Supervised learning of gene-regulatory networks based on graph distance profiles of transcriptomics data

Abstract

Characterisation of gene-regulatory network (GRN) interactions provides a stepping stone to understanding how genes affect cellular phenotypes. Yet, despite advances in profiling technologies, GRN reconstruction from gene expression data remains a pressing problem in systems biology. Here, we devise a supervised learning approach, GRADIS, which utilises support vector machine to reconstruct GRNs based on distance profiles obtained from a graph representation of transcriptomics data. By employing the data from Escherichia coli and Saccharomyces cerevisiae as well as synthetic networks from the DREAM4 and five network inference challenges, we demonstrate that our GRADIS approach outperforms the state-of-the-art supervised and unsupervided approaches. This holds when predictions about target genes for individual transcription factors as well as for the entire network are considered. We employ experimentally verified GRNs from E. coli and S. cerevisiae to validate the predictions and obtain further insights in the performance of the proposed approach. Our GRADIS approach offers the possibility for usage of other network-based representations of large-scale data, and can be readily extended to help the characterisation of other cellular networks, including protein-protein and protein-metabolite interactions.

Combination of network and molecule structure accurately predicts competitive inhibitory interactions

“…While instances that represent CI-reaction interactions are available from the gold standard described above, specifying metabolite-reaction pairs that are not involved in competitive inhibitory interactions is not straightforward due to the lack of information about absence of competitive inhibitions between a metabolite and a reaction. To overcome this issue, CIRI applies the strategy proposed by [16] to identify such instances.…”

“…Here we devise a supervised machine learning approach, called CIRI that determines whether or not a metabolite is involved in a c ompetitive i nhibitory r egulatory i nteraction with an enzyme, provided information about the reactions that the enzyme can catalyze. To this end, we employ a machine learning procedure to identify metabolite-reaction, and thereby metabolite-enzyme, pairs that are not involved in competitive inhibitory interactions [16] . We validate the performance of CIRI on several unseen data sets and databases of metabolite-protein interactions not used in the training [10] , [17] .…”

TAPIOCA: Topological Attention and Predictive Inference of Chromatin Arrangement Using Epigenetic Features

“…These approaches have spanned a variety of applications including: Assay denoising (Hong et al 2020) (Dimmick, Lee, and Frey 2020) (Highsmith and Cheng 2020). 3D modeling (Oluwadare, Highsmith, and Cheng 2019), and regulatory network prediction (Razaghi-Moghadam and Nikoloski 2020). In this paper we outline the application of a recently developed machine learning algorithm, the Transformer, to the task of topologically associated domain (TAD) identification using epigenetic features as a proxy for Hi-C data.…”

Improved Fuzzy Cognitive Maps for Gene Regulatory Networks Inference Based on Time Series Data

“…Supervised learning-based approaches such as SIRENE [6] and GENIES [9] use well-known regulations in genomic data to infer gene regulation networks. In [10], a supervised learning method based on a support vector machine is proposed to infer gene regulation networks. In this method, various features are extracted based on the distance graph profile of genes.…”