Researchers at Carnegie Mellon University have found a new and effective way of characterizing cell types after single-cell RNA sequencing (scRNA-seq).
ktsdesign | Shutterstock
The new method involves the use of neural networks and supervised machine learning techniques rather than marker genes, which are not available to all cell types.
With the help of this new automated technology, researchers can analyze all scRNA seq data and select only the parameters needed to differentiate one type of cell from another. This allows researchers to analyze and compare all types of cells.
The authors of the study also describe a web server called scQuery that allows the technology to be used by any researcher.
In recent years single cell sequencing has become a popular tool that allows researchers to identify subtypes of cells or to see the difference between a healthy and healthy cell or a young compared to the aged cell.
Previously, researchers could only process lots of cells to get results that reflected an overall average of their value.
The new method, which has recently been described in the newspaper nature Communications, will be used as part of the National Institutes of Health's new Human BioMolecular Atlas Program, which creates a 3D map of the human body that will show how tissues differ on a cellular level.
The calculation biologist Amir Alavi says that the hundreds of thousands of data points generated with each experiment create a "Big Data" problem that traditional analysis methods can not handle.
Alavi and colleagues developed an automated pipeline with the purpose of downloading all public scRNA seq data available on mice from the largest repositories so that genes and proteins expressed in each cell could be identified.
The cells were then labeled according to type and a calculated neural network modeled on the human brain was used to compare individual cells and identify parameters that distinguish them.
To test the model, Alavi and the team used scRNA-seq data from a animal study of a disease similar to Alzheimer's. As expected, similar numbers of brain cells were seen in both healthy and diseased tissues, with the diseased tissue comprising significantly more immune cells as an answer to disease.
The researchers used their automated pipeline and methods to develop the scQuery web server, accelerating comparative analysis of new scRNA seq data.
Once a single-cell experiment has been entered into scQuery, the team's neural network and matching methods identify rapidly related related subtypes of cells, as well as previous studies of similar cells.
Neural networks substitute marker genes for single cell RNA sequencing analysis. EurekAlert. 13th November 2018