Welcome to the Algorithmic Biology Lab @ GSU
At the Algorithmic Biology Lab, we combine cutting-edge computational techniques with biological insights to tackle some of the most pressing challenges in genomics, bioinformatics, health AI, and medical imaging. Our interdisciplinary team develops innovative algorithms, machine learning models, and data-driven approaches to understand the genetic and molecular basis of diseases, analyze biological sequences, and advance precision medicine.
Our research spans a wide range of topics at the intersection of computer science, biology, and healthcare. Here are some of our key focus areas:
-
Biological Sequence Analysis: We apply machine learning and deep learning techniques to analyze biological sequences, including proteins, viruses, and DNA. Our work includes developing novel embedding methods for sequence classification, feature extraction, and predictive modeling to identify biomarkers and therapeutic targets.
-
Cancer Phylogenetics: Using single-cell sequencing data, we reconstruct the evolutionary history of tumors to identify key mutations and pathways driving cancer progression. This research aims to improve cancer diagnostics and personalized treatment strategies.
-
Computational Antibody Design: We use computational methods to develop pipeline for potential antigen targets, predict antigen-antibody interactions, and optimize antibody design. Our bioinformatics tools and pipelines help accelerate the discovery of new therapies for complex diseases.
-
Medical Imaging and Neuroimaging: We develop advanced machine learning models for analyzing medical and neuroimaging data, including MRI and CT scans. Our work includes: Brain Age Estimation: Predicting brain age from MRI data to study aging and neurodegenerative diseases. Alzheimer’s Disease Detection: Early detection and interpretation of Alzheimer’s disease using multimodal imaging data. Tumor Analysis: Quantifying the impact of brain tumors on brain age and identifying imaging biomarkers for cancer progression.
-
Health AI and Federated Learning: We leverage AI to analyze healthcare data, enabling predictive modeling and decision-making in a privacy-preserving manner. Our research in federated learning allows decentralized analysis of sensitive data across multiple institutions.
Technologies and Methods
We employ a variety of advanced computational and experimental techniques, including:
- Whole-genome and whole-exome sequencing for genetic analysis.
- Machine learning and deep learning for predictive modeling, sequence analysis, and medical imaging.
- Federated learning for decentralized and privacy-preserving data analysis.
- Bioinformatics tools such as BLAST, NCBI Entrez, and MEGA for sequence alignment and evolutionary analysis.
- Medical imaging tools for MRI and CT scan analysis, including 3D CNN, ResNet, and Vision Transformers.
Collaborators
We work with closely with numerous collaborators, including:
- Gianluca Della Vedova, Paola Bonizzoni and Simone Ciccolella at University of Milano-Bicocca, Italy
- Imdad Ullah Khan, Muhammad Shaoib and Khurram Bashir at LUMS, Pakistan
- S. Ashley Byun and Danushka Bandara at Fairfield University, Connecticut
Joining Algorithmic Biology Lab
If you are interested in joining or collaborating, please go to the contact or team page.