Update README.md
Browse files
README.md
CHANGED
|
@@ -7,15 +7,15 @@ tags:
|
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
---
|
| 9 |
# Model description
|
| 10 |
-
**PPPSL
|
| 11 |
|
| 12 |
-
**PPPSL
|
| 13 |
Train Loss: 0.0148
|
| 14 |
Train Accuracy: 0.9923
|
| 15 |
Validation Loss: 0.0718
|
| 16 |
Validation Accuracy: 0.9893
|
| 17 |
Epoch: 20
|
| 18 |
-
# The dataset for training **PPPSL
|
| 19 |
The full dataset contains 11,970 protein sequences, including Cellwall (87), Cytoplasmic (6,905), CYtoplasmic Membrane (2,567), Extracellular (1,085), Outer Membrane (758), and Periplasmic (568).
|
| 20 |
The highly imbalanced sample sizes across the six categories in this dataset pose a significant challenge for classification.
|
| 21 |
|
|
@@ -24,7 +24,7 @@ The dataset was downloaded from the website at [**DeepLocPro - 1.0**](https://se
|
|
| 24 |
# Model training code at GitHub
|
| 25 |
https://github.com/pengsihua2023/PPPSL-ESM2
|
| 26 |
|
| 27 |
-
# How to use **PPPSL
|
| 28 |
### An example
|
| 29 |
Pytorch and transformers libraries should be installed in your system.
|
| 30 |
### Install pytorch
|
|
|
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
---
|
| 9 |
# Model description
|
| 10 |
+
**PPPSL**(PPPSL, Prediction of prokaryotic protein subcellular localization) is a protein language model fine-tuned from [**ESM2**](https://github.com/facebookresearch/esm) pretrained model [(***facebook/esm2_t36_3B_UR50D***)](https://huggingface.co/facebook/esm2_t36_3B_UR50D) on a prokaryotic protein subcellular localization dataset.
|
| 11 |
|
| 12 |
+
**PPPSL** achieved the following results:
|
| 13 |
Train Loss: 0.0148
|
| 14 |
Train Accuracy: 0.9923
|
| 15 |
Validation Loss: 0.0718
|
| 16 |
Validation Accuracy: 0.9893
|
| 17 |
Epoch: 20
|
| 18 |
+
# The dataset for training **PPPSL**
|
| 19 |
The full dataset contains 11,970 protein sequences, including Cellwall (87), Cytoplasmic (6,905), CYtoplasmic Membrane (2,567), Extracellular (1,085), Outer Membrane (758), and Periplasmic (568).
|
| 20 |
The highly imbalanced sample sizes across the six categories in this dataset pose a significant challenge for classification.
|
| 21 |
|
|
|
|
| 24 |
# Model training code at GitHub
|
| 25 |
https://github.com/pengsihua2023/PPPSL-ESM2
|
| 26 |
|
| 27 |
+
# How to use **PPPSL**
|
| 28 |
### An example
|
| 29 |
Pytorch and transformers libraries should be installed in your system.
|
| 30 |
### Install pytorch
|