Kseniia-Kholina commited on
Commit
2aebbc2
·
verified ·
1 Parent(s): e615467

Update app_new.py

Browse files
Files changed (1) hide show
  1. app_new.py +117 -0
app_new.py CHANGED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ import pandas as pd
3
+ import torch
4
+ from transformers import AutoTokenizer, AutoModelForMaskedLM
5
+ import logging
6
+ import numpy as np
7
+ import matplotlib.pyplot as plt
8
+ import seaborn as sns
9
+ from io import BytesIO
10
+ from PIL import Image
11
+
12
+ logging.getLogger("transformers.modeling_utils").setLevel(logging.ERROR)
13
+ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
14
+ print(f"Using device: {device}")
15
+
16
+ # Load the tokenizer and model
17
+ model_name = "ChatterjeeLab/FusOn-pLM"
18
+ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
19
+ model = AutoModelForMaskedLM.from_pretrained(model_name, trust_remote_code=True)
20
+ model.to(device)
21
+ model.eval()
22
+
23
+ def process_sequence(sequence, domain_bounds, n):
24
+ start_index = int(domain_bounds['start'][0]) - 1
25
+ end_index = int(domain_bounds['end'][0])
26
+
27
+ top_n_mutations = {}
28
+ all_logits = []
29
+
30
+ for i in range(len(sequence)):
31
+ if start_index <= i <= end_index:
32
+ masked_seq = sequence[:i] + '<mask>' + sequence[i+1:]
33
+ inputs = tokenizer(masked_seq, return_tensors="pt", padding=True, truncation=True, max_length=2000)
34
+ inputs = {k: v.to(device) for k, v in inputs.items()}
35
+ with torch.no_grad():
36
+ logits = model(**inputs).logits
37
+ mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
38
+ mask_token_logits = logits[0, mask_token_index, :]
39
+ # Decode top n tokens
40
+ top_n_tokens = torch.topk(mask_token_logits, n, dim=1).indices[0].tolist()
41
+ mutation = [tokenizer.decode([token]) for token in top_n_tokens]
42
+ top_n_mutations[(sequence[i], i)] = mutation
43
+
44
+ logits_array = mask_token_logits.cpu().numpy()
45
+ # filter out non-amino acid tokens
46
+ filtered_indices = list(range(4, 23 + 1))
47
+ filtered_logits = logits_array[:, filtered_indices]
48
+ all_logits.append(filtered_logits)
49
+
50
+ token_indices = torch.arange(logits.size(-1))
51
+ tokens = [tokenizer.decode([idx]) for idx in token_indices]
52
+ filtered_tokens = [tokens[i] for i in filtered_indices]
53
+
54
+ all_logits_array = np.vstack(all_logits)
55
+ normalized_logits_array = (all_logits_array - all_logits_array.min()) / (all_logits_array.max() - all_logits_array.min())
56
+ transposed_logits_array = normalized_logits_array.T
57
+
58
+ # Plotting the heatmap
59
+ step = 50
60
+ y_tick_positions = np.arange(0, len(sequence), step)
61
+ y_tick_labels = [str(pos) for pos in y_tick_positions]
62
+
63
+ plt.figure(figsize=(15, 8))
64
+ sns.heatmap(transposed_logits_array, cmap='plasma', xticklabels=y_tick_labels, yticklabels=filtered_tokens)
65
+ plt.title('Logits for masked per residue tokens')
66
+ plt.ylabel('Token')
67
+ plt.xlabel('Residue Index')
68
+ plt.yticks(rotation=0)
69
+ plt.xticks(y_tick_positions, y_tick_labels, rotation = 0)
70
+
71
+ # Save the figure to a BytesIO object
72
+ buf = BytesIO()
73
+ plt.savefig(buf, format='png')
74
+ buf.seek(0)
75
+ plt.close()
76
+
77
+ # Convert BytesIO object to an image
78
+ img = Image.open(buf)
79
+
80
+ original_residues = []
81
+ mutations = []
82
+ positions = []
83
+
84
+ for key, value in top_n_mutations.items():
85
+ original_residue, position = key
86
+ original_residues.append(original_residue)
87
+ mutations.append(value)
88
+ positions.append(position + 1)
89
+
90
+ df = pd.DataFrame({
91
+ 'Original Residue': original_residues,
92
+ 'Predicted Residues (in order of decreasing likelihood)': mutations,
93
+ 'Position': positions
94
+ })
95
+
96
+ df = df[start_index:end_index]
97
+
98
+ return df, img
99
+
100
+ demo = gr.Interface(
101
+ fn=process_sequence,
102
+ inputs=[
103
+ "text",
104
+ gr.Dataframe(
105
+ headers=["start", "end"],
106
+ datatype=["number", "number"],
107
+ row_count=(1, "fixed"),
108
+ col_count=(2, "fixed"),
109
+ ),
110
+ gr.Dropdown([i for i in range(1, 21)]), # Dropdown with numbers from 1 to 20 as integers
111
+ ],
112
+ outputs=["dataframe", "image"],
113
+ description="Choose a number between 1-20 to predict n tokens for each position. Choose the start and end index of the domain of interest (indexing starts at 1).",
114
+ )
115
+
116
+ if __name__ == "__main__":
117
+ demo.launch()