Ryan L. Keivanfar

Ryan L. Keivanfar is a computational biologist and machine learning researcher specializing in AI-driven genomics and molecular phenotype prediction. She is completing her PhD in Computational Biology at UC Berkeley, where her work integrates deep learning with large-scale genomic datasets to uncover regulatory mechanisms. She earned her BS in Cell and Developmental Biology from the University of California, Santa Barbara.

Her doctoral work focuses on AI-driven genomics, including developing DeepShape, a deep learning model that integrates DNA sequence and structural features to predict molecular phenotypes. She also builds fine-tuning strategies for allele-specific expression, designs large-scale deep learning analyses to interpret complex genome regulation, and develops automated ML pipelines on high-performance computing systems. Her research bridges computational modelling with experimental workflows, including prioritizing genomic variants for cancer studies.

Previously, she worked as a computational biologist at Nautilus Biotechnology, where she built NGS analysis pipelines, automated data workflows, and led cross-functional assay-development efforts. Earlier roles included data analyst and research associate at 10x Genomics, quality control analyst at Agilent Technologies, and research associate in the Human Ecological Immunology Lab at UCSB.

She has co-authored publications in genome research and cryopreservation, and her work has been presented at many scientific conferences.