Machine Learning for Cancer Research
While in the lab of Dr. Dan Landau at Weill Cornell Medicine and the New York Genome Center, I contributed to novel computational biology research, particularly in the field of genomics. I contributed my engineering and scientific skills to two main projects, one on microsatellite phylodynamics and one on motif analysis of SF3B1-mutant cryptic 3’ splice sites. The latter was published:
Cortés-López, M., Chamely, P., Hawkins, A. G., Stanley, R. F., Swett, A. D., Ganesan, S., Mouhieddine, T. H., Dai, X., Kluegel, L., Chen, C., Batta, K., Furer, N., Vedula, R. S., Beaulaurier, J., Drong, A. W., Hickey, S., Dusaj, N., Mullokandov, G., Stasiw, A. M., Su, J., … Landau, D. A. (2023). Single-cell multi-omics defines the cell-type-specific impact of splicing aberrations in human hematopoietic clonal outgrowths. Cell stem cell, 30(9), 1262–1281.e8. https://doi.org/10.1016/j.stem.2023.07.012
Before the lab, at Flatiron Health, I built regulatory-grade datasets to help clients answer targeted cancer research questions. Outside of my daily work, I had the great privilege of contributing to scientific research through Hackathons. Two of my abstracts were published in peer-reviewed journals - one that I co-authored, and one for which I was the lead author:
Stasiw A, Falk S, Garapati S, Sridharma S, Mendelsohn D, Lakhtakia S, Rech A, Oldridge D, Adamson BJ, Chen R.
”Generalizable Machine Learning Framework for Predictive Modeling of Patient Outcomes Using Oncology Electronic Health Records”. Value in Health 23, S74. https://doi.org/10.1016/j.jval.2020.04.1752Chen R, Garapati S, Wu D, Ko S, Falk S, Dierov D, Stasiw A, Opong AS, & Carson KR. “Machine Learning Based Predictive Model of 5-Year Survival in Multiple Myeloma Autologous Transplant Patients” Blood 2019; 134 (Supplement_1): 2156. https://doi.org/10.1182/blood-2019-129432
Algorithmic Arts (“Deep Learning for Dance Performance”)
Artistic richness abounds at the intersection of technology and performance. I explored this theme in my original production, "Superhighway", presented at Dixon Place on 10/6/16. You can also read more in my original research paper, "Software for Choreography: Real-Time Analysis of Expressiveness in Dance Performance", which I wrote as an undergraduate in the Computer Science department at Princeton. In it, I combined computer vision (on a Microsoft Kinect) with deep learning and neural networks. My work was also written up in the Princeton Engineering newsletter.
Using this work as a backdrop, I taught "Introduction to Digital Dance" to students with Gibney Dance's Digital Technology Initiative; I also taught “Computers as Collaborators”, to introduce the fundamentals of using deep-learning and other algorithmic techniques to enhance on-stage performances.