Abstract Background The battle against Helicobacter pylori (H. pylori) infections demands fast, reliable, and sensitive methods for pathogen identification (ID), antimicrobial susceptibility tests (ASTs) based on metabolic response, and genome-wide mutation profiling that reveals resistance mechanisms. Methods Here we introduce Clinical Antimicrobial Susceptibility Test Ramanometry for H. pylori (CAST-R-HP), and its validation with clinical samples. This method performs rapid ID, metabolism inhibition–based AST, and high-quality whole-genome sequencing for cells of targeted resistance phenotype, all at precisely 1-cell resolution and directly from biopsy samples. Results In CAST-R-HP, automated acquisition and machine learning of single-cell Raman spectra (SCRS) enable distinguishing individual H. pylori cells directly from a biopsy sample, with 98.5 ± 0.27% accuracy in ID. Moreover, by adding a 48- to72-h D2O feeding and drug exposure step prior to SCRS acquisition, CAST-R-HP reports AST for levofloxacin and clarithromycin with 100% accuracy, based on metabolic inhibition level. Furthermore, CAST-R-HP supports rapid sorting, low-bias DNA amplification, and full genome sequencing of single H. pylori cells with the SCRS defined, targeted drug-susceptibility phenotype, via Raman-activated gravity-driven cell encapsulation and sequencing. The genome-wide mutation map (maximum 99.70% coverage), at precisely 1-cell resolution, not only elucidates the drug-susceptibility phenotypes but also unveils their underlying molecular mechanisms. Conclusion The culture independency, shorter turnaround time, high resolution, and comprehensive information output suggest that CAST-R-HP is a powerful tool for diagnosing and treating H. pylori infections. 

OUP accepted manuscript

Pathogens and antimicrobial resistance (AMR) are emerging as major global threats to public health. Wastewater, as the unique interface between environments and humans receiving and spreading pathogens and AMR, is playing a more important role than ever before for monitoring of public health. Here, by pinpointing pathogens and AMR, we reviewed the most recent technological advancements in Raman biosensors (single-cell Raman, Raman-stable isotope probing, surface-enhanced Raman, statistical analysis) and molecular methods (polymerase chain reaction, metagenomics and single-cell genomics) for phenotypic and genotypic surveillance, respectively. In particular, the importance of integrating phenotypic and genotypic analysis via targeted single-cell sorting for a complementary and holistic surveillance and understanding of health risk was highlighted. We further suggest technological requirements to enhance wastewater surveillance and better inform tackling strategy against pathogens and AMR.

Raman biosensor and molecular tools for integrated monitoring of pathogens and antimicrobial resistance in wastewater

Raman Spectroscopy has long been anticipated to augment clinical decision making, such as classifying oncological samples. Unfortunately, the complexity of Raman data has thus far inhibited their routine use in clinical settings. Traditional machine learning models have been used to help exploit this information, but recent advances in deep learning have the potential to improve the field. However, there are a number of potential pitfalls with both traditional and deep learning models. We conduct a literature review to ascertain the recent machine learning methods used to classify cancers using Raman spectral data. We find that while deep learning models are popular, and ostensibly outperform traditional learning models, there are many methodological considerations which may be leading to an over-estimation of performance; primarily, small sample sizes which compound sub-optimal choices regarding sampling and validation strategies. Amongst several recommendations is a call to collate large benchmark Raman datasets, similar to those that have helped transform digital pathology, which researchers can use to develop and refine deep learning models.

/pdf/machine-learning-of-raman-spectroscopy-data-for-classifying-8k7lgjbi.pdf

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature

Accurate and rapid identification of infectious bacteria is important in medicine. Raman microspectroscopy holds great promise in performing label-free identification at the single-cell level. However, due to the naturally weak Raman signal, it is a challenge to build extensive databases and achieve both accurate and fast identification. Here, we used signal-to-noise ratio (SNR) as a standard indicator for Raman data quality and performed bacterial identification using 11, 141 single-cell Raman spectra from nine bacterial strains. Subsequently, using two machine learning methods, a simple filter, and a neural network-based denoising autoencoder (DAE), we demonstrated 92% (simple filter using 1 s/cell spectra) and 84% (DAE using 0.1 s/cell spectra) identification accuracy. Our machine learning-aided Raman analysis paves the way for high-speed Raman microspectroscopic clinical diagnostics.

/pdf/high-speed-diagnosis-of-bacterial-pathogens-at-the-single-1gigso8t.pdf

High-Speed Diagnosis of Bacterial Pathogens at the Single Cell Level by Raman Microspectroscopy with Machine Learning Filters and Denoising Autoencoders.

SERS-based antibiotic susceptibility testing: Towards point-of-care clinical diagnosis.

Raman spectroscopy and machine learning for the classification of breast cancers.

Human health is at great risk due to the spreading of antimicrobial resistance (AMR). The lengthy procedure of conventional antimicrobial susceptibility testing (AST) usually requires a few days. We developed a fast Raman-assisted antibiotic susceptibility test (FRAST), which detects single bacterial metabolic activity in the presence of antibiotics, using Raman single-cell spectroscopy. It was found that single-cell Raman spectra (SCRS) would show a clear and distinguishable Raman band at the "silent zone" (2000-2300 cm-1), due to the active incorporation of deuterium from heavy water (D2O) by antibiotic-resistant bacteria. This pilot study has compared the FRAST and the conventional AST for six clinical standard quality controls (four Gram-negative and two Gram-positive bacteria strains) in response to 38 antibiotics. In total, 3200 treatments have been carried out and approximately 64 000 SCRS have been acquired for FRAST analysis. The result showed an overall agreement of 88.0% between the FRAST and the conventional AST assay. The gram-staining classification based on the linear discriminant analysis (LDA) model of SCRS was developed, seamlessly coupling with the FRAST to further reduce the turnaround time. We applied the FRAST to real clinical analysis for nine urinary infectious samples and three sepsis samples. The results were consistent with MALDI-TOF identification and the conventional AST. Under the optimal conditions, the "sample to report" of the FRAST could be reduced to 3 h for urine samples and 21 h for sepsis samples. The FRAST provides fast and reliable susceptibility tests, which could speed up microbiological analysis for clinical practice and facilitate antibiotic stewardship.

Development of a Fast Raman-Assisted Antibiotic Susceptibility Test (FRAST) for the Antibiotic Resistance Analysis of Clinical Urine and Blood Samples.

The utility model relates to a raman scattering fast acquisition and imaging device of fixed wave length, including laser emission unit, speculum group, raman scattering signal filter unit and raman scattering signal acquisition element. Laser emission unit is used for obtaining the laser behind the the power adjustment, and speculum group is used for the laser -bounce behind the the power adjustment to the sample surface, and raman scattering signal filter unit is used for faling into two strands target signal and background noises with the raman scattering signal to wavelength coverage withtwo strands of signals reduces respectively, and raman scattering signal acquisition element is used for collecting two strands of raman signals. Compared with the prior art, the utility model discloses save the grating beam split, change to the light filter instead and filter object wave long signal scope to adopt photon count or photomultiplier to collect the signal, promoted the raman signal intensity of sample greatly, reduce the acquisition time, realize forming images fast. Save optics original papers such as grating, the cost on than market current raman product reduce by a wide margin.

Raman scattering fast acquisition and imaging device of fixed wave length

The invention relates to a fixed-wavelength Raman scattering quick collection and imaging equipment, which comprises a laser emission unit, a reflector group, a Raman scattering signal filtering unitand a Raman scattering signal collection unit, wherein the laser emission unit is used for obtaining laser of which the power is regulated; the reflector group is used for reflecting the laser of which the power is regulated to the surface of a sample; the Raman scattering signal filtering unit is used for dividing the Raman scattering signal into a target signal and a background noise, and independently reducing the wavelength ranges of the target signal and the background noise; and the Raman scattering signal collection unit is used for collecting two types of Raman signals. Compared with the prior art, the fixed-wavelength Raman scattering quick collection and imaging equipment is characterized in that optical grating light splitting is omitted, instead, an optical filter is used for filtering the signal range of the target wavelength, photon counting or a photomultiplier is adopted to collect signals, the intensity of the Raman signal of the sample is greatly improved, collectiontime is shortened, and quick imaging is realized. Optical elements, including optical gratings and the like, are omitted, and the construction cost of the fixed-wavelength Raman scattering quick collection and imaging equipment is lowered than that of a traditional Raman product in the market.

Yi Xiaofei

Papers

Raman spectroscopy and machine learning for the classification of breast cancers.

Development of a Fast Raman-Assisted Antibiotic Susceptibility Test (FRAST) for the Antibiotic Resistance Analysis of Clinical Urine and Blood Samples.

Raman scattering fast acquisition and imaging device of fixed wave length

Fixed-wavelength Raman scattering quick collection and imaging equipment