LucaOne/LucaGPLM LucaOne/LucaGPLM The LUCA Gene Protein language model. Installation You can install the package from source using pip: Usage Please refer to the huggingface branch of LucaOne: https://github.com/LucaOne/LucaOne. 1. Feature Extraction/Embedding Extract high dimensional embeddings for downstream analysis or training downstream tasks using LucaOne Embedding. 2. MLM Pre training and Sequence Recovery Continue to perform MLM pre training or sequence recovery. 3. Sequence Classification Predict properties for the entire sequence (e.g., Enzyme vs. Non Enzyme). Supports multi class classification , binary classification , multi label classification , and regression tasks. 4. Token Classification Predict properties for each residue/nucleotide (e.g., Secondary Structure, Binding Sites, and , Post Translational Modifications). Supports multi class classification , binary classification , multi label classification , and regression tasks. Github For long sequence embedding or using LucaOne for downstream tasks, please refer to the git repository: https://github.com/LucaOne/LucaOne, https://github.com/LucaOne/LucaOneTasks
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy