Associate Research Scientist
Columbia University Department of Biomedical Informatics
I have a broad background in biomedical science, with specific training and expertise in bioinformatics and biomedical informatics. I am primarily trained in the methods of bioinformatics, statistical learning, machine learning, and their use for biomedical discovery using large-scale genomic data. I used these skills to develop a novel knowledge-guided feature selection method in machine learning related tasks for high-dimensional omics data. In addition to my training in bioinformatics, I am recently trained in clinical informatics, phenotyping, natural language processing, and observational data analysis. I have developed a novel system called Doc2Hpo for interactive and efficient phenotype concept curation from clinical text with automated concept normalization using the Human Phenotype Ontology (HPO). I also developed a user-center clinical trial searching application compatible with OHDSI to reduce the information overload.
1. Liu, C., Yuan, C., Butler, A. M., Carvajal, R. D., Li, Z. R., Ta, C. N., & Weng, C. (2019). DQueST: dynamic questionnaire for search of clinical trials. Journal of the American Medical Informatics Association.
2. Hripcsak, G., Shang, N., Peissig, P. L., Rasmussen, L. V., Liu, C., Benoit, B., … & Gainer, V. S. (2019). Facilitating phenotype transfer using a common data model. Journal of biomedical informatics, 96, 103253.
3. Liu, C., Kury, P., Sampaio, F., Li, Z., Ta, C., Wang, K., & Weng, C. (2019). Doc2Hpo: a web application for efficient and accurate HPO concept curation. Nucleic acids research.