Inverse-fold proteins with the SolubleMPNN model to optimize solubility.
npx skills add https://github.com/PKU-YuanGroup/OpenAI4S --skill solublempnn-pku-yuangroup
Please help me install this Agent Skill. Skill: solublempnn Source: https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/solublempnn Command: npx skills add https://github.com/PKU-YuanGroup/OpenAI4S --skill solublempnn-pku-yuangroup
This Skill enables the inverse-folding of proteins with improved solubility using a retrained SolubleMPNN model, addressing issues with aggregation and inclusion bodies.
To run the solublempnn skill, use the following command:
pip install torch numpy # if not already present
git clone --depth 1 https://github.com/dauparas/ProteinMPNN.git proteinmpnn
cd proteinmpnn
python protein_mpnn_run.py \
--pdb_path backbone.pdb --pdb_path_chains "A" \
--out_folder out --num_seq_per_target 16 \
--sampling_temp "0.1" --use_soluble_model
High-intent search queries and answers about installing and using this skill.
To optimize protein structures for soluble expression and reduce aggregation, you can use inverse folding with a retrained SolubleMPNN model. This approach addresses inclusion body issues by predicting sequences optimized for solubility.
Inverse folding for soluble proteins is the process of designing protein sequences from a backbone structure using a model trained on soluble PDB subsets. Use it when redesigning membrane-adjacent folds or preparing E. coli expression screens.
To run soluble protein folding, clone the ProteinMPNN repository, ensure PyTorch and NumPy are installed, and execute the run script with the --use_soluble_model flag along with your target PDB path and sampling parameters.
Yes, you can use this inverse folding model for E. coli expression screens. It is specifically designed to predict more soluble protein structures, making it ideal for preparing sequences before expression screening.
Yes, the soluble MPNN model requires cloning the ProteinMPNN library from its official repository. You must also have PyTorch and NumPy installed to execute the inverse folding and solubility optimization scripts.
Protein sequences result in inclusion bodies during expression when they are prone to aggregation. Using a retrained SolubleMPNN model for inverse folding can redesign the sequence to improve solubility and prevent aggregation.
PKU-YuanGroupConverts PDF documents to clean, structured Markdown.
adaptyvbioDesign solubility-optimized protein sequences for given backbones using soluble model weights.
zongtingweiDesign solubility-optimized protein sequences for a given backbone using SolubleMPNN.
junior1pGenerate solubility-optimized protein sequences using SolubleMPNN workflows.