Advanced biomedical research requires systems biology approaches where bioinformatics and computation biology play an important role. The primary research in Laboratory of Computational Functional Genomics is the development of methods for analysis and integration of omics data to understand underlying mechanisms, derive new hypotheses, and identify therapeutics in human and animal studies. We are also interested in modeling host-microbiome interaction to understand its role in shaping the wellness or disease of the human body.


    11.12.2018. Jingting passed the Ph.D. Preliminary Exam. Title: Computational Analysis of DNA Methylation and Gene Regulation. Congrats!
    08.16.2018. Congrats to Ahmed on the new postdoc position at Standford!
    05.16.2018. The R package “MetaLonDA” enjoyed more than 2100 downloads since its release in January 2018. Well done, Ahmed!
    05.16.2018. Congrats to Ahmed on successful Ph.D. thesis defense (Title: Computational Methods for Longitudinal Microbiome Analysis: Identification, Modeling, and Classification).
    08.30.2017. Congrats to Peter Larsen on successful Ph.D. thesis defense!
    06.07.2017. Ahmed’s new paper was accepted for oral presentation at the ACM BCB 2017 held at Boston. Congrats!
    06.01.2017. Derek’s paper was accepted for oral presentation at EMBC2017 held in Korea.Congrats!
    05.25.2017. Ahmed passed the Ph.D. Preliminary Exam. Title: Computational Methods For Longitudinal Microbiome Analysis: Identification, Modeling, and Classification. Congrats!
    05.18.2017. Ahmed won the 2nd place for poster “Microbiome Dynamics as Predictors of Lung Transplant Rejection” at GLBIO2017 at Chicago. Congrats!

The GPU awarded from NVIDIA for deep learning

The microbiome has been shown to have an impact on the development of various diseases in the host. Being able to make an accurate prediction of the phenotype of a genomic sample based on its microbial taxonomic abundance profile is an important problem for personalized medicine. We developed a deep learning framework, a Convolutional Neural Network (CNN), for such a prediction. To facilitate the CNN learning, we explore the structure of abundance profiles by creating the phylogenetic tree and by designing a scheme to embed the tree to a matrix that retains the spatial relationship of nodes in the tree and their quantitative characteristics. The proposed CNN framework is highly accurate, achieving a 99.47% of accuracy based on the evaluation on a dataset 1967 samples of three phenotypes. Our result demonstrated the feasibility and promising aspect of CNN in the classification of sample phylotype.

Link to the project

Lab Location (West Campus)

Department of Bioengineering, 835 South Wolcott Avenue, CSN, Suite W100, Rm.164E, Chicago, Illinois 60612