1.     Modelling binding specificities of RBPs using Artificial Neural Networks

Supervisor:  Panagiotis Alexiou, Ph.D.                                  

Annotation:

RNA Binding Proteins are a class of proteins that function via direct binding to coding and non-coding RNA molecules. Artificial Neural Networks, and especially Convolutional and Recurrent neural networks are machine learning methods increasingly used to classify genomic sequences with promising results. This project involves the training of such Artificial Neural Networks on experimental data from RNA Binding Protein binding sites, and producing tools that can be used to classify nucleotide sequences as potentially bound by specific RNA Binding Proteins. The project will involve development and training of machine learning models, production of online tools, and publication of results in conferences and scientific journals.

Requirements on candidates:

The ideal candidate will have:

  • A masters degree in Bioinformatics, Computational Biology, Biostatistics, Computer Science, or similar fields.
  • Working and demonstrable knowledge of python programming language. Knowledge of other programming languages is a plus. Understanding of clean code principles and software development principles also a strong point. Knowledge of Machine Learning libraries (e.g. Tensorflow, fast-ai) a very strong point. Candidates will be asked to demonstrate such knowledge in practice during interviews.
  • A working understanding of basic biological processes. The ability to read and comprehend bioinformatics journal papers.
  • The drive to work with a multidisciplinary team, in a fast-paced research field. Ability to quickly grasp new concepts from various disciplines (biology, statistics, informatics etc) and creatively apply them.
  • Good communication skills, ability to write concise and clean scientific texts, and code.

Literature:

  1. Alipanahi, B., Delong, A., Weirauch, M. et al. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat Biotechnol 33, 831–838 (2015). https://doi.org/10.1038/nbt.3300
  2. Pan, X., Fang, Y., Li, X. et al. RBPsuite: RNA-protein binding sites prediction suite based on deep learning. BMC Genomics 21, 884 (2020). https://doi.org/10.1186/s12864-020-07291-6

 

Keywords: Bioinformatics, RBP, Machine Learning, Deep Learning

Head of Core Facility

Panagiotis Alexiou, Ph.D.
Panagiotis Alexiou, Ph.D.
Head of Core Facility, Research Group Leader Junior
Personal Profile