HySonLab/Protein_Pretrain
Multimodal Pretraining for Unsupervised Protein Representation Learning
This project helps biological researchers and computational chemists better understand proteins by generating rich, unified computational representations. It takes raw protein sequence data and 3D structural information (like from Swiss-Prot or AlphaFold) and processes it into advanced representations. These representations can then be used to predict protein-ligand binding, classify protein folds, identify enzymes, or assess mutation stability. It is intended for researchers working in molecular biology, drug discovery, and bioinformatics.
No commits in the last 6 months.
Use this if you need to generate comprehensive, data-driven representations of proteins to improve predictions for their function, stability, or interactions.
Not ideal if you primarily work with experimental protein data and do not need computational modeling or predictive analysis.
Stars
22
Forks
2
Language
Python
License
—
Category
Last pushed
Jul 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HySonLab/Protein_Pretrain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xianglin226/Benchmarking-Single-Cell-Perturbation
Single-Cell (Perturbation) Model Library
tirtharajdash/LMLFStar
Generating target-specific novel lead molecules using an LLM
raghavagps/pptstab
PPTStab: Designing of thermostable proteins with a desired melting temperature
CelVoxes/ceLLama
Cell type annotation with local Large Language Models (LLMs) - Ensuring privacy and speed with...
kenflab/LLM-scCurator
Data-centric marker distillation for zero-shot cell-type and spatial annotation with LLMs.