regel-corpus
commited on
Commit
•
b25a50c
1
Parent(s):
081aa42
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +50 -0
- pytorch_model.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
|
README.md
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- flair
|
4 |
+
- hunflair
|
5 |
+
- token-classification
|
6 |
+
- sequence-tagger-model
|
7 |
+
language: en
|
8 |
+
widget:
|
9 |
+
- text: Two putative extended promoters consensus sequences (p1 and p2).
|
10 |
+
---
|
11 |
+
|
12 |
+
## HunFlair2 model for PROMOTER
|
13 |
+
|
14 |
+
[HunFlair](https://github.com/flairNLP/flair/blob/master/resources/docs/HUNFLAIR2.md) (biomedical flair) for enhancer entity:
|
15 |
+
|
16 |
+
- pre-trained language model: michiyasunaga/BioLinkBERT-base
|
17 |
+
- fine-tuned on RegEl corpus for `Promoter` entity type
|
18 |
+
|
19 |
+
Predicts 1 tag:
|
20 |
+
|
21 |
+
| **tag** | **meaning** |
|
22 |
+
| -------- | ------------------- |
|
23 |
+
| Promoter | DNA promoter region |
|
24 |
+
|
25 |
+
______________________________________________________________________
|
26 |
+
|
27 |
+
## Info
|
28 |
+
|
29 |
+
### Demo: How to use in Flair
|
30 |
+
|
31 |
+
Requires:
|
32 |
+
|
33 |
+
- **[Flair](https://github.com/flairNLP/flair/)>=0.14.0** (`pip install flair` or `pip install git+https://github.com/flairNLP/flair.git`)
|
34 |
+
|
35 |
+
```python
|
36 |
+
from flair.data import Sentence
|
37 |
+
from flair.nn import Classifier
|
38 |
+
from flair.tokenization import SciSpacyTokenizer
|
39 |
+
|
40 |
+
text = "The upstream region of the glnA gene contained two putative extended promoter consensus sequences (p1 and p2)."
|
41 |
+
sentence = Sentence(text, use_tokenizer=SciSpacyTokenizer())
|
42 |
+
|
43 |
+
tagger = Classifier.load("regel-corpus/hunflair2-regel-enhancer")
|
44 |
+
tagger.predict(sentence)
|
45 |
+
|
46 |
+
print('The following NER tags are found:')
|
47 |
+
# iterate over entities and print
|
48 |
+
for entity in sentence.get_spans('ner'):
|
49 |
+
print(entity)
|
50 |
+
```
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f88df9e5adc6ece132a12693fc8d31033c0db57520fe738d31706aa89c13366
|
3 |
+
size 433710127
|