Trade-offs in model compression for sequencing data-carrying DNA

DNA is a leading candidate as the next archival storage media due to its density, durability and sustainability. To read (and write) data DNA storage exploits technology that has been developed over decades to sequence naturally occurring DNA in the life sciences. To achieve higher accuracy for previously unseen, biological DNA, sequencing relies on extending and training deep machine learning models known as basecallers. This growth in model complexity requires substantial computational resources. It also eliminates the possibility of a compact read head for DNA as a storage medium. We argue that we need to depart from blindly using sequencing models from the life sciences for DNA data storage. The difference is striking: for life science applications we have no control over the DNA, however, in the case of DNA data storage, we control how it is written, as well as the particular write head. More specifically, data-carrying DNA can be modulated and embedded with alignment markers and error correcting codes to guarantee higher fidelity and to carry out some of the work that the machine learning models perform. In this paper, we focus on the basecalling models used to read back data from DNA storage. Specifically, we study trade-offs between the size of the basecalling model and the accuracy with which the data is read. We show that while model compression reduces the model size considerably, the loss in accuracy can be compensated by using simple error correcting codes in the DNA sequences. While error correction codes also require space in the DNA sequence, we show experimentally that the associated overhead is marginal. In our experiments, we show that a substantial reduction in the size of the model does not incur an undue penalty for the error correcting codes used. Crucially, we show that through the joint use of model compression and error correcting codes, we achieve a higher read accuracy than without compression and error correction codes.