• Developed Shiny/Streamlit applications for exploration of complex single-cell results (e.g., ligand-receptor interactions, gene regulatory networks, differentially expressed genes, gene ontologies, patient stratification).
• Trained foundation single-cell large language models (scLLMs) with publicly and/or internally available single-cell datasets to build disease-associated scLLMs.
• Applied cutting-edge ML and AI techniques for the analysis of large complex (multimodal) omics datasets.
• Proposed and supervised a master’s-level internship on a Computational Systems Biology project.
• Leveraged collaborations both internally and externally to accelerate biomarker discovery.
• Adopted the Agile way of working.

• Performed advanced statistical analysis of large complex omics datasets.
• Developed methods for multi-level data representation (multi-level networks) and integration (e.g., https://github.com/iPC-project-H2020/ipcrg/tree/master/scripts/data-driven_relational_graphs).
• Designed pipelines to analyze interaction networks of statistical associations among features (genes) and similarity networks among observations (patients).
• Created pipelines that integrate machine learning and optimization techniques to model cell metabolism.
• Produced a data catalog containing links to Ewing sarcoma omics datasets (https://sysbio-curie.github.io/EwSOmicsAtlas/index.html).
• Collaborated with biologists, computational biologists, engineers, and physicists within the H2020-ICT-2018-2 individualized Pediatric Cure project to design algorithms that address cancer-specific questions.

• I was responsible of the evaluation of my students.
• I managed class activities to enhance learning.
• I participate to the internship’s jury of my students.

Second-year master research internship in population genetics, under the supervision of O. Martin.
• I developed a general model able to calculate the probabilities of multi-locus genotypes in brother and sister mating.
• I constructed the associated algorithm in R. I showed a practical application of the model for data imputation.