The Evo can design DNA sequences to manipulate cell functions, create new genes, and even develop an entirely new CRISPR gene-editing system
read more
A team of bioengineers, computer scientists, and AI specialists from the Arc Institute and Stanford University joined hands to develop an AI-based model which is capable of decoding and designing genetic sequences. In their research paper published in the journal Science, the group elucidated the factors that went into designing and building the innovative model.
While listing multiple possible uses of the model, the researchers named it Evo. Meanwhile, Christina Theodoris, with the Gladstone Institute of Cardiovascular Disease, published a perspective piece on it in which she suggested that the development of Evo could have major implications for medical research along with treating several diseases in the future.
The Evo can design DNA sequences to manipulate cell functions, create new genes, and even develop an entirely new CRISPR gene-editing system. As per the research paper, the “multimodal machine learning model” has been trained on “2.7 million evolutionarily diverse microbial genomes in order to decode and design DNA, RNA, and protein sequences from the molecular to genomic scale” with unparalleled accuracy.
The ‘Rosetta Stone’ of biology
It is pertinent to note that this is the first foundation model trained to design DNA to this extent. It has been described by the Arc Research Institute in Palo Alto, where it was developed, as the “Rosetta Stone” of biology.
As per the paper, EVO uses deep learning techniques to efficiently process long sequences of genetic data. This allows it to develop an understanding of the interplay of the genetic code. The model can predict how small DNA changes can affect the evolutionary fitness of an organism and generate realistic, genome-length sequences more than one megabase in length that greatly surpass prior models.
As per the study, EVO is equipped with seven billion parameters and uses frontier, deep-learning architecture to model biological sequences at a single-nucleotide resolution.
“Further development of large-scale biological sequence models like Evo, combined with advances in DNA synthesis and genome engineering, will accelerate our ability to engineer life,” the researchers concluded.
This post was originally published on here
