Deep learning used to reveal mysteries behind gene expression levels
A team of researchers from Chalmers University of Technology, led by SciLifeLab Fellow Aleksej Zelezniak, recently applied deep learning algorithms to 20,000 mRNA datasets in a new study published in Nature Communications. The datasets came from seven different model organisms, ranging from bacteria to Human, and the purpose of the study was to examine the genetic regulatory code controlling mRNA abundance.
Our genes provide the cellular machinery with information about how to produce different kinds of proteins in a process known as gene expression, but so far the mechanisms responsible for determining the exact amount of each protein has remained unclear. The amount of specific proteins in a single cell can range from a few molecules to tens of thousands.
In a new study, led by SciLifeLab Fellow Aleksej Zelezniak, researchers have made a ground-breaking discovery with the help of supercomputers and artificial intelligence. By applying AI algorithms to 20,000 mRNA datasets they could predict the mRNA abundance directly from the DNA sequence and with up to 82% of the variation of transcript levels encoded in the gene regulatory structure.
The results show that most of the information behind quantity regulation can be found embedded in the DNA itself, and that this can be revealed using AI and supercomputers. Understanding the mechanism behind this process can also help us better understand how mutations affect gene expression and thereby unravel many unanswered questions about how cancer arises and functions.
“Co-evolution across coding and non-coding regions suggests that it is not single motifs or regions, but the entire gene regulatory structure and specific combination of regulatory elements that define gene expression levels”, the team writes in their publication.
Aleksej Zelezniak believes that the new method could become an important tool in several research fields – genetics and evolutionary research, systems biology, medicine, and biotechnology, and could be significant for the pharmaceutical industry.
“It is conceivable that this method could help improve the genetic modification of the microorganisms already used today as ‘biological factories’ – leading to a faster and cheaper development and production of new drugs”, says Aleksej, in a press release from chalmers.
Read the entire article and interview here.
STAY UP TO DATE