Some new projects that I am working on:
📱 Rhodo: AI-powered molecular viewer for iPad
I am using this project to learn SwiftUI and the Apple MLX machine learning framework.
Some previous projects:
🤖 Protein transformers
Simple, hackable implementations transformer models for protein sequences. PyTorch dataset classes for character-level and BytePair-encoding for protein sequences.
☕️ Espresso: design native-looking genes with generative AI
Python package implementing different nucleotide encoding algorithms for designing genes for heterologous expression, including a sequence-to-sequence transformer–based method trained on fungal genes
🃏 Cribbage for your command line
Command-line cribbage game, including AI players
🍖 Heme: protein structural modeling in Rust
Protein structural modeling implemented in Rust. Heme contains the basic functions necessary to load, transform, and extract protein structural data in high throughput, particularly for machine learning pipelines