糖心Vlog

Proteins, often called the building blocks of life, play a central role in drug development. When scientists develop new treatments, they must understand how drugs interact with proteins involved in disease mechanisms and with proteins in the human body that influence drug response.

Scientists commonly use cryo-electron microscopy (cryo-EM) 3D imaging data to study proteins. While recent advances have enabled higher-resolution images that are easier to analyze, medium-resolution images鈥攚hich are more difficult to interpret鈥攁re still the most common for larger protein complexes.

Salim Sazzed, Ph.D., an assistant professor in the computer science department of 糖心Vlog鈥檚 Allen E. Paulson College of Engineering and Computing, has been awarded a two-year National Science Foundation grant of about $175,000 to lead a groundbreaking project to develop novel Artificial Intelligence (AI) techniques for determining protein secondary structures from medium-resolution cryo-electron microscopy (cryo-EM) images.

Improved modeling from medium-resolution images will help researchers study more proteins efficiently, giving new insights into diseases and potentially guiding the development of new treatments and future drugs.

At its core, this research will combine biology and machine learning to study protein structures. The multidisciplinary approach and potential impacts on public health are what most excite Sazzed.

鈥淭he impetus behind this research is the positive impact on public health and possibly contributing to the biomedical workforce,鈥� he said. 鈥淪eeing biology and computer science combine for that kind of impact is incredibly moving.鈥�

As the Principal Investigator (PI) for the project, Sazzed will use his expertise in deep learning computer models to focus on a major challenge in structural biology: identifying the two main secondary structures of proteins鈥攖he alpha helix and the beta sheet. These structures are critical for a protein鈥檚 overall shape and function, but in medium-resolution cryo-EM images they often appear indistinct or lack clear detail, making them particularly difficult to analyze.

Sazzed鈥檚 research will focus on two main goals. First, he will quantify the variability of alpha helices and beta sheets in medium-resolution images, comparing them to idealized structures. Second, by integrating this structural variability with the image data in a deep learning model, he will aim to generate more precise and accurate representations of protein secondary structures.

鈥淲hen we feed this information into a deep learning model along with the image data, the model should be able to determine protein secondary structures more precisely,鈥� Sazzed elaborated.

Sazzed believes students will greatly benefit from this multi-disciplinary approach. In addition to a Ph.D. student, several undergraduate students will be directly engaged in the research. A full-day workshop will also be organized, allowing Georgia Southern students from diverse disciplines to participate. This initiative will build on Georgia Southern鈥檚 strong tradition of involving undergraduates in research and will support the University鈥檚 recent focus on biomedical and health sciences.

鈥淭here are many different knowledge areas coming together in this work,鈥� Sazzed said. 鈥淚t involves computer science, biology, chemistry, and even public health. I look forward to students following the research and exploring these different fields themselves.鈥�

Allen E. Paulson College of Engineering & Computing Interim Associate Dean of Research, Masoud Davari, Ph.D., echoes this sentiment and emphasizes its importance to the University鈥檚 research profile.

鈥淪azzed鈥檚 interdisciplinary research, which bridges the gap between biology and computer science, will foster multidisciplinary research in our college鈥攁s it is cutting-edge and potentially groundbreaking in drug development to impact people鈥檚 lives nationally and globally,鈥� Davari said. 鈥淚t鈥檚 also well aligned with the college鈥檚 strategic research plan鈥攁s we make the move to R1 status to be aligned with 鈥楽oaring to R1,鈥� which is among the transformational initiatives for the University.鈥�