Instructions to use isikz/phosphorylation_binaryclassification_esm1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use isikz/phosphorylation_binaryclassification_esm1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="isikz/phosphorylation_binaryclassification_esm1b")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("isikz/phosphorylation_binaryclassification_esm1b") model = AutoModelForSequenceClassification.from_pretrained("isikz/phosphorylation_binaryclassification_esm1b") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ base_model:
|
|
| 11 |
|
| 12 |
This repository provides a fine-tuned version of the [ESM-1b]([https://website-name.com](https://huggingface.co/facebook/esm1b_t33_650M_UR50S)) model, trained to classify phosphosites using unlabeled phosphosites(ie, which kinases phosphorylate those phosphosites is unknown) from [PhosphoSitePlus](https://www.phosphosite.org/staticDownloads). The model is designed for binary classification, distinguishing phosphosites from non-phosphorylated peptid sequences [(Musite, a Tool for Global Prediction of General and Kinase-specific Phosphorylation Sites)](https://www.sciencedirect.com/science/article/pii/S1535947620311518)
|
| 13 |
|
|
|
|
|
|
|
| 14 |
### **Dataset & Labeling Strategy**
|
| 15 |
|
| 16 |
The dataset was constructed using phosphosite information from **PhosphoSitePlus**, with the following assumptions:
|
|
|
|
| 11 |
|
| 12 |
This repository provides a fine-tuned version of the [ESM-1b]([https://website-name.com](https://huggingface.co/facebook/esm1b_t33_650M_UR50S)) model, trained to classify phosphosites using unlabeled phosphosites(ie, which kinases phosphorylate those phosphosites is unknown) from [PhosphoSitePlus](https://www.phosphosite.org/staticDownloads). The model is designed for binary classification, distinguishing phosphosites from non-phosphorylated peptid sequences [(Musite, a Tool for Global Prediction of General and Kinase-specific Phosphorylation Sites)](https://www.sciencedirect.com/science/article/pii/S1535947620311518)
|
| 13 |
|
| 14 |
+
### **Developed by:**
|
| 15 |
+
Zeynep Işık (MSc, Sabanci University)
|
| 16 |
### **Dataset & Labeling Strategy**
|
| 17 |
|
| 18 |
The dataset was constructed using phosphosite information from **PhosphoSitePlus**, with the following assumptions:
|