GEESE: Metabolically driven latent space learning for gene expression data

Abstract

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.Here 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. Availability: Source code of GEESE is available at https://bitbucket.org/mbarsacchi/geese/.

Machine and deep learning meet genome-scale metabolic modeling

“…Moreover, metabolism and GSMMs can be used as a basis to understand underlying genomic variation. The Gene Expression Latent Space Encoder (GEESE) is a recently proposed approach [92] in which transcriptomic information is fed into a deep generative model (specifically, a variational autoencoder) combined with a GSMM. Initially, gene expression data is provided as an input to the autoencoder, returning reconstructed gene expression vectors that are then used to train an FBA approximator.…”

Low-dimensional representations of genome-scale metabolism

“…Several strategies have been developed to characterize the geometry of the flux cone, many of which involve random sampling or computation of geometric properties such as extreme pathways or elementary flux modes 1 . Recent years have witnessed a growing interest in the use of machine learning in tandem with GEMs 11,16 , particularly for improving phenotype predictions 20,21 , enrich the quality of metabolic models 22,23 , or interpreting gene expression data 24 .…”