Data Science Unit

The extraordinary progress in DNA sequencing, barcoding and microscopy technologies provided the scientific community with the tools to quantitatively tackle cutting-edge problems in healthcare. The Data Science Unit was established in 2022 to meet the need of implementing advanced analytics in the context of complex multi-omics (genomics, transcriptomics, etc.) and microscopy data.

The Data Science Unit provides supports in the development of analysis solutions with the goal of maximizing data extracting from experimental and clinical data.

More specifically, we provide supports for:

• Development of solutions for the standard analysis of multi-omics data.
• Development of novel solutions for non-standard analysis of multi-omics data.
• Implementation of automated analyses pipelines for microscopy data (segmentation, patches detection, tracking, etc.).
• Automation of pipelines for higher reproducibility and massive parallelization.
• Build dashboard for case-specific data parsing.
• Implement end-to-end machine learning solutions to predicting clinical response.
• Training young scientists to be dry-lab independent. 

Tools we use:

• Microscopy data analysis: Fiji, Jython, python, TensorFlow.
• Genomics data: R, python.
• Pipeline managers: Nextflow, bash.