File size: 5,453 Bytes
ab90cdb
edd898f
22619e0
 
 
 
 
 
 
 
 
 
 
 
ab90cdb
edd898f
 
33998ff
 
 
 
7895fd5
 
 
 
 
 
 
 
 
 
edd898f
 
33998ff
 
 
 
907da65
 
 
33998ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
edd898f
33998ff
 
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
---
library_name: peft
license: mit
language:
- en
metrics:
- f1
- precision
- recall
tags:
- ems
- esm2
- protein language model
- biology
---
## Training procedure

This model was trained with Hugging Face's Parameter Efficient Fine-Tuning (PEFT) library, in particular, 
a Low Rank Adaptation (LoRA) was trained on top of the model 
[AmelieSchreiber/esm2_t6_8M_finetuned_cafa5](https://huggingface.co./AmelieSchreiber/esm2_t6_8M_finetuned_cafa5). 

```
Epoch 3/3 
Training Loss: 0.0152 
Validation Loss: 0.0153 
Val F1 Score: 0.7361
Micro-Average Precision: 0.9977
Micro-Average Recall: 0.2264
Micro-Average ROC AUC: 0.8894
```

### Framework versions

- PEFT 0.4.0

## Using the Model

To use the model, try downloading the data [from here](https://huggingface.co./datasets/AmelieSchreiber/cafa_5), 
adjust the paths to the files in the code below to their local paths on your machine, and try running:

```python
import os
import numpy as np
import torch
from transformers import AutoTokenizer, EsmForSequenceClassification, AdamW
from torch.nn.functional import binary_cross_entropy_with_logits
from sklearn.model_selection import train_test_split
from sklearn.metrics import f1_score, precision_score, recall_score
from accelerate import Accelerator
from Bio import SeqIO

# Step 1: Data Preprocessing
fasta_file = "data/Train/train_sequences.fasta"
tsv_file = "data/Train/train_terms.tsv"

fasta_data = {}
tsv_data = {}

for record in SeqIO.parse(fasta_file, "fasta"):
    fasta_data[record.id] = str(record.seq)

with open(tsv_file, 'r') as f:
    for line in f:
        parts = line.strip().split("\t")
        tsv_data[parts[0]] = parts[1:]

unique_terms = list(set(term for terms in tsv_data.values() for term in terms))

def parse_fasta(file_path):
    """
    Parses a FASTA file and returns a list of sequences.
    """
    with open(file_path, 'r') as f:
        content = f.readlines()

    sequences = []
    current_sequence = ""

    for line in content:
        if line.startswith(">"):
            if current_sequence:
                sequences.append(current_sequence)
                current_sequence = ""
        else:
            current_sequence += line.strip()

    if current_sequence:
        sequences.append(current_sequence)

    return sequences

# Parse the provided FASTA file
fasta_file_path = "data/Test/testsuperset.fasta"
protein_sequences = parse_fasta(fasta_file_path)
# protein_sequences[:3]  # Displaying the first 3 sequences for verification

import torch
from transformers import AutoTokenizer, EsmForSequenceClassification
from sklearn.metrics import precision_recall_fscore_support

# 1. Parsing the go-basic.obo file (Assuming this is still needed)
def parse_obo_file(file_path):
    with open(file_path, 'r') as f:
        data = f.read().split("[Term]")
        
    terms = []
    for entry in data[1:]:
        lines = entry.strip().split("\n")
        term = {}
        for line in lines:
            if line.startswith("id:"):
                term["id"] = line.split("id:")[1].strip()
            elif line.startswith("name:"):
                term["name"] = line.split("name:")[1].strip()
            elif line.startswith("namespace:"):
                term["namespace"] = line.split("namespace:")[1].strip()
            elif line.startswith("def:"):
                term["definition"] = line.split("def:")[1].split('"')[1]
        terms.append(term)
    return terms

# Let's assume the path to go-basic.obo is as follows (please modify if different)
obo_file_path = "data/Train/go-basic.obo"  
parsed_terms = parse_obo_file("data/Train/go-basic.obo")  # Replace with your path

# 2. Load the saved model and tokenizer
# Assuming the model path provided is correct
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from peft import PeftModel, PeftConfig

# Load the tokenizer and model
model_id = "AmelieSchreiber/esm2_t6_8M_lora_cafa5"  # Replace with your Hugging Face hub model name
tokenizer = AutoTokenizer.from_pretrained(model_id)

# First, we load the underlying base model
base_model = AutoModelForSequenceClassification.from_pretrained(model_id)

# Then, we load the model with PEFT
model = PeftModel.from_pretrained(base_model, model_id)
loaded_model = model
loaded_tokenizer = AutoTokenizer.from_pretrained(model_id)

# 3. The predict_protein_function function
def predict_protein_function(sequence, model, tokenizer, go_terms):
    inputs = tokenizer(sequence, return_tensors="pt", padding=True, truncation=True, max_length=1022)
    model.eval()
    with torch.no_grad():
        outputs = model(**inputs)
        predictions = torch.sigmoid(outputs.logits)
        predicted_indices = torch.where(predictions > 0.05)[1].tolist()
    
    functions = []
    for idx in predicted_indices:
        term_id = unique_terms[idx]  # Use the unique_terms list from your training script
        for term in go_terms:
            if term["id"] == term_id:
                functions.append(term["name"])
                break
                
    return functions

# 4. Predicting protein function for the sequences in the FASTA file
protein_functions = {}
for seq in protein_sequences[:20]:  # Using only the first 3 sequences for demonstration
    predicted_functions = predict_protein_function(seq, loaded_model, loaded_tokenizer, parsed_terms)
    protein_functions[seq[:20] + "..."] = predicted_functions  # Using first 20 characters as key

protein_functions
```