About Me

As the computational science lead at Sanofi, my team and I are focused on developing innovative algorithms for spatial transcriptomics that support drug development efforts and enable more effective spatial discovery studies. In addition to this work, I am also involved in SaMD development at Sanofi.

Previously, I served as a principal data scientist at Sanofi where I worked on RWE studies aimed at accelerating rare disease diagnostics using causal inference techniques. My experience in data science and drug development has allowed me to contribute to a range of projects aimed at advancing scientific discovery and improving healthcare outcomes. Prior to this, I worked at Western Digital on next-generation computational non-volatile storage, consulted for Altran and Tessella on various data science projects with companies such as Airbus, Liebherr Aerospace, and Schneider Electric. During my postdoctoral appointment at Los Alamos National Laboratory, I worked on R&D100 award-winning EDGE Bioinformatics platform developing microbiome analysis tools, participated in a DOE exascale computation project (ECP), and was extending my dissertation research on recurrent behaviors discovery towards unsupervised spatio-temporal data mining.

Throughout my academic career, I worked on various research projects at MIAT INRA, INRIA, and DOE-JGI, focusing on topics such as transcriptome annotation refinement, analysis of microbial communities, identifying disease-related SNPs, identifying transcripts and pathways involved in fruit ripening processes, and developing single-cell sequencing processes and pathogen databases. At RCUH, I contributed to the first transgenic genome assembly for papaya.

Under the mentorship of Professor Philip M Johnson at the Collaborative Software Development Laboratory at UH Manoa ICS, I conducted research on empirical software processes for my dissertation. Through my work, I created the Software Trajectory Analysis (STA) framework and SAX-VSM algorithm, which enable the analysis of software telemetry data to identify recurrent behaviors in software processes and products. By examining a contrast set of measurements, STA uncovers process-characteristic behaviors that serve as the foundation of software processes.