IBM/regression-transformer
Regression Transformer (2023; Nature Machine Intelligence)
This project helps scientists in chemistry and materials science explore new molecules, proteins, and chemical reactions with desired properties. You input an existing chemical structure (like a small molecule or protein) and specify target property values (e.g., higher solubility, better stability). The system then suggests new chemical structures that are similar to your input but are predicted to have the desired properties. This is for researchers who need to design novel materials or compounds by fine-tuning specific characteristics.
159 stars. No commits in the last 6 months.
Use this if you need to generate new chemical compounds, proteins, or polymers that are optimized for specific properties like solubility, synthesizability, or stability, starting from a known structure.
Not ideal if you need to predict properties for existing structures without generating new ones, or if your domain is outside of chemistry and materials science.
Stars
159
Forks
23
Language
Python
License
MIT
Category
Last pushed
Sep 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IBM/regression-transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in...
kyegomez/LongNet
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
pbloem/former
Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)
NVIDIA/FasterTransformer
Transformer related optimization, including BERT, GPT
kyegomez/SimplifiedTransformers
SimplifiedTransformer simplifies transformer block without affecting training. Skip connections,...