Are you looking for a PhD position where you develop state-of-the-art machine learning methods for the life sciences (geometric deep learning, transformer-based approaches, ...) with a focus on protein-ligand interaction dynamics in collaboration with wet-lab researchers? If so, this fully funded PhD position might be an excellent match for you.
The interactions and dynamics of proteins and ligands are essential to the biological function of all organisms. For example, haemoglobin must change conformation to bind oxygen and fulfil its biological function. While machine learning approaches that predict the static structure of proteins have become invaluable tools for biologists and medicinal chemists, machine learning-based prediction of protein dynamics is still in its infancy. An additional challenge is the modelling and prediction of the dynamic interaction between proteins and small-molecule ligands, such as hormones, neurotransmitters, or therapeutic drugs. The computational representation of such dynamic interactions between molecules is one of the research lines at the ProbstLab. Beyond introducing new machine learning methodologies and computational representations of molecules, we collaborate with wet-lab researchers to apply the developed methods to problems, including the search for new and potent therapeutics and the development of more sustainable processes to synthesise chemical compounds.
As a PhD student, you will be embedded in a diverse group of international scientists. Your responsibilities and opportunities will encompass:
- developing new machine learning methodologies that have direct application in the life sciences, focusing on protein-ligand interaction dynamics;
- following, evaluating, and synthesising state-of-the-art machine learning, chemistry, and biology research, working at the intersection of multiple fields;
- connecting and collaborating with other national and international researchers in the life sciences and computer science;
- writing and presenting/publishing research papers at/in internationally renowned conferences/journals. As a group, we aim to publish our work in natural science journals (applications) and at computer science conferences (methods).
You are a computer scientist, a computational biologist or a computational chemist with proven expertise in implementing machine learning methods in Python. You write or have written your master's thesis on a topic relevant to this project. Proven experience in molecular dynamics simulations of proteins or protein-ligand complexes is an advantage.
You possess:
- a successfully completed MSc degree in computer science or a strongly related field (e.g. computational biology or computational chemistry).
- proven experience in Python programming or high proficiency in another language such as C/++ or Rust. It is an advantage if you can provide a link to a code repository of a project where you are the main contributor.
- experience in implementing machine learning methodologies, specifically neural network-based methods, including a mathematical understanding of the methods.
- an interest in applying state-of-the-art machine learning techniques to various fields in the life sciences.
- a collaborative attitude valuing the importance of interdisciplinarity and open science.
- the drive to present and share your work at international conferences and to network with peers at these conferences.
- excellent English writing skills and experience in scientific writing.
For this position, your command of the English language is expected to be at C1 level. In some cases, it is necessary to submit an internationally recognised Certificate of Proficiency in the English Language.
Please submit your application through our website: www.wur.nl/en/vacancy/phd-student-position-in-ai-for-life-sciences-with-a-focus-on-protein-ligand-interaction-dynamics.htm