Qianyu Zheng

Current GPA: 4.00/4.00

Developing and applying computational methods to study the structure and function of proteins and enzymes.
- Spearheaded protein engineering research, establishing scalable and visualizable strategies to investigate protein families of millions of sequences and extract meaningful insights via sequence similarity networks and graph analysis.
- Crafted biologically significant data splitting strategies with clustering and evolutionary algorithms, encouraging fair model evaluation and ensuring the reliability of research outcomes.

Advisor: Victor Fung

Researching the applications of Graph Neural Networks (GNNs) in material science, under the guidance of Assoc. Prof. Victor Fung at Georgia Tech.
- Conduct independent research to design more stable machine learning force fields for molecular dynamics simulation.
- Obtained proficiency in GNNs, PyTorch, deep learning, and research methodologies.

For research project "Accurate and stable machine learning force field for crystal structures"

For academic excellence with GPA of 4.0

Expertise in Manage workbook options and settings, Manage and format data, Create advanced formulas and macros, and Manage advanced charts and tables in Excel.

Expertise in Manage worksheets and workbooks, Manage data cells and ranges, Manage tables and table data, Perform operations by using formulas and functions, and Manage charts in Excel.

Expertise in building, training, tuning, and deploying machine learning (ML) models on AWS.

Foundational, high-level understanding of AWS Cloud, services, and terminology

Designed a multimodal tool for flexible queries for human protein sequences in UniProt database.
- Leveraged LLM Llama 3 to generate text queries as training data, a CLIP model (BERT + ESM) in contrastive learning of protein sequence and user query embeddings.
- Developed a Flask application (Flask, HTML/CSS) deployed with AWS Fargate, ECR, ECS. Now live at nl2prot.org.
- Obtained experience in multimodal learning, LLM training, Cloud Computing, PyTorch, and deep learning.

Participate in the Workout Of the Day (WOD) prediction project group at Data Science @ GT.
- Use Python to perform data cleaning and feature engineering pipelines for the downstream machine learning tasks.
- Leverage modern optimization libraries to design an automated hyperparameter search pipeline for modeling.

Developed a Machine Learning solution for audio classification in a group of 4.
- Utilized Python to preprocess audio data by audio signal processing and feature extraction (e.g. Mel spectrogram, STFT, chroma features).
- Finetune large vision models (ResNet, ViT) for genre classification with Mel spectrogram.

Developed a diet management app in a group of 4 using Android Studio and Java.
- Designed a user-friendly interface for users to track their diet and nutrition.
- Implemented MVVM architecture, Design Patterns, Firebase for backend, and Unit Testing.
- Gained experience in Git CI/CD pipeline, Android Studio, Java, and software engineering.

Explored the applications of Singular Value Decomposition (SVD) in image compression and signal denoising.

Implement a pipeline to extract source data from various forms of scientific plots.
- Utilized YOLO and fineuned OCR to extract data from various forms of scientific plots.
- Deploy with Flask backend and HTML/CSS frontend.

A tool tailored for PR teams of companies to analyze impact of tweets on stock prices.
- Trained a word2vec model for tweet analysis.
- Utilized GPT for generation of sample tweets.
- Deploy with Flask backend and Wix on Google Cloud.