KP Fellow Essays


While studying Bioinformatics, I came across one graph that Geneticists are particularly excited about: it outlines the cost of sequencing a human genome against Moore's law. There is something particularly riveting about the cost decrease in sequencing a human genome, which fell from over $10 million a decade ago to $1,000 today. Yet, we still need to decide how to make use of all these new data points. 


It is my goal to make a mark on the world by contributing to the effort to make sense of the enormous amounts of biological data being generated. Whether in the realm of genetics or outside of it, I am passionate about unearthing actionable insights from biological data to gain a deeper understanding of our genetic blueprint and recommend methods to improve population health.


In particular, I'm interested in the integration of genomics into clinical care by identifying at-risk patients. Several disorders, such as Celiac Disease, Breast Cancer, Age-related macular degeneration, and obesity, can be attributed to variations in specific parts of the human genome. By developing an algorithm that detects these variances in human genome sequences through Genome-Wide Association Studies, it would be possible to identify and diagnose patients who are at-risk even before they are born! The use of data to tailor a personalized plan based on prevention can help healthcare professionals decrease the onset of diseases by over 40%.

Meaningful Experience

Upon joining my University, I fortuitously pursued Bioinformatics due to my interest in Computer Science, Mathematics, and Biology, and my desire to pursue an interdisciplinary and flexible major. I figured Bioinformatics would be an amalgamation of my favorite subjects and did not realize the enthralling implications of the field at that moment. Bioinformatics has no bounds.


During my freshman year, I grew involved in a project that utilized Python to determine dependencies between various data objects in hospital admissions data provided by the US Department of Health. With the millions of records of hospital admissions data, I was able to quantify synchrony between the alarming increase in female drug abuse cases and county-wide increases in domestic violence reports. After presenting the findings to New York County officials, mandates were made county-wide to train healthcare professionals on identifying signs of domestic violence and drug abuse in female admissions, which is not only expected to decrease case number by 13% but also cut in-patient costs by 11%.


More recently, as an AI and Deep-learning intern at the University of Buffalo School of Medicine, I have been able to see first-hand how computational biology is translational. Utilizing MATLAB, I create packages and pipelines for different Quantitative Susceptibility Mapping Algorithms, which maps the magnetic susceptibility of different MRI images. The end-goal is to utilize deep learning to correlate different QSM maps to neurodegenerative disorders, such as Parkinson’s and Alzheimer’s; this would completely disrupt the field of diagnostic medicine and finally allow healthcare professions to screen for these disorders.


Throughout my undergraduate and graduate years, I have fully grown into a bioinformatics engineer by understanding the vast potential that information extracted from biological datasets can have. Moreover, I am excited to contribute to meaningful projects that truly harness the power of Big Data in Biology in the near future!