Temporal data integration for developmental biology - QARMA (MARSEILLE)
9 Septembre 2021
Catégorie : Post-doctorant
Recent years have witnessed an explosion of data in biology and medicine. Many acquisition techniques, like microscopy or sequencing techniques, provide complementary views of the same system, e.g. an organ, an embryo, a tumor. To understand the dynamics happening at single cell resolution and develop new personalized treatments, we need to integrate these complementary sources of information. To tackle this problem, this project aims at developing new Temporal Data Integration theoretical and computational methods for various complementary acquisition techniques (microscopy, and multi-omics).
The successful candidate will work jointly within Paul Villoutreix’s interdisciplinary group (http://bioml.lis-lab.fr/) and under the supervision of Thierry Artières within the Machine Learning team of the Computer Science lab in Marseille (https://qarma.lis-lab.fr). The position is part of the Turing Center for Living Systems (https://centuri-livingsystems.org), which is a vibrant interdisciplinary community composed of mathematicians, computer scientists, physicists, …, interested in questions of biology in the scenic Mediterranean city of Marseille, France.
When studying a biological system such as a developing embryo, many acquisition techniques are available. Each of them brings out unique features of the system, however, they are often incompatible and cannot be performed at the same time. To address this challenge we need to develop multi-domain integration techniques. Current approaches rely either on the tools of optimal transport, or multiple autoencoders, however, they are not designed to address temporal data. With this project, we propose to take advantage of multi-domain dynamical data in high-dimensional spaces to infer a dynamical coupling between sequencing data acquisition techniques (such as sc-RNASeq) and microscopy data. This will include theoretical work and computational experiments on artificial and real data. The results of the project are expected to have large impact in the machine learning community and be of wide applicability in real world biological problems. The scientific environment for this project is ideal as it combines expertise in interdisciplinary approaches of machine learning applied to biological data, and expertise in theoretical machine learning.
Optimal Transport, Autoencoders, Single Cell Transcriptomics
We are looking for a PhD in machine learning, computer science, applied mathematics with strong interest in machine learning and its applications to biology. The postdoc will take place in Paul Villoutreix’s interdisciplinary team (Learning meaningful representation of life http://bioml.lis-lab.fr/) and the Machine Learning team of the Computer Science lab in Marseille (https://qarma.lis-lab.fr).
CENTURI offers a two-year contract from the University of Aix-Marseille. The salary will be based on Aix-Marseille University’s salary scale, depending on the candidate’s profile and experience. If you are interested, we encourage you to apply by sending your application to Paul Villoutreix (firstname.lastname@example.org).
Applications must include:
- A CV
- A cover letter
- Two references we can contact
-Towards a general framework for spatio-temporal transcriptomics
Julie Pinol, Thierry Artières, Paul Villoutreix, NeurIPS, LMRL workshop, 2020
-Gene expression cartography
Nitzan, Mor, et al., Nature, 2019
-Multi-domain translation between single-cell imaging and sequencing data using autoencoders
Dai Yang, Karren, et al., Nature Communications, 2021