Spaces:
Running
Running
File size: 5,451 Bytes
8279c69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
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
class DrugGENConfig:
submodel='DrugGEN'
act='relu'
max_atom=45
dim=32
depth=1
heads=8
mlp_ratio=3
dropout=0.
features=False
inference_sample_num=1000
inf_batch_size=1
protein_data_dir='data/akt'
drug_index='data/drug_smiles.index'
drug_data_dir='data/akt'
mol_data_dir='data'
log_dir='experiments/logs'
model_save_dir='experiments/models'
inference_model="experiments/models/DrugGEN"
sample_dir='experiments/samples'
result_dir="experiments/tboard_output"
dataset_file="chembl45_train.pt"
drug_dataset_file="akt_train.pt"
raw_file='data/chembl_train.smi'
drug_raw_file="data/akt_train.smi"
inf_dataset_file="chembl45_test.pt"
inf_drug_dataset_file='akt_test.pt'
inf_raw_file='data/chembl_test.smi'
inf_drug_raw_file="data/akt_test.smi"
log_sample_step=1000
set_seed=False
seed=1
class NoTargetConfig(DrugGENConfig):
submodel="NoTarget"
dim=128
inference_model="experiments/models/NoTarget"
model_configs = {
"DrugGEN": DrugGENConfig(),
"NoTarget": NoTargetConfig(),
}
def function(model_name: str, mol_num: int, seed: int) -> tuple[PIL.Image, pd.DataFrame, str]:
'''
Returns:
image, score_df, file path
'''
config = model_configs[model_name]
config.inference_sample_num = mol_num
config.seed = seed
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'
import os
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")
rng = random.Random(seed)
selected_molecules = rng.choices(generated_molecule_list,k=12)
selected_molecules = [Chem.MolFromSmiles(mol) for mol in selected_molecules]
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.
- **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", "NoTarget"),
value="DrugGEN",
label="Select a model to make inference",
info=" DrugGEN model design molecules to target the AKT1 protein"
)
num_molecules = gr.Number(
label="Number of molecules to generate",
precision=0, # integer input
minimum=1,
value=1000,
maximum=10_000,
)
seed_num = gr.Number(
label="RNG seed value (can be used for reproducibility):",
precision=0, # integer input
minimum=0,
value=42,
)
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)", "Novelty (AKT)", "MaxLen", "MeanAtomType", "SNN (ChEMBL)", "SNN (AKT)"],
)
file_download = gr.File(
label="Click to download generated molecules",
)
image_output = gr.Image(
label="Structures of randomly selected 12 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.launch()
|