The research portfolio of KAUST's Computational Bioscience Research Center (CBRC) encompasses computational biology and bioinformatics with applications in life sciences.
Core activity: Big Data analytics in life sciences
CBRC aims at solving the methodological and practical challenges linked to extracting useful information from Big Data in Health, Medicine, Biology, and Biotechnology. The center focuses on Artificial Intelligence (AI) / Machine Learning (ML) / Deep Learning (DL) and high-performance data analytics for efficient knowledge-, data-, and text-mining. When suitable, we integrate computational approaches with experimental methods for data generation and validation. Applications are in domains of human health, medicine, and biotechnology.
CBRC aims to advance life sciences by developing innovative methods, systems, and resources for targeted knowledge discovery from life science data.
- Design novel computational biology/bioinformatics methods, resources, models, and tools suited for high-performance computing systems that will lead to and speed up the development of applications in Human Health and Medicine, and Biotechnology, and validate these applications.
- Improve the capacity to extract targeted relevant information from biomedical data through Big Data methods and analytics.
- Integrate experimental design, data generation, and data analysis.
- Train high profile specialists in our multi- and inter-disciplinary environment.
- Engage with industrial partners in technology development and transfer.
The latest technological developments in experimental biology, the depth of scientific questions raised, and the demands of genomic sciences clearly demonstrate that bioinformatics and computational biology are necessary key components of the process leading to fundamental discoveries and technological developments. CBRC focuses its resources and activities to three domains:
- Human Health and Medicine,
- Metagenomics, and
The first topic heavily relies not only on the experimental and clinical data but also on AI/ML/DL and integration of information that can only be obtained from high-throughput assays, omics-type experiments including next-generation sequencing (NGS), as well as other information available in biomedical databases. In recent years biology and medicine have witnessed a dramatic increase in the volume of data generated through such experiments. This demands novel computational solutions that can fully exploit the modern computational architectures enabling efficient analyses and necessary scientific insights for many important functional aspects of cellular behavior critical for understanding human diseases and molecular functioning at different levels.
Human Health and Medicine
CBRC addresses problems of
- Identification of disease biomarkers,
- Finding the new uses of existing drugs (drug repurposing/repositioning) and combination of drugs,
- Biomedical/Health knowledge mining,
- Medical informatics,
- Medical metagenomics,
- Specific medical devices.
The studies of environmental samples open ways for a deeper understanding of the role of various microbial communities in their effects on the environment. CBRC has developed a powerful system and data warehouse for deep analyses of functions of microbial communities identified in environmental samples. Although initially, we have been focused on marine metagenomics, now CBRC covers a variety of application domains, including the oil industry and medical metagenomics.
As for the activities in this domain, CBRC focuses on single-cell technologies aimed primarily on identification of novel molecules and diagnostic purposes, and 3D/4D printing of artificial tissues for potential use in various medical applications.