Nitya Thakkar
CS PhD Student
Stanford University
Hello!
I am a third year Computer Science PhD student at Stanford advised by James Zou. My research is supported by the Stanford Graduate Fellowship and the NSF Graduate Research Fellowship. Previously, I graduated from Brown University where I was advised by Ritambhara Singh.
My research generally lies at the intersection of machine learning and health. I am interesting in understanding how we can integrating multimodal biomedical data to develop machine learning models for biomarker discovery, treatment guidance, and prognosis prediction. I am also passionate about women’s health, and collaborate with Irene Chen on developing computational methods to better understand health trajectories among the female population.
Interests
- Machine learning for health
- Precision medicine
- Women’s health
Education
-
PhD in Computer Science, 2028 (expected)
Stanford University
-
BS in Computer Science, 2023
Brown University
Publications
(2026).
Integrated histopathology–transcriptomic biomarker enhances survival prediction in HNSCC patients treated with immunotherapy.
Translational Oncology.
(2026).
Characterization of menopause onset and associated disease risks using large-scale electronic health records.
medRxiv.
(2026).
A large-scale randomized study of large language model feedback in peer review.
Nature Machine Intelligence.
(2024).
Predicting A/B compartments from histone modifications using deep learning.
iScience, 27(5).
(2023).
Protein generation with evolutionary diffusion: sequence is all you need.
bioRxiv.
Experience
Graduate Teaching Assistant
Stanford University
Graduate student instructor for CS 227 (Foundation Models for Healthcare). Responsibilities include designing and grading assignments and holding weekly office hours.
Undergraduate Research Assistant
- Honors senior thesis: developed a graph convolutional neural network trained on gene expression data from patients with Glioblastoma to predict cell state energy and learn the underlying graph structure of the gene-gene interactions
- Co-first author on ENCODE Consortium project, CoRNN, to predict three-dimensional organization of the genome (A/B compartments) from one-dimensional data (histone modification signals) using deep learning methods
Undergraduate Teaching Assistant
Brown University
Head TA for Deep Learning Spring ‘23. TA for Deep Learning (Fall ‘22, Spring ‘22), Introduction to Computer Systems (Fall ‘21), and Linear Algebra (Spring ‘21). Responsibilities included course development, grading problem sets/projects, and holding weekly office hours and labs.
Undergraduate Research Intern
Advised by Kevin Yang, Ava Amini, and Sarah Alamdari. Contributions during internship led to the publication of EvoDiff, a diffusion framework for generating proteins from sequence information. Assisted in project conceptualization, creation of generation models for 2D alignments, and analysis of the generations.
Undergraduate Research Intern
Advised by Neriman Tokcan through the Broad Summer Research Program (BSRP). Applied machine learning methods to spatial transcriptomic data. The project goal was to understand how Classical Hodgkin’s Lymphoma tumor cells survive based on interactions with nonmalignant immune cells in the cancerous environment. Presented work at Annual Biomedical Research Conference for Minority Students in November 2021.
Honors & Awards
National Science Foundation Graduate Research Fellowship
NSF GRFP recognizes and supports outstanding graduate students who have demonstrated the potential to be high achieving scientists and engineers, early in their careers. It provides three years of support.
Stanford Graduate Fellowship in Science and Engineering
Three year fellowship providing support to outstanding students pursuing doctoral degrees in science and engineering
Senior Prize in Computer Science
Recipient of the Senior Prize in Computer Science for excellence in academics and service to the department
CRA Outstanding Undergraduate Researcher Award Honorable Mention
This award program recognizes undergraduate students in North American colleges and universities who show outstanding research potential in an area of computing research