I work where plant genomics and machine learning meet experimental discovery.
I am a computational biologist and quantitative geneticist interested in how genomes encode biological function. My work combines plant genomics, biostatistics, regulatory sequence analysis and machine learning to connect genetic variation with gene regulation and complex traits.
I am a biochemist by training and began my scientific career in experimental biology. During my PhD, I moved from the bench into computational genomics, generating and analyzing multi-omics, epigenomic and single-cell datasets for non-model plant systems.
In my current postdoctoral work, I use machine learning as one quantitative tool to model regulatory DNA, interpret genetic variation and understand how plant genomes shape complex traits.
PETAL is an end-to-end machine learning platform for predictive modeling of regulatory DNA sequences. It combines model prediction, interpretation and sequence evolution workflows in a web-accessible format.
PETAL is currently being deployed and will be released soon.
SEPAL is a low-cost, modular plant environment monitoring system built on a Raspberry Pi. It provides a user-friendly interface for monitoring environmental parameters such as temperature, humidity and light in plant growth chambers or greenhouses.
Helixer is a deep learning-based gene annotation tool for eukaryotic genomes. It combines deep neural networks with a hidden Markov model to predict primary gene models from genomic DNA sequences.
I contributed to Helixer as a co-author involved in the biological validation and interpretation of the model.
Predmoter is a deep learning-based tool for predicting plant promoter and enhancer regions across species.
I contributed to Predmoter as a co-author involved in project conceptualization, data analysis and interpretation of the model.