Deep Learning for Genomic and Transcriptomic Pattern Identification

Project description: Research in my newly formed laboratory revolves around the utilization of novel Deep Neural Network approaches to identify patterns in genomic and transcriptomic regions harboring functional elements. Specifically, we focus on the characterisation of three categories of functional elements: short genomic functional elements (e.g. small RNA gene loci), transcriptomic functional elements (e.g. RNA Binding Protein binding sites), and small RNA driven transcriptomic functional elements (e.g. microRNA target sites). The identification of such functional elements using in silico methods has been a field of intensive research, but the current low precision of methods when scanning over large regions of the genome/transcriptome has confined practical implementation to a small minority of well studied and easy to identify elements (e.g. microRNA target sites), and heavily biased by the prior theoretical knowledge. My research instead focuses on less biased methods of modelling these complex biological processes from raw data (genomic or high-throughput sequencing) using Deep Learning architecture to achieve pattern identification precision levels at unprecedented levels. For genomic functional elements we have developed a novel training approach involving iterative background selection that has boosted the accuracy of small RNA identification orders of magnitude beyond the state of the art. For transcriptomic functional elements, we will utilize characteristics of binding to train a Deep Learning model on CLIP-Seq data from hundreds of sequenced RBPs. We are exploring the interpretation of the trained model aspects in order to predict functionality of novel enigmatic RBPs based on their binding characteristics. Finally, for small RNA driven functional elements we utilize Deep Learning models to identify unbiased binding rules from chimeric CLIP-Seq reads beyond the theoretical biases existing in current models.

Molecular basis of aberrant splicing of CFTR exon 9

Project description:  Alternative splicing of pre-mRNAs is tightly regulated and any imbalance can change the outcome of gene expression which often leads to disease. Despite the importance of alternative splicing regulation our knowledge at the molecular level is still in its infancy hampering development of effective therapies. We plan to study the regulatory RNA-protein interaction network leading to skipping of CFTR exon 9 associated with severe forms of cystic fibrosis. Structure determination of regulatory complexes by NMR spectroscopy in combination with biochemical and functional in vivo studies will be used to deepen our molecular understanding of the regulatory networks governing the proper assembly of mRNAs. With this, we want to lay a rational, structure-function-based foundation for novel approaches to cure diseases.

Structural studies of human and animal pathogens from the order Picornavirales

Project description: Numerous viruses from the order Picornavirales cause disease in humans (picornaviruses) or are economically important pathogens of honeybee (iflaviruses and dicistroviruses). We propose to study molecular structures of representative viruses from these families and their life cycle intermediates in order to provide mechanistic description of genome replication and virion assembly. In addition, our results will lay the foundations for structure-based development of antiviral drugs. We will use X-ray crystallography to determine virion structures of representative picornaviruses from parechovirus and kobuvirus genera and Human Rhinovirus-C species. We will use cryo-electron microscopy to study picornavirus replication complexes in order to explain the mechanism of copy-choice recombination of picornavirus RNA genomes that leads to creation of new picornavirus species. We will determine whether picornavirus virions assemble from capsid protein protomers around the condensed genome or if the genome is packaged into a pre-formed empty capsid.