IonNTxPred

A computational framework for predicting and designing ion channel-impairing proteins using alignment-based, machine learning, and protein language model-based methods.

📌 Introduction

IonNTxPred is developed to help researchers identify proteins and peptides that modulate ion channels such as sodium (Na⁺), potassium (K⁺), calcium (Ca²⁺), and others. It integrates traditional ML models, motif discovery, and state-of-the-art protein language models (PLMs) to deliver accurate predictions and insightful biological analysis. It employs large language model for predicting toxic activity against ion channel. The final model offers Prediction, Protein-Scanning, and Design modules, implemented using protein language models.

🔗 Visit the web server for more information: IonNTxPred Web Server

🔗 Visit the Hugging Face: IonNTxPred

📖 Please cite relevant content for complete details, including the algorithm behind the approach.

📚 Reference

Rathore et al. LLM-based Prediction and Designing of Ion Channel Impairing Proteins. #Coming Soon#

🖼️ IonNTxPred Workflow Representation

🧪 Quick Start for Reproducibility

Follow these steps to replicate the core results of our paper:

# 1. Clone the repository
git clone https://github.com/raghavagps/IonNTxPred.git
cd IonNTxPred

# 2. Set up the environment (conda recommended)
conda env create -f environment.yml
conda activate IonNTxPred

# 3. Download pre-trained models
# Visit: https://webs.iiitd.edu.in/raghava/IonNTxPred/download.html
# Download the model ZIP and extract it in the root directory

# 4. See the available optiopns
python ionntxpred.py -h

# 5. Run prediction on sample input
python ionntxpred.py -i example.fasta -o output.csv  -j 1 -m 1 -wd working_direcotory_path

🛠️ Installation Options

🧰 Pip Installation

To install IonNTxPred via PIP, run:

pip install ionntxpred

To check available options, type:

ionntxpred -h

🔹 Standalone Installation

IonNTxPred is written in Python 3 and requires the following dependencies:

✅ Required Libraries

python=3.10.7
pytorch

Additional required packages:

pip install scikit-learn==1.5.2
pip install pandas==1.5.3
pip install numpy==1.25.2
pip install torch==2.1.0
pip install transformers==4.34.0
pip install joblib==1.4.2
pip install onnxruntime==1.15.1
Bio (Biopython): 1.81
tqdm: 4.64.1
torch: 2.6.0

🔹 Installation using environment.yml

1. Create a new Conda environment:

conda env create -f environment.yml

2. Activate the environment:

conda activate IonNTxPred

⚠️ Important Note- 1

• Due to the large size of the model file, the model directory has been compressed and uploaded.
• Download the zip file from Download Page.
• Extract the file before using the code or model.

⚠️ Important Note- 2

• Due to the large size of the model file, the model directory has been compressed and uploaded.
• Download the zip file from Download Page.
• Extract the file before using the code or model.

🔹 BLAST+ Dependency

IonNTxPred requires BLAST+ version 2.17.0+ for running the Hybrid model.

• Download the blast binaries file from Download Page. Please download the BLAST+ binary compatible with your operating system:

• Linux (x64): ncbi-blast-2.17.0+-x64-linux.tar.gz

• macOS (x64/arm64): ncbi-blast-2.17.0+-x64-macosx.tar.gz

• Windows (x64): ncbi-blast-2.17.0+-x64-win64.tar.gz

🔗 NCBI BLAST+ Download Page

After downloading:

# Example for Linux
tar -xvzf ncbi-blast-2.17.0+-x64-linux.tar.gz

---

## 🔬 Classification
**IonNTxPred** classifies peptides and proteins as **ion channel impairing or non-impairing** based on their primary sequence.

🔹 **Model Options**
- **ESM2-t33**
- **Hybrid model (ESM2-t33+BLAST)**: Default Mode **

---

## 🚀 Usage

### 🔹 Minimum Usage
```bash
ionntxpred.py -h

To run an example:

ionntxpred.py -i example.fasta

🔹 Full Usage

usage: ionntxpred.py [-h]
                   [-i INPUT]
                   [-o OUTPUT]
                   [-t THRESHOLD]
                   [-j {1,2,3,4,5}]
                   [-c {1,2,3,4}]
                   [-m {1,2}]
                   [-d {1,2}]
                   [-wd WORKING DIRECTORY]

Required Arguments

📂 Input & Output Files

✅ Input File Format

IonNTxPred supports two formats:

1. FASTA Format: (Example: example.fasta)
2. Simple Format: (Example: example.seq, each sequence on a new line)

✅ Output File

• Results are saved in CSV format.
• If no output file is specified, results are stored in outfile.csv.

🔍 Jobs & Features

🔹 Job Types

🔹 Additional Options

📑 Package Contents

📦 PIP Installation (Again for Reference)

pip install ionntxpred

Check options:

ionntxpred -h

🚀 Start predicting toxicity with IonNTxPred today!

🔗 Visit: IonNTxPred Web Server