ViTAL deep learning models for lineage assignment under low coverage

ViTAL, is a lineage assignment algorithm which inputs a low-coverage genome, transforms it into embedded genome fragments which are then fed into a classification neural network, that outputs the most likely lineages the input genome might belong to. The ViTAL algorithm is therefore divided into preprocessing phase (MinHash) followed by embedding, and the classification phase (Vision Transformer). The upload contains trained models for lineage assignment.