Fangfang Xia

This paper addresses data imbalance in drug response prediction by introducing a multi-objective optimization approach using a custom loss function to improve model performance.

The paper introduces a deep learning method called Shutter Island to detect genomic islands by using image-based transfer learning, achieving better generalization than existing tools.

The paper introduces a deep learning method called Operon Hunter to detect operons in bacterial genomes by learning from visual representations of genomic data, achieving better accuracy than existing tools.

Open-source KBase platform unites reference genomes and biochemistry, over 70 apps, Jupyter-based Narratives with provenance, and a Docker SDK for reproducible plant and microbial systems biology.

This study develops an XGBoost-based machine learning model to predict minimum inhibitory concentrations for 20 antibiotics in Klebsiella pneumoniae using whole genome sequencing data, achieving 92% overall accuracy.