genomic sequencies of phages (prokaryotic vriuses) and their hosts

This repository contains data relevant to the reserach Multi-Instance Contrastive Learning with Binomial K-Mers for Phage Host Interaction Prediction. It is comprised of the preprocessed data (data_preprocessed.zip) to quickly reproduce our results and the raw genomic sequencies (data_raw.zip) of phages and hosts, originally from CHERRY's dataset.