About Me
I develop statistical and deep learning methods for predicting the functional effects of regulatory genetic variants, and apply them to understand cell-type-specific gene regulation in neurodegenerative disease. My current work integrates genomic deep learning models with functional genomics data to identify causal variants and uncover missing regulation in Alzheimer’s disease.
I am a Senior Research Scientist at the New York Genome Center, working with David Knowles (Columbia University/New York Genome Center) and Towfique Raj (Icahn School of Medicine at Mount Sinai), and a member of the NIH Alzheimer’s Disease Sequencing Project consortium, where I collaborate with members of the AI/ML and Functional Genomics Working Group. My work is supported by the NIH/NIA-funded FunGen-xQTL project (R01 AG086467) and was previously supported by U01 AG068880, Learning the Regulatory Code of Alzheimer’s Disease Genomes, both part of the ADSP Functional Genomics Consortium (FunGen-AD).
Trained in pure mathematics, I moved through computational topology and geometric data analysis into industry machine learning, then to biomedical data science at Harvard Medical School, before joining the Genome Center in 2021.
Contact: clakhani (at) nygenome.org
Research Interests
- Deep learning models of gene regulation and variant effect prediction
- Rare variant gene discovery and common variant fine-mapping in Alzheimer’s disease
- Discovery of cell-specific deep learning annotations which can be used as priors for fine-mapping and rare variant association testing