sophtang/TR2-D2

Code for TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion

36
/ 100
Emerging

This project helps biological engineers and computational chemists design new biomolecules like DNA regulatory sequences and therapeutic peptides. It takes existing diffusion models for these molecules and fine-tunes them to generate sequences with specific desired properties, such as enhanced gene activity or improved drug efficacy. The output is a refined model that can create novel, high-performing molecular sequences.

Use this if you need to optimize the generation of discrete biological sequences, like DNA or peptides, to meet specific, quantifiable design goals.

Not ideal if you are looking to generate continuous data or if your target properties cannot be represented as a reward signal for optimization.

biomolecular-design drug-discovery genomic-engineering peptide-optimization synthetic-biology
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Python

License

MIT

Last pushed

Feb 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sophtang/TR2-D2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.