A model for learning topographically organized parts-based representations of objects in visual cortex: topographic nonnegative matrix factorization

A deep matrix factorization framework for identifying underlying tissue-specific patterns of DCE-MRI: applications for molecular subtype classification in breast cancer

Objective.Breast cancer is heterogeneous in that different angiogenesis and blood flow characteristics could be present within a tumor. The pixel kinetics of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can assume several distinct signal patterns related to specific tissue characteristics. Identification of the latent, tissue-specific dynamic patterns of intratumor heterogeneity can shed light on the biological mechanisms underlying the heterogeneity of tumors.Approach.To mine this information, we propose a deep matrix factorization-based dynamic decomposition (DMFDE) model specifically designed according to DCE-MRI characteristics. The time-series imaging data were decomposed into tissue-specific dynamic patterns and their corresponding proportion maps. The image pixel matrix and the reference matrix of population-level kinetics obtained by clustering the dynamic signals were used as the inputs. Two multilayer neural network branches were designed to collaboratively project the input matrix into a latent dynamic pattern and a dynamic proportion matrix, which was justified using simulated data. Clinical implications of DMFDE were assessed by radiomics analysis of proportion maps obtained from the tumor/parenchyma region for classifying the luminal A subtype.Main results.The decomposition performance of DMFDE was evaluated by the root mean square error and was shown to be better than that of the conventional convex analysis of mixtures (CAM) method. The predictive model withK = 3, 4, and 5 dynamic proportion maps generated AUC values of 0.780, 0.786 and 0.790, respectively, in distinguishing between luminal A and nonluminal A tumors, which are better than the CAM method (AUC = 0.726). The combination of statistical features from images with different proportion maps has the highest prediction value (AUC = 0.813), which is significantly higher than that based on CAM.Conclusion.This proposed method identified the latent dynamic patterns associated with different molecular subtypes, and radiomics analysis based on the pixel compositions of the uncovered dynamic patterns was able to determine molecular subtypes of breast cancer.

Prediction of Potential Associations Between miRNAs and Diseases Based on Matrix Decomposition

It is known that miRNA plays an increasingly important role in many physiological processes. Disease-related miRNAs could be potential biomarkers for clinical diagnosis, prognosis, and treatment. Therefore, accurately inferring potential miRNAs related to diseases has become a hot topic in the bioinformatics community recently. In this study, we proposed a mathematical model based on matrix decomposition, named MFMDA, to identify potential miRNA-disease associations by integrating known miRNA and disease-related data, similarities between miRNAs and between diseases. We also compared MFMDA with some of the latest algorithms in several established miRNA disease databases. MFMDA reached an AUC of 0.9061 in the fivefold cross-validation. The experimental results show that MFMDA effectively infers novel miRNA-disease associations. In addition, we conducted case studies by applying MFMDA to three types of high-risk human cancers. While most predicted miRNAs are confirmed by external databases of experimental literature, we also identified a few novel disease-related miRNAs for further experimental validation.

Computational drug repositioning based on multi-similarities bilinear matrix factorization

With the development of high-throughput technology and the accumulation of biomedical data, the prior information of biological entity can be calculated from different aspects. Specifically, drug-drug similarities can be measured from target profiles, drug-drug interaction and side effects. Similarly, different methods and data sources to calculate disease ontology can result in multiple measures of pairwise disease similarities. Therefore, in computational drug repositioning, developing a dynamic method to optimize the fusion process of multiple similarities is a crucial and challenging task. In this study, we propose a multi-similarities bilinear matrix factorization (MSBMF) method to predict promising drug-associated indications for existing and novel drugs. Instead of fusing multiple similarities into a single similarity matrix, we concatenate these similarity matrices of drug and disease, respectively. Applying matrix factorization methods, we decompose the drug-disease association matrix into a drug-feature matrix and a disease-feature matrix. At the same time, using these feature matrices as basis, we extract effective latent features representing the drug and disease similarity matrices to infer missing drug-disease associations. Moreover, these two factored matrices are constrained by non-negative factorization to ensure that the completed drug-disease association matrix is biologically interpretable. In addition, we numerically solve the MSBMF model by an efficient alternating direction method of multipliers algorithm. The computational experiment results show that MSBMF obtains higher prediction accuracy than the state-of-the-art drug repositioning methods in cross-validation experiments. Case studies also demonstrate the effectiveness of our proposed method in practical applications. Availability: The data and code of MSBMF are freely available at https://github.com/BioinformaticsCSU/MSBMF. Corresponding author: Jianxin Wang, School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, P. R. China. E-mail: jxwang@mail.csu.edu.cn Supplementary Data: Supplementary data are available online at https://academic.oup.com/bib.

Inferring the Disease-Associated miRNAs Based on Network Representation Learning and Convolutional Neural Networks

Identification of disease-associated miRNAs (disease miRNAs) are critical for understanding etiology and pathogenesis. Most previous methods focus on integrating similarities and associating information contained in heterogeneous miRNA-disease networks. However, these methods establish only shallow prediction models that fail to capture complex relationships among miRNA similarities, disease similarities, and miRNA-disease associations. We propose a prediction method on the basis of network representation learning and convolutional neural networks to predict disease miRNAs, called CNNMDA. CNNMDA deeply integrates the similarity information of miRNAs and diseases, miRNA-disease associations, and representations of miRNAs and diseases in low-dimensional feature space. The new framework based on deep learning was built to learn the original and global representation of a miRNA-disease pair. First, diverse biological premises about miRNAs and diseases were combined to construct the embedding layer in the left part of the framework, from a biological perspective. Second, the various connection edges in the miRNA-disease network, such as similarity and association connections, were dependent on each other. Therefore, it was necessary to learn the low-dimensional representations of the miRNA and disease nodes based on the entire network. The right part of the framework learnt the low-dimensional representation of each miRNA and disease node based on non-negative matrix factorization, and these representations were used to establish the corresponding embedding layer. Finally, the left and right embedding layers went through convolutional modules to deeply learn the complex and non-linear relationships among the similarities and associations between miRNAs and diseases. Experimental results based on cross validation indicated that CNNMDA yields superior performance compared to several state-of-the-art methods. Furthermore, case studies on lung, breast, and pancreatic neoplasms demonstrated the powerful ability of CNNMDA to discover potential disease miRNAs.

A graph regularized non-negative matrix factorization method for identifying microRNA-disease associations

MOTIVATION

MicroRNAs (miRNAs) play crucial roles in post-transcriptional regulations and various cellular processes. The identification of disease-related miRNAs provides great insights into the underlying pathogenesis of diseases at a system level. However, most existing computational approaches are biased towards known miRNA-disease associations, which is inappropriate for those new diseases or miRNAs without any known association information.

RESULTS

In this study, we propose a new method with graph regularized non-negative matrix factorization in heterogeneous omics data, called GRNMF, to discover potential associations between miRNAs and diseases, especially for new diseases and miRNAs or those diseases and miRNAs with sparse known associations. First, we integrate the disease semantic information and miRNA functional information to estimate disease similarity and miRNA similarity, respectively. Considering that there is no available interaction observed for new diseases or miRNAs, a preprocessing step is developed to construct the interaction score profiles that will assist in prediction. Next, a graph regularized non-negative matrix factorization framework is utilized to simultaneously identify potential associations for all diseases. The results indicated that our proposed method can effectively prioritize disease-associated miRNAs with higher accuracy compared with other recent approaches. Moreover, case studies also demonstrated the effectiveness of GRNMF to infer unknown miRNA-disease associations for those novel diseases and miRNAs.

AVAILABILITY AND IMPLEMENTATION

The code of GRNMF is freely available at https://github.com/XIAO-HN/GRNMF/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Eigenanatomy improves detection power for longitudinal cortical change

We contribute a novel and interpretable dimensionality reduction strategy, eigenanatomy, that is tuned for neuroimaging data. The method approximates the eigendecomposition of an image set with basis functions (the eigenanatomy vectors) that are sparse, unsigned and are anatomically clustered. We employ the eigenanatomy vectors as anatomical predictors to improve detection power in morphometry. Standard voxel-based morphometry (VBM) analyzes imaging data voxel-by-voxel--and follows this with cluster-based or voxel-wise multiple comparisons correction methods to determine significance. Eigenanatomy reverses the standard order of operations by first clustering the voxel data and then using standard linear regression in this reduced dimensionality space. As with traditional region-of-interest (ROI) analysis, this strategy can greatly improve detection power. Our results show that eigenanatomy provides a principled objective function that leads to localized, data-driven regions of interest. These regions improve our ability to quantify biologically plausible rates of cortical change in two distinct forms of neurodegeneration. We detail the algorithm and show experimental evidence of its efficacy.