Can Evo AI Read DNA Sequences and Explain Their Function?

Researchers describe an AI model, schooled on billions of lines of genetic sequences, that can deduce how bacterial and viral genomes operate and use that information to design new proteins and even whole microbial genomes.

Here, we present a comprehensive, unbiased benchmark of five models (DNABERT-2, Nucleotide Transformer V2, HyenaDNA, Caduceus-Ph, and GROVER) across diverse genomic and genetic tasks including sequence classification, gene expression prediction, ...

The results were largely consistent when evaluating the annotations at region level through SOV scores38, although the improvement over AUGUSTUS was smaller for the whole-chromosome test set compared with the nucleotide-level metrics (Fig. 4f–h). Overall, our results agree with the limitations of this type of tools when scanned through the whole genome, in contrast to their very high accuracy when segmenting a genic region, and highlights the superior performance of SegmentNT on the complex task of whole-genome segmentation.

The function of most genes is unknown. The best results in automated function prediction are obtained with machine learning-based methods that combine multiple data sources, typically sequence derived features, protein structure and interaction data. Even though there is ample evidence showing that a gene’s function is not independent of its location, the few available examples of gene function prediction based on gene location rely on sequence identity between genes of different organisms and are thus subjected to the limitations of the relationship between sequence and function.

In summary, deep learning techniques have made significant breakthroughs in the field of TE annotation. Despite of offering higher identification accuracy, they are able to handle diversity across different species and individuals more effectively, addressing the challenges posed by TE evolution and variation. These tools not only enhance our understanding of TEs in the genome but also provide vital resources for further research into genome evolution, function and regulation.

Checking your browser before accessing pmc.ncbi.nlm.nih.gov · Click here if you are not automatically redirected after 5 seconds

Checking your browser before accessing pmc.ncbi.nlm.nih.gov · Click here if you are not automatically redirected after 5 seconds

The answer was a resounding “yes.” The machine learning models succeeded in identifying human-specific (and fruit fly-specific) DNA sequences. Importantly, the AI-predicted functions of the extreme sequences were verified in Kadonaga’s ...

Evo 2 also includes machine learning models that will tell you if the sequence exists in nature and predict how this new sequence will function in real life. Then we go into the lab and synthesize the DNA and insert it into a living cell to ...