@article{lin_volkel_cao_hook_polak_clark_san miguel_timp_tuck_velev_et al._2024, title={A primordial DNA store and compute engine}, volume={8}, ISSN={1748-3387 1748-3395}, url={http://dx.doi.org/10.1038/s41565-024-01771-6}, DOI={10.1038/s41565-024-01771-6}, journal={Nature Nanotechnology}, publisher={Springer Science and Business Media LLC}, author={Lin, Kevin N. and Volkel, Kevin and Cao, Cyrus and Hook, Paul W. and Polak, Rachel E. and Clark, Andrew S. and San Miguel, Adriana and Timp, Winston and Tuck, James M. and Velev, Orlin D. and et al.}, year={2024}, month={Aug} }
 @article{volkel_lin_hook_timp_keung_tuck_2023, title={FrameD: framework for DNA-based data storage design, verification, and validation}, volume={39}, ISSN={["1367-4811"]}, url={https://doi.org/10.1093/bioinformatics/btad572}, DOI={10.1093/bioinformatics/btad572}, abstractNote={Abstract
               
                  Motivation
                  DNA-based data storage is a quickly growing field that hopes to harness the massive theoretical information density of DNA molecules to produce a competitive next-generation storage medium suitable for archival data. In recent years, many DNA-based storage system designs have been proposed. Given that no common infrastructure exists for simulating these storage systems, comparing many different designs along with many different error models is increasingly difficult. To address this challenge, we introduce FrameD, a simulation infrastructure for DNA storage systems that leverages the underlying modularity of DNA storage system designs to provide a framework to express different designs while being able to reuse common components.
               
               
                  Results
                  We demonstrate the utility of FrameD and the need for a common simulation platform using a case study. Our case study compares designs that utilize strand copies differently, some that align strand copies using multiple sequence alignment algorithms and others that do not. We found that the choice to include multiple sequence alignment in the pipeline is dependent on the error rate and the type of errors being injected and is not always beneficial. In addition to supporting a wide range of designs, FrameD provides the user with transparent parallelism to deal with a large number of reads from sequencing and the need for many fault injection iterations. We believe that FrameD fills a void in the tools publicly available to the DNA storage community by providing a modular and extensible framework with support for massive parallelism. As a result, it will help accelerate the design process of future DNA-based storage systems.
               
               
                  Availability and implementation
                  The source code for FrameD along with the data generated during the demonstration of FrameD is available in a public Github repository at https://github.com/dna-storage/framed, (https://dx.doi.org/10.5281/zenodo.7757762).
               }, number={10}, journal={BIOINFORMATICS}, author={Volkel, Kevin D. and Lin, Kevin N. and Hook, Paul W. and Timp, Winston and Keung, Albert J. and Tuck, James M.}, editor={Kelso, JanetEditor}, year={2023}, month={Oct} }
 @article{lin_volkel_tuck_keung_2020, title={Dynamic and scalable DNA-based information storage}, volume={11}, ISSN={["2041-1723"]}, url={https://doi.org/10.1038/s41467-020-16797-2}, DOI={10.1038/s41467-020-16797-2}, abstractNote={AbstractThe physical architectures of information storage systems often dictate how information is encoded, databases are organized, and files are accessed. Here we show that a simple architecture comprised of a T7 promoter and a single-stranded overhang domain (ss-dsDNA), can unlock dynamic DNA-based information storage with powerful capabilities and advantages. The overhang provides a physical address for accessing specific DNA strands as well as implementing a range of in-storage file operations. It increases theoretical storage densities and capacities by expanding the encodable sequence space and simplifies the computational burden in designing sets of orthogonal file addresses. Meanwhile, the T7 promoter enables repeatable information access by transcribing information from DNA without destroying it. Furthermore, saturation mutagenesis around the T7 promoter and systematic analyses of environmental conditions reveal design criteria that can be used to optimize information access. This simple but powerful ss-dsDNA architecture lays the foundation for information storage with versatile capabilities.}, number={1}, journal={NATURE COMMUNICATIONS}, publisher={Springer Science and Business Media LLC}, author={Lin, Kevin N. and Volkel, Kevin and Tuck, James M. and Keung, Albert J.}, year={2020}, month={Jun} }