File size: 3,166 Bytes
76df63f cff9fff 76df63f 1efc8c1 76df63f |
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 |
import numpy as np
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import pandas as pd
from transformers import set_seed
import torch
import torch.nn as nn
from collections import OrderedDict
import warnings
import gradio as gr
warnings.filterwarnings('ignore')
set_seed(4)
device = "cpu"
model_checkpoint = "facebook/esm2_t30_150M_UR50D"
class MyModel(nn.Module):
def __init__(self):
super().__init__()
self.bert = AutoModelForSequenceClassification.from_pretrained(model_checkpoint,num_labels=320)
self.bn1 = nn.BatchNorm1d(256)
self.bn2 = nn.BatchNorm1d(128)
self.bn3 = nn.BatchNorm1d(64)
self.relu = nn.ReLU()
self.fc1 = nn.Linear(320,256)
self.fc2 = nn.Linear(256,128)
self.fc3 = nn.Linear(128,64)
self.output_layer = nn.Linear(64,2)
self.dropout = nn.Dropout(0)
def forward(self,x):
with torch.no_grad():
bert_output = self.bert(input_ids=x['input_ids'].to(device),attention_mask=x['attention_mask'].to(device))
output_feature = self.dropout(bert_output["logits"])
output_feature = self.relu(self.bn1(self.fc1(output_feature)))
output_feature = self.relu(self.bn2(self.fc2(output_feature)))
output_feature = self.relu(self.bn3(self.fc3(output_feature)))
output_feature = self.output_layer(output_feature)
return torch.softmax(output_feature,dim=1)
def Kmers_funct(seq,num):
for i in range(len(seq)):
a = seq[i]
l = []
for index in range(len(a)):
t = a[index:index + num]
if (len(t)) == num:
l.append(t)
return l
def ACE(file):
model = MyModel()
model.load_state_dict(torch.load("best_model.pth", map_location=torch.device('cpu')), strict=False)
model = model.to(device)
model.eval()
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
test_sequences = file
max_len = 30
test_data = tokenizer(test_sequences, max_length=max_len, padding="max_length",truncation=True, return_tensors='pt')
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-ACE", 1:"ACE"}
return id2str[test_argmax[0]], out_probability[0]
def main(file):
test_seq = file
all = []
seq_all = []
output_all = []
probability_all = []
for j in range(2, 11):
X = Kmers_funct([test_seq], j)
all.extend(X)
for seq in all:
output, probability = ACE(str(seq))
seq_all.append(seq)
output_all.append(output)
probability_all.append(probability)
summary = OrderedDict()
summary['Seq'] = seq_all
summary['Class'] = output_all
summary['Probability'] = probability_all
summary_df = pd.DataFrame(summary)
summary_df.to_csv('output.csv', index=False)
return 'outputs.csv'
iface = gr.Interface(fn=main,
inputs="text",
outputs= "file")
iface.launch() |