Machine learning for design of degenerate Cas13a crRNAs using lassa virus as a model of highly variable RNA target.

The design of minimum CRISPR RNA (crRNA) sets for detection of diverse RNA targets using sequence degeneracy has not been systematically addressed. We tested candidate degenerate Cas13a crRNA sets designed for detection of diverse RNA targets (Lassa virus). A decision tree machine learning (ML) algorithm (RuleFit) was applied to define the top attributes that determine the specificity of degenerate crRNAs to elicit collateral nuclease activity. Although the total number of mismatches (0-4) is important, the specificity depends as well on the spacing of mismatches, and their proximity to the 5' end of the spacer. We developed a predictive algorithm for design of candidate degenerate crRNA sets, allowing improved discrimination between "included" and "excluded" groups of related target sequences. A single degenerate crRNA set adhering to these rules detected representatives of all Lassa lineages. Our general ML approach may be applied to the design of degenerate crRNA sets for any CRISPR/Cas system.

A portable array biosensor for detecting multiple analytes in complex samples.

The Multi-Analyte Array Biosensor (MAAB) has been developed at the Naval Research Laboratory (NRL) with the goal of simultaneously detecting and identifying multiple target agents in complex samples with minimal user manipulation. This paper will focus on recent improvements in the biochemical and engineering aspects of this instrument. These improvements have enabled the expansion of the repertoire of analytes detected to include Salmonella typhimurium and Listeria monocytogenes, and also expanded the different sample matrices tested. Furthermore, all components of the biochemical assays could be prepared well in advance of sample testing, resulting in a "plug-and-play" methodology. Simultaneous detection of three toxins (ricin, staphylococcal enterotoxin B, and cholera toxin) was demonstrated using a novel fluidics cube module that limits the number of manipulations to only the initial sample loading. This work demonstrates the utility of the MAAB for rapid analysis of complex samples with multianalyte capability, with a minimum of operator manipulations required for either sample preparation or final analysis.