K-mer-prediction

This is the code associated with the publication ~

prerequisite

We have provided the processed data which if downloaded from https://cbb.ittc.ku.edu/software/kmer/data.zip, you should just copy-paste the link to any web browser and start downloading. You will need to install the following Python 3.7.9 packages to replicate our findings.

1. scikit-learn==0.24.2
2. numpy==1.21.6
3. pandas==1.3.5
4. scipy==1.7.3

If you want to replicate our findings from scratch, you should install the following software as well.

1. FastQC (v0.11.8)
2. Trimmomatic (0.38)
3. Fiona (0.2.10)
4. BWA (0.7.16a-r1185-dirty)
5. MetaPhlAn (version 4.0.3)
6. UProC (1.2.0)
7. KMC3 (3.2.1)

You are strongly suggested to install SRAtools to download the raw data from SRA, but it's not mandatory, find more details from ~/preprocess