About the role:

The Owkin R&D department aims at leveraging high-quality multi-modal datasets and powerful AI modeling to accelerate bringing the right drugs to the right patients faster. A large pluri-disciplinary team or research scientists works on different AI drug discovery aspects such as identifying new promising therapeutic targets, new indications and subgroups, as well as positioning drugs on the right patient subgroups.

The Computational Drug Discovery team in Owkin’s R&D operates multiple workstreams, interacting closely with other R&D teams and transversal functions. One critical workstream aims to enhance the efficiency of druggability assessment of given targets and candidate compounds through automation. Druggability assessment, a crucial step in drug discovery, involves evaluating protein targets and their interactions with potential drug compounds.

The team is looking for a promising intern to focus on automation and augmentation of Owkin’s current target assessment process, e.g., regarding druggability. As part of the project, the intern will have the opportunity to learn about the steps involved in target druggability assessment, identify and propose automation strategies for each step and implement the most promising ones. Once this first automated pipeline is completed and tested, a second phase will consist in interviewing key stakeholders involved in this process to identify additional steps or components – e.g. additional information via data scraping or internal data modeling or visualization tools – to add to the pipeline in order to facilitate the decision making process. This topic will be tightly integrated within both the Computational Drug Discovery group as well as the Biomedical and Discovery Engine teams to ensure close alignment of needs and solutions in vue of the druggability assessment process.

This internship provides a unique opportunity to study a fast-growing and important field, with clear applications for drug discovery.

In particular, as your main missions, you will:

• Collaborate closely with, and receive mentorship from the other members of the R&D team;
• Contribute to the implementation of an end-to-end automated pipeline for druggability assessment, relying on data sources such as OpenTarget and PubChem and leveraging available APIs and internal solutions;
• Conduct validation of the automated pipeline in alignment with previous druggability assessment activities and results;
• Conduct comparative and primary research on possible solutions for extension of the automated assessment pipeline, examples of possible research avenues could be: looking for and evaluating protein 3D structures, extracting patent information, explore solutions for LLM generated result reports, propose visualization modules for the pipeline and gathered data, implementing quality filters for small molecules, etc.;
• Report your detailed findings and solutions to the group.

Position is based on-site only, in our Paris or Nantes offices.

About you

We are looking for someone who has:

• MSc year 2+ level in data science / engineering / computational chemistry or related fields;
• Motivation to work at the intersection of biology and AI
• Excellence in communication and technical writing
• Experience in Linux/Unix-like environments, Python and good programming skills
• Fluent in English (spoken and written)
• Authorization to work legally in France

And the following would also be beneficial:

• Participation in data science projects and competitions
• Fluency with Git and basic software engineering patterns
• Previous work or projects with large language models or with NLP methods
• Knowledge in (structural) biology and biochemistry
• Previous experience with front-end development
• Contribution to publications in conferences and journals

Please submit your CV in English

#LI-HB1