AspirinCode/DiffIUPAC
Diffusion-based generative drug-like molecular editing with chemical natural language
This project helps medicinal chemists and drug designers by translating chemical names into molecular structures. You input an IUPAC name, which is a standardized chemical language, and it outputs a SMILES string, a line notation for chemical structures. This allows researchers to quickly generate potential drug-like molecules and explore different designs based on chemical language descriptions.
No commits in the last 6 months.
Use this if you need to generate drug-like molecular structures (SMILES strings) from their IUPAC chemical names, especially for tasks like analogue or linker design.
Not ideal if you primarily work with 2D graphs or 3D geometries of molecules, or if you don't have access to systems with large memory (228GB system RAM or 80GB GPU memory).
Stars
18
Forks
1
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AspirinCode/DiffIUPAC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MinkaiXu/GeoDiff
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).
MinkaiXu/GeoLDM
Geometric Latent Diffusion Models for 3D Molecule Generation
caio-freitas/GraphARM
An implementation of the Autoregressive Diffusion Model for Graph Generation from [Kong et al. 2023]
microsoft/foldingdiff
Diffusion models of protein structure; trigonometry and attention are all you need!
Membrizard/ml_conformer_generator
Shape-constrained molecule generation via Equivariant Diffusion and GCN