A team of scientists at A*STAR’s Genome Institute of Singapore (GIS) and Bioinformatics Institute (BII) has created a new AI software tool named “BANKSY” that can identify the different types of cells found in a tissue, such as muscle cells, nerve cells, and fat cells. This tool goes beyond traditional AI tools that group cells based on similar molecules, by also taking into account how similar the cells’ surroundings in the tissue are.BANKSY is a new AI tool that can group cells together into clusters based on their similarities, as well as considering the similarities of the cells’ surroundings in the tissue. This advanced technology will help researchers better understand tissue processes in various diseases such as cancer and neurological disorders. The development of more effective diagnostics and treatments can be supported by using BANKSY, which will ultimately lead to quicker and more accurate advancements in the field. The research on this breakthrough technology was published in the article “BANKSY unifies cell typing and tissue domain segmentation for scalable sp”
BANKSY published a study on spatial omics data analysis in Nature Genetics on 27 February 2024.
BANKSY has the ability to identify subtle differences in cell groups in spatial molecular profiles from tissue samples. Additionally, BANKSY can also differentiate between functionally distinct anatomical regions in tissue sections, such as layered structures in the human forebrain.
Spatial molecular profiling (Spatial Omics) technologies are advanced microscopes that enable scientists to examine tissues in great detail by revealing the precise locations of individual biological molecules.BANKSY is designed to help biologists analyze the spatial organization of cells and tissues. This understanding is crucial for accurate diagnosis and personalized treatment of patients, as well as for the development of new drugs. BANKSY can interpret and extract insights from the latest Spatial Omics technologies, making it a versatile, accurate, fast, and scalable tool.The software BANKSY is proficient in analyzing both RNA and protein-based Spatial Omics data . It is capable of handling large datasets of over two million cells and has been found to be 10 to 1,000 times faster than competing methods. Additionally, BANKSY is two to 60 times more scalable, making it suitable for other important data-processing tasks such as detecting and removing low-quality areas of the sample, and combining samples from different patients for analysis.
Independent benchmarking has shown that BANKSY is the best-performing algorithm for spatial omics data, with two separate studies concluding that it can be a valuable tool for data analysis.A powerful solution has been developed for domain identification. In a recent study, six algorithms were put to the test, and BANKSY was determined to be the most accurate for data analysis.
Dr Shyam Prabhakar, Senior Group Leader at ASTAR’s GIS, expressed the anticipation that BANKSY will revolutionize the use of emerging Spatial Omics technologies. It is hoped that this tool will enhance understanding of tissue processes in various diseases, leading to more effective treatments for conditions such as cancer and neurological disorders.
The article discusses the development of BANKSY, a new technology aimed at identifying cells that contribute to the growth and spread of tumors. Professor Liu Jian Jun, Acting Executive Director at ASTAR’s GIS, highlights the potential of combining high-throughput technologies with AI software to solve medical problems. Dr Iain Tan, Senior Consultant at the National Cancer Centre Singapore, emphasizes the use of BANKSY to target cells that aid in tumor growth and spread.
Â
