Bradley Woolf
Programmer
Computational biology, programming, design
Merging computers, software, and engineering principles to program biology
Want to build something? Book a call
Projects
Calculating my Polygenic Risk Scores from the Nucleus Origin Model
Sampling energy-based models with Extropic’s thrml
GPU-based whole genome analysis
Building a VAE cell-type annotator
CPU-based whole-genome analysis
Fine-tuning Evo2 to generate novel phage designs
Gene therapy pipeline (in silico)
Frances: optimizing E. Coli gene edits → output yields
K-mer counting CUDA kernel
scRNA-seq Leukemia cell pipeline with DL
Ranking proteins with reinforcement learning
Automated variant interpretation (FASTQ → Clinic)
cfDNA fragmentomics with Python
Automated scraping from UniProt, PubMed, Reactome, and KEGG
A soil microbiome pipeline with Nextflow, Kraken2, and MultiQC
De novo antivenom binders with BindCraft, Rosetta, and ProteinMPNN
Writings
Genes from the sci-fi book Upgrade
How each programming language thinks
Shaping a neural network like marble
The core primitives all computer programs are built on
Who can I raise money from for my biotech startup?
How do I leverage LLMs to program better?
Cost modeling DL vs linear regression paper
Using AI game engines to simulate synthetic biology
Can deep learning solve bottlenecks in gene therapy?
Gene therapy: can we perceive the body as an RL agent’s environment?
GPU programming and custom kernels
The Quantification of biology
The technical bottlenecks that high frequency trading overcame
Making illiquid data liquid
A brief history of quantifying biology
Filtering nature through the dominant technology of the day
High Level Global Statistics
Woolf Software, Inc © 2025
