Machine Learning in Computational Biology
We are using and developing cutting-edge AI and machine learning algorithms to help answer challenging biological, medical and environmental questions.
Participants
Summary
Working with our collaborators, the Wu group have been developing powerful Machine Learning algorithms to address challenging computational problems derived from biology and environmental sciences, including hierarchical clustering in evolutionary analysis, hidden Markov chain models in population genomics, and phylogenetic networks. More recently, we are increasingly exploring applications of artificial intelligence and deep learning models to improve our understanding of hidden patterns in large and complex genomic and phenotypic datasets from basic, clinical, and environmental research projects.
)
The brown lines represent the lineages of the first-wave “Out of Africa” migration, and the brown-green line represents the lineages admixed by the two-wave “Out of Africa” migration, and the brown-green line represents the lineages admixed by the two-wave “Out of Africa” migration. Red arrow lines represent the Neanderthal-like introgression events and blue arrow lines represent the Denisovan-like introgression events. Shadow areas of different colors stand for different continents/regions.
Partners
Publications
[1]Xu, J., Cui, L., Zhuang, Z., Meng, Y., Bing, P., He, B., Tian, G., Choi, K.P., Wu, T., Wang, B., and Yang, J. (2022) Evaluating the performance of dropout imputation and clustering methods for single-cell RNA sequencing. Computers in Biology and Medicine, 146:105697.
[2]Yuan, K., Ni, X., Liu C., Pan Y., Deng, L., Zhang, R., Gao. Y., Ge, X., Liu J., Ma, X., Lou, H., Wu, T., and Xu, S. (2021) Refining models of archaic admixture in Eurasia with ArchaicSeeker 2.0. Nature Communications, 12:6232.