Instructions to use OneScience-Group/Antibody_deep_learning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use OneScience-Group/Antibody_deep_learning with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy) # See https://github.com/keras-team/tf-keras for more details. from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("OneScience-Group/Antibody_deep_learning") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_name": "Antibody Deep Learning", | |
| "framework": "TensorFlow", | |
| "task": "antibody-binder-prediction-and-cdr3-generation", | |
| "description": "Predict CTLA-4 and PD-1 antibody binders with CNN models and generate synthetic CDR3K/CDR3H antibody sequences with GAN models.", | |
| "entry_points": { | |
| "prepare_data": "scripts/01_prepare_data_compat.R", | |
| "cnn_inference": "scripts/02_cnn_inference.R", | |
| "gan_inference": "scripts/03_gan_inference.R", | |
| "export_cnn_npz": "scripts/04_export_cnn_npz.R", | |
| "train_cnn": "scripts/05_train_cnn.py", | |
| "export_gan_npz": "scripts/06_export_gan_npz.R", | |
| "train_gan": "scripts/07_train_gan.py", | |
| "generate_from_trained_gan": "scripts/08_generate_from_trained_gan.py" | |
| }, | |
| "source_package": "model", | |
| "config": "conf/config.json", | |
| "data": { | |
| "blosum62": "model/BLOSUM62_with_deletion.Rdata", | |
| "cnn_raw": "model/CNN/all_ab_pre_post.txt", | |
| "cnn_preprocessed": [ | |
| "model/CNN/c1.RDS", | |
| "model/CNN/c1_train.RDS", | |
| "model/CNN/c1_train_y.RDS", | |
| "model/CNN/c1_test.RDS", | |
| "model/CNN/c1_test_y.RDS", | |
| "model/CNN/p1.RDS", | |
| "model/CNN/p1_train.RDS", | |
| "model/CNN/p1_train_y.RDS", | |
| "model/CNN/p1_test.RDS", | |
| "model/CNN/p1_test_y.RDS" | |
| ], | |
| "gan_preprocessed": [ | |
| "model/GAN/seq_all.RDS", | |
| "model/GAN/seq_all_encoded.RDS" | |
| ] | |
| }, | |
| "weight_dir": { | |
| "cnn": [ | |
| "weight/CNN/model_c1", | |
| "weight/CNN/model_p1" | |
| ], | |
| "gan": [ | |
| "weight/GAN/GAN_model_1", | |
| "weight/GAN/GAN_model_2", | |
| "weight/GAN/GAN_model_3", | |
| "weight/GAN/GAN_model_4", | |
| "weight/GAN/GAN_model_5", | |
| "weight/GAN/GAN_model_6", | |
| "weight/GAN/GAN_model_7", | |
| "weight/GAN/GAN_model_8", | |
| "weight/GAN/GAN_model_9", | |
| "weight/GAN/GAN_model_10", | |
| "weight/GAN/GAN_model_11", | |
| "weight/GAN/GAN_model_12", | |
| "weight/GAN/GAN_model_13", | |
| "weight/GAN/GAN_model_14", | |
| "weight/GAN/GAN_model_15" | |
| ] | |
| }, | |
| "runtime": { | |
| "python": "3.11", | |
| "tensorflow": "2.13.1 or compatible TensorFlow/DCU build", | |
| "r": "3.6.3", | |
| "dcu_module": "compiler/dtk/26.04" | |
| }, | |
| "license": "CC-BY-NC-SA-4.0" | |
| } | |