|
import numpy as np |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification, EsmForSequenceClassification |
|
from transformers import set_seed |
|
import torch |
|
import torch.nn as nn |
|
import warnings |
|
from tqdm import tqdm |
|
import gradio as gr |
|
|
|
warnings.filterwarnings('ignore') |
|
device = "cpu" |
|
model_checkpoint1 = "facebook/esm2_t12_35M_UR50D" |
|
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint1) |
|
|
|
|
|
class MyModel(nn.Module): |
|
def __init__(self): |
|
super().__init__() |
|
self.bert1 = EsmForSequenceClassification.from_pretrained(model_checkpoint1, num_labels=3000) |
|
self.bn1 = nn.BatchNorm1d(256) |
|
self.bn2 = nn.BatchNorm1d(128) |
|
self.bn3 = nn.BatchNorm1d(64) |
|
self.relu = nn.LeakyReLU() |
|
self.fc1 = nn.Linear(3000, 256) |
|
self.fc2 = nn.Linear(256, 128) |
|
self.fc3 = nn.Linear(128, 64) |
|
self.output_layer = nn.Linear(64, 2) |
|
self.dropout = nn.Dropout(0.3) |
|
|
|
def forward(self, x): |
|
with torch.no_grad(): |
|
bert_output = self.bert1(input_ids=x['input_ids'], |
|
attention_mask=x['attention_mask']) |
|
|
|
|
|
|
|
|
|
|
|
|
|
output_feature = self.dropout(bert_output["logits"]) |
|
output_feature = self.dropout(self.relu(self.bn1(self.fc1(output_feature)))) |
|
output_feature = self.dropout(self.relu(self.bn2(self.fc2(output_feature)))) |
|
output_feature = self.dropout(self.relu(self.bn3(self.fc3(output_feature)))) |
|
output_feature = self.dropout(self.output_layer(output_feature)) |
|
|
|
return torch.softmax(output_feature, dim=1) |
|
|
|
|
|
def AMP(test_sequences, model): |
|
|
|
max_len = 18 |
|
test_data = tokenizer(test_sequences, max_length=max_len, padding="max_length", truncation=True, |
|
return_tensors='pt') |
|
model = model.to(device) |
|
model.eval() |
|
out_probability = [] |
|
with torch.no_grad(): |
|
predict = model(test_data) |
|
out_probability.extend(np.max(np.array(predict.cpu()), axis=1).tolist()) |
|
test_argmax = np.argmax(predict.cpu(), axis=1).tolist() |
|
id2str = {0: "non-AMP", 1: "AMP"} |
|
return id2str[test_argmax[0]], out_probability[0] |
|
|
|
|
|
def classify_sequence(sequence): |
|
|
|
valid_amino_acids = set("ACDEFGHIKLMNPQRSTVWY") |
|
sequence = sequence.upper() |
|
|
|
if all(aa in valid_amino_acids for aa in sequence) and len(sequence) >= 3: |
|
result, probability = AMP(sequence, model) |
|
return "yes" if result == "AMP" else "no" |
|
else: |
|
return "Invalid Sequence" |
|
|
|
|
|
|
|
model = MyModel() |
|
model.load_state_dict(torch.load("best_model.pth", map_location=torch.device('cpu'))) |
|
|
|
if __name__ == "__main__": |
|
title = """<h1 align="center">🔥AMP Sequence Detector</h1>""" |
|
css = ".json {height: 527px; overflow: scroll;} .json-holder {height: 527px; overflow: scroll;}" |
|
theme = gr.themes.Soft(primary_hue="zinc", secondary_hue="blue", neutral_hue="green", |
|
text_size=gr.themes.sizes.text_lg) |
|
with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;} #chatbot {height: 520px; overflow: auto;}""", |
|
theme=theme) as demo: |
|
|
|
gr.Markdown("<h1>Diff-AMP</h1>") |
|
gr.HTML(title) |
|
|
|
|
|
gr.Markdown( |
|
"<p align='center' style='font-size: 20px;'>🔥Welcome to Antimicrobial Peptide Recognition Model. See our <a href='https://github.com/wrab12/diff-amp'>Project</a></p>") |
|
gr.HTML( |
|
'''<center> |
|
<a href="https://huggingface.co/spaces/jackrui/ampD?duplicate=true"> |
|
<img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"> |
|
</a> |
|
</center>''') |
|
gr.HTML( |
|
'''<center>🌟Note: This is an antimicrobial peptide recognition model derived from Diff-AMP, which is a branch of a comprehensive system integrating generation, recognition, and optimization. In this recognition model, you can simply input a sequence, and it will predict whether it is an antimicrobial peptide. Due to limited website capacity, we can only perform simple predictions. |
|
If you require large-scale computations, please contact my email at [email protected]. Feel free to reach out if you have any questions or inquiries.</center>''') |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
examples = [ |
|
["QGLFFLGAKLFYLLTLFL"], |
|
["FLGLLFHGVHHVGKWIHGLIHGHH"], |
|
["GLMSTLKGAATNAAVTLLNKLQCKLTGTC"] |
|
] |
|
|
|
|
|
iface = gr.Interface( |
|
fn=classify_sequence, |
|
inputs="text", |
|
outputs="text", |
|
|
|
examples=examples |
|
) |
|
gr.Markdown( |
|
"<p align='center'><img src='https://pic4.zhimg.com/v2-eb2a7c0e746e67d1768090eec74f6787_b.jpg'></p>") |
|
gr.Markdown("<p align='center' style='font-size: 20px;'>Related job links in the same series: </p>") |
|
|
|
gr.Markdown("<p align='center'><a href='https://huggingface.co/spaces/jackrui/ampG'><img style='margin:-0.8em 0 2em 0;' src='https://shields.io/badge/Diff_AMP-Generator-blue' alt='Diff_AMP-Generator-blue'></a></p>" |
|
"<p align='center'><a href='https://huggingface.co/spaces/jackrui/ampPP'><img style='margin:-0.8em 0 2em 0;' src='https://shields.io/badge/Diff_AMP-property_prediction-blue' alt='Diff_AMP-property_prediction-blue'></a></p>") |
|
gr.Markdown('''📝 **Citation** |
|
If our work is useful for your research, please consider citing: |
|
``` |
|
waiting... |
|
``` |
|
📋 **License** |
|
|
|
None |
|
|
|
📧 **Contact** |
|
|
|
If you have any questions, please feel free to reach me out at <b>[email protected]</b>. |
|
|
|
🤗 **Find Me:** |
|
<style type="text/css"> |
|
td { |
|
padding-right: 0px !important; |
|
} |
|
</style> |
|
<table> |
|
<tr> |
|
<td><a href="https://github.com/wrab12"><img style="margin:-0.8em 0 2em 0" src="https://img.shields.io/github/followers/wrab12?style=social" alt="Github Follow"></a></td> |
|
|
|
</tr> |
|
</table> |
|
<center><img src='https://api.infinitescript.com/badgen/count?name=jackrui/ampD<ext=Visitors&color=6dc9aa' alt='visitors'></center> |
|
""" |
|
''') |
|
|
|
demo.launch() |
|
|
