dacarlin/protein-transformers
Use generative ML to design new proteins using this simple, hackable implementation of protein transformer models
This project helps biological researchers and biochemists design new proteins using generative machine learning. You provide a dataset of protein sequences, and it trains a transformer model to generate novel protein sequences. The output is new protein sequences that can then be folded and analyzed for their structural and functional properties.
No commits in the last 6 months.
Use this if you need a straightforward, adaptable tool for experimenting with protein sequence generation and understanding how transformer models can be applied to protein design.
Not ideal if you need a production-ready, highly optimized, or extensively validated protein design platform rather than a research or educational tool.
Stars
9
Forks
—
Language
Python
License
—
Category
Last pushed
Nov 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dacarlin/protein-transformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/alphagenome
Implementation of AlphaGenome, Deepmind's updated genomic attention model
BiomedSciAI/biomed-multi-omic
Build foundation model for RNA or DNA data
BioinfoMachineLearning/DeepInteract
A geometric deep learning framework (Geometric Transformers) for predicting protein interface...
Gleghorn-Lab/Protify
Low code molecular property prediction
raimondilab/precogx
A predictor of GPCR couplings with G-proteins/B-arrs using Transformers