Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Multifidelity simulations for high-throughput generative protein engineering pipelines


   School of Biological Sciences

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr G Stracquadanio, Prof Julien Michel  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

The goal of this PhD project is to develop and combine data-driven and physics-driven computational methods to enable the rapid and accurate optimisation of protein sequences for bioengineering applications.

The research will combine expertise in deep learning and atomistic simulations established in the Stracquadanio (www.stracquadaniolab.org) and Michel (www.julienmichel.net) groups to create optimised software pipelines. These pipelines will be used for optimising the function of a protein from sequence, structure and dynamics datasets [1-3].

Throughout the project the student will gain expertise in state-of-the art deep learning methodologies such as large language models and geometric deep learning for de novo generative design of protein sequences, and in molecular dynamics simulations methods augmented with machine learning potentials. The seamless integration of these methodologies will deliver a novel computational platform broadly applicable to a diverse range of protein engineering tasks. Proof of concept of the computational methodologies will be initially demonstrated via high throughput experiments on model systems for which standard operating protocols have been established in the Stracquadanio group. Later, the project will focus on enzymes of pharmaceutical interests, where we will design mutations to optimise a range of parameters (function, thermal stability, immunogenicity) relevant to biologics development.

Applicants should hold a degree in a relevant subject (typically Chemistry, Biochemistry, Physics, Informatics or Mathematics). Previous experience in Python programming is strongly desirable. 

The student will receive training in geometric deep learning, protein language models as well as molecular simulation and structural bioinformatics methods to analyse proteomic datasets. The student will also learn how to write reproducible scientific pipelines and research software. We expect the successful candidate to build a competitive profile in machine learning and protein engineering and drug design, which ultimately will support a career in academia or industry.

www.stracquadaniolab.org

www.julienmichel.net

The School of Biological Sciences is committed to Equality & Diversity: https://www.ed.ac.uk/biology/equality-and-diversity

Biological Sciences (4) Chemistry (6) Computer Science (8) Mathematics (25)

Funding Notes

This 4 year PhD project is funded by EPSRC Doctoral Training Partnership.
This opportunity is open to UK and International students and provides funding to cover stipend at UKRI standard rate (£18,622 for 2023-24) and UK level tuition fees. The fee difference will be covered by the University of Edinburgh for successful international applicants, however any Visa or Health Insurance costs are not covered.
UKRI eligibility guidance:
Terms and Conditions: https://www.ukri.org/wp-content/uploads/2023/11/UKRI-16112023-UKRI_Training-Grant-Terms-And-Conditions-Guidance-November-2023.pdf
International/EU: https://www.ukri.org/wp-content/uploads/2023/03/ESRC-020323-InternationalEligibilityImplementationGuidance-TrainingGrantHolders.pdf
Closing date for applications: Friday 15th March 2024

References

1. "Designing human Sphingosine-1-phosphate lyases using a temporal Dirichlet variational autoencoder." Lobzaev, E. ; Herrera, M. A. ; Campopiano D. J. ; Stracquadanio, G. bioRxiv https://doi.org/10.1101/2022.02.14.480330, 2022.
2. ‘’Dynamic design: manipulation of millisecond timescale motions on the energy landscape of Cyclophilin A’’ Juárez-Jiménez, J.; Gupta, A. A. ; Karunanithy, G.; Mey, A. S. J. S.; Georgiou, C.; Ioannidis, H.; De Simone, A.; Barlow, P. N. ; Hulme, A. N.; Walkinshaw, M. D. ; Baldwin, A. J. ; Michel, J. Chem. Sci. , 11, 2670-2680, 2020
3. ‘’Deconstructing Allostery: Computational Assessment of the Binding Determinants of Allosteric PTP1B Modulators’’ Hardie, A. ; Cossins, B. P. ; Lovera, S. ; Michel, J. Commun. Chem. 6, 125, 2023

How good is research at University of Edinburgh in Biological Sciences?


Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Where will I study?

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.