Postdoctoral Fellowship, Pathology

The Role

As postdoctoral fellow in our Pathology group, you will work with a highly collaborative team of scientists in the translational research and data science teams to build an end-to-end phenotypic discovery pipeline for multiplex immunofluorescence (mIF) panels. You will integrate the outcome of the pipeline with other data at Genmab including imaging features, transcriptomics, genomics, and circulating biomarkers to derive new insights within the tumor microenvironment and improve understand of the mechanism of action of immuno-oncology therapies and patient response.

Responsibilities

• Implementation of robust image analysis algorithms to perform cell segmentation, cell phenotyping and neighborhood analysis to interrogate the tumor microenvironment across different mIF panels for different programs.

   

• Application of machine learning methods to identify relevant phenotypic signatures and spatial features from mIF images to help understand mechanisms of action and clinical response.

   

• Work closely with colleagues from Data Science to utilize Genmab’s commercially procured database of histopathology images, IHC, genomics, clinical, and transcriptomics data to expand on the spatial features learned from mIF images and build multi-omics models to analyze and predict response to therapy.

   

• Stay updated on the latest relevant scientific literature, summarize and interpret new findings, prepare manuscripts for publications and present results both internally and at external conferences.

   

Requirements

• Recent PhD in a quantitative field (e.g. biomedical engineering, physics, data science, mathematics, electrical engineering, or related field)

   

• Have expert knowledge and deep understanding of digital image analysis, feature extraction, pattern recognition, machine learning and data mining methods; application in digital pathology and fluorescence microscopy is a plus.

   

• Have excellent programming skills (Python, Matlab, Java, etc) and experience using common machine and deep learning frameworks (e.g., Pytorch, Tensorflow, Scikit-learn).

   

• Strong understanding of fluorescence microscopy, whole slide imaging and different microscopic slide file formats.

   

• A track record of publications and independent contributions to the literature.

   

• Positive, open and creative mindset to develop innovate image analysis algorithms in close collaboration with pathologists and other scientists.

   

• Passion for the field of digital pathology and desire to explore new technology platforms related to image analysis.

   

• Background in immunology and/or immuno-oncology are desired but not required.