brunoasm/varkoder repository overview

A tool that uses variation in K-mer frequecies as DNA barcodes.

This python program can generate varKodes from raw reads, which are images encoding the relative frequencies of different k-mers in a genome. It can also train a convolutional neural network to recognize species based on these images, and query new samples using a trained model.

For more information see below:

⁠Preprint:

de Medeiros, B.A.S, et al.. (2024). A universal DNA barcode for the Tree of Life. EcoEvoRxiv. https://doi.org/10.32942/X24891⁠

⁠GitHub repository:

https://github.com/brunoasm/varKoder⁠