Postdoctoral Fellow – Applying novel computer vision and AI to multimodal digital pathology to [...] in Cambridge

Do you have expertise in, and passion for applying computer vision and AI in medical imaging? Would you like to apply your knowledge to impact drug discovery projects in a company that follows the science and turns ideas into life-changing medicines? Then join the Pathology department at AstraZeneca and unlock the power of what science can do!

In this Postdoctoral Fellow position, you’ll research, develop and apply computational pathology and AI tools for the prediction and identification of patients at high risk of Chronic Kidney Disease (CKD) from multimodal digital pathology datasets. This project is supported by the Clinical Pharmacology & Safety Sciences (CPSS) group that works across all of AstraZeneca’s therapy areas from early-stage drug discovery to late-stage clinical development.

The Pathology department is driving the use of innovative computational pathology approaches to transform drug discovery and development to deliver better medicines to patients. This project will conduct groundbreaking research in the development of computational pathology approaches to identify high-risk CKD patients who would benefit from early and new drug treatments.

Our Postdoc will have access to unique and extensive multimodal datasets from NURTuRE (the National Unified Renal Translational Research Enterprise), the first UK national Kidney biobank led by Kidney Research UK. NURTuRE contains multimodal imaging datasets including digital pathology, whole slide multiplex immunofluorescence, spatial transcriptomics, and clinical data from 1000 patients.

You will collaborate with experienced AZ interdisciplinary scientists with diverse backgrounds and an exceptional academic mentor specifically aligned to the project, to develop computational pathology approaches to uncover new patient stratification biomarkers from spatial data and relate these biomarkers to disease outcomes, using them to identify new therapeutic targets.

Supported by Arthur Lewis (Director) and Magnus Soderburg (Senior Director, Pathologist) at AstraZeneca, you'll also receive academic mentorship and guidance from Fabian Spill, Professor of Applied Mathematics at the University of Birmingham. You will work in an industry-leading group with a strong publication track record and be supported by a leading academic supervisor.

Our Postdoctoral Fellow will conduct ground-breaking research using computational pathology, computer vision, and machine learning methods for the identification of spatial imaging biomarkers of patient risk stratification. You will develop computational tools to integrate features from multimodal datasets including digital pathology, whole slide multiplex immunofluorescence, spatial transcriptomics, and clinical data. This will involve the application of innovative machine learning techniques including foundation models, transfer learning, and GenAI to characterize the disease, uncover potential new imaging biomarkers of disease progression, and identify novel tissue biomarker patterns that can identify patient phenotypes that allow for much-needed improved patient stratification in clinical trials in renal disease.

Research, design, and implement innovative computational pathology tools to characterize disease, uncover potential new biomarkers of disease progression, and identify novel tissue biomarkers that can identify patient phenotypes to improve patient stratification in clinical trials in renal disease. Lead and drive the project under the supervision of a cross-functional AstraZeneca team and in collaboration with the academic expert. Plan, write, publish, and present high-quality scientific papers.

• Experience using computer vision, machine learning, mathematics, computer science or closely related subject areas.
• Experience in applying computer vision and AI to medical imaging or similar non-medical imaging fields.
• Experience using developing, validating and using computer vision based machine learning & deep learning & image analysis processes to address quantification questions within tissue based images.
• Experience in developing and deploying programming tools.
• Experience in analysing real world data.
• The ability to work in interdisciplinary teams, in a highly collaborative manner.
• The capability to communicate your work to scientists from other teams.
• PhD degree or equivalent experience in computational biology / chemistry, or cheminformatics.
• Experience with structure-based molecular modelling.
• Good knowledge of machine learning methods and data science concepts.

• Proficiency in programming (preferably Python).
• Validated knowledge of one or more of the following areas: Immuno-informatics, Computational biology, Cheminformatics or Computational chemistry.
• Excellent written and oral communication skills.
• Strong planning, organisational and time management skills.
• Ability to work optimally in a multi-disciplinary research environment.

At AstraZeneca, we are committed to making a difference. We have built our business around our passion for science. Now we are fusing data and technology with the latest scientific innovations to achieve the next wave of breakthroughs. Our combination of curiosity and courage drives us, passionate about the possibility of doing things that have never been done before. We work seamlessly as one team, bringing to bear our diverse global knowledge to build the greatest impact on disease. For those who want to continuously learn and try new things, this is the place to build a significant career as we push the boundaries of science to deliver life-changing medicines.

Our mission is to build an inclusive and equitable environment. We want people to feel they belong at AstraZeneca and Alexion, starting with our recruitment process. We welcome and consider applications from all qualified candidates, regardless of characteristics. We offer reasonable adjustments/accommodations to help all candidates to perform at their best. If you have a need for any adjustments/accommodations, please complete the section in the application form.