Using AI to identify genetic trade-offs between types of mutations

(2022). DOI: 10.1016 / j.celrep.2022.111351″ width=”800″ height=”530″/>

Graphic abstract. attributed to him: cell reports (2022). DOI: 10.1016 / j.celrep.2022.111351

A team of researchers at Southern Medical University has developed an application of artificial intelligence to help identify genetic trade-offs between different types of mutations that have occurred as humans evolved. In their paper published in the magazine cell reportsthe group describes how they used data from existing genome assemblies to teach their system and what it showed when exposed to new data.

Previous research has shown that as creatures evolve, mutations occur. mutations that remain in genome It is what leads the organism to evolution. Previous research has also shown that some mutations lead to direct benefits, such as the ability to process certain foods, allowing a creature to exist in a new environment. On the other hand, other spikes sometimes just keep riding. They do not necessarily provide any benefits but remain in the genome by mistake or due to the proximity of genes that provide benefit.

Scientists who study genomes have long wanted a tool that could be used to determine which mutations in the human genome were favored and which were merely mere mobile. In this new effort, researchers have developed such a tool, although it remains unclear how useful it really is.

The tool called DeepFavored was created by developing a file deep learning The AI ​​system fed with data from the menu Genome-wide association studies To learn from the experiences of other researchers working on previous specific efforts. Those the team included were restricted to alleles related to diet and other metabolic activities, as well as mutations that allowed to deal with differences in climate – the focus was on humans’ unique ability to adapt to many different parts of the planet. The team then ran the tool over three separate groups and found what they describe as examples of hiking mutations that lead to susceptibility to disease.

When testing their new gadget, the researchers also found what they describe as a favorite mutations among the three populations tested. They suggest that their overall findings suggest that their tool is able to find evidence of mutational trade-offs in human genes. They also compared results from DeepFavored with two other algorithms created by other teams and found that it outperformed both.


Using machine learning to find mutations in genome sequences similar to cancer samples


more information:
Ji Tang et al, Uncovering the broad trade-off between adaptive development and disease susceptibility, cell reports (2022). DOI: 10.1016 / j.celrep.2022.111351

© 2022 Science X Network

the quote: Using Artificial Intelligence to Identify Genetic Trade-offs Between Mutation Types (2022, September 19) Retrieved September 20, 2022 from

This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.