Scientists from Carnegie Mellon University developed SPICEMIX, a machine learning method that allows researchers to better understand the contribution of various spatial patterns to gene expression in complex tissues such as the brain. The study reporting the SPICEMIX method was featured as the main story in the latest edition of Nature Genetics.
Genes that are activated and expressed display similar patterns in cells that share the same type and function across different tissues and organs. By identifying these patterns, our understanding of cells is improved, which can lead to a better understanding of the mechanisms behind diseases.
The emergence of technologies that allow for gene expression analysis in relation to a spatial location in tissue samples has created a need for new computational methods to understand and interpret this data. These methods can aid in the identification and comprehension of gene expression patterns.
Spatial transcriptomics is a technology that allows for the simultaneous analysis of the transcriptomes (the set of all RNAs expressed by a particular cell or tissue) of thousands of individual cells within a tissue section. It does this by using a microscope to image the tissue section and then using a particular type of RNA sequencing (called in situ RNA sequencing) to determine the transcriptomes of each cell in the image. This allows researchers to study the gene expression patterns of cells in their native context rather than dissociating them from the tissue and studying them individually.
Spatial transcriptomics allows the discovery of gene expression patterns in various cells within complex tissues. However, it’s challenging to use this information to figure out what type of cells they are.
SPICEMIX for Understanding Cell Identity
SPICEMIX is an interpretable method that uses probabilistic, latent variable modeling to analyze spatial information and gene expression from spatial transcriptome data. Simulation and real data evaluations show that SPICEMIX significantly improves cell types identification and spatial patterns compared to other methods.
The researchers employed SPICEMIX to examine the transcriptomes of cells in different regions of the brain in both mice and humans. They used the unique features of SPICEMIX to discover the types of cells present and the way they are arranged in the brain.
The researchers named their algorithm SPICEMIX because it is similar to how you can make different flavors with the same set of spices. Similarly, cells may use the same set of biological processes, but the specific combination of these processes gives them their unique identity, just like different flavor combinations.
When used on brain tissue samples, SPICEMIX has been shown to be more effective in identifying different types of cells and their locations within the tissue compared to other techniques. Additionally, it also revealed new information about the gene expression patterns of different brain cell types through the use of spatial metagenes.
The use of Spatial transcriptomics is on the rise, and with the help of a tool called SPICEMIX, scientists can make the most out of the high quantity and complexity of data generated by this technology.
The SPICEMIX algorithm holds the potential to significantly improve spatial transcriptomics research and deepen our understanding of the fundamental processes of biology and how diseases develop and progress in complex tissues.
The implementation of a machine learning method in the field of cell identity understanding has proven to be a valuable advancement. This approach allows for the efficient and accurate analysis of large amounts of data, which in turn enables a deeper understanding of cell identity and function. The ability to identify and classify cells accurately and at a large scale has the potential to greatly enhance our understanding of various biological processes, including disease progression and development. The continued development and application of machine learning techniques in this field hold great promise for the future of cell biology research.
Freely available courses to learn each and every aspect of bioinformatics.
Stay updated with the latest discoveries in the field of bioinformatics.
Dr. Tamanna Anwar is a Scientist and Co-founder of the Centre of Bioinformatics Research and Technology (CBIRT). She is a passionate bioinformatics scientist and a visionary entrepreneur. Dr. Tamanna has worked as a Young Scientist at Jawaharlal Nehru University, New Delhi. She has also worked as a Postdoctoral Fellow at the University of Saskatchewan, Canada. She has several scientific research publications in high-impact research journals. Her latest endeavor is the development of a platform that acts as a one-stop solution for all bioinformatics related information as well as developing a bioinformatics news portal to report cutting-edge bioinformatics breakthroughs.