- 36 hours a week
- 4 years
- Date of publication: 30 July 2019
- Deadline: 1 October 2019
- Scale 10A: max € 43305 gross per year at full employment (incl. vacation bonus and end of year payments)
Job descriptionWe are looking for a Ph.D. candidate who is enthusiastic and ambitious about interdisciplinary research on the interface of structural biology, machine learning, and immunology. The goal of this Ph.D. project is to investigate and drastically improve the identification of personalized cancer vaccine candidates using AI-boosted 3D modeling techniques.
Cancer immunotherapy is making clinical breakthroughs in eliminating tumors. The patient’s immune defenses are unleashed against tumor cells, by their T-cell receptor (TCR) specifically binding to tumor-specific mutations (neoantigens) that are presented by MHC proteins on the surface of the tumor, forming the TCR:peptide:MHC (TCR:pMHC) complex. A vital step of a successful personalized T-cell-mediated cancer immunotherapy is to efficiently identify which cancer-specific peptides of a patient can be presented by his/her MHC molecules on the tumor cell surface (such peptides are referred to as MHC epitopes). Currently, machine learning based methods are dominating MHC epitope predictions and overwhelmingly outperform 3D modeling methods. However, the enormous potential of 3D modeling cannot be ignored, as 1) it can reflect the minor changes of mutations in 3D space and energy landscape, 2) it significantly reduces the necessity of massive amount of experimental binding affinity data, thus could potentially applied to many other MHC alleles with little binding affinity data, and 3) it offers 3D models of MHC-peptide and TCR:pMHC, which can be used to guide experimental work, such as TCR engineering.
The Ph.D. candidate will:
- work together with the advisor on the investigation of bridging the data-driven machine learning methods and the physics-based 3D modeling on MHC peptide predictions.
- contribute to DeepRank, our deep learning framework for 3D protein complex images.
- apply and modify DeepRank and design other machine learning methods for the prediction of MHC epitopes.
Tasks and responsibilities
- Perform research on the proposed project.
- Complete a Ph.D. dissertation consisting of several peer-reviewed publications.
- Follow courses and workshops for relevant scientific topics and generic scientific skills.
- Attend and present research on internal and external conferences.
- Assist in teaching.
- Supervise Bachelor/Master students (optional).
ProfileThe success of the project requires expertise from two domains: 1) computational structural biology and 2) machine learning especially deep learning.
- The candidate should have a Master of Science degree in computational structural biology or related fields.
- Knowledge of programming skills (Python, R, Perl, or other languages).
- Linux experience and shell scripting.
Expertise preferred but not required:
- 3D modeling of antibodies.
- Machine learning, deep learning.
- HPC (High-performance computing), PBS job scheduler or Slurm job scheduler.
You work in a structured way, document your code and results and use version control systems (like Git). You are flexible and communicative, know how to explain your research to peers within and outside your field, and enjoy working in a multidisciplinary team.
Note: Candidates who have a strong deep learning background and has a Master degree in Computer Science can also be considered. Such candidates must have a strong interest in molecular biology and biomedical research.
OrganizationRadboud University is one of the top universities in the world (World University Rankings 2019: 123). The Centre for Biomolecular and Molecular Informatics (CMBI) embeds in the Radboud University Medical Center (Radboudumc), which is one of the key medical research centers in the Netherlands. CMBI is well known for the development of new computational approaches for the study of the genetic variation and commonly used tools and web services for protein function and structure prediction.
CMBI has an excellent history of computational structural biology and is the birthplace of well-known What-if software suite. With the arrival of the new department head, Prof. Peter-Bram ‘t Hoen, the department is focusing on joint research projects with the Human Genetics, cancer development, and immune defense, and other departments in Radboudumc into personalized diagnostics and personalized medicine approaches based on the analysis of molecular-omics profiles. The department puts emphasis on the reusability of data, software, and services following the FAIR principles.
HPC (high-performance computing) and GPU Computing facility:
- HPC at the CMBI department: An expandable cluster, based on SGE (sun grid engine), with 216 CPU cores, 3.4 TByte RAM and 100 TByte storage is available to end-users.
- A GPU island with 100 GPU nodes: hosted by RTC Deep Learning (Ajay Patel)/ Radiology and Nuclear Medicine department/section Medical Imaging (head: Prof. Bram van Ginneken).
- Digital Research environment; scalable cloud computing and the storage solution deployed on the Microsoft Azure cloud.
Radboudumc strives to be a leading developer of sustainable, innovative and affordable healthcare to improve the health and wellbeing of people and society in the Netherlands and beyond. This is the core of our mission: To have a significant impact on healthcare. To get a better picture of what this entails, check out our strategy.
Read more about what it means to work at Radboudumc and how you can do your part.
Employment conditionsThe Ph.D. candidate will start from salary scale 10A.0 with an increase each year (scale 10A has a maximum of 3 increasing steps).
Read more about the Radboudumc employment conditions and what our International Office can do for you when moving to the Netherlands.
Comments and contact informationIn your application letter, please clearly indicate how your expertise and experience fit with the proposed project. The application procedure will consist of a round of interviews and a presentation of one of your research projects in a second stage.
All additional information about the vacancy can be obtained from Dr. Li Xue, assistant professor via: Li.Xue@radboudumc.nl. Use the Apply button to submit your application.
Please apply before October 1st, 2019.
Recruitment agencies are asked not to respond to this job posting.
apply to job