General Approach for Machine Learning-Aided Design of DNA-Stabilized Silver Clusters

Abstract

DNA-templated silver clusters (AgN-DNA) are known to exhibit a wide range of fluorescence colors for different choices of the DNA template sequence. While these clusters are promising biosensors and biomarkers, rational design of AgN-DNA is challenged by the huge space of possible DNA template sequences. Recent work employed machine learning methods trained on experimental data to design new DNA templates that select for AgN-DNA color, for the specific case of 10-base DNA oligomers. An important open question is whether such a design process developed for a specific biopolymer template length is applicable at other lengths, with different numbers and diverse configurations of cluster nucleation sites. Here, we develop a flexible design approach that builds on color-correlated DNA base motifs learned from data on more than 2000 10-base DNA oligomers. We test this motif-based design for templates ranging from 8 bases to 16 bases long, for which the sizes of the sequence spaces differ by nearly 5 orders of magnitude. The experimental data show that designed strands of all lengths are selective for AgN-DNA color in the target wavelength band of 600–660 nm, strongly suggesting that color-selective motifs learned for one template length generalize to other lengths. Thus, a motif-based design approach may be broadly suitable for future AgN-DNA applications.