Biology subjects

Andres-Terre, H.

Publications and source records attributed to Andres-Terre, H..

4 recordsLinked to original sources

bioRxiv2020

CellVGAE: An unsupervised scRNA-seq analysis workflow with graph attention networks

AO_SCPLOWBSTRACTC_SCPLOWCurrently, single-cell RNA sequencing (scRNA-seq) allows high-resolution views of individual cells, for libraries of up to (tens of) thousands of samples. In this study, we introduce the use of graph neural networks (GNN) in the unsupervised study of scRNA-seq data, namely for dimensionality reduction and clustering. Motivated by the success of non-neural graph-based techniques in bioinformatics, as well as the now common feedforward neural networks being applied to scRNA-seq measurements, we develop an architecture based on a variational graph autoencoder with graph attention layers that works directly on the connectivity of cells. With the help of three case studies, we show that our model, named CellVGAE, can be effectively used for exploratory analysis, even on challenging datasets, by extracting meaningful features from the data and providing the means to visualise and interpret different aspects of the model. Furthermore, we evaluate the dimensionality reduction and clustering performance on 9 well-annotated datasets, where we compare with leading neural and non-neural techniques. CellVGAE outperforms competing methods in all 9 scenarios. Finally, we show that CellVGAE is more interpretable than existing architectures by analysing the graph attention coefficients. The software and code to generate all the figures are available at https://github.com/davidbuterez/CellVGAE.

bioinformatics↗

bioRxiv2019

Unsupervised generative and graph representation learning for modelling cell differentiation

Using machine learning techniques to build representations from biomedical data can help us understand the latent biological mechanism of action and lead to important discoveries. Recent developments in single-cell RNA-sequencing protocols have allowed measuring gene expression for individual cells in a population, thus opening up the possibility of finding answers to biomedical questions about cell differentiation. In this paper, we explore unsupervised generative neural methods, based on the variational autoencoder, that can model cell differentiation by building meaningful representations from the high dimensional and complex gene expression data. We use disentanglement methods based on information theory to improve the data representation and achieve better separation of the biological factors of variation in the gene expression data. In addition, we use a graph autoencoder consisting of graph convolutional layers to predict relationships between single-cells. Based on these models, we develop a computational framework that consists of methods for identifying the cell types in the dataset, finding driver genes for the differentiation process and obtaining a better understanding of relationships between cells. We illustrate our methods on datasets from multiple species and also from different sequencing technologies.

bioinformatics↗

bioRxiv2019

Variational Autoencoders for Cancer Data Integration: Design Principles and Computational Practice

International initiatives such as the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) are collecting multiple data sets at different genome-scales with the aim to identify novel cancer bio-markers and predict patient survival. To analyse such data, several machine learning, bioinformatics and statistical methods have been applied, among them neural networks such as autoencoders. Although these models provide a good statistical learning framework to analyse multi-omic and/or clinical data, there is a distinct lack of work on how to integrate diverse patient data and identify the optimal design best suited to the available data.\n\nIn this paper, we investigate several autoencoder architectures that integrate a variety of cancer patient data types (e.g., multi-omics and clinical data). We perform extensive analyses of these approaches and provide a clear methodological and computational framework for designing systems that enable clinicians to investigate cancer traits and translate the results into clinical applications. We demonstrate how these networks can be designed, built and, in particular, applied to tasks of integrative analyses of heterogeneous breast cancer data. The results show that these approaches yield relevant data representations that, in turn, lead to accurate and stable diagnosis.

bioinformatics↗

bioRxiv2018

GEESE: Metabolically driven latent space learning for gene expression data

Gene expression microarrays provide a characterisation of the transcriptional activity of a particular biological sample. Their high dimensionality hampers the process of pattern recognition and extraction. Several approaches have been proposed for gleaning information about the hidden structure of the data. Among these approaches, deep generative models provide a powerful way for approximating the manifold on which the data reside.\n\nHere we develop GEESE, a deep learning based framework that provides novel insight into the manifold learning for gene expression data, employing a metabolic model to constrain the learned representation. We evaluated the proposed framework, showing its ability to capture biologically relevant features, and encoding that features in a much simpler latent space. We showed how using a metabolic model to drive the autoencoder learning process helps in achieving better generalisation to unseen data. GEESE provides a novel perspective on the problem of unsupervised learning for biological data.\n\nAvailabilitySource code of GEESE is available at https://bitbucket.org/mbarsacchi/geese/.

systems biology↗