Groenning, A. G. B. | bioRxiv Science

bioRxiv2020

Comparative single-cell trajectory network enrichment identifies pseudo-temporal systems biology patterns in hematopoiesis and CD8 T-cell development

Single cell transcriptomics (scRNA-seq) technologies allow for investigating cellular processes on an unprecedented resolution. While software packages for scRNA-seq raw data analysis exist, no method for the extraction of systems biology signatures that drive different pseudo-time trajectories exists. Hence, pseudo-temporal molecular sub-network expression profiles remain undetermined, thus, hampering our understanding of the molecular control of cellular development on a single cell resolution. We have developed Scellnetor, the first network-constraint time-series clustering algorithm implemented as interactive webtool to identify modules of genes connected in a molecular interaction network that show differentiating temporal expression patterns. Scellnetor allows selecting two differentiation courses or two developmental trajectories for comparison on a systems biology level. Scellnetor identifies mechanisms driving hematopoiesis in mouse and mechanistically interpretable subnetworks driving dysfunctional CD8 T-cell development in chronic infections. Scellnetor is the first method to allow for single cell trajectory network enrichment for systems level hypotheses generation, thus lifting scRNA-seq data analysis to a systems biology level. It is available as an interactive online tool at https://exbio.wzw.tum.de/scellnetor/.

bioinformatics↗

bioRxiv2019

DeepCLIP: Predicting the effect of mutations on protein-RNA binding with Deep Learning

Nucleotide variants can cause functional changes by altering protein-RNA binding in various ways that are not easy to predict. This can affect processes such as splicing, nuclear shuttling, and stability of the transcript. Therefore, correct modelling of protein-RNA binding is critical when predicting the effects of sequence variations. Many RNA-binding proteins recognize a diverse set of motifs and binding is typically also dependent on the genomic context, making this task particularly challenging. Here, we present DeepCLIP, the first method for context-aware modeling and predicting protein binding to nucleic acids using exclusively sequence data as input. We show that DeepCLIP outperforms existing methods for modelling RNA-protein binding. Importantly, we demonstrate that DeepCLIP is able to reliably predict the functional effects of contextually dependent nucleotide variants in independent wet lab experiments. Furthermore, we show how DeepCLIP binding profiles can be used in the design of therapeutically relevant antisense oligonucleotides, and to uncover possible position-dependent regulation in a tissue-specific manner. DeepCLIP can be freely used at http://deepclip.compbio.sdu.dk.\n\nHighlightsO_LIWe have designed DeepCLIP as a simple neural network that requires only CLIP binding sites as input. The architecture and parameter settings of DeepCLIP makes it an efficient classifier and robust to train, making high performing models easy to train and recreate.\nC_LIO_LIUsing an extensive benchmark dataset, we demonstrate that DeepCLIP outperforms existing tools in classification. Furthermore, DeepCLIP provides direct information about the neural networks decision process through visualization of binding motifs and a binding profile that directly indicates sequence elements contributing to the classification.\nC_LIO_LITo show that DeepCLIP models generalize to different datasets we have demonstrated that predictions correlate with in vivo and in vitro experiments using quantitative binding assays and minigenes.\nC_LIO_LIIdentifying the binding sites for regulatory RNA-binding proteins is fundamental for efficient design of (therapeutic) antisense oligonucleotides. Employing a reported disease associated mutation, we demonstrate that DeepCLIP can be used for design of therapeutic antisense oligonucleotides that block regions important for binding of regulatory proteins and correct aberrant splicing.\nC_LIO_LIUsing DeepCLIP binding profiles, we uncovered a possible position-dependent mechanism behind the reported tissue-specificity of a group of TDP-43 repressed pseudoexons.\nC_LIO_LIWe have made DeepCLIP available as an online tool for training and application of proteinRNA binding deep learning models and prediction of the potential effects of clinically detected sequence variations (http://deepclip.compbio.sdu.dk/). We also provide DeepCLIP as a configurable stand-alone program (http://www.github.com/deepclip).\nC_LI

bioinformatics↗