EMBL Grenoble is looking for a Data Scientist to develop innovative approaches for the analysis of structure guided drug design data based on advanced computing and machine learning technologies. The HTX lab at Grenoble provides access to fully automated crystallographic pipelines based on the CrystalDirect technology. These pipelines are applied to support large scale ligand and fragment screening projects and generate tens of terabytes of data yearly. Data and metadata is automatically captured by the Crystallographic Information Management System (CRIMS), developed by EMBL. The successful candidate will join the Marquez Team and will work towards expanding the CRIMS software with advanced capabilities for the analysis of crystallographic data produced at the HTX lab and other EMBL facilities with a focus on fragment screening and structure guided drug design applications. He/She will integrate a multidisciplinary team composed of scientists, engineers and software developers. These activities will be carried out in the context of EMBL-wide data science and EOSC initiatives and will count with access to High Performance Computing (HPC) centers.
Your role
EMBL are looking for a highly motivated person with experience in the use of computational approaches in structural biology and a willingness to contribute towards the development of innovative methods for large scale crystallographic data analysis based on advanced computing technologies and machine learning. Your activities will include:
• Development of advanced methods for the analysis of crystallographic data produced at the HTX lab and other EMBL facilities, with a focus on fragment screening and structure guide drug design applications.
• Adapting existing CRIMS data analysis pipelines to the use of cloud computing.
• Contribute towards the development of FAIR resources and data repositories in the context of EMBL-wide data science and EOSC initiatives.
• Cooperate towards the development and operation of the CRIMS software in collaboration with the CRIMS development Team.
Moreover, you will be part of a multidisciplinary team and will be tasked with proactively seeking and maintaining appropriate collaborations. You will also be expected to drive forward the project, working closely with structural biologists, bioinformaticians and computer scientists within and outside the Team to accomplish scientific objectives.
You have
• Either a PhD in bioinformatics or a degree in computer science, software engineering or physics with at least 4 years of demonstrable research experience in the areas of structural biology, analysis of small molecule protein interactions or related fields.
• Familiarity with software containerization (e.g. Docker, Singularity)
• Proficiency in at least one programming/scripting language (e.g. Python, PHP) and relational databases
• Capacity to work accurately and quickly to meet deadlines
• Capacity to work both as part of a team and independently
• Excellent communication skills (both verbal and presentational) and relational abilities
You might also have
• Experience in the use of high-performance and cloud computing resources.
• Familiarity with graphical databases.
• Familiarity with methods for machine learning and artificial intelligence.
Why join EMBL
This post offers a unique opportunity to join a dynamic and multidisciplinary team and contribute to the development of innovative methods with impact in biomedicine and biotechnology within a highly international environment.
Find out more and apply here.