thrumbel commited on
Commit
1e5470a
1 Parent(s): 82b26f3

Push model using huggingface_hub.

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
  **SmallMoleculeMultiView**, multi-view molecular foundation model.
16
 
17
  - **Developers:** IBM Research
18
- - **GitHub Repository:** [https://github.com/BiomedSciAI/biomed.multi-view](https://github.com/BiomedSciAI/biomed.multi-view)
19
  - **Paper:** [Multi-view biomedical foundation models for molecule-target and property prediction](https://arxiv.org/abs/TBD)
20
  - **Release Date**: Oct 29th, 2024
21
  - **License:** [apache-2.0](https://www.apache.org/licenses/LICENSE-2.0).
@@ -24,9 +24,9 @@ tags:
24
 
25
  This model contains the implementation of the Multi-view Molecular Embedding with Late Fusion (MMELON) architecture. MMELON combines molecular representations from three views — image, 2-dimensional chemically-bonded graph, and text (SMILES) —to learn a joint embedding that can be finetuned for downstream tasks in chemical and biological property prediction.
26
 
27
- It was introduced in the paper [Multi-view biomedical foundation models for molecule-target and property prediction](https://arxiv.org/) by authors and first released in [this repository](https://github.com/BiomedSciAI/biomed.multi-view).
28
 
29
- ![SmallMoleculeMultiView Overview](https://github.com/BiomedSciAI/biomed.multi-view/docs/overview.png)
30
 
31
  * Image Representation: Captures the 2D visual depiction of molecular structures, highlighting features like symmetry, bond angles, and functional groups. Molecular images are generated using RDKit and undergo data augmentation during training to enhance robustness.
32
  * Graph Representation: Encodes molecules as undirected graphs where nodes represent atoms and edges represent bonds. Atom-specific properties (e.g., atomic number, chirality) and bond-specific properties (e.g., bond type, stereochemistry) are embedded using categorical embedding techniques.
@@ -37,7 +37,7 @@ The embeddings from these single-view pre-trained encoders are combined using an
37
 
38
  ## Usage
39
 
40
- Using `SmallMoleculeMultiView` requires [https://github.com/BiomedSciAI/biomed.multi-view](https://github.com/BiomedSciAI/biomed.multi-view)
41
 
42
  ## Installation
43
  Follow these steps to set up the `biomed.multi-view` codebase on your system.
@@ -86,14 +86,14 @@ mkdir -p $ROOT_DIR/code
86
  cd $ROOT_DIR/code
87
 
88
  # Clone the repository using HTTPS
89
- git clone https://github.com/BiomedSciAI/biomed.multi-view.git
90
 
91
  # Navigate into the cloned repository
92
  cd biomed.multi-view
93
  ```
94
  Note: If you prefer using SSH, ensure that your SSH keys are set up with GitHub and use the following command:
95
  ```bash
96
- git clone git@github.com:BiomedSciAI/biomed.multi-view.git
97
  ```
98
 
99
  #### Step 5: Install package dependencies
@@ -186,7 +186,7 @@ print("Prediction:", prediction)
186
  Prediction: {'prediction': [0.85], 'label': None}
187
  ```
188
 
189
- For more advanced usage, see our detailed examples at: https://github.com/BiomedSciAI/biomed.multi-view
190
 
191
 
192
  ## Citation
 
15
  **SmallMoleculeMultiView**, multi-view molecular foundation model.
16
 
17
  - **Developers:** IBM Research
18
+ - **GitHub Repository:** [https://github.com/BiomedSciAI/biomed-multi-view](https://github.com/BiomedSciAI/biomed-multi-view)
19
  - **Paper:** [Multi-view biomedical foundation models for molecule-target and property prediction](https://arxiv.org/abs/TBD)
20
  - **Release Date**: Oct 29th, 2024
21
  - **License:** [apache-2.0](https://www.apache.org/licenses/LICENSE-2.0).
 
24
 
25
  This model contains the implementation of the Multi-view Molecular Embedding with Late Fusion (MMELON) architecture. MMELON combines molecular representations from three views — image, 2-dimensional chemically-bonded graph, and text (SMILES) —to learn a joint embedding that can be finetuned for downstream tasks in chemical and biological property prediction.
26
 
27
+ It was introduced in the paper [Multi-view biomedical foundation models for molecule-target and property prediction](https://arxiv.org/) by authors and first released in [this repository](https://github.com/BiomedSciAI/biomed-multi-view).
28
 
29
+ ![SmallMoleculeMultiView Overview](https://github.com/BiomedSciAI/biomed-multi-view/docs/overview.png)
30
 
31
  * Image Representation: Captures the 2D visual depiction of molecular structures, highlighting features like symmetry, bond angles, and functional groups. Molecular images are generated using RDKit and undergo data augmentation during training to enhance robustness.
32
  * Graph Representation: Encodes molecules as undirected graphs where nodes represent atoms and edges represent bonds. Atom-specific properties (e.g., atomic number, chirality) and bond-specific properties (e.g., bond type, stereochemistry) are embedded using categorical embedding techniques.
 
37
 
38
  ## Usage
39
 
40
+ Using `SmallMoleculeMultiView` requires [https://github.com/BiomedSciAI/biomed-multi-view](https://github.com/BiomedSciAI/biomed-multi-view)
41
 
42
  ## Installation
43
  Follow these steps to set up the `biomed.multi-view` codebase on your system.
 
86
  cd $ROOT_DIR/code
87
 
88
  # Clone the repository using HTTPS
89
+ git clone https://github.com/BiomedSciAI/biomed-multi-view.git
90
 
91
  # Navigate into the cloned repository
92
  cd biomed.multi-view
93
  ```
94
  Note: If you prefer using SSH, ensure that your SSH keys are set up with GitHub and use the following command:
95
  ```bash
96
+ git clone git@github.com:BiomedSciAI/biomed-multi-view.git
97
  ```
98
 
99
  #### Step 5: Install package dependencies
 
186
  Prediction: {'prediction': [0.85], 'label': None}
187
  ```
188
 
189
+ For more advanced usage, see our detailed examples at: https://github.com/BiomedSciAI/biomed-multi-view
190
 
191
 
192
  ## Citation