underlying cancer biology and personalizing treatment. However, the development of methods for effectively integrating multimodal data in a principled manner is lagging behind our ability to generate the data. In this article, we introduce an extension to a multiview nonnegative matrix factorization algorithm (NNMF) for dimensionality reduction and integration of heterogeneous data types and compare the predictive modeling performance of the method on unimodal and multimodal data. We also present a comparative evaluation of our novel multiview approach and current data integration methods. Our work provides an efficient method to extend an existing dimensionality reduction method. We report rigorous evaluation of the method on large-scale quantitative protein and phosphoprotein tumor data from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) acquired using state-of-the-art liquid chromatography mass spectrometry. Exome sequencing and RNA-Seq data were also available from The Cancer Genome Atlas for the same tumors. For unimodal data, in case of breast cancer, transcript levels were most predictive of estrogen and progesterone receptor status and copy number variation of human epidermal growth factor receptor 2 status. For ovarian and colon cancers, phosphoprotein and protein levels were most predictive of tumor grade and stage and residual tumor, respectively. When multiview NNMF was applied to multimodal data to predict outcomes, the improvement in performance is not overall statistically significant beyond unimodal data, suggesting that proteomics data may contain more predictive information regarding tumor phenotypes than transcript levels, probably due to the fact that proteins are the functional gene products and therefore a more direct measurement of the functional state of the tumor. Here, we have applied our proposed approach to multimodal molecular data for tumors, but it is generally applicable to dimensionality reduction and joint analysis of any type of multimodal data.

Project description:BackgroundAlthough surgical methods are the most effective treatments for colon adenocarcinoma (COAD), the cure rates remain low, and recurrence rates remain high. Furthermore, platelet adhesion-related genes are gaining attention as potential regulators of tumorigenesis. Therefore, identifying the mechanisms responsible for the regulation of these genes in patients with COAD has become important. The present study aims to investigate the underlying mechanisms of platelet adhesion-related genes in COAD patients.MethodsThe present study was an experimental study. Initially, the effects of platelet number and related genomic alteration on survival were explored using real-world data and the cBioPortal database, respectively. Then, the differentially expressed platelet adhesion-related genes of COAD were analyzed using the TCGA database, and patients were further classified by employing the non-negative matrix factorization (NMF) analysis method. Afterward, some of the clinical and expression characteristics were analyzed between clusters. Finally, least absolute shrinkage and selection operator regression analysis was used to establish the prognostic nomogram. All data analyses were performed using the R package.ResultsHigh platelet counts are associated with worse survival in real-world patients, and alternations to platelet adhesion-related genes have resulted in poorer prognoses, based on online data. Based on platelet adhesion-related genes, patients with COAD were classified into two clusters by NMF-based clustering analysis. Cluster2 had a better overall survival, when compared to Cluster1. The gene copy number and enrichment analysis results revealed that two pathways were differentially enriched. In addition, the differentially expressed genes between these two clusters were enriched for POU6F1 in the transcription factor signaling pathway, and for MATN3 in the ceRNA network. Finally, a prognostic nomogram, which included the ALOX12 and ACTG1 genes, was established based on the platelet adhesion-related genes, with a concordance (C) index of 0.879 (0.848-0.910).ConclusionThe mRNA expression-based NMF was used to reveal the potential role of platelet adhesion-related genes in COAD. The series of experiments revealed the feasibility of targeting platelet adhesion-associated gene therapy.

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

The Incremental Multiresolution Matrix Factorization Algorithm.

Publications

The Incremental Multiresolution Matrix Factorization Algorithm.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets