46 rue d'Ulm
Deep learning enabled the community to obtain impressive results in pattern recognition from various type of large datasets and especially those made of images. Coupled with robotics and high throughput microscopy, that can generate hundreds of thousands images from automated experiments, we and others showed that a deep network model, correctly conceived and trained, enabled to discriminate subtle visual cellular phenotypes that we couldn't hope to distinguish a few years ago with classical image analysis algorithms. While some work was developed to classify, annotate or generate videos, it has not proven yet to be effective to analyses complex interaction of moving biological objects from time lapse video microscopy experiments.
In this project we aim at extracting dynamic properties of interacting cell types from video microscopy from tumor on chip experiments, by developing new deep learning based approaches.
Our lab aim at designing methods in computational and data science, especially from large set of images and genomic sequences. However, for this project we work in tight collaboration with biologist and biophysicist colleagues from Institut Curie next door who set up a microfluidic system that enable to reconstitute a tumor microenvironment ex vivo. Altogether, we seek to establish this system as a convenient way to study and decipher the complex interplay that occurs between different cell types in a tumor. Finally, we aim at using this system to develop new type of immunotherapies against breast and lung cancer.
The successful candidate will join our lab and to engage a research work to decipher dynamic properties from microscopy videos. He/she will interact with the other lab members to use and possibly augment his/her expertise in deep and machine learning to the benefit of his/her project under the form of novel compelling idea, proposition of numerical experiment based on data, algorithms or network architectures. He/she will also be in charge to write one or several manuscripts to be submit to international journal with review committee, describing a novel method validated quantitatively.
Candidates should :
- hold a PhD degree in deep/machine learning, computer science, statistics, applied mathematics or image analysis.
- be rigorous and organized to lead his/her project to success.
- be able to adapt to the constraints inherent to research projects.
- be able to work and be benevolent with colleagues share knowledge and receive advices from other team members.
- be willing to write manuscripts in English.
A previous experience related to biology and/or microscopy would be considered a plus but is not required.
A previous experience in deep learning would be considered a plus but is not required.
The host lab (Computational Bioimaging and Bioinformatics: https://www.ibens.ens.fr/spip.php?rubrique47), led by Auguste Genovesio comprises about 10 computer scientists. The lab is part of the Center for Computational Biology, an interdisciplinary and international research center located at the Ecole Normale Supérieure in Paris, France. The research of the lab concerns the development of advance data analytics and computer science methods to study cell morphology and dynamic at large scale and functional genomics. The École Normale Supérieure is a renown public higher education and research institution, located in the Latin Quarter in the center of Paris, close to numerous public transportation options (RER, subway, bus) and in a very nice and student area.