https://github.com/bioinfomachinelearning/tulip
Template-based modeling for accurate prediction of ligand-protein complex structures (TULIP)
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.6%) to scientific vocabulary
Repository
Template-based modeling for accurate prediction of ligand-protein complex structures (TULIP)
Basic Info
- Host: GitHub
- Owner: BioinfoMachineLearning
- Language: Python
- Default Branch: main
- Size: 14.4 MB
Statistics
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
TULIP
The template-based modeling for accurate ligand-protein complex structure prediction (TULIP).
Input : Query protein, Ligand molecule (.smiles ), Protein Template Hits
Output : .sdf file of ligand molecule that potentially binds to input query protein
Setup Environment
- The required packages are found in
environment.yml
conda env create -f environment.yml
- Once the installation is completed, activate the conda environment
conda activate tulip
- The pipeline makes use of UCSF Chimera and PyRosetta. Please install them through their websites
UCSF Chimera Download , this link will take users to: https://www.cgl.ucsf.edu/chimera/download.html
PyRosetta Download , this link will take users to: https://www.pyrosetta.org/downloads
To adjust the target ligand's binding pose and orientation by rotation and translation, TULIP uses LS-align to align the target ligand with template ligands of higher similarity by both flexible and rigid alignments.
The LS-align tool can be downloaded and compiled into local machine from the below link:
LS-align , this link will take users to: https://zhanggroup.org/LS-align/
Run
To run TULIP pipeline run the following:
git clone https://github.com/BioinfoMachineLearning/tulip.git
cd ProteinLigand
python3 complex_generator.py --config=../configs/configs.yml
configs/configs.yml contains the configuration of the pipeline. Enter the correct paths in config file.
Post Processing
Once the ligand templates are identified using the above script, use the script below to run the post-processing for multi-atom ligands. Update the ls_align_path variable in the script to the path where LS-align is installed.
python3 post_process.py
For ions and small molecules run:
python3 process_small_mol.py
Clustering
To perform clustering in case we have same ligand SMILES for a protein.
python3 cluster_files.py
Outputs
TULIP returns the identified ligand molecules in ranks. Example : rank_0.sdf, rank_1.sdf, and so on for each protein.
Owner
- Name: BioinfoMachineLearning
- Login: BioinfoMachineLearning
- Kind: organization
- Repositories: 29
- Profile: https://github.com/BioinfoMachineLearning