In this interactive tutorial we will preform machine-learning (deep learning) analysis of bacterial DNA gyrase/topoisomerase genes in order to predict resistance to Fluoroquinolones antibiotics. We will used Convolutional Neural Network (CNN) based classifier from Python library of Keras (TensorFlow) to achieve it.
To start the tutorial, click on the Deep_Learning_to_predict_resistance_to_FQ_antibiotics.ipynb which is a Jupyter Notebook interactive format (created this time using Google Colab).
If you want to only step-by-step read through the markedown tutorial, you can stop there. But if you want to run each part of the code yourself, click on the "Open in Colab" icon at the top of the page. You need to change the paths to the input files (fasta and labels) to your Google Drive (mount your Google Drive folders to be accessible with Google Colab, run the 1st code cell). Note: download the fasta and labels files from the input_data folder. You need to decompress the fasta file before use (in linux: gzip -d *.fasta.gz).