Hugging Face's logo

Spaces:
khairi
/
ProtNLA
Runtime error

App Files Community
khairi commited on
Commit
a67f37a
•
1 Parent(s): 98f2a54

code tempalte

Browse files
Files changed (11) hide show
  1. app.py +26 -0
  2. data/tokenizers/protein_tokenizer/special_tokens_map.json +37 -0
  3. data/tokenizers/protein_tokenizer/tokenizer.json +0 -0
  4. data/tokenizers/protein_tokenizer/tokenizer_config.json +52 -0
  5. data/tokenizers/term_tokenizer/special_tokens_map.json +5 -0
  6. data/tokenizers/term_tokenizer/tokenizer.json +0 -0
  7. data/tokenizers/term_tokenizer/tokenizer_config.json +69 -0
  8. data/tokenizers/text_tokenizer/special_tokens_map.json +5 -0
  9. data/tokenizers/text_tokenizer/tokenizer.json +0 -0
  10. data/tokenizers/text_tokenizer/tokenizer_config.json +61 -0
  11. inference.py +4 -0
app.py CHANGED
@@ -1,3 +1,29 @@
1
  import streamlit as st
 
2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
 
 
1
  import streamlit as st
2
+ from transformers import AutoModelForSeq2SeqLM, PreTrainedTokenizerFast
3
 
4
+ from io import StringIO
5
+ from Bio import SeqIO
6
+
7
+ textarea_placeholder = "Input your sequences in fasta format"
8
+ sample_protein = """"
9
+
10
+ """
11
+
12
+ tokenizers_path = ('data/tokenizers/protein_tokenizer', 'data/tokenizers/text_tokenizer')
13
+
14
+ model = AutoModelForSeq2SeqLM.from_pretrained("khairi/ProtNLA")
15
+
16
+ protein_tokenizer = PreTrainedTokenizerFast.from_pretrained(tokenizers_path[0])
17
+ text_tokenizer = PreTrainedTokenizerFast.from_pretrained(tokenizers_path[1])
18
+
19
+
20
+ fasta_sequences = st.text_area("Input Sequences:", value=sample_protein, placeholder=textarea_placeholder)
21
+ num_annotations = st.number_input(label="Num Annotations: ", min_value=1, max_value=5)
22
+ predict = st.button(label='Run')
23
+
24
+ if predict:
25
+ fasta_io = StringIO(fasta_sequences)
26
+ records = SeqIO.parse(fasta_io, "fasta")
27
+ for record in records:
28
+
29
 
data/tokenizers/protein_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "<cls>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<sep>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
data/tokenizers/protein_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
data/tokenizers/protein_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<sep>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "<cls>",
46
+ "mask_token": "<mask>",
47
+ "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "<pad>",
49
+ "sep_token": "<sep>",
50
+ "tokenizer_class": "PreTrainedTokenizerFast",
51
+ "unk_token": "<unk>"
52
+ }
data/tokenizers/term_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>"
5
+ }
data/tokenizers/term_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
data/tokenizers/term_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<molecular_function>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<biological_process>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<cellular_component>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<unk>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "<bos>",
61
+ "bp_token": "<biological_process>",
62
+ "cc_token": "<cellular_component>",
63
+ "clean_up_tokenization_spaces": true,
64
+ "eos_token": "<eos>",
65
+ "mf_token": "<molecular_function>",
66
+ "model_max_length": 1000000000000000019884624838656,
67
+ "pad_token": "<pad>",
68
+ "tokenizer_class": "PreTrainedTokenizerFast"
69
+ }
data/tokenizers/text_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>"
5
+ }
data/tokenizers/text_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
data/tokenizers/text_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<molecular_function>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<biological_process>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<cellular_component>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<bos>",
53
+ "bp_token": "<biological_process>",
54
+ "cc_token": "<cellular_component>",
55
+ "clean_up_tokenization_spaces": true,
56
+ "eos_token": "<eos>",
57
+ "mf_token": "<molecular_function>",
58
+ "model_max_length": 1000000000000000019884624838656,
59
+ "pad_token": "<pad>",
60
+ "tokenizer_class": "PreTrainedTokenizerFast"
61
+ }
inference.py ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+
2
+
3
+ def run_inference(model, protein_tokenizer, text_tokenizer, protein_sequences):
4
+ pass