Abstract
As global demand for digital storage capacity grows, storage technologies based on synthetic DNA have emerged as a dense and durable alternative to traditional media. Existing approaches leverage robust error correcting codes and precise molecular mechanisms to reliably retrieve specific files from large databases. Typically, files are retrieved using a pre-specified key, analogous to a filename. However, these approaches lack the ability to perform more complex computations over the stored data, such as similarity search: e.g., finding images that look similar to an image of interest without prior knowledge of their file names. Here we demonstrate a technique for executing similarity search over a DNA-based database of 1.6 million images. Queries are implemented as hybridization probes, and a key step in our approach was to learn an image-to-sequence encoding ensuring that queries preferentially bind to targets representing visually similar images. Experimental results show that our molecular implementation performs comparably to state-of-the-art in silico algorithms for similarity search.
Highlights
As global demand for digital storage capacity grows, storage technologies based on synthetic DNA have emerged as a dense and durable alternative to traditional media
Recent advances in DNA nanotechnology have demonstrated synthetic DNA’s ability to carry out molecular computations for biochemical applications, such as gene expression classification[1,2,3,4]. These applications reflect a paradigm shift in the field of DNA computing, away from parallel computing in the style of Adleman’s solution to the traveling salesperson problem[5], and towards DNA strand-displacement circuits[6,7] and algorithmic self-assembly[8,9]. This shift was motivated by the recognition that encoding combinatorial problems requires synthesizing exponential amounts of DNA, and that synthetic DNA is better suited to implement circuits, which autonomously analyze information already encoded in the concentrations and sequences of nucleic acid molecules
To store an arbitrary digital file in DNA, its binary data are translated into a DNA sequence using error-correcting codes that account for limitations and errors in DNA synthesis and sequencing
Summary
Sequence encoder maps similar images to similar DNA sequences. As in our prior work, we focus on encoding feature vectors derived from images, because large datasets and feature extractors are readily available, and similarity between images is easy to visualize. After determining whether or not they are similar, the pair of image feature vectors are encoded independently to produce a pair of softmax-encoded DNA sequences These sequences are passed to the hybridization predictor, which computes local matches in a small sliding window that allows for misalignments (Supplementary Fig. S3B), performs pooling and convolution operations to produce a predicted yield.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
