Skip to content

GitLab

Unverified Commit 3f0c1005 authored by Mufei Li's avatar Mufei Li Committed by GitHub
Browse files

[DGL-LifeSci] Fix broken links (#1248) 

* Fix

* Update
parent 77ae4d53
Hide whitespace changes
Inline Side-by-side
Showing with 38 additions and 46 deletions
apps/life_sci/README.md
View file @ 3f0c1005
...@@ -117,7 +117,7 @@ for i in range(4): ...@@ -117,7 +117,7 @@ for i in range(4):
SVG(Draw.MolsToGridImage(mols, molsPerRow=4, subImgSize=(180, 150), useSVG=True)) SVG(Draw.MolsToGridImage(mols, molsPerRow=4, subImgSize=(180, 150), useSVG=True))
``` ```
![](https://s3.us-east-2.amazonaws.com/dgl-data/model_zoo/drug_discovery/dgmg_model_zoo_example2.png) ![](https://data.dgl.ai/dgllife/dgmg/dgmg_model_zoo_example2.png)
## Speed Reference ## Speed Reference
......
apps/life_sci/examples/generative_models/dgmg/README.md
View file @ 3f0c1005
...@@ -83,7 +83,7 @@ You can also use your own dataset with additional arguments ...@@ -83,7 +83,7 @@ You can also use your own dataset with additional arguments
We can monitor the training process with tensorboard as below: We can monitor the training process with tensorboard as below:
![](https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/dgmg/tensorboard.png) ![](https://data.dgl.ai/dgllife/dgmg/tensorboard.png)
To use tensorboard, you need to install [tensorboardX](https://github.com/lanpa/tensorboardX) and To use tensorboard, you need to install [tensorboardX](https://github.com/lanpa/tensorboardX) and
[TensorFlow](https://www.tensorflow.org/). You can lunch tensorboard with `tensorboard --logdir=.` [TensorFlow](https://www.tensorflow.org/). You can lunch tensorboard with `tensorboard --logdir=.`
...@@ -124,15 +124,13 @@ directory, with three statistics logged in `generation_stats.txt` under `eval_re ...@@ -124,15 +124,13 @@ directory, with three statistics logged in `generation_stats.txt` under `eval_re
We also provide a jupyter notebook where you can visualize the generated molecules We also provide a jupyter notebook where you can visualize the generated molecules
![](https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/dgmg/DGMG_ZINC_canonical_vis.png) ![](https://data.dgl.ai/dgllife/dgmg/DGMG_ZINC_canonical_vis.png)
and compare their property distributions against the training molecule property distributions and compare their property distributions against the training molecule property distributions
![](https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/dgmg/DGMG_ZINC_canonical_dist.png) ![](https://data.dgl.ai/dgllife/dgmg/DGMG_ZINC_canonical_dist.png)
Download it with `wget https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/dgmg/eval_jupyter.ipynb` from the s3 You can download the notebook with `wget https://data.dgl.ai/dgllife/dgmg/eval_jupyter.ipynb`.
bucket in U.S. or `wget https://s3.cn-north-1.amazonaws.com.cn/dgl-data/dgllife/dgmg/eval_jupyter.ipynb` from the
s3 bucket in China.
### Pre-trained models ### Pre-trained models
......
apps/life_sci/examples/generative_models/jtnn/README.md
View file @ 3f0c1005
...@@ -89,10 +89,7 @@ Below gives the statistics of pre-trained `JTNN_ZINC` model. ...@@ -89,10 +89,7 @@ Below gives the statistics of pre-trained `JTNN_ZINC` model.
### Visualization ### Visualization
Here we draw some "neighbor" of a given molecule, by adding noises on the intermediate representations. Here we draw some "neighbor" of a given molecule, by adding noises on the intermediate representations.
You can download the script with `https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/jtnn_viz_neighbor_mol.ipynb` from the s3 You can download the script with `wget https://data.dgl.ai/dgllife/jtnn_viz_neighbor_mol.ipynb`.
bucket in U.S. or `https://s3.cn-north-1.amazonaws.com.cn/dgl-data/dgllife/jtnn_viz_neighbor_mol.ipynb` from the s3 bucket
in mainland China.
Please put this script at the current directory (`examples/pytorch/model_zoo/chem/generative_models/jtnn/`). Please put this script at the current directory (`examples/pytorch/model_zoo/chem/generative_models/jtnn/`).
#### Given Molecule #### Given Molecule
......
apps/life_sci/examples/property_prediction/README.md
View file @ 3f0c1005
...@@ -113,12 +113,9 @@ Note that the dataset is randomly split so this number is only for reference. ...@@ -113,12 +113,9 @@ Note that the dataset is randomly split so this number is only for reference.
[8] visualizes the weights of atoms in readout for possible interpretations like the figure below. [8] visualizes the weights of atoms in readout for possible interpretations like the figure below.
We provide a jupyter notebook for performing the visualization and you can download it with We provide a jupyter notebook for performing the visualization and you can download it with
`wget https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/attentive_fp/atom_weight_visualization.ipynb` `wget https://data.dgl.ai/dgllife/attentive_fp/atom_weight_visualization.ipynb`.
from the s3 bucket in U.S. or
`wget https://s3.cn-north-1.amazonaws.com.cn/dgl-data/dgllife/attentive_fp/atom_weight_visualization.ipynb`
from the s3 bucket in China.
![](https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/attentive_fp_vis_example.png) ![](https://data.dgl.ai/dgllife/attentive_fp_vis_example.png)
## Dataset Customization ## Dataset Customization
......
apps/life_sci/implemented.md
View file @ 3f0c1005
...@@ -3,43 +3,43 @@ ...@@ -3,43 +3,43 @@
## Datasets/Benchmarks ## Datasets/Benchmarks
- MoleculeNet: A Benchmark for Molecular Machine Learning [[paper]](https://arxiv.org/abs/1703.00564), [[website]](http://moleculenet.ai/) - MoleculeNet: A Benchmark for Molecular Machine Learning [[paper]](https://arxiv.org/abs/1703.00564), [[website]](http://moleculenet.ai/)
- [Tox21 with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/data/tox21.py) - [Tox21 with DGL](dgllife/data/tox21.py)
- [PDBBind with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/data/pdbbind.py) - [PDBBind with DGL](dgllife/data/pdbbind.py)
- Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models [[paper]](https://arxiv.org/abs/1906.09427), [[github]](https://github.com/tencent-alchemy/Alchemy) - Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models [[paper]](https://arxiv.org/abs/1906.09427), [[github]](https://github.com/tencent-alchemy/Alchemy)
- [Alchemy with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/data/alchemy.py) - [Alchemy with DGL](dgllife/data/alchemy.py)
## Property Prediction ## Property Prediction
- Semi-Supervised Classification with Graph Convolutional Networks (GCN) [[paper]](https://arxiv.org/abs/1609.02907), [[github]](https://github.com/tkipf/gcn) - Semi-Supervised Classification with Graph Convolutional Networks (GCN) [[paper]](https://arxiv.org/abs/1609.02907), [[github]](https://github.com/tkipf/gcn)
- [GCN-Based Predictor with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/gcn_predictor.py) - [GCN-Based Predictor with DGL](dgllife/model/model_zoo/gcn_predictor.py)
- [Example for Molecule Classification](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/property_prediction/classification.py) - [Example for Molecule Classification](examples/property_prediction/classification.py)
- Graph Attention Networks (GAT) [[paper]](https://arxiv.org/abs/1710.10903), [[github]](https://github.com/PetarV-/GAT) - Graph Attention Networks (GAT) [[paper]](https://arxiv.org/abs/1710.10903), [[github]](https://github.com/PetarV-/GAT)
- [GAT-Based Predictor with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/gat_predictor.py) - [GAT-Based Predictor with DGL](dgllife/model/model_zoo/gat_predictor.py)
- [Example for Molecule Classification](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/property_prediction/classification.py) - [Example for Molecule Classification](examples/property_prediction/classification.py)
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions [[paper]](https://arxiv.org/abs/1706.08566), [[github]](https://github.com/atomistic-machine-learning/SchNet) - SchNet: A continuous-filter convolutional neural network for modeling quantum interactions [[paper]](https://arxiv.org/abs/1706.08566), [[github]](https://github.com/atomistic-machine-learning/SchNet)
- [SchNet with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/schnet_predictor.py) - [SchNet with DGL](dgllife/model/model_zoo/schnet_predictor.py)
- [Example for Molecule Regression](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/property_prediction/regression.py) - [Example for Molecule Regression](examples/property_prediction/regression.py)
- Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective (MGCN) [[paper]](https://arxiv.org/abs/1906.11081) - Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective (MGCN) [[paper]](https://arxiv.org/abs/1906.11081)
- [MGCN with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/mgcn_predictor.py) - [MGCN with DGL](dgllife/model/model_zoo/mgcn_predictor.py)
- [Example for Molecule Regression](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/property_prediction/regression.py) - [Example for Molecule Regression](examples/property_prediction/regression.py)
- Neural Message Passing for Quantum Chemistry (MPNN) [[paper]](https://arxiv.org/abs/1704.01212), [[github]](https://github.com/brain-research/mpnn) - Neural Message Passing for Quantum Chemistry (MPNN) [[paper]](https://arxiv.org/abs/1704.01212), [[github]](https://github.com/brain-research/mpnn)
- [MPNN with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/mpnn_predictor.py) - [MPNN with DGL](dgllife/model/model_zoo/mpnn_predictor.py)
- [Example for Molecule Regression](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/property_prediction/regression.py) - [Example for Molecule Regression](examples/property_prediction/regression.py)
- Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism (AttentiveFP) [[paper]](https://pubs.acs.org/doi/abs/10.1021/acs.jmedchem.9b00959) - Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism (AttentiveFP) [[paper]](https://pubs.acs.org/doi/abs/10.1021/acs.jmedchem.9b00959)
- [AttentiveFP with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/attentivefp_predictor.py) - [AttentiveFP with DGL](dgllife/model/model_zoo/attentivefp_predictor.py)
- [Example for Molecule Regression](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/property_prediction/regression.py) - [Example for Molecule Regression](examples/property_prediction/regression.py)
## Generative Models ## Generative Models
- Learning Deep Generative Models of Graphs (DGMG) [[paper]](https://arxiv.org/abs/1803.03324) - Learning Deep Generative Models of Graphs (DGMG) [[paper]](https://arxiv.org/abs/1803.03324)
- [DGMG with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/dgmg.py) - [DGMG with DGL](dgllife/model/model_zoo/dgmg.py)
- [Example Training Script](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/generative_models/dgmg) - [Example Training Script](examples/generative_models/dgmg)
- Junction Tree Variational Autoencoder for Molecular Graph Generation (JTNN) [[paper]](https://arxiv.org/abs/1802.04364) - Junction Tree Variational Autoencoder for Molecular Graph Generation (JTNN) [[paper]](https://arxiv.org/abs/1802.04364)
- [JTNN with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/jtnn) - [JTNN with DGL](dgllife/model/model_zoo/jtnn)
- [Example Training Script](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/generative_models/jtnn) - [Example Training Script](examples/generative_models/jtnn)
## Binding Affinity Prediction ## Binding Affinity Prediction
- Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity (ACNN) [[paper]](https://arxiv.org/abs/1703.10603), [[github]](https://github.com/deepchem/deepchem/tree/master/contrib/atomicconv) - Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity (ACNN) [[paper]](https://arxiv.org/abs/1703.10603), [[github]](https://github.com/deepchem/deepchem/tree/master/contrib/atomicconv)
- [ACNN with DGL](https://github.com/dmlc/dgl/tree/master/apps/life_sci/dglls/model/model_zoo/acnn.py) - [ACNN with DGL](dgllife/model/model_zoo/acnn.py)
- [Example Training Script](https://github.com/dmlc/dgl/tree/master/apps/life_sci/examples/binding_affinity_prediction) - [Example Training Script](examples/binding_affinity_prediction)
examples/pytorch/jtnn/jtnn/datautils.py
View file @ 3f0c1005
...@@ -27,7 +27,7 @@ class JTNNDataset(Dataset): ...@@ -27,7 +27,7 @@ class JTNNDataset(Dataset):
self.dir = get_download_dir() self.dir = get_download_dir()
self.zip_file_path='{}/jtnn.zip'.format(self.dir) self.zip_file_path='{}/jtnn.zip'.format(self.dir)
download(_get_dgl_url('dglls/jtnn.zip'), path=self.zip_file_path) download(_get_dgl_url('dgllife/jtnn.zip'), path=self.zip_file_path)
extract_archive(self.zip_file_path, '{}/jtnn'.format(self.dir)) extract_archive(self.zip_file_path, '{}/jtnn'.format(self.dir))
print('Loading data...') print('Loading data...')
data_file = '{}/jtnn/{}.txt'.format(self.dir, data) data_file = '{}/jtnn/{}.txt'.format(self.dir, data)
......
examples/pytorch/model_zoo/chem/README.md
View file @ 3f0c1005
...@@ -129,7 +129,7 @@ for i in range(4): ...@@ -129,7 +129,7 @@ for i in range(4):
SVG(Draw.MolsToGridImage(mols, molsPerRow=4, subImgSize=(180, 150), useSVG=True)) SVG(Draw.MolsToGridImage(mols, molsPerRow=4, subImgSize=(180, 150), useSVG=True))
``` ```
![](https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/dgmg_model_zoo_example2.png) ![](https://data.dgl.ai/dgllife/dgmg/dgmg_model_zoo_example2.png)
## Binding affinity prediction ## Binding affinity prediction
......
examples/pytorch/model_zoo/chem/generative_models/dgmg/README.md
View file @ 3f0c1005
...@@ -83,7 +83,7 @@ You can also use your own dataset with additional arguments ...@@ -83,7 +83,7 @@ You can also use your own dataset with additional arguments
We can monitor the training process with tensorboard as below: We can monitor the training process with tensorboard as below:
![](https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/dgmg/tensorboard.png) ![](https://data.dgl.ai/dgllife/dgmg/tensorboard.png)
To use tensorboard, you need to install [tensorboardX](https://github.com/lanpa/tensorboardX) and To use tensorboard, you need to install [tensorboardX](https://github.com/lanpa/tensorboardX) and
[TensorFlow](https://www.tensorflow.org/). You can lunch tensorboard with `tensorboard --logdir=.` [TensorFlow](https://www.tensorflow.org/). You can lunch tensorboard with `tensorboard --logdir=.`
...@@ -130,9 +130,7 @@ and compare their property distributions against the training molecule property ...@@ -130,9 +130,7 @@ and compare their property distributions against the training molecule property
![](https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/dgmg/DGMG_ZINC_canonical_dist.png) ![](https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/dgmg/DGMG_ZINC_canonical_dist.png)
Download it with `wget https://s3.us-west-2.amazonaws.com/dgl-data/dglls/dgmg/eval_jupyter.ipynb` from the s3 You can download the notebook with `wget https://data.dgl.ai/dgllife/dgmg/eval_jupyter.ipynb`.
bucket in U.S. or `wget https://s3.cn-north-1.amazonaws.com.cn/dgl-data/dglls/dgmg/eval_jupyter.ipynb` from the
s3 bucket in China.
### Pre-trained models ### Pre-trained models
......
examples/pytorch/model_zoo/chem/generative_models/jtnn/README.md
View file @ 3f0c1005
...@@ -88,7 +88,9 @@ Below gives the statistics of pre-trained `JTNN_ZINC` model. ...@@ -88,7 +88,9 @@ Below gives the statistics of pre-trained `JTNN_ZINC` model.
### Visualization ### Visualization
Here we draw some "neighbor" of a given molecule, by adding noises on the intermediate representations. Detailed script can be found [here](https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/jtnn/viz_neighbor_mol.ipynb). Please put this script at the current directory (`examples/pytorch/model_zoo/chem/generative_models/jtnn/`). Here we draw some "neighbor" of a given molecule, by adding noises on the intermediate representations.
You can download the script with `wget https://data.dgl.ai/dgllife/jtnn_viz_neighbor_mol.ipynb`.
Please put this script at the current directory (`examples/pytorch/model_zoo/chem/generative_models/jtnn/`).
#### Given Molecule #### Given Molecule
![image](https://user-images.githubusercontent.com/8686776/63773593-0d37da00-c90e-11e9-8933-0abca4b430db.png) ![image](https://user-images.githubusercontent.com/8686776/63773593-0d37da00-c90e-11e9-8933-0abca4b430db.png)
......
examples/pytorch/model_zoo/chem/generative_models/jtnn/jtnn/datautils.py
View file @ 3f0c1005
...@@ -32,7 +32,7 @@ class JTNNDataset(Dataset): ...@@ -32,7 +32,7 @@ class JTNNDataset(Dataset):
def __init__(self, data, vocab, training=True): def __init__(self, data, vocab, training=True):
self.dir = get_download_dir() self.dir = get_download_dir()
self.zip_file_path='{}/jtnn.zip'.format(self.dir) self.zip_file_path='{}/jtnn.zip'.format(self.dir)
download(_get_dgl_url('dglls/jtnn.zip'), path=self.zip_file_path) download(_get_dgl_url('dgllife/jtnn.zip'), path=self.zip_file_path)
extract_archive(self.zip_file_path, '{}/jtnn'.format(self.dir)) extract_archive(self.zip_file_path, '{}/jtnn'.format(self.dir))
print('Loading data...') print('Loading data...')
if data in ['train', 'test']: if data in ['train', 'test']:
......
examples/pytorch/model_zoo/chem/property_prediction/README.md
View file @ 3f0c1005
...@@ -113,7 +113,7 @@ on the training and validation set for reference. ...@@ -113,7 +113,7 @@ on the training and validation set for reference.
We provide a jupyter notebook for performing the visualization and you can download it with We provide a jupyter notebook for performing the visualization and you can download it with
`wget https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/AttentiveFP/atom_weight_visualization.ipynb`. `wget https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/AttentiveFP/atom_weight_visualization.ipynb`.
![](https://s3.us-east-2.amazonaws.com/dgl.ai/model_zoo/drug_discovery/AttentiveFP/vis_example.png) ![](https://s3.us-west-2.amazonaws.com/dgl-data/dgllife/attentive_fp_vis_example.png)
## Dataset Customization ## Dataset Customization
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment