Rapid and accurate identification of marine microbes with single-cell Raman spectroscopy

Liu, Yaoyao; Xu, Jingjing; Tao, Yi; Fang, Teng; Du, Wei; Ye, Anpei

doi:10.1039/c9an02069a

Cited by 29 publications

(31 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for phototrophs such as microalgae, potential remains elusive . Specifically, for photosynthetic cells, two types of SCRS including “pigment spectrum” (PS; acquired before quenching) and “whole spectrum” (WS; collected after quenching) are possible, yet past studies have generally sampled either PS or WS, but not both; − thus, the optimal strategy to extract information from SCRS remains to be developed. ,− Moreover, the breadth of sampling over the microalgal space has been extremely limited, as only a few species were included in tests for phylogenetic classification , or metabolite profiling. − Furthermore, SCRS are sensitive to not only “phylogeny” but also the “state” of a cell, yet existing experimental designs have generally failed to distinguish them. Consequentially, how broadly applicable or reliable the approach is for microalgae remains unclear.…”

Section: Introductionmentioning

confidence: 99%

Culture-Free Identification and Metabolic Profiling of Microalgal Single Cells via Ensemble Learning of Ramanomes

Baladehi

Hekmatara

et al. 2021

Anal. Chem.

View full text Add to dashboard Cite

Microalgae are among the most genetically and metabolically diverse organisms on earth, yet their identification and metabolic profiling have generally been slow and tedious. Here, we established a reference ramanome database consisting of single-cell Raman spectra (SCRS) from >9000 cells of 27 phylogenetically diverse microalgal species, each under stationary and exponential states. When combined, prequenching (“pigment spectrum” (PS)) and postquenching (“whole spectrum” (WS)) signals can classify species and states with 97% accuracy via ensemble machine learning. Moreover, the biosynthetic profile of Raman-sensitive metabolites was unveiled at single cells, and their interconversion was detected via intra-ramanome correlation analysis. Furthermore, not-yet-cultured cells from the environment were functionally characterized via PS and WS and then phylogenetically identified by Raman-activated sorting and sequencing. This PS–WS combined approach for rapidly identifying and metabolically profiling single cells, either cultured or uncultured, greatly accelerates the mining of microalgae and their products.

show abstract

Section: Introductionmentioning

confidence: 99%

Culture-Free Identification and Metabolic Profiling of Microalgal Single Cells via Ensemble Learning of Ramanomes

Baladehi

Hekmatara

et al. 2021

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…Recently, Raman spectroscopy was indicated to identify and quantify the molecular modifications of collagen and seems to be an interesting tool to study biological processes [162]. A novel detecting method, single-cell Raman spectroscopy (scRS) coupled with one-dimensional convolutional neural networks (1DCNN) was explored to identify individual marine microorganisms quickly and accurately [163]. Moreover, combined microscopy-infrared (AFM-IR) spectroscopy and tip-enhanced Raman spectroscopy (TERS) provided a novel and automated approach to identify the structure of viruses [164].…”

Section: Developing Technologies For Structure Characterizationmentioning

confidence: 99%

Development of Marine-Derived Compounds for Cancer Therapy

Zuo

Kwok

2021

Marine Drugs

View full text Add to dashboard Cite

Cancer has always been a threat to human health with its high morbidity and mortality rates. Traditional therapy, including surgery, chemotherapy and radiotherapy, plays a key role in cancer treatment. However, it is not able to prevent tumor recurrence, drug resistance and treatment side effects, which makes it a very attractive challenge to search for new effective and specific anticancer drugs. Nature is a valuable source of multiple pharmaceuticals, and most of the anticancer drugs are natural products or derived from them. Marine-derived compounds, such as nucleotides, proteins, peptides and amides, have also shed light on cancer therapy, and they are receiving a fast-growing interest due to their bioactive properties. Their mechanisms contain anti-angiogenic, anti-proliferative and anti-metastasis activities; cell cycle arrest; and induction of apoptosis. This review provides an overview on the development of marine-derived compounds with anticancer properties, both their applications and mechanisms, and discovered technologies.

show abstract

“…Raman spectroscopy is a label-free, rapid, and highly sensitive analytical technology [4][5][6][7], and in recent years, it has been used to identify bacteria [6,[8][9][10]. In various Raman technologies, surface-enhanced Raman spectroscopy (SERS) is a commonly used tool for bacterial analysis, which has been widely used in bacterial cell cycle monitoring [11], drug resistance [12], and identification [4,8,[13][14][15].…”

Section: Introductionmentioning

confidence: 99%

“…Compared with traditional algorithms, such as support vector machine (SVM), linear discriminant analysis (LDA), and k‐nearest‐neighbor (KNN) algorithms, the classification accuracy of DL algorithms has been dramatically improved. Liu et al explored the rapid identification of 10 marine microorganisms and three nonmarine actinomycetes via single‐cell Raman spectroscopy, with an average accuracy of 88.5% ± 4% using one‐dimensional convolutional neural networks (1DCNN) [9]. Lu et al achieved an average accuracy of 95.64% ± 5.46% at a single‐cell level using CNNs (ConvNet) to classify 14 microbial species [4].…”

Section: Introductionmentioning

confidence: 99%

Rapid and accurate identification of pathogenic bacteria at the single‐cell level using laser tweezers Raman spectroscopy and deep learning

Sun

Fang

et al. 2022

Journal of Biophotonics

Self Cite

View full text Add to dashboard Cite

We report a new method for the rapid identification of pathogenic bacterial species at the single‐cell level that combines laser tweezers Raman spectroscopy (LTRS) with deep learning (DL). LTRS can accurately measure single‐cell Raman spectra (scRS) without destroying and labeling cells. Based on the scRS data, DL rapidly and accurately identifies pathogenic bacteria. We measured scRS of 15 species bacteria using homemade LTRS. For each species, approximately, 160 cells from three different patients were measured, one patient's data were used as test set, and the rest after being augmented was used as training set. A residual network (ResNet) model, trained on the augmented training set, achieved an accuracy of 94.53% on the test set. Moreover, we applied gradient‐weighted class activation mapping to visualize the proposed model. Finally, we demonstrated the advantages of ResNet over traditional machine‐learning algorithms.

show abstract

Rapid and accurate identification of marine microbes with single-cell Raman spectroscopy

Abstract: Rapid and accurate identification of individual microorganisms using single-cell Raman spectra combining with one-dimensional convolutional neural networks.

Cited by 29 publications

References 34 publications

Culture-Free Identification and Metabolic Profiling of Microalgal Single Cells via Ensemble Learning of Ramanomes

Culture-Free Identification and Metabolic Profiling of Microalgal Single Cells via Ensemble Learning of Ramanomes

Development of Marine-Derived Compounds for Cancer Therapy

Rapid and accurate identification of pathogenic bacteria at the single‐cell level using laser tweezers Raman spectroscopy and deep learning

Contact Info

Product

Resources

About