Research Expertise and Interest
computational biology, genomics, machine learning, artificial intelligence, personal genome interpretation, precision health, rare diseases, statistical genetics, biophysics
Research Description
Nilah Ioannidis is an Assistant Professor with a joint appointment in EECS and the Center for Computational Biology (CCB). Her group works on computational methods to analyze and interpret personal genomes, including machine learning methods to predict the clinical significance of genetic variants of uncertain significance (VUS) and models to link genome variation with molecular phenotypes such as epigenome and transcriptome variation to predict disease risks.
Dr. Ioannidis was previously a postdoctoral scholar in the Department of Biomedical Data Science at Stanford University, where she worked on several machine learning tools to predict the pathogenicity of single nucleotide variants, including the ensemble predictor REVEL for missense variants. During her PhD in Biophysics at Harvard University, she worked in the Department of Biological Engineering at MIT and developed methods to analyze the dynamics of intracellular particles using hidden Markov modeling and Bayesian inference. She also previously served as Research Director at the Jain Foundation, a non-profit foundation focused on the rare genetic disease dysferlinopathy.
Recent and ongoing research projects include:
- Assessing the utility of genomic deep learning models for disease-relevant variant effect prediction
- Sequence-to-expression models of compact promoters for cell-type-specific promoter design
- Evaluating the use of sequence-to-expression predictors for personalized expression prediction
- Tissue-specific impacts of aging and genetics on gene expression patterns in humans
- Unsupervised density estimation for noncoding variant effect prediction
Full publication list at Google Scholar: scholar.google.com/citations?user=42m4tGIAAAAJ
Recent awards:
- Chan Zuckerberg Biohub Investigator Award
- Okawa Foundation Research Grant
- NIH K99/R00 Pathway to Independence Award
