The project

This exploratory research project aims at identifying novel biological targets for antiviral drugs by means of computational methods. A cross-functional team with experts in cheminformatics, computational biology, machine learning, and virology will support you. You will help us analyze data generated from phenotypic screenings for antivirals using state-of-the-art analytical tools, especially causal inference and network-based machine learning, to infer novel targets for viral infection. The aim is to derive high- confidence biological targets, with which we can design and conduct follow-up experiments to validate the targets and to start drug-discovery programs.

The position is funded for 3 months, however it can be combined with another 6-month position with similar requirements for skill sets. Please indicate your availability.

In this position, you will

• Collaborate with a small team of 2-3 colleagues to prepare data and biological knowledgebase required for this and future projects in a findable, accessible, interoperable and reproducible (FAIR) way;
• Build, benchmark, and interpret machine-learning models to discover, validate or refute causal paths between putative targets and readouts from the phenotypic screening;
• Contribute to an emerging software toolbox of network-based target identification and validation with software packages and pipelines;

Who you are

You are an ambitious student who is enthusiastic about understanding biology with computational models and data analysis. You are currently enrolled in a Ph.D. program in the field of computational biology, bioinformatics, cheminformatics, computer science, biomedicine, or a related discipline.

Moreover, you are

• Experienced in applying computational methods to address questions in biology, chemistry, pharmacology, or toxicology, demonstrated by peer-reviewed publications;
• Proficient in programming with Python, demonstrated by contributions to open-source software projects;
• Skilled in causal inference and interpretable graph neural networks;
• Constantly striving for high-quality work, readable and reusable code, and effective oral and written communication;
• Motivated to work in a multidisciplinary team.

To be considered, please send us your complete application merged into one PDF including

• ● A Motivation Letter (including desired start date & duration)
• ● CV, containing links to at least one open-source project that we can access
• ● A certificate of enrollment (if you are currently studying)
• ● For non-EU/EFTA citizens: Certificate from the university stating that an internship is mandatory (required due to regulations)

We’d like to let you know that for this recruitment process we are going to invite you to an Online Assessment in case a first review of your application was successful. Roche embraces diversity and equal opportunity in a serious way. We are dedicated to building a team that represents a range of backgrounds, perspectives, and skills. The more inclusive we are, the better our work will be.

For more information about opportunities for students and graduates, visit genext.roche.com