Thesis work, 30 credits - PROTACsplitter – Machine Learning for Understanding and Predicting Targeted Protein Degradation

Are you passionate about AI, machine learning, and its impact on drug discovery? Join a cutting-edge joint academic-industrial master’s thesis between Chalmers University and AstraZeneca to revolutionize the design of PROTAC molecules through deep learning. 

About AstraZeneca: 

AstraZeneca is a global, science-led, patient-centered biopharmaceutical company focusing on discovering, developing, and commercializing prescription medicines for some of the world’s most serious diseases. But we’re more than a global leading pharmaceutical company. At AstraZeneca, we're dedicated to being a Great Place to Work and empowering employees to push the boundaries of science and fuel their entrepreneurial spirit.  

Thesis work description:   

In this thesis, you will develop a machine learning model—the PROTACsplitter—to automatically dissect PROTAC molecules into their three core components: 

• POI binder (responsible for binding to the protein of interest), 
• E3 binder (binds to the E3 ubiquitin ligase), and Linker (connects the POI and E3 binders). 

This task, currently performed manually by domain experts, will be automated through deep learning techniques to achieve higher accuracy, scalability, and efficiency. The ability to automatically split PROTACs will be a powerful tool to streamline the design of these molecules and facilitate new therapeutic discoveries. 

What is PROTAC? 

PROTACs (PROteolysis TArgeting Chimeras) are small molecules designed to selectively degrade disease-causing proteins, showing great potential in treating neurodegenerative diseases and cancers. PROTACs bind to two critical proteins: 

• A Protein of Interest (POI) associated with a disease. 
• An E3 ubiquitin ligase, which tags the POI for degradation by the cellular proteasome system. 

By connecting these proteins, PROTACs trigger the degradation of the POI, offering a novel therapeutic approach. However, designing effective PROTACs is incredibly complex, as it requires carefully optimizing the POI binder, E3 ligase binder, and the linker that connects them. This process is not only labor-intensive but also time-consuming and expensive, which limits the rapid development of new PROTAC molecules. 

Research Objectives: 

• PROTAC Decomposition: Train a machine learning model to split PROTAC molecules into their functional components (POI binder, E3 binder, and linker) using publicly available PROTAC data and advanced deep learning architectures. 
• Degradation Prediction: Use this decomposition to enhance the prediction of PROTAC activity, focusing on the DC50 value, a critical measure of a PROTAC's potency. The DC50 value indicates the concentration of a PROTAC required to degrade 50% of the target protein, with lower values reflecting higher efficacy. 
• Weighting Components: Incorporate component-specific weights into degradation prediction models, emphasizing the linker (a key determinant of degradation efficiency), while assigning lower weights to relatively unchanged components like the POI binder and E3 ligase. 
• Insight Generation: Provide insights into the molecular design principles of effective PROTACs, guiding the future development of more potent and selective protein degraders. 

Mentorship and Collaboration: 

This will be a joint MSc thesis project between the AI Laboratory for Molecular Engineering (AIME) at Chalmers University and the R&I Computational Chemistry team at AstraZeneca. You will receive guidance and mentorship from an interdisciplinary team of experts, including: 

• Assistant Prof. Rocío Mercado Oropeza (AIME, Chalmers), 
• Stefano Ribes, PhD student in AIME, 
• Dr. Eva Nittinger and Dr. Christian Tyrchan from AstraZeneca. 

You will have access to AstraZeneca’s supercomputing resources as well as NAISS computing infrastructure, allowing you to run complex simulations and deep learning models efficiently. You will be invited to seminars, events, and group activities hosted by both Chalmers and AstraZeneca, giving you a valuable opportunity to network and learn from leading experts in molecular engineering, AI, and drug discovery. 

Requirements: 

We are looking for highly motivated individuals with: 

• A background in data science, machine learning, or informatics (optional: biology, biophysics, chemistry, or molecular modeling). 
• Proficiency in Python and at least 3 libraries (e.g., numpy, matplotlib, rdkit, sklearn, pytorch, tensorflow). 
• A team-oriented, positive, and proactive mindset with strong problem-solving skills. 
• Interest in drug discovery and chemistry (prior knowledge is not required, but curiosity and enthusiasm are encouraged!). 

Location & Resources: 

• Main Seat: AstraZeneca, with occasional work from Chalmers. 
• Access to AZ and NAISS supercomputing resources. 

So, what’s next?  

Apply today and take the chance to be part of making a difference, making connections, and gaining the tools and experience to open doors and fulfil your potential. We can´t wait to hear from you!  

We welcome your application as soon as possible, but ahead of the scheduled closing date 31st of October 2024. In the event that we identify suitable candidates ahead of the scheduled closing date, we reserve the right to withdraw the vacancy earlier than published.  

AstraZeneca embraces diversity and equality of opportunity. We are committed to building an inclusive and diverse team representing all backgrounds, with as wide a range of perspectives as possible, and harnessing industry-leading skills. We believe that the more inclusive we are, the better our work will be. We welcome and consider applications to join our team from all qualified candidates, regardless of their characteristics. We comply with all applicable laws and regulations on non-discrimination in employment (and recruitment), as well as work authorisation and employment eligibility verification requirements.