Full Electronic Multiplexed Nucleic Acid Detection via Machine Learning Enhanced Solid-State Nanopore Sensing

NSF Award Search · 01002627DB NSF RESEARCH & RELATED ACTIVIT · $494,396 · view on nsf.gov ↗

Abstract

Accurate and affordable detection of respiratory infections remains difficult outside centralized laboratories. Many respiratory pathogens circulate at the same time and produce similar symptoms, which makes rapid diagnosis challenging. This project will develop a compact electronic approach for multiplex nucleic acid detection that avoids the optics, fluorescent probes, and gel-based analysis used in many current tests. The work addresses a fundamental problem in molecular diagnostics: how to convert complex biochemical reactions into simple and reliable electronic signals. If successful, the project will advance portable molecular testing, support broader access to timely infectious disease detection, and strengthen the scientific foundation for next-generation diagnostic technologies. The project will also contribute to education and workforce development through curriculum modules, mentored student research, and community-facing activities that introduce biosensing, nanotechnology, and data-driven health technologies to broad audiences. This project will develop the electronic Multiplexed Amplicon Profiling (eMAP) platform, a fully electronic and probe-free framework that integrates single-pot multiplex recombinase polymerase amplification (RPA), solid-state nanopore sensing, and machine-learning-based signal classification for automated, gel-free molecular readout. Using a respiratory pathogen panel as a model system, the work has three aims. Aim 1 will develop and optimize a multi-target RPA assay with balanced amplification and minimal cross-reactivity. Aim 2 will establish a nanopore-machine-learning analytical engine that extracts multidimensional event-level current features and classifies amplicons across pores, voltages, and experimental variability. Aim 3 will integrate the assay and analytical engine into the complete eMAP workflow and evaluate performance through blinded zero-shot testing and benchmarking against conventional gel-based analysis for

Key facts

NSF award ID
2603909
Awardee
Indiana University (IN)
SAM.gov UEI
YH86RTW2YVJ4
PI
Weihua Guan
Primary program
01002627DB NSF RESEARCH & RELATED ACTIVIT
All programs
Artificial Intelligence (AI), Sensor Technology
Estimated total
$494,396
Funds obligated
$494,396
Transaction type
Standard Grant
Period
05/01/2026 → 04/30/2029