A two-year postdoctoral position in machine learning is available at Institut Pasteur in Paris within the Chemoinformatics and Proteochemometrics group of Olivier Sperandio and the Structural Bioinformatics unit of Pr Michael Nilges. This position is funded by an ANR project that aims to study the interplay between epigenetic regulation and infectious diseases in the context of antimicrobial resistance (AMR). The consortium mobilized for the project combines expertise in the biology and epigenetics of infection, proteomics, drug design, and medicinal chemistry of epigenetics.
For this project, we are looking for a highly motivated postdoctoral researcher to use and/or develop state-of-the-art machine/deep learning methodologies that assist drug discovery projects and the design of target-based focused chemical libraries.
Project background: A common phenomenon in most microbial infections is the attenuation of the host’s immediate immune response, allowing for long-term colonization. Many pathogens achieve this by manipulating the epigenetic regulation of the host. Indeed, pathogens either release factors that directly target the host chromatin or hijack its epigenetic machinery, both resulting in alterations of the host epigenome. This project is based on the hypothesis that inhibiting these phenomena will give an advantage to the host and thus facilitate the elimination of the microbe. Importantly, epigenetic modifications, such as DNA and histone modifications, are reversible and modulate gene expression without changing the DNA sequence. This makes them ideal drug targets. In cancer treatment, epigenetic regulators (enzymes and chromatin-binding proteins) are already validated drug targets, with several molecules approved for clinical use. In the context of infection, drugs targeting chromatin have been poorly explored.
This project proposes an innovative strategy to fight AMR by chemically targeting epigenetic modifications. The recent findings of the consortium strongly suggest that this could be an innovative therapeutic strategy to counteract bacterial advantages and strengthen the host’s natural defenses. By targeting the host, this strategy should also minimize the possibility of resistance emergence.
To facilitate the identification of pertinent host epigenetic targets and the effect of their modulation on infection, the successful candidate will have to design a focused chemical library using/developing innovative machine learning technologies. In addition to their epigenetic-compliant profile, the selected compounds shall be characterized by drug-like properties, the capacity to penetrate cell membrane and nuclei, and possess promising profiles for further drug development.
Profile: Applicants must hold a Ph.D. in chemoinformatics or data science applied to drug discovery. Prior experience in drug discovery, with the design of focused chemical libraries, various machine learning technics, and several architectures of deep learning is highly desirable. A background in chemistry would be a plus. High motivation, excellent communication skills, and the ability to work collaboratively are essential. The ideal candidate, therefore, has an open and creative mindset, strong analytical skills (including coding in Python), and a passion for solving problems using unconventional approaches. Strong communication skills and English proficiency are required.
Position: The position is available immediately and will remain open until filled. The expected start date is May 2022. The position is initially for 2 years, with the possibility of extension. Salary is commensurate with experience according to the institutional guidelines.
To apply: Please send a single pdf file containing a CV, a cover letter summarizing research interests and career goals, and contact information of 2 (or more) references to: email@example.com