|About this Abstract
||2022 TMS Annual Meeting & Exhibition
||Functional Nanomaterials: Functional Low-Dimensional (0D, 1D, 2D) Materials 2022
||Machine Learning Analysis of Spectral Data Using Bacteria for Signal Amplification
||Hong Wei, Yixin Huang, Peter Santiago , Allon Hochbaum, Regina Ragan
|On-Site Speaker (Planned)
Bacterial metabolism is sensitive to chemistry in the local environment and this stress response can serve as amplifiers of solution chemistry, including measuring nutrient deprivation, which is useful for feedback on growth conditions for the pharmaceutical industry, and detection of toxic heavy metal contaminants in water. Surface enhanced Raman scattering (SERS) sensors with controlled surface chemistry and gold nanogap spacing are used to detect changes in bacterial metabolism. When spectral data is analyzed with machine learning (ML) algorithms, nutrition source deprivation of E.Coli MG1655 strain. For example, changes in metabolism due to changing glucose and sucrose sources as well as the diauxic shift between glucose and xylose are observable. Detection of arsenic (Ⅲ) ions (As3+) and chromium (Ⅵ) ions (Cr6+) is possible at ultralow concentrations. As3+ is detectable at concentrations as low as 0.65 ng/L.
||Machine Learning, Nanotechnology,