Machine learning-assisted single-cell Raman fingerprinting for in situ and nondestructive classification of prokaryotes

Abstract

Summary Accessing enormous uncultivated microorganisms (microbial dark matter) in various Earth environments requires accurate, nondestructive classification, and molecular understanding of the microorganisms in in situ and at the single-cell level. Here we demonstrate a combined approach of random forest (RF) machine learning and single-cell Raman microspectroscopy for accurate classification of phylogenetically diverse prokaryotes (three bacterial and three archaeal species from different phyla). Our RF classifier achieved a 98.8 ± 1.9% classification accuracy among the six species in pure populations and 98.4% for three species in an artificially mixed population. Feature importance scores against each wavenumber reveal that the presence of carotenoids and structure of membrane lipids play key roles in distinguishing the prokaryotic species. We also find unique Raman markers for an ammonia-oxidizing archaeon. Our approach with moderate data pretreatment and intuitive visualization of feature importance is easy to use for non-spectroscopists, and thus offers microbiologists a new single-cell tool for shedding light on microbial dark matter.

Resonance Raman analysis of intracellular vitamin B12 analogs in methanogenic archaea

“…In recent years, Raman microspectroscopy has proven itself useful for analyzing microbial cellular activity in environmental samples [18][19][20] and for discriminating microbial species at the single-cell level. 21,22 Here, we demonstrate that resonance Raman microspectroscopy can selectively detect intracellular cobamides in methanogenic cells.…”

Surface-Enhanced Raman Scattering Spectroscopy Reveals the Phonon Softening of Yttrium-Doped Barium Zirconate Thin Films

“…The background of each spectra was subtracted using an iterative method (see details in Supporting Information, Figure S1) . All background-subtracted spectra were normalized using the vector normalization method . In this method, the Raman intensity of each spectrum was divided by the square root of the sum of the squared intensities of the spectrum (Supporting Information).…”

“…34 All background-subtracted spectra were normalized using the vector normalization method. 35 In this method, the Raman intensity of each spectrum was divided by the square root of the sum of the squared intensities of the spectrum (Supporting Information). The spectra for each of the films were obtained by averaging the respective normalized spectra.…”

Label-free identification of spore-forming bacteria using ultra-broadband multiplex CARS (coherent anti-Stokes Raman scattering) microspectroscopy

“…To overcome the limitation, coherent Raman processes such as coherent anti-Stokes Raman scattering (CARS) and stimulated Raman scattering (SRS) have been utilized to boost the weak Raman signal and to obtain vibrational images of live cells and tissues 11,12,13,14,15,16 . So far, monochromatic and multiplex CARS imaging have been applied to visualizing intra-spore DPA.…”