sanjaradylov/smiles-gpt
Generative Pre-Training from Molecules
This tool helps drug discovery scientists design new molecules by learning patterns from existing molecular structures. It takes a large collection of SMILES strings (a text representation of molecules) as input and generates new, diverse molecular structures, or can be fine-tuned to predict specific properties of molecules. Medicinal chemists and researchers in drug design would use this to accelerate the discovery of new therapeutic compounds.
No commits in the last 6 months.
Use this if you need to generate novel molecular structures for drug discovery or predict properties of existing molecules from SMILES data.
Not ideal if you are working with 3D molecular structures or require high-throughput screening of a very large chemical space without any prior learning.
Stars
23
Forks
9
Language
Jupyter Notebook
License
BSD-3-Clause-Clear
Category
Last pushed
Apr 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sanjaradylov/smiles-gpt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rxn4chemistry/rxn-onmt-models
Training of OpenNMT-based RXN models
CTCycle/ADSMOD-Adsorption-Modeling
Streamline adsorption modeling by automatically fitting theoretical adsorption models to...
lamalab-org/MatText
Text-based modeling of materials.
VectorInstitute/atomgen
Library for handling atomistic graph datasets focusing on transformer-based implementations,...
mikemayuare/apetokenizer
Tokenizer for chemnical SMILES and SELFIES for use in transformers models.