File size: 6,007 Bytes
8279c69
 
 
 
 
 
 
 
 
 
f87af8c
8279c69
 
 
e90a921
 
 
 
 
 
 
8279c69
 
b29080a
8279c69
 
 
 
1dd4981
e90a921
 
2caba59
8279c69
 
 
 
 
e90a921
8279c69
 
 
 
0cd6b71
8279c69
 
 
 
1dd4981
8279c69
 
 
 
0cd6b71
 
 
8279c69
ce56756
2084a51
90e4f53
19be6e8
90e4f53
724b603
 
 
02d2df4
 
724b603
 
8279c69
f87af8c
8279c69
 
 
 
 
 
 
 
 
 
 
 
 
14b9a92
8279c69
ce56756
 
 
 
14b9a92
ce56756
a6f835f
8279c69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8cbec0c
8279c69
 
9bf9415
8279c69
 
8cbec0c
 
8279c69
 
a877740
8279c69
 
 
f36db65
cd01954
19be6e8
8279c69
9651f63
02d2df4
c81f62d
 
 
8279c69
 
 
 
 
 
 
 
 
81e39b1
8279c69
 
 
 
 
091e498
8279c69
 
 
 
8c2ce19
 
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
166
167
168
169
170
171
172
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=128
    depth=1
    heads=8
    mlp_ratio=3
    dropout=0.
    log_sample_step=100
    set_seed=True
    seed=10
    correct=True


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 config.sample_num > 250:
        raise gr.Error("You have requested to generate more than the allowed limit of 250 molecules. Please reduce your request to 250 or fewer.")

    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("[![arXiv](https://img.shields.io/badge/arXiv-2302.07868-b31b1b.svg)](https://arxiv.org/abs/2302.07868)")
                gr.Markdown("[![github-repository](https://img.shields.io/badge/GitHub-black?logo=github)](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=100,
                maximum=999999,
                info="This space runs on a CPU, which may result in slower performance. Generating 200 molecules takes approximately 6 minutes. Therefore, We set a 250-molecule cap. On a GPU, the model can generate 10,000 molecules in the same amount of time. Please check our GitHub repo for running our models on GPU."
            )

            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()