https://github.com/jcaperella29/lstm_amino_acid_predictor
https://github.com/jcaperella29/lstm_amino_acid_predictor
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/jcaperella29/lstm_amino_acid_predictor
- Owner: jcaperella29
- Created: 2024-11-12T17:12:16.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-11-12T17:21:15.000Z (6 months ago)
- Last Synced: 2024-11-12T18:27:23.295Z (6 months ago)
- Language: Python
- Size: 5.86 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LSTM_amino_acid_predictor
# Amino Acid Prediction with LSTM
This project demonstrates the use of an LSTM model to predict the next amino acid in a synthetic peptide sequence. The project showcases fundamental bioinformatics and deep learning techniques, including synthetic data generation, one-hot encoding, LSTM sequence modeling, and model evaluation.
## Project Overview
1. **Synthetic Data Generation**: Generates short synthetic peptide sequences of variable lengths (10-30 amino acids) using the 20 standard amino acids.
2. **LSTM Model**: Trains an LSTM model to predict the next amino acid in a sequence based on a specified sequence length.
3. **Performance Evaluation**: Evaluates the model with metrics like AUC, sensitivity, and specificity for each amino acid.
4. **Visualization**: Interactive visualizations using Plotly to analyze the model's performance across amino acids.
## Folder Structure
- `main.py`: Main script with LSTM training and evaluation.
- `requirements.txt`: List of required packages.
- `amino_acid_metrics.csv`: Output file with AUC, sensitivity, and specificity for each amino acid (generated by the script).
- `README.md`: Project overview and instructions.
## Installation
1. Clone the repository:
```bash
git clone https://github.com/yourusername/amino-acid-lstm.git
cd amino-acid-lstm
pip install -r requirements.txt
## excute
python main.py