Andrea Rodriguez Delherbe
Genomics data science
My doctoral training focuses on implementing computational models based on diverse machine learning techniques and high-performance computing to study the principles of gene regulation across evolution and species. Within the scientific context of developmental biology in zebrafish and chicken embryos, and as a D.Phil. student in the Sauka-Spengler group, I am currently studying the impacts of chromatin architecture dynamics on gene regulation throughout the different developmental stages using transfer-learning methods. Added to the previously described, I am also using convolutional neural networks to unveil genomic features that represent the underlying decision-making process in the migration and transition of cranial neural crest cells.
Before joining the RDM D.Phil in Medical Sciences program, I obtained a BSc in Computer Science at Universidad Tecnica Federico Santa Maria, Chile, where I worked as a research assistant in implementing machine learning models to answer diverse scientific questions in the fields of biomedical imaging, bioinformatics, astronomy, and particle physics.
My academic goal is to become a genomics data scientist focused on developing and applying machine learning algorithms to answer biological questions that support the generation of knowledge in developmental biology, physiology, immunology, and/or oncology.
GenoVi, an open-source automated circular genome visualizer for bacteria and archaea
Cumsille A. et al, (2023), PLOS Computational Biology, 19, e1010998 - e1010998
A novel ensemble feature selection method for pixel-level segmentation of HER2 overexpression
Aguilera A. et al, (2022), Complex & Intelligent Systems