Robust Attribute and Structure Preserving Graph Embedding
Ontology highlight
ABSTRACT:
SUBMITTER: Lauw H
PROVIDER: S-EPMC7206273 | biostudies-literature | 2020 Apr
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Artifacts in biomedical signal recordings, such as gene expression, sonar image and electroencephalogram, have a great influence on the related research because the artifacts with large value usually break the neighbor structure in the datasets. However, the conventional graph embedding (GE) used for dimension reduction such as linear discriminant analysis, principle component analysis and locality preserving projections is essentially defined in the L2 norm space and is prone to the presence of artifacts, resulting in biased sub-structural features. In this work, we defined graph embedding in the L1 norm space and used the maximization strategy to solve this model with the aim of restricting the influence of outliers on the dimension reduction of signals. The quantitative evaluation with different outlier conditions demonstrates that an L1 norm-based GE structure can estimate hyperplanes, which are more stable than those of conventional GE-based methods. The applications to a variety of datasets also show that the proposed L1 GE is more robust to outlier influence with higher classification accuracy estimated. The proposed L1 GE may be helpful for capturing reliable mapping information from the datasets that have been contaminated with outliers.
| S-EPMC5844917 | biostudies-literature
Project description:Many scientific datasets are of high dimension, and the analysis usually requires retaining the most important structures of data. Principal curve is a widely used approach for this purpose. However, many existing methods work only for data with structures that are mathematically formulated by curves, which is quite restrictive for real applications. A few methods can overcome the above problem, but they either require complicated human-made rules for a specific task with lack of adaption flexibility to different tasks, or cannot obtain explicit structures of data. To address these issues, we develop a novel principal graph and structure learning framework that captures the local information of the underlying graph structure based on reversed graph embedding. As showcases, models that can learn a spanning tree or a weighted undirected `1 graph are proposed, and a new learning algorithm is developed that learns a set of principal points and a graph structure from data, simultaneously. The new algorithm is simple with guaranteed convergence. We then extend the proposed framework to deal with large-scale data. Experimental results on various synthetic and six real world datasets show that the proposed method compares favorably with baselines and can uncover the underlying structure correctly.
| S-EPMC5899072 | biostudies-literature
Project description:The goal of dimensionality reduction is to embed high-dimensional data in a low-dimensional space while preserving structure in the data relevant to exploratory data analysis such as clusters. However, existing dimensionality reduction methods often either fail to separate clusters due to the crowding problem or can only separate clusters at a single resolution. We develop a new approach to dimensionality reduction: tree preserving embedding. Our approach uses the topological notion of connectedness to separate clusters at all resolutions. We provide a formal guarantee of cluster separation for our approach that holds for finite samples. Our approach requires no parameters and can handle general types of data, making it easy to use in practice and suggesting new strategies for robust data visualization.
| S-EPMC3193256 | biostudies-literature
Project description:In this research, we improve upon the current state of the art in entity retrieval by re-ranking the result list using graph embeddings. The paper shows that graph embeddings are useful for entity-oriented search tasks. We demonstrate empirically that encoding information from the knowledge graph into (graph) embeddings contributes to a higher increase in effectiveness of entity retrieval results than using plain word embeddings. We analyze the impact of the accuracy of the entity linker on the overall retrieval effectiveness. Our analysis further deploys the cluster hypothesis to explain the observed advantages of graph embeddings over the more widely used word embeddings, for user tasks involving ranking entities.
| S-EPMC7148245 | biostudies-literature
Project description:The network embedding task is to represent a node in a network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix, either directly or implicitly. In this work, we introduce a network embedding method from a new perspective, which leverages Modern Hopfield Networks (MHN) for associative learning. Our network learns associations between the content of each node and that node's neighbors. These associations serve as memories in the MHN. The recurrent dynamics of the network make it possible to recover the masked node, given that node's neighbors. Our proposed method is evaluated on different benchmark datasets for downstream tasks such as node classification, link prediction, and graph coarsening. The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.
| S-EPMC9713410 | biostudies-literature
Project description:Recent advances in chromatin architecture profiling technologies, such as single-cell Hi-C (scHi-C), allow us to dissect the heterogeneity of chromosome higher-order structures across diverse cell states and different individuals. However, scHi-C experiments are still expensive and not immediately available for population-scale profiling. Here, we present scENCORE, a computational method, to reconstruct personalized and cell-type-specific higher-order chromatin structures, such as A/B compartments, directly from more cost-effective and widely available single-cell epigenetic data (e.g., scATAC-seq). We apply scENCORE on scATAC-seq data from post-mortem prefrontal cortex brains and demonstrate its utility to 1) project Mega-base scale chromatin regions into lower dimensional space by leveraging graph embedding technologies based on cell-type-specific co-variability patterns, 2) define A/B compartments via unsupervised clustering, 3) perform an alignment algorithm for multi-graph embedding to derive comparable chromatin representations and highlight dynamic chromatin compartments across cell states and individuals. Validated by Hi-C experiments using FACS-sorted cells, scENCORE can faithfully reconstruct cell-type-specific chromatin compartments. Furthermore, scENCORE uniformly constructs chromosome conformation across population-scale scATAC-seq data and discovers key 3D structural switching events associated with psychiatric disorders. In summary, scENCORE allows cost-effective cell-type-specific and personalized reconstruction that delineate higher-order chromatin structures.
2023-09-27 | GSE216270 | GEO
Project description:BackgroundProtein-protein interactions (PPIs) are central to many biological processes. Considering that the experimental methods for identifying PPIs are time-consuming and expensive, it is important to develop automated computational methods to better predict PPIs. Various machine learning methods have been proposed, including a deep learning technique which is sequence-based that has achieved promising results. However, it only focuses on sequence information while ignoring the structural information of PPI networks. Structural information of PPI networks such as their degree, position, and neighboring nodes in a graph has been proved to be informative in PPI prediction.ResultsFacing the challenge of representing graph information, we introduce an improved graph representation learning method. Our model can study PPI prediction based on both sequence information and graph structure. Moreover, our study takes advantage of a representation learning model and employs a graph-based deep learning method for PPI prediction, which shows superiority over existing sequence-based methods. Statistically, Our method achieves state-of-the-art accuracy of 99.15% on Human protein reference database (HPRD) dataset and also obtains best results on Database of Interacting Protein (DIP) Human, Drosophila, Escherichia coli (E. coli), and Caenorhabditis elegans (C. elegan) datasets.ConclusionHere, we introduce signed variational graph auto-encoder (S-VGAE), an improved graph representation learning method, to automatically learn to encode graph structure into low-dimensional embeddings. Experimental results demonstrate that our method outperforms other existing sequence-based methods on several datasets. We also prove the robustness of our model for very sparse networks and the generalization for a new dataset that consists of four datasets: HPRD, E.coli, C.elegan, and Drosophila.
| S-EPMC7372763 | biostudies-literature
Project description:The microbiome-wide association studies are to figure out the relationship between microorganisms and humans, with the goal of discovering relevant biomarkers to guide disease diagnosis. However, the microbiome data is complex, with high noise and dimensions. Traditional machine learning methods are limited by the models' representation ability and cannot learn complex patterns from the data. Recently, deep learning has been widely applied to fields ranging from text processing to image recognition due to its efficient flexibility and high capacity. But the deep learning models must be trained with enough data in order to achieve good performance, which is impractical in reality. In addition, deep learning is considered as black box and hard to interpret. These factors make deep learning not widely used in microbiome-wide association studies. In this work, we construct a sparse microbial interaction network and embed this graph into deep model to alleviate the risk of overfitting and improve the performance. Further, we explore a Graph Embedding Deep Feedforward Network (GEDFN) to conduct feature selection and guide meaningful microbial markers' identification. Based on the experimental results, we verify the feasibility of combining the microbial graph model with the deep learning model, and demonstrate the feasibility of applying deep learning and feature selection on microbial data. Our main contributions are: firstly, we utilize different methods to construct a variety of microbial interaction networks and combine the network via graph embedding deep learning. Secondly, we introduce a feature selection method based on graph embedding and validate the biological meaning of microbial markers. The code is available at https://github.com/MicroAVA/GEDFN.git.
| S-EPMC6883002 | biostudies-literature
Project description:Single-cell trajectories can unveil how gene regulation governs cell fate decisions. However, learning the structure of complex trajectories with multiple branches remains a challenging computational problem. We present Monocle 2, an algorithm that uses reversed graph embedding to describe multiple fate decisions in a fully unsupervised manner. We applied Monocle 2 to two studies of blood development and found that mutations in the genes encoding key lineage transcription factors divert cells to alternative fates.
| S-EPMC5764547 | biostudies-literature
Project description:Matching 16S rRNA gene sequencing data to a metabolic reference database is a meaningful way to predict the metabolic function of bacteria and archaea, bringing greater insight to the working of the microbial community. However, some operational taxonomy units (OTUs) cannot be functionally profiled, especially for microbial communities from non-human samples cultured in defective media. Therefore, we herein report the development of Hierarchical micrObial functions Prediction by graph aggregated Embedding (HOPE), which utilizes co-occurring patterns and nucleotide sequences to predict microbial functions. HOPE integrates topological structures of microbial co-occurrence networks with k-mer compositions of OTU sequences and embeds them into a lower-dimensional continuous latent space, while maximally preserving topological relationships among OTUs. The high imbalance among KEGG Orthology (KO) functions of microbes is recognized in our framework that usually yields poor performance. A hierarchical multitask learning module is used in HOPE to alleviate the challenge brought by the long-tailed distribution among classes. To test the performance of HOPE, we compare it with HOPE-one, HOPE-seq, and GraphSAGE, respectively, in three microbial metagenomic 16s rRNA sequencing datasets, including abalone gut, human gut, and gut of Penaeus monodon. Experiments demonstrate that HOPE outperforms baselines on almost all indexes in all experiments. Furthermore, HOPE reveals significant generalization ability. HOPE's basic idea is suitable for other related scenarios, such as the prediction of gene function based on gene co-expression networks. The source code of HOPE is freely available at https://github.com/adrift00/HOPE.
| S-EPMC7874084 | biostudies-literature