We are looking for a researcher who is interested to develop and apply tools for analyzing spatial-omics data, particularly from multiplexed Fluorescence In-Situ Hybridization (FISH) assays.
Multiplexed FISH is an imaging based approach that measures the expression of 100s to 1000s genes in intact biological samples, at the resolution of individual cells. However, the spatial-omics field is relatively new and lacks established computational analysis tools which leverage the spatial context of the gene-expression data to reveal new biological insight, such as how cells interact with each other and the processes by which organs and tissues develop. We will work to develop new algorithms and analysis techniques specific to this type of data, which are relevant to the questions our biology/clinician collaborators seek to answer. We have ready access to many interesting datasets already being collected by the lab and by collaborators.
The Research Fellow will:
• Develop new algorithms to analyse multiplexed FISH data from tissue samples, organoids and cells lines. Adapt and apply existing methods in the spatial and single-cell analysis literature. (Examples include detecting spatial patterns of gene-expression, assigning cell types based on spatial context, inferring cell-cell interactions etc.)
• Incorporate deep-learning techniques, where relevant, in the analysis pipeline
• Work closely with biology/clinical collaborators to understand their needs and develop the most relevant tools and approaches
• PhD or Masters in Computer Science/Statistics/Electrical Engineering/Biomedical Engineering/Applied Physics or related fields
• Strong proficiency in Python (optional: R/Matlab)
• Experience in machine learning and/or computer vision
• Experience developing and deploying deep learning solutions preferred
• Excellent written and verbal communication skills in English
• Able to work both independently and as a part of the team
On-the-job training will be provided by other members of the team.