Update README.md
Browse files
README.md
CHANGED
@@ -8,11 +8,11 @@ tags:
|
|
8 |
library_name: biomed
|
9 |
license: apache-2.0
|
10 |
base_model:
|
11 |
-
- ibm/biomed.omics.bl.sm.ma-ted-
|
12 |
---
|
13 |
|
14 |
Protein solubility is a critical factor in both pharmaceutical research and production processes, as it can significantly impact the quality and function of a protein.
|
15 |
-
This is an example for finetuning `ibm/biomed.omics.bl.sm-ted-
|
16 |
|
17 |
The benchmark defined in: https://academic.oup.com/bioinformatics/article/34/15/2605/4938490
|
18 |
Data retrieved from: https://zenodo.org/records/1162886
|
@@ -28,13 +28,13 @@ Data retrieved from: https://zenodo.org/records/1162886
|
|
28 |
|
29 |
## Usage
|
30 |
|
31 |
-
Using `ibm/biomed.omics.bl.sm.ma-ted-
|
32 |
|
33 |
```
|
34 |
pip install git+https://github.com/BiomedSciAI/biomed-multi-alignment.git
|
35 |
```
|
36 |
|
37 |
-
A simple example for a task already supported by `ibm/biomed.omics.bl.sm.ma-ted-
|
38 |
```python
|
39 |
import os
|
40 |
|
@@ -45,10 +45,10 @@ from mammal.keys import CLS_PRED, SCORES
|
|
45 |
from mammal.model import Mammal
|
46 |
|
47 |
# Load Model
|
48 |
-
model = Mammal.from_pretrained("ibm/biomed.omics.bl.sm.ma-ted-
|
49 |
|
50 |
# Load Tokenizer
|
51 |
-
tokenizer_op = ModularTokenizerOp.from_pretrained("ibm/biomed.omics.bl.sm.ma-ted-
|
52 |
|
53 |
# convert to MAMMAL style
|
54 |
sample_dict = {"protein_seq": protein_seq}
|
|
|
8 |
library_name: biomed
|
9 |
license: apache-2.0
|
10 |
base_model:
|
11 |
+
- ibm/biomed.omics.bl.sm.ma-ted-458m
|
12 |
---
|
13 |
|
14 |
Protein solubility is a critical factor in both pharmaceutical research and production processes, as it can significantly impact the quality and function of a protein.
|
15 |
+
This is an example for finetuning `ibm/biomed.omics.bl.sm-ted-458m` for protein solubility prediction (binary classification) based solely on the amino acid sequence.
|
16 |
|
17 |
The benchmark defined in: https://academic.oup.com/bioinformatics/article/34/15/2605/4938490
|
18 |
Data retrieved from: https://zenodo.org/records/1162886
|
|
|
28 |
|
29 |
## Usage
|
30 |
|
31 |
+
Using `ibm/biomed.omics.bl.sm.ma-ted-458m` requires installing [https://github.com/BiomedSciAI/biomed-multi-alignment](https://github.com/TBD)
|
32 |
|
33 |
```
|
34 |
pip install git+https://github.com/BiomedSciAI/biomed-multi-alignment.git
|
35 |
```
|
36 |
|
37 |
+
A simple example for a task already supported by `ibm/biomed.omics.bl.sm.ma-ted-458m`:
|
38 |
```python
|
39 |
import os
|
40 |
|
|
|
45 |
from mammal.model import Mammal
|
46 |
|
47 |
# Load Model
|
48 |
+
model = Mammal.from_pretrained("ibm/biomed.omics.bl.sm.ma-ted-458m.protein_solubility")
|
49 |
|
50 |
# Load Tokenizer
|
51 |
+
tokenizer_op = ModularTokenizerOp.from_pretrained("ibm/biomed.omics.bl.sm.ma-ted-458m.protein_solubility")
|
52 |
|
53 |
# convert to MAMMAL style
|
54 |
sample_dict = {"protein_seq": protein_seq}
|