I do not share about my fiction writing much on my blog.
So, this article caught my attention for how DNA computing may soon be viable.
Thanks for tuning in.
AI can decode digital data stored in DNA in minutes instead of days
A new AI-based method can accurately recover digital data from DNA strands nearly 90 times faster than older techniques, raising the possibility of practical DNA storage for computing
By Jeremy Hsu
21 February 2025
Artificial intelligence can read data stored in DNA strands within 10 minutes rather than the days required for previous methods, bringing DNA storage closer to practical use in computing.
“DNA can store vast amounts of data in an extremely compact form and remain intact for thousands of years,” says Daniella Bar-Lev at the University of California, San Diego. “Additionally, DNA is naturally replicable, offering a unique advantage for long-term data preservation.”
But retrieving the information encoded within DNA is a monumental challenge because the strands are mixed and jumbled together when stored. During the data-encoding process, individual strands are sometimes replicated imperfectly, and some fragments may be lost entirely. As a result, reading data stored in DNA can resemble reconstructing a book from a box filled with shredded, typo-ridden pages.
“Traditional methods struggle with this chaos, requiring days of processing,” says Bar-Lev. The new approach “streamlines this with AI trained to spot patterns in the noise”, she says.
Bar-Lev and her colleagues developed an AI-powered method called DNAformer that can quickly and accurately decode jumbled DNA sequences. The system includes a deep learning AI model trained to reconstruct DNA sequences, a separate computer algorithm that identifies and corrects errors and a third decoding algorithm that converts everything back into digital data while fixing any remaining mistakes.
In experiments, DNAformer could read 100 megabytes of DNA-stored data nearly 90 times faster than the next fastest method – which was developed with traditional, rules-based computing algorithms – while achieving better or comparable accuracy. The decoded data included a coloured image of test tubes, a 24-second audio clip of astronaut Neil Armstrong’s famous moon landing speech and written text about why DNA is a promising data storage medium.
The team plans to develop versions of DNAformer tailored to newer techniques for encoding data into DNA, says Omer Sabary at Technion – Israel Institute of Technology.
“Crucially, because our approach does not rely on specific [DNA] synthesis or sequencing methods, it can be adapted to future, as-yet-undeveloped technologies that may be more commercially viable,” he says.
Journal reference
Nature Machine Intelligence DOI: 10.1038/s42256-025-01003-z
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
- New note - On 1807.06, I ceased daily transmission of my Hey Mom feature after three years of daily conversations. I post Hey Mom blog entries on special occasions. I post the days since ("Days Ago") count on my blog each day, and now I have a second count for Days since my Dad died on August 28, 2024. I am now in the same time zone as Google! So, when I post at 10:10 a.m. PDT to coincide with the time of Mom's death, I am now actually posting late, so it's really 1:10 p.m. EDT. But I will continue to use the time stamp of 10:10 a.m. to remember the time of her death and sometimes 13:40 EDT for the time of Dad's death. The blog entry numbering in the title has changed to reflect total Sense of Doubt posts since I began the blog on 0705.04, which include Hey Mom posts, Daily Bowie posts, and Sense of Doubt posts. Hey Mom posts will still be numbered sequentially. New Hey Mom posts will use the same format as all the other Hey Mom posts; all other posts will feature this format seen here.
No comments:
Post a Comment