LegumeLoc: Deep Learning-based Subcellular Localization Prediction for Legume Crop Proteins

---

Input Data

LegumeLoc server accepts only protein (amino acid) sequence(s) in FASTA format.

Prediction approach

Predictions can be excuted using two different approaches using different models: Fast and Sensitive.

• The Fast mode is good for large number of protein sequences.

• The Sensitive model provides a more accurate prediction at the cost of longer computation time. This approach is useful in annotationg small number of proteins with high-quality prediction.

Development Environment and Prerequisites

This source code was developed in Linux, and has been tested on Linux and OS X. Python v3.7 or above is required.

Installation

LegumeLoc can be installed in two ways:

1. Create a dedicated miniconda3 environment:
• Download LegumeLoc from: https://kaabil.net/legumeloc/download/LegumeLoc.tar.gz
• Download the Miniconda installer: https://docs.conda.io/en/latest/miniconda.html#linux-installers
• Extract the downloaded file:
  • tar -xvzf LegumeLoc.tar.gz
  • cd LegumeLoc
• Create and activate a conda environment:
  • conda env create -f environment.yml
  • conda activate LegumeLoc
  • pip3 install .
2. Install using system Python3
• Download LegumeLoc from: https://kaabil.net/legumeloc/download/LegumeLoc.tar.gz
• Extract the downloaded file:
  • tar -xvzf LegumeLoc.tar.gz
  • cd LegumeLoc
  • pip3 install .

Example

To run LegumeLoc, execute the below command:

• python3 LegumeLoc.py -i ./example/test.fasta -o output -m fast

Queries and Contact

Developed at Kaundal Artificial Intelligence & Advanced Bioinformatics Lab (KAABiL)

For any technical issues or questions related to LegumeLoc, please contact: bioinfo@kaabil.net