Sun, March 3, 3:00 PM
90 MINUTES
Utilizing Machine Learning in Bioinformatics and Computational Biology

Machine Learning (ML) and Deep Learning (DL) have emerged as powerful tools in addressing complex issues within Bioinformatics and Computational Biology, offering promising alternatives to traditional experimental and computational methodologies. At the Machine Learning, Bioinformatics, and Computational Biology (MLBC) lab at Center for Computational and Integrative Biology (CCIB) at Rutgers University, Camden, we are dedicated to tackling a wide range of challenging problems. These include predicting protein folding, structural classification, subcellular localization, and post-translational modifications (PTMs), alongside problems in biomedical image processing, cancer detection, and cancer subtype identification. Our approach involves leveraging various classification techniques, with an emphasis on deep learning architectures trained on novel features extracted from evolutionary and structural properties of proteins and genes. In this presentation, I will discuss both past and ongoing research aimed at constructing integrated models to tackle these challenges, while also outlining future directions for solving these crucial issues.

Iman Dehzangi

Assistant Professor @ Rutgers University

Iman Dehzangi received the B.Sc. degree in Computer Engineering-Hardware from Shiraz University, Iran in 2007, the master’s degree in Bioinformatics from Multimedia University (MMU), Cyberjaya, Malaysia in 2011, and the Ph.D. degree in Bioinformatics and computational biology from Griffith University, Brisbane, Australia. He is currently an Assistant Professor at the department of computer science and a member of Center for Computational and Integrative Biology (CCIB) at Rutgers University, Camden, NJ, USA. His research focus is on machine learning, deep learning, artificial intelligence, and bioinformatics & computational biology in general. Specifically, his aim is to work on the challenges associated with the design and development of robust, general, and accurate systems for several important problems in bioinformatics and computational biology such as, protein local and global structure prediction, genome variants analysis, cancer subtype classification, and studying the impact of somatic mutations in cancer research. His research in these areas has led to more than 100 publications in prestigious peer-reviewed journals and conferences with over 4200 citations according to Google scholar citations. He has also been awarded several scholarships including full scholarship to conduct bachelor’s degree (Shiraz University), Griffith University Higher Degree Research scholarship (GUPRS), Griffith University International Postgraduate Research Scholarship (GUIPRS), and National ICT Australia (NICTA) research scholarship.