Kingdom-and-DNAtype-Classification-using-Codon-Bias-Level [DEMO]

Problem Statement:

Given codon usage data, we can train machine learning models which could classify the organism into different classes of Kingdom and DNAtype, if the codon usage data is known.

Dataset

The dataste is taken from UCI machine learning repository LINK

Demo Link

Future Work :

• Deep learning models can also be tried for prediction.
• Custom models can be improved further to increase predictions.
• Some new features can be engineered.
• Instead of two different models for each task, we may also use a single model for the prediction of both DNA type and Kingdom.

References:

• Dataset: https://archive.ics.uci.edu/ml/datasets/Codon+usage
• Github repo for the project: https://github.com/vishalsingha/Kingdom-and-DNAtype-Classification-using-Codon-Bias-Level
• Paper: https://www.biorxiv.org/content/10.1101/2020.10.26.356295v1.full.pdf