Ph.D. in Quantitative Computational Biosciences, Baylor College of Medicine
- Invent and implement a new and interpretable neural network algorithm that converges 35% faster, reduces 200 times of parameters, and marginally outperforms (AUROC>0.88) traditional neural network in PyTorch.
- Merged and cleaned data from 3 databases and generated a network of 215,000+ drug-gene-disease associations
- Implemented and validated graph-based diffusion in Python to predict associations with >90% precision
- Wrote report with interactive visualization of the analysis of 5,500 job descriptions (1,100+ views in a week)
- Decreased 94% of time spent in manual annotation by creating a machine learning pipeline using Scikit-learn
- Postdoctoral Associate & Data Science Certificate