Raman spectrum combined with deep learning for precise recognition of Carbapenem-resistant Enterobacteriaceae.

Carbapenem-resistant Enterobacteriaceae (CRE) is a major pathogen that poses a serious threat to human health. Unfortunately, currently, there are no effective measures to curb its rapid development. To address this, an in-depth study on the surface-enhanced Raman spectroscopy (SERS) of 22 strains of 7 categories of CRE using a gold silver composite SERS substrate was conducted. The residual networks with an attention mechanism to classify the SERS spectrum from three perspectives (pathogenic bacteria type, enzyme-producing subtype, and sensitive antibiotic type) were performed. The results show that the SERS spectrum measured by the composite SERS substrate was repeatable and consistent. The SERS spectrum of CRE showed varying degrees of species differences, and the strain difference in the SERS spectrum of CRE was closely related to the type of enzyme-producing subtype. The introduced attention mechanism improved the classification accuracy of the residual network (ResNet) model. The accuracy of CRE classification for different strains and enzyme-producing subtypes reached 94.0% and 96.13%, respectively. The accuracy of CRE classification by pathogen sensitive antibiotic combination reached 93.9%. This study is significant for guiding antibiotic use in CRE infection, as the sensitive antibiotic used in treatment can be predicted directly by measuring CRE spectra. Our study demonstrates the potential of combining SERS with deep learning algorithms to identify CRE without culture labels and classify its sensitive antibiotics. This approach provides a new idea for rapid and accurate clinical detection of CRE and has important significance for alleviating the rapid development of resistance to CRE.

Dual-modal identification of jadeite based on optical coherence tomography images and Raman spectral features.

Low-quality jadeite is often subjected to bleaching, filling, and dyeing to improve its texture and consequently increase its value. In this study, natural jadeite, bleached and filled jadeite, and dyed jadeite were investigated by combining Raman spectroscopy and optical coherence tomography (OCT). The results show that jadeite composition can be identified from Raman peaks around 205, 377, 700, and 1040c m -1. The presence of epoxy filler can be detected from Raman peaks at 1113, 1187, and 1609c m -1, among which the features of 1113 and 1609c m -1 are particularly significant. Dyed jadeite exhibits a pronounced fluorescence background in its Raman spectrum due to the injected dye. After noise reduction, texture vectors representing the texture of bleached or dyed jadeite can be obtained from OCT images. These vectors differ from the corresponding texture vector of natural jadeite. Most processed jadeites have relatively low texture vector intensities due to particle reduction and texture damage during processing. However, the texture vector strengths of jadeites can be increased through internal silting.

Raman spectroscopy combined with deep learning for rapid detection of melanoma at the single cell level.

Melanoma is an aggressive and metastatic skin cancer caused by genetic mutations in melanocytes, and its incidence is increasing year by year. Understanding the gene mutation information of melanoma cases is very important for its precise treatment. The current diagnostic methods for melanoma include radiological, pharmacological, histological, cytological and molecular techniques, but the gold standard for diagnosis is still pathological biopsy, which is time consuming and destructive. Raman spectroscopy is a rapid, sensitive and nondestructive detection method. In this study, a total of 20,000 Surface-enhanced Raman scattering (SERS) spectra of melanocytes and melanoma cells were collected using a positively charged gold nanoparticles planar solid SERS substrate, and a classification network system based on convolutional neural networks (CNN) was constructed to achieve the classification of melanocytes and melanoma cells, wild-type and mutant melanoma cells and their drug resistance. Among them, the classification accuracy of melanocytes and melanoma cells was over 98%. Raman spectral differences between melanocytes and melanoma cells were analyzed and compared, and the response of cells to antitumor drugs were also evaluated. The results showed that Raman spectroscopy provided a basis for the medication of melanoma, and SERS spectra combined with CNN classification model realized classification of melanoma, which is of great significance for rapid diagnosis and identification of melanoma.

Combining fiber optical tweezers and Raman spectroscopy for rapid identification of melanoma.

Cutaneous melanoma is a skin tumor with a high degree of malignancy and fatality rate, the incidence of which has increased in recent years. Therefore, a rapid and sensitive diagnostic technique of melanoma cells is urgently needed. In this paper, we present a new approach using fiber optical tweezers to manipulate melanoma cells to measure their Raman spectra. Then, combined with Principal Component Analysis and Support Vector Machines (PCA-SVM) classification model, to achieve the classification of common mutant, wild-type and drug-resistant melanoma cells. A total of 150 Raman spectra of 30 cells were collected from mutant, wild-type and drug-resistant melanoma cell lines, and the classification accuracy was 92%, 94%, 97.5%, respectively. These results suggest that the study of tumor cells based on fiber optical tweezers and Raman spectroscopy is a promising method for early and rapid identification and diagnosis of tumor cells.

[Experimental study on an auditory method for analyzing DNA segments].

To explore a new method for analyzing biological molecules that have already been sequenced, an experimental study on an auditory method was carried out. The auditory method for analyzing biological molecules includes audible representation of sequence data. Audible representation of sequence data was implemented by using a multimedia computer. Each mononucleotide in a DNA sequence was matched with a corresponding sound, i.e., a DNA sequence was "dubbed" in a sound sequence. When the sound sequence is played, a special cadence can be heard. In the audible representation experiment, special cadences of different exons can be clearly heard. The results show that audible representation of DNA sequence data can be implemented by using a multimedia technique. After a 5-time auditory training, subjects both in internal testing and external testing can obtain 93%-100% of judgment accuracy rate for the difference between two sound sequences of two different exons, thus providing an experimental basis for the practicability of this method. Auditory method for analyzing DNA segments might be beneficial for the research in comparative genomics and functional genomics. This new technology must be robust and be carefully evaluated and improved in a high-throughput environment before its implementation in an application setting.