Tao Feng

This paper introduces HRPredict, a method using one-class SVM and language model-based word vectors to predict plasmid host ranges across bacterial taxa, achieving high accuracy in benchmark tests.

MOBFinder classifies plasmid metagenomic fragments into MOB categories using natural language models, achieving higher accuracy than existing tools.

DeePVP improves PVP identification and classification using deep learning, achieving higher accuracy than existing tools in both tasks.