Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

MolE-XGBoost-08.03.2024_14.20.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66874f9019beab0eb02378893c064d63d34df3482f8f6f0495d144597e972d0
+size 10210090

README.md

@@ -0,0 +1,22 @@
+# MolE - Antimicrobial Prediction
+
+This model uses MolE's pre-trained representation to train XGBoost models to predict the antimicrobial activity of compounds based on their molecular structure.
+
+## Files:
+
+- `model.pth` - the pre-trained representation model's weights
+- `config.yaml` - model configuration
+- `MolE-XGBoost-08.03.2024_14.20.pkl` - pretrained XGBoost model
+
+## Usage
+
+Not ready yet.
+
+## Publication
+For more information about MolE, and how we use it to predict antimicrobial activity, you can check out the paper in Nature Communications:  
+[**Pre-trained molecular representations enable antimicrobial discovery**](https://www.nature.com/articles/s41467-025-58804-4) 
+
+## GitHub
+
+The code is available here:
+[**Link to GitHub repo**](https://github.com/rolayoalarcon/mole_antimicrobial_potential)

config.yaml

@@ -0,0 +1,28 @@
+batch_size: 1000                         # batch size
+warm_up: 10                             # warm-up epochs
+epochs: 1000                             # total number of epochs
+
+load_model: None                        # resume training
+eval_every_n_epochs: 1                  # validation frequency
+save_every_n_epochs: 5                  # automatic model saving frequecy
+
+fp16_precision: False                   # float precision 16 (i.e. True/False)
+init_lr: 0.0005                         # initial learning rate for Adam
+weight_decay: 1e-5                      # weight decay for Adam
+gpu: cuda:0                             # training GPU 
+
+model_type: gin_concat                         # GNN backbone (i.e., gin/gcn)
+model: 
+  num_layer: 5                          # number of graph conv layers
+  emb_dim: 200                          # embedding dimension in graph conv layers
+  feat_dim: 8000                          # output feature dimention
+  drop_ratio: 0.0                         # dropout ratio
+  pool: add                            # readout pooling (i.e., mean/max/add)
+
+dataset:
+  num_workers: 50                       # dataloader number of workers
+  valid_size: 0.1                      # ratio of validation data
+  data_path: data/pubchem_data/pubchem_100k_random.txt # path of pre-training data
+
+loss:
+  l: 0.0001 # Lambda parameter

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d324644c5f43e7be6734a9cd7a7966f975bfcc113610c13be897d11674defd8
+size 803807667