Spaces:
Running
Running
| import gradio as gr | |
| from inference import Inference | |
| import PIL | |
| from PIL import Image | |
| import pandas as pd | |
| import random | |
| from rdkit import Chem | |
| from rdkit.Chem import Draw | |
| from rdkit.Chem.Draw import IPythonConsole | |
| import shutil | |
| import os | |
| class DrugGENConfig: | |
| submodel='DrugGEN' | |
| inference_model="experiments/models/DrugGEN/" | |
| sample_num=1000 | |
| inf_dataset_file="chembl45_test.pt" | |
| inf_raw_file='data/chembl_test.smi' | |
| inf_batch_size=1 | |
| mol_data_dir='data' | |
| features=False | |
| act='relu' | |
| max_atom=45 | |
| dim=32 | |
| depth=1 | |
| heads=8 | |
| mlp_ratio=3 | |
| dropout=0. | |
| log_sample_step=100 | |
| set_seed=True | |
| seed=10 | |
| class NoTargetConfig(DrugGENConfig): | |
| submodel="NoTarget" | |
| dim=128 | |
| inference_model="experiments/models/NoTarget/" | |
| model_configs = { | |
| "DrugGEN": DrugGENConfig(), | |
| "NoTarget": NoTargetConfig(), | |
| } | |
| def function(model_name: str, num_molecules: int, seed_num: int) -> tuple[PIL.Image, pd.DataFrame, str]: | |
| ''' | |
| Returns: | |
| image, score_df, file path | |
| ''' | |
| if model_name == "DrugGEN-NoTarget": | |
| model_name = "NoTarget" | |
| config = model_configs[model_name] | |
| config.sample_num = num_molecules | |
| if seed_num is None or seed_num.strip() == "": | |
| config.seed = random.randint(0, 10000) | |
| else: | |
| try: | |
| config.seed = int(seed_num) | |
| except ValueError: | |
| raise gr.Error("The seed must be an integer value!") | |
| inferer = Inference(config) | |
| scores = inferer.inference() # create scores_df out of this | |
| score_df = pd.DataFrame(scores, index=[0]) | |
| output_file_path = f'experiments/inference/{model_name}/inference_drugs.txt' | |
| new_path = f'{model_name}_denovo_mols.smi' | |
| os.rename(output_file_path, new_path) | |
| with open(new_path) as f: | |
| inference_drugs = f.read() | |
| generated_molecule_list = inference_drugs.split("\n")[:-1] | |
| rng = random.Random(config.seed) | |
| if num_molecules > 12: | |
| selected_molecules = rng.choices(generated_molecule_list, k=12) | |
| else: | |
| selected_molecules = generated_molecule_list | |
| selected_molecules = [Chem.MolFromSmiles(mol) for mol in selected_molecules if Chem.MolFromSmiles(mol) is not None] | |
| drawOptions = Draw.rdMolDraw2D.MolDrawOptions() | |
| drawOptions.prepareMolsBeforeDrawing = False | |
| drawOptions.bondLineWidth = 0.5 | |
| molecule_image = Draw.MolsToGridImage( | |
| selected_molecules, | |
| molsPerRow=3, | |
| subImgSize=(400, 400), | |
| maxMols=len(selected_molecules), | |
| # legends=None, | |
| returnPNG=False, | |
| drawOptions=drawOptions, | |
| highlightAtomLists=None, | |
| highlightBondLists=None, | |
| ) | |
| return molecule_image, score_df, new_path | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| gr.Markdown("# DrugGEN: Target Centric De Novo Design of Drug Candidate Molecules with Graph Generative Deep Adversarial Networks") | |
| with gr.Row(): | |
| gr.Markdown("[](https://arxiv.org/abs/2302.07868)") | |
| gr.Markdown("[](https://github.com/HUBioDataLab/DrugGEN)") | |
| with gr.Accordion("Expand to display information about models", open=False): | |
| gr.Markdown(""" | |
| ### Model Variations | |
| - **DrugGEN** is the default model. The input of the generator is the real molecules (ChEMBL) dataset (to ease the learning process) and the discriminator compares the generated molecules with the real inhibitors of the given target protein. | |
| - **DrugGEN-NoTarget** is the non-target-specific version of DrugGEN. This model only focuses on learning the chemical properties from the ChEMBL training dataset. | |
| """) | |
| model_name = gr.Radio( | |
| choices=("DrugGEN", "DrugGEN-NoTarget"), | |
| value="DrugGEN", | |
| label="Select a model to make inference", | |
| info=str("DrugGEN model designs small molecules to target the human AKT1 protein (UniProt id: P31749)." + '\n' | |
| + "DrugGEN-NoTarget model designs random drug-like small molecules.") | |
| ) | |
| num_molecules = gr.Number( | |
| label="Number of molecules to generate", | |
| precision=0, # integer input | |
| minimum=1, | |
| value=1000, | |
| maximum=10_000, | |
| info="It will take ~20-60 seconds to generate 1000 mols." | |
| ) | |
| seed_num = gr.Textbox( | |
| label="RNG seed value", | |
| value=None, | |
| info="This is optional, it can be used for reproducibility." | |
| ) | |
| submit_button = gr.Button( | |
| value="Start Generating" | |
| ) | |
| with gr.Column(scale=2): | |
| scores_df = gr.Dataframe( | |
| label="Scores", | |
| headers=["Runtime (seconds)", "Validity", "Uniqueness", "Novelty (Train)", "Novelty (Inference)"] | |
| ) | |
| file_download = gr.File( | |
| label="Click to download generated molecules", | |
| ) | |
| image_output = gr.Image( | |
| label="Structures of randomly selected de novo molecules from the inference set:" | |
| ) | |
| submit_button.click(function, inputs=[model_name, num_molecules, seed_num], outputs=[image_output, scores_df, file_download], api_name="inference") | |
| #demo.queue(concurrency_count=1) | |
| demo.queue() | |
| demo.launch() | |