Priya Sharma

Ph.D. Candidate in Computational Biology

Stanford University · School of Medicine

psharma@stanford.edu

Phone

+1 (650) 555-0198

Web

priyasharma.dev

GitHub

github.com/psharma

linkedin.com/in/psharma

EDUCATION

2022 –

Present

Ph.D. in Computational Biology

Stanford University, Stanford, CA

Advisor: Prof. Michael Chen • GPA: 3.96/4.0

Dissertation: "Scalable graph neural networks for predicting epistatic interactions in protein sequences."

2018 – 2022

B.S. in Computer Science, Minor in Biology

University of California, Berkeley, CA

GPA: 3.92/4.0 • High Distinction • Phi Beta Kappa

Thesis: "Attention-based deep learning models for antimicrobial peptide discovery."

RESEARCH EXPERIENCE

2022 –

Present

Graduate Research Assistant

Stanford Computational Biology Lab — Advisor: Prof. Michael Chen

Developed EpistNet, a graph neural network that predicts pairwise epistatic effects in SARS-CoV-2 spike

protein with 0.87 Spearman correlation, outperforming leading sequence-based models by 12%.

Built a scalable training pipeline in PyTorch and Dask to process 14 million sequence variants across 10

GPUs, reducing training time from 14 days to 31 hours.

Designed a novel attention masking strategy that improved generalization to unseen protein families by

18% in zero-shot transfer experiments.

2021 – 2022

Undergraduate Research Fellow

Berkeley AI Research Lab — Advisor: Prof. Lina Zhao

Implemented a protein language model (BERT-style) with 650M parameters using JAX and TPUv3,

achieving state-of-the-art results on the FLIP secondary structure prediction benchmark (F1 = 0.89).

Curated and cleaned a dataset of 2.3 million unlabeled protein sequences from UniRef50; developed a

distributed deduplication and clustering pipeline using MinHash and Spark.

Co-authored a paper accepted at ICML 2022 on masked language modeling objectives for protein

sequence representation learning.

Summer 2021

Research Intern

Genentech, Computational Biology Group — Mentor: Dr. Aisha Kapoor

Built a PyTorch-based deep learning model to predict antibody-antigen binding affinity from sequence

data, achieving a mean absolute error of 0.42 log KD on a held-out test set of 1,200 antibody pairs.

Developed a feature importance framework using integrated gradients that identified key CDR-H3 loop

residues driving binding specificity, validated against 3 published crystal structures.

PUBLICATIONS

Sharma, P., Nguyen, T., & Chen, M.

EpistNet: A Graph Neural Network for Predicting Epistatic Interactions in Viral Proteins.

Nature Machine Intelligence.

in press

Sharma, P., Okafor, K., & Zhao, L.

Understanding the Role of Masking Strategies in Protein Language Models.

Proceedings

of the 41st International Conference on Machine Learning (ICML), Vienna, Austria.

oral (top 3.5%)

1 / 3

Ramesh, A., Sharma, P., & Chen, M.

Scalable Variant Effect Prediction with Sparse Attention.

Bioinformatics, 39(8),

btad481.

Sharma, P., & Kapoor, A.

Deep Learning for Antibody-Antigen Binding Affinity Prediction.

Cell Systems, 13(4), 312–325.

Zhao, L., Sharma, P., Okafor, K., & Lee, J.

ProteinBERT: A Masked Language Model for Protein Sequence Understanding.

arXiv preprint, arXiv:2206.05423.

under review at PLoS CB

CONFERENCE PRESENTATIONS

Dec 2024

"Graph Neural Networks for Epistasis Prediction"

NeurIPS 2024, Machine Learning in Structural Biology Workshop — Vancouver, Canada

Contributed talk (acceptance rate 18%) • Presented to ~200 attendees

July 2023

"Protein Language Models: Masking Strategies and Beyond"

ICML 2023, CompBiology Workshop — Honolulu, HI

Poster presentation • Awarded Best Poster (1 of 12)

TEACHING & MENTORING

Fall 2024

Teaching Assistant, CS 279: Computational Biology

Stanford University — Instructor: Prof. Michael Chen

Led weekly discussion sections for 45 students; developed 3 homework assignments on sequence

alignment, hidden Markov models, and deep learning for genomics. Student rating: 4.7/5.0.

Spring 2024

Mentor, Undergraduate Research Program

Stanford BioSciences

Supervised two undergraduate students on independent research projects in protein structure prediction.

Both students presented at the Stanford Undergraduate Research Symposium.

HONORS & AWARDS

2024

Stanford Graduate Fellowship in Science & Engineering (SGF) — full tuition + stipend, 3 years

2023

NSF Graduate Research Fellowship Program (GRFP) — Honorable Mention

2022

Phi Beta Kappa — UC Berkeley Chapter

2022

Berkeley Chancellor's Award for Undergraduate Research — $3,000 grant

2021

Barry Goldwater Scholar — National recognition for excellence in STEM research

2020

Regents' Scholarship — UC Berkeley's highest undergraduate merit award

SKILLS & METHODS

Programming

Python, C++, Julia, R, Bash

Deep Learning

PyTorch, JAX, TensorFlow, DGL, PyG

Scientific Computing

NumPy, SciPy, Pandas, scikit-learn,

Biopython

HPC & Infrastructure

SLURM, Docker, Kubernetes, AWS

(SageMaker, EC2), GCP (TPU, Vertex)

Bioinformatics

BLAST, HMMER, Rosetta, AlphaFold2,

PyMOL, GROMACS

Data & Workflows

Snakemake, Nextflow, Git, DVC,

Weights & Biases

PROFESSIONAL SERVICE

2024 –

Present

Peer Reviewer

PLOS Computational Biology, ICML CompBiology Workshop, NeurIPS Learning on Graphs Workshop

Reviewed 8 manuscripts and 12 conference submissions to date.

2 / 3

2023 –

Present

Organizer, Stanford Computational Biology Journal Club

Co-organize weekly meetings with 25+ graduate student attendees; schedule speakers and lead discussions on

recent advances in protein design, single-cell genomics, and AI for drug discovery.

REFERENCES

Available upon request.

3 / 3

Graduate Student CV

Prompt to Clone This Graduate Student CV

Apply this example's core structure, strategic pacing, and structural hierarchy directly to your own topic.

What are you generating today?

More Examples