Docs | Tutorials | Benchmarks | Papers Implemented

TorchDrug is a PyTorch-based machine learning toolbox designed for several purposes.

• Easy implementation of graph operations in a PyTorchic style with GPU support
• Being friendly to practitioners with minimal knowledge about drug discovery
• Rapid prototyping of machine learning research

TorchDrug can be installed on either Linux, Windows or macOS. It is compatible with 3.7 <= Python <= 3.10 and PyTorch >= 1.8.0.

conda install torchdrug -c milagraph -c conda-forge -c pytorch -c pyg

pip install torch==1.9.0 pip install torch-scatter torch-cluster -f https://pytorch-geometric.com/whl/torch-1.9.0+cu102.html pip install torchdrug

To install torch-scatter for other PyTorch or CUDA versions, please see the instructions in https://github.com/rusty1s/pytorch_scatter

git clone https://github.com/DeepGraphLearning/torchdrug cd torchdrug pip install -r requirements.txt python setup.py install

We need to first install the build tools for Visual Studio. We then install the following modules in PowerShell.

Install-Module Pscx -AllowClobber Install-Module VSSetup

Initialize Visual Studio in PowerShell with the following commands. We may setup this for all PowerShell sessions by writing it to the PowerShell profile. Change the library path according to your own case.

Import-VisualStudioVars-Architecture x64 $env:LIB+=";C:\Program Files\Python37\libs"

We need PyTorch >= 1.13 to run TorchDrug on Apple silicon. For torch-scatter and torch-cluster, they can be compiled from their sources. Note TorchDrug doesn't support mps devices.

pip install torch==1.13.0 pip install git+https://github.com/rusty1s/pytorch_scatter.git pip install git+https://github.com/rusty1s/pytorch_cluster.git pip install torchdrug

TorchDrug is designed for humans and focused on graph structured data. It enables easy implementation of graph operations in machine learning models. All the operations in TorchDrug are backed by PyTorch framework, and support GPU acceleration and auto differentiation.

fromtorchdrugimportdataedge_list= [[0, 1], [1, 2], [2, 3], [3, 4], [4, 5], [5, 0]] graph=data.Graph(edge_list, num_node=6) graph=graph.cuda() # the subgraph induced by nodes 2, 3 & 4subgraph=graph.subgraph([2, 3, 4])

Molecules are also supported in TorchDrug. You can get the desired molecule properties without any domain knowledge.

mol=data.Molecule.from_smiles("CCOC(=O)N", atom_feature="default", bond_feature="default") print(mol.node_feature) print(mol.atom_type) print(mol.to_scaffold())

You may also register custom node, edge or graph attributes. They will be automatically processed during indexing operations.

withmol.edge(): mol.is_CC_bond= (mol.edge_list[:, :2] ==td.CARBON).all(dim=-1) sub_mol=mol.subgraph(mol.atom_type!=td.NITROGEN) print(sub_mol.is_CC_bond)

TorchDrug provides a wide range of common datasets and building blocks for drug discovery. With minimal code, you can apply standard models to solve your own problem.

importtorchfromtorchdrugimportdatasetsdataset=datasets.Tox21() dataset[0].visualize() lengths= [int(0.8*len(dataset)), int(0.1*len(dataset))] lengths+= [len(dataset) -sum(lengths)] train_set, valid_set, test_set=torch.utils.data.random_split(dataset, lengths)

fromtorchdrugimportmodels, tasksmodel=models.GIN(dataset.node_feature_dim, hidden_dims=[256, 256, 256, 256]) task=tasks.PropertyPrediction(model, task=dataset.tasks)

Training and inference are accelerated by multiple CPUs or GPUs. This can be seamlessly switched in TorchDrug by just a line of code.

fromtorchdrugimportcore# Single CPU / Multiple CPUs / Distributed CPUssolver=core.Engine(task, train_set, valid_set, test_set, optimizer) # Single GPUsolver=core.Engine(task, train_set, valid_set, test_set, optimizer, gpus=[0]) # Multiple GPUssolver=core.Engine(task, train_set, valid_set, test_set, optimizer, gpus=[0, 1, 2, 3]) # Distributed GPUssolver=core.Engine(task, train_set, valid_set, test_set, optimizer, gpus=[0, 1, 2, 3, 0, 1, 2, 3])

Experiments can be easily tracked and managed through Weights & Biases platform.

solver=core.Engine(task, train_set, valid_set, test_set, optimizer, logger="wandb")

Everyone is welcome to contribute to the development of TorchDrug. Please refer to contributing guidelines for more details.

TorchDrug is released under Apache-2.0 License.