Zhenfeng Liu, Ph.D.

Zhenfeng Liu, Ph.D. has an extensive work experience in the field of bioinformatics and data science. From 2019 to present, they have worked as a Bioinformatics Scientist at Zymo Research Corp, where they have developed RNAseq, ChIPseq, miRNAseq bioinformatics pipelines, led the effort to consolidate and clean internal and public methylation array and targeted MethylSeq data to build databases, and performed bioinformatics and statistical analysis on numerous customer projects. From 2018 to 2019, they worked as a Data Science Fellow at Springboard, where they designed machine learning models to predict toxic algal blooms in California with >96% accuracy and built multiple models such as SVM and Gradient Boost from >3000 samples, as well as designed machine learning models to predict whether and how much NBA players improve with both classification and regression models. From 2012 to 2018, they worked as a Computational Scientist at the University of Southern California, where they developed computational pipelines to generate statistical results from >10TB of RNA-Seq and amplicon-seq data, created data visualizations and written publications for >10 projects, and designed experiments, computer simulations, and models to estimate number of RNA molecules in cells. From 2005 to 2012, they worked as a Graduate Research Assistant at Penn State University, where they generated and assembled genomes of ~30 bacteria, discovered 2 important genes through comparative genomics, and was among the first to apply NGS to metatranscriptome studies.

Zhenfeng Liu, Ph.D. received their Bachelor of Science degree in Biological Sciences from Peking University in 2005. Zhenfeng then went on to receive their Doctor of Philosophy in Biochemistry, Microbiology, and Molecular Biology from Penn State University in 2012. In 2018, they completed a Data Science Career Track certification from Springboard.