Similarity-driven multi-view embeddings from high-dimensional biomedical data.
Ontology highlight
ABSTRACT:
SUBMITTER: Avants BB
PROVIDER: S-EPMC8009088 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Modern biomedical studies often collect multi-view data, that is, multiple types of data measured on the same set of objects. A popular model in high-dimensional multi-view data analysis is to decompose each view's data matrix into a low-rank common-source matrix generated by latent factors common across all data views, a low-rank distinctive-source matrix corresponding to each view, and an additive noise matrix. We propose a novel decomposition method for this model, called decomposition-based generalized canonical correlation analysis (D-GCCA). The D-GCCA rigorously defines the decomposition on the L2 space of random variables in contrast to the Euclidean dot product space used by most existing methods, thereby being able to provide the estimation consistency for the low-rank matrix recovery. Moreover, to well calibrate common latent factors, we impose a desirable orthogonality constraint on distinctive latent factors. Existing methods, however, inadequately consider such orthogonality and may thus suffer from substantial loss of undetected common-source variation. Our D-GCCA takes one step further than generalized canonical correlation analysis by separating common and distinctive components among canonical variables, while enjoying an appealing interpretation from the perspective of principal component analysis. Furthermore, we propose to use the variable-level proportion of signal variance explained by common or distinctive latent factors for selecting the variables most influenced. Consistent estimators of our D-GCCA method are established with good finite-sample numerical performance, and have closed-form expressions leading to efficient computation especially for large-scale data. The superiority of D-GCCA over state-of-the-art methods is also corroborated in simulations and real-world data examples.
| S-EPMC9380864 | biostudies-literature
Project description:Linked data and bio-ontologies enabling knowledge representation, standardization, and dissemination are an integral part of developing biological and biomedical databases. That is, linked data and bio-ontologies are employed in databases to maintain data integrity, data organization, and to empower search capabilities. However, linked data and bio-ontologies are more recently being used to represent information as multi-relational heterogeneous graphs, "knowledge graphs". The reason being, entities and relations in the knowledge graph can be represented as embedding vectors in semantic space, and these embedding vectors have been used to predict relationships between entities. Such knowledge graph embedding methods provide a practical approach to data analytics and increase chances of building machine learning models with high prediction accuracy that can enhance decision support systems. Here, we present a comparative assessment and a standard benchmark for knowledge graph-based representation learning methods focused on the link prediction task for biological relations. We systematically investigated and compared state-of-the-art embedding methods based on the design settings used for training and evaluation. We further tested various strategies aimed at controlling the amount of information related to each relation in the knowledge graph and its effects on the final performance. We also assessed the quality of the knowledge graph features through clustering and visualization and employed several evaluation metrics to examine their uses and differences. Based on this systematic comparison and assessments, we identify and discuss the limitations of knowledge graph-based representation learning methods and suggest some guidelines for the development of more improved methods.
| S-EPMC7959619 | biostudies-literature
Project description:Delay embedding-a method for reconstructing dynamical systems by delay coordinates-is widely used to forecast nonlinear time series as a model-free approach. When multivariate time series are observed, several existing frameworks can be applied to yield a single forecast combining multiple forecasts derived from various embeddings. However, the performance of these frameworks is not always satisfactory because they randomly select embeddings or use brute force and do not consider the diversity of the embeddings to combine. Herein, we develop a forecasting framework that overcomes these existing problems. The framework exploits various "suboptimal embeddings" obtained by minimizing the in-sample error via combinatorial optimization. The framework achieves the best results among existing frameworks for sample toy datasets and a real-world flood dataset. We show that the framework is applicable to a wide range of data lengths and dimensions. Therefore, the framework can be applied to various fields such as neuroscience, ecology, finance, fluid dynamics, weather, and disaster prevention.
| S-EPMC6971065 | biostudies-literature
Project description:Data anonymization is an important building block for ensuring privacy and fosters the reuse of data. However, transforming the data in a way that preserves the privacy of subjects while maintaining a high degree of data quality is challenging and particularly difficult when processing complex datasets that contain a high number of attributes. In this article we present how we extended the open source software ARX to improve its support for high-dimensional, biomedical datasets. For improving ARX's capability to find optimal transformations when processing high-dimensional data, we implement 2 novel search algorithms. The first is a greedy top-down approach and is oriented on a formally implemented bottom-up search. The second is based on a genetic algorithm. We evaluated the algorithms with different datasets, transformation methods, and privacy models. The novel algorithms mostly outperformed the previously implemented bottom-up search. In addition, we extended the GUI to provide a high degree of usability and performance when working with high-dimensional datasets. With our additions we have significantly enhanced ARX's ability to handle high-dimensional data in terms of processing performance as well as usability and thus can further facilitate data sharing.
| S-EPMC8489190 | biostudies-literature
Project description:Large-scale efforts for parallel acquisition of multi-omics profiling continue to generate extensive amounts of multi-dimensional biomedical data. Thus, integrated clustering of multiple types of omics data is essential for developing individual-based treatments and precision medicine. However, while rapid progress has been made, methods for integrated clustering are lacking an intuitive web interface that facilitates the biomedical researchers without sufficient programming skills. Here, we present a web tool, named Integrated Clustering of Multi-dimensional biomedical data (ICM), that provides an interface from which to fuse, cluster and visualize multi-dimensional biomedical data and knowledge. With ICM, users can explore the heterogeneity of a disease or a biological process by identifying subgroups of patients. The results obtained can then be interactively modified by using an intuitive user interface. Researchers can also exchange the results from ICM with collaborators via a web link containing a Project ID number that will directly pull up the analysis results being shared. ICM also support incremental clustering that allows users to add new sample data into the data of a previous study to obtain a clustering result. Currently, the ICM web server is available with no login requirement and at no cost at http://biotech.bmi.ac.cn/icm/.
| S-EPMC4987925 | biostudies-literature
Project description:Multi-modal molecular profiling data in bulk tumors or single cells are accumulating at a fast pace. There is a great need for developing statistical and computational methods to reveal molecular structures in complex data types toward biological discoveries. Here, we introduce Nebula, a novel Bayesian integrative clustering analysis for high dimensional multi-modal molecular data to identify directly interpretable clusters and associated biomarkers in a unified and biologically plausible framework. To facilitate computational efficiency, a variational Bayes approach is developed to approximate the joint posterior distribution to achieve model inference in high-dimensional settings. We describe a pan-cancer data analysis of genomic, epigenomic, and transcriptomic alterations in close to 9000 tumor samples across canonical oncogenic signaling pathways, immune and stemness phenotype, with comparisons to state-of-the-art clustering methods. We demonstrate that Nebula has the unique advantage of revealing patterns on the basis of shared pathway alterations, offering biological and clinical insights beyond tumor type and histology in the pan-cancer analysis setting. We also illustrate the utility of Nebula in single cell data for immune cell decomposition in peripheral blood samples.
| S-EPMC7933297 | biostudies-literature
Project description:The segmentation of time series and genomic data is a common problem in computational biology. With increasingly complex measurement procedures individual data points are often not just numbers or simple vectors in which all components are of the same kind. Analysis methods that capitalize on slopes in a single real-valued data track or that make explicit use of the vectorial nature of the data are not applicable in such scenaria. We develop here a framework for segmentation in arbitrary data domains that only requires a minimal notion of similarity. Using unsupervised clustering of (a sample of) the input yields an approximate segmentation algorithm that is efficient enough for genome-wide applications. As a showcase application we segment a time-series of transcriptome sequencing data from budding yeast, in high temporal resolution over ca. 2.5 cycles of the short-period respiratory oscillation. The algorithm is used with a similarity measure focussing on periodic expression profiles across the metabolic cycle rather than coverage per time point.
| S-EPMC5617875 | biostudies-literature
Project description:BackgroundIn recent years, to investigate challenging bioinformatics problems, the utilization of multiple genomic and proteomic sources has become immensely popular among researchers. One such issue is feature or gene selection and identifying relevant and non-redundant marker genes from high dimensional gene expression data sets. In that context, designing an efficient feature selection algorithm exploiting knowledge from multiple potential biological resources may be an effective way to understand the spectrum of cancer or other diseases with applications in specific epidemiology for a particular population.ResultsIn the current article, we design the feature selection and marker gene detection as a multi-view multi-objective clustering problem. Regarding that, we propose an Unsupervised Multi-View Multi-Objective clustering-based gene selection approach called UMVMO-select. Three important resources of biological data (gene ontology, protein interaction data, protein sequence) along with gene expression values are collectively utilized to design two different views. UMVMO-select aims to reduce gene space without/minimally compromising the sample classification efficiency and determines relevant and non-redundant gene markers from three cancer gene expression benchmark data sets.ConclusionA thorough comparative analysis has been performed with five clustering and nine existing feature selection methods with respect to several internal and external validity metrics. Obtained results reveal the supremacy of the proposed method. Reported results are also validated through a proper biological significance test and heatmap plotting.
| S-EPMC7772934 | biostudies-literature
Project description:Here, a workflow of 4D DIA proteomics by using the predicted multi-dimensional in silico library was established. A deep learning model Deep4D that could high-accurately predict the CCS and RT of both the unmodified and phosphorylated peptides was developed, which is the model based on self-attention14 that completely avoid the use of recurrent neural network (RNN) or LSTM. Deep4D exhibited higher accuracy in the prediction of CCS and RT of peptides than the current models based on deep learning. By using Deep4D and MS/MS prediction tool, an integrated in silico library containing CCS, RT, and fragment ion intensities of millions of peptides for 4D DIA proteomics was established based on the SwissProt H. sapiens database, which enables the deeper peptide and proteome coverage for human samples compared to using sample-specific experimental library. We further demonstrate that the introduction of in silico prediction library can greatly complement the experimental library of directly obtained phosphorylated peptides, resulting in a greater increase in the identification of phosphorylated peptides and phosphorylated proteins.
2023-04-19 | PXD034553 |
Project description:In statistical modelling with Gaussian process regression, it has been shown that combining (few) high-fidelity data with (many) low-fidelity data can enhance prediction accuracy, compared to prediction based on the few high-fidelity data only. Such information fusion techniques for multi-fidelity data commonly approach the high-fidelity model f h(t) as a function of two variables (t, s), and then use f l(t) as the s data. More generally, the high-fidelity model can be written as a function of several variables (t, s 1, s 2….); the low-fidelity model f l and, say, some of its derivatives can then be substituted for these variables. In this paper, we will explore mathematical algorithms for multi-fidelity information fusion that use such an approach towards improving the representation of the high-fidelity function with only a few training data points. Given that f h may not be a simple function-and sometimes not even a function-of f l, we demonstrate that using additional functions of t, such as derivatives or shifts of f l, can drastically improve the approximation of f h through Gaussian processes. We also point out a connection with 'embedology' techniques from topology and dynamical systems. Our illustrative examples range from instructive caricatures to computational biology models, such as Hodgkin-Huxley neural oscillations.
| S-EPMC6501345 | biostudies-literature