This repository is no longer being maintained and has been archived for historical purposes.
We have now developed DeepRank2, an improved and unified version of DeepRank, DeepRank-GNN, and DeepRank-Mut.
✨ DeepRank2 allows for transformation and storage of 3D representations of both protein-protein interfaces (PPIs) and protein single-residue variants (SRVs) into either graphs or volumetric grids containing structural and physico-chemical information. These can be used for training neural networks for a variety of patterns of interest, using either our pre-implemented training pipeline for graph neural networks (GNNs) or convolutional neural networks (CNNs) or external pipelines.
- 🔧 Pull Requests at github.com/DeepRank/deeprank2/pulls
- 🐛 Bugs: Reports of bugs can be filed agains our new repo github.com/DeepRank/deeprank2/issues
- ⭐ Feature Requests: Add your request or discuss the project w/ the community at github.com/DeepRank/deeprank2/issues
We look forward to seeing you in our new space - DeepRank2!
DeepRank is a general, configurable deep learning framework for data mining protein-protein interactions (PPIs) using 3D convolutional neural networks (CNNs).
DeepRank contains useful APIs for pre-processing PPIs data, computing features and targets, as well as training and testing CNN models.
- Predefined atom-level and residue-level PPI feature types
- e.g. atomic density, vdw energy, residue contacts, PSSM, etc.
- Predefined target types
- e.g. binary class, CAPRI categories, DockQ, RMSD, FNAT, etc.
- Flexible definition of both new features and targets
- 3D grid feature mapping
- Efficient data storage in HDF5 format
- Support both classification and regression (based on PyTorch)
DeepRank requires a Python version 3.7 or 3.8 on Linux and MacOS.
Make sure that mpi4py is installed in your environment before installing deeprank: conda install mpi4py
DeepRank is available in stable releases on PyPI:
- Install the module
pip install deeprank
You can also install the under development source code from the branch development
- Clone the repository
git clone --branch development https://github.com/DeepRank/deeprank.git - Go there
cd deeprank - Install the package
pip install -e ./
To check if installation is successful, you can run a test
- Go into the test directory
cd test - Run the test suite
pytest
We give here the tutorial like introduction to the DeepRank machinery. More informatoin can be found in the documentation http://deeprank.readthedocs.io/en/latest/. We quickly illsutrate here the two main steps of Deeprank:
- the generation of the data
- running deep leaning experiments.
The generation of the data require only require PDBs files of decoys and their native and the PSSM if needed. All the features/targets and mapped features onto grid points will be auomatically calculated and store in a HDF5 file.
from deeprank.generate import *
from mpi4py import MPI
comm = MPI.COMM_WORLD
# let's put this sample script in the test folder, so the working path will be deeprank/test/
# name of the hdf5 to generate
h5file = './hdf5/1ak4.hdf5'
# for each hdf5 file where to find the pdbs
pdb_source = ['./1AK4/decoys/']
# where to find the native conformations
# pdb_native is only used to calculate i-RMSD, dockQ and so on.
# The native pdb files will not be saved in the hdf5 file
pdb_native = ['./1AK4/native/']
# where to find the pssm
pssm_source = './1AK4/pssm_new/'
# initialize the database
database = DataGenerator(
chain1='C', chain2='D',
pdb_source=pdb_source,
pdb_native=pdb_native,
pssm_source=pssm_source,
data_augmentation=0,
compute_targets=[
'deeprank.targets.dockQ',
'deeprank.targets.binary_class'],
compute_features=[
'deeprank.features.AtomicFeature',
'deeprank.features.FullPSSM',
'deeprank.features.PSSM_IC',
'deeprank.features.BSA',
'deeprank.features.ResidueDensity'],
hdf5=h5file,
mpi_comm=comm)
# create the database
# compute features/targets for all complexes
database.create_database(prog_bar=True)
# define the 3D grid
grid_info = {
'number_of_points': [30,30,30],
'resolution': [1.,1.,1.],
'atomic_densities': {'C': 1.7, 'N': 1.55, 'O': 1.52, 'S': 1.8},
}
# Map the features
database.map_features(grid_info,try_sparse=True, time=False, prog_bar=True)This script can be exectuted using for example 4 MPI processes with the command:
NP=4
mpiexec -n $NP python generate.py
In the first part of the script we define the path where to find the PDBs of the decoys and natives that we want to have in the dataset. All the .pdb files present in pdb_source will be used in the dataset. We need to specify where to find the native conformations to be able to compute RMSD and the dockQ score. For each pdb file detected in pdb_source, the code will try to find a native conformation in pdb_native.
We then initialize the DataGenerator object. This object (defined in deeprank/generate/DataGenerator.py) needs a few input parameters:
- pdb_source: where to find the pdb to include in the dataset
- pdb_native: where to find the corresponding native conformations
- compute_targets: list of modules used to compute the targets
- compute_features: list of modules used to compute the features
- hdf5: Name of the HDF5 file to store the data set
We then create the data base with the command database.create_database(). This function autmatically create an HDF5 files where each pdb has its own group. In each group we can find the pdb of the complex and its native form, the calculated features and the calculated targets. We can now mapped the features to a grid. This is done via the command database.map_features(). As you can see this method requires a dictionary as input. The dictionary contains the instruction to map the data.
- number_of_points: the number of points in each direction
- resolution: the resolution in Angs
- atomic_densities: {'atom_name': vvdw_radius} the atomic densities required
The atomic densities are mapped following the protein-ligand paper. The other features are mapped to the grid points using a Gaussian function (other modes are possible but somehow hard coded)
To explore the HDf5 file and vizualize the features you can use the dedicated browser https://github.com/DeepRank/DeepXplorer. This tool saloows to dig through the hdf5 file and to directly generate the files required to vizualie the features in VMD or PyMol. An iPython comsole is also embedded to analyze the feature values, plot them etc ....
The HDF5 files generated above can be used as input for deep learning experiments. You can take a look at the file test/test_learn.py for some examples. We give here a quick overview of the process.
from deeprank.learn import *
from deeprank.learn.model3d import cnn_reg
import torch.optim as optim
import numpy as np
# input database
database = '1ak4.hdf5'
# output directory
out = './my_DL_test/'
# declare the dataset instance
data_set = DataSet(database,
chain1='C',
chain2='D',
grid_info={
'number_of_points': (10, 10, 10),
'resolution': (3, 3, 3)},
select_feature={
'AtomicDensities': {'C': 1.7, 'N': 1.55, 'O': 1.52, 'S': 1.8},
'Features': ['coulomb', 'vdwaals', 'charge', 'PSSM_*']},
select_target='DOCKQ',
normalize_features = True, normalize_targets=True,
pair_chain_feature=np.add,
dict_filter={'DOCKQ':'<1'})
# create the network
model = NeuralNet(data_set,cnn_reg,model_type='3d',task='reg',
cuda=False,plot=True,outdir=out)
# change the optimizer (optional)
model.optimizer = optim.SGD(model.net.parameters(),
lr=0.001,
momentum=0.9,
weight_decay=0.005)
# start the training
model.train(nepoch = 50,divide_trainset=0.8, train_batch_size = 5,num_workers=0)In the first part of the script we create a Torch database from the HDF5 file. We can specify one or several HDF5 files and even select some conformations using the dict_filter argument. Other options of DataSet can be used to specify the features/targets the normalization, etc ...
We then create a NeuralNet instance that takes the dataset as input argument. Several options are available to specify the task to do, the GPU use, etc ... We then have simply to train the model. Simple !
If you have questions or find a bug, please report the issue in the Github issue channel.
If you want to change or further develop DeepRank code, please check the Developer Guideline to see how to conduct further development.