Société Française de Bioinformatique

Mots-Clés

deep learning genomics disease

Description

Project Summary:

We are seeking a highly motivated postdoctoral researcher to join an interdisciplinary project at the intersection of artificial intelligence, genomics, and gene therapy. The project aims to develop and validate a generative AI-based strategy to modify the genome to upregulate utrophin (UTRN) as a mutation-independent therapeutic approach for Duchenne Muscular Dystrophy (DMD). The successful candidate will work jointly with the ARchE team (MNHN, CNRS, INSERM and Sorbonne Université) and the gene editing team of Mario Amendola (Genethon).

Key Responsibilities:

• Integrate and curate multimodal genomic datasets (RNA-seq, CAGE, ChIP-seq, ATAC-seq).

• Adapt and fine-tune deep learning models (e.g., Borzoi, Enformer) for muscle-specific regulatory prediction.

• Design and prioritize genome edits using generative AI pipelines.

• Collaborate with experimentalists to validate edits in muscle cell models using CRISPR-based technologies.

• Iterate between computational predictions and experimental feedback to refine models and strategies.

Candidate Profile:

• PhD in Computational Biology, Bioinformatics, Machine Learning, or a related field.

• Strong experience in deep learning, preferably applied to genomics.

• Familiarity with genome editing technologies (CRISPR/Cas9, base/prime editing) is a plus.

• Proficiency in Python and deep learning frameworks (e.g., PyTorch, TensorFlow).

• Excellent communication skills and ability to work in a collaborative, interdisciplinary environment.

We Offer:

• A dynamic and supportive research environment in Paris.

• Access to high-performance computing resources (Jean-Zay HPC).

• A competitive salary (€55,000/year) and research budget.

• Opportunities for international collaboration and conference travel.