NCM 2022: Direct high-throughput deconvolution of unnatural bases via nanopore sequencing and bootstrapped learning

The discovery of synthetic xeno-nucleic acids (XNAs) that can basepair as unnatural bases (UBs) to expand the genetic alphabet has spawned interest in many applications, from synthetic biology to DNA storage. However, the inability to read XNAs in a direct, high-throughput manner has been a significant limitation for xenobiology. We demonstrate that XNA-containing templates can be directly and robustly sequenced (>2.3 million reads/flowcell, similar to DNA controls) on a MinION sequencer from Oxford Nanopore Technologies to obtain signal data that is significantly different relative to natural bases (median fold-change >5). To enable training of machine learning models that directly call XNAs along with natural bases, we developed a framework to synthesize a complex pool of 1,024 XNA-containing templates with different sequence contexts and high XNA purity (>90% on average). Combining this with a bootstrapping approach to filter non-XNA-containing templates during machine learning, we show that a model can be trained to call natural as well as unnatural bases with high accuracy (>91%). These results highlight the versatility of nanopore sequencing as a platform for interrogating nucleic acids for xenobiology applications, and the potential to study genetic material beyond those that use canonical bases.