An outlier removal method based on PCA-DBSCAN for blood-SERS data analysis.

Surface-enhanced Raman spectroscopy (SERS) has shown promising potential in cancer screening. In practical applications, Raman spectra are often affected by deviations from the spectrometer, changes in measurement environments, and anomalies in spectrum characteristic peak intensities due to improper sample storage. Previous research has overlooked the presence of outliers in categorical data, leading to significant impacts on model learning outcomes. In this study, we propose a novel method, called Principal Component Analysis and Density Based Spatial Clustering of Applications with Noise (PCA-DBSCAN) to effectively remove outliers. This method employs dimensionality reduction and spectral data clustering to identify and remove outliers. The PCA-DBSCAN method introduces adjustable parameters (Eps and MinPts) to control the clustering effect. The effectiveness of the proposed PCA-DBSCAN method is verified through modeling on outlier-removed datasets. Further refinement of the machine learning model and PCA-DBSCAN parameters resulted in the best cancer screening model, achieving 97.41% macro-average recall and 97.74% macro-average F1-score. This paper introduces a new outlier removal method that significantly improves the performance of the SERS cancer screening model. Moreover, the proposed method serves as inspiration for outlier detection in other fields, such as biomedical research, environmental monitoring, manufacturing, quality control, and hazard prediction.

Laser tweezer Raman spectroscopy combined with deep neural networks for identification of liver cancer cells.

Rapid identification of cancer cells is crucial for clinical treatment guidance. Laser tweezer Raman spectroscopy (LTRS) that provides biochemical characteristics of cells can be used to identify cell phenotypes through classification models in a non-invasive and label-free manner. However, traditional classification methods require extensive reference databases and clinical experience, which is challenging when sampling at inaccessible locations. Here, we describe a classification method combing LTRS with deep neural network (DNN) for differential and discriminative analysis of multiple liver cancer (LC) cells. By using LTRS, we obtained high-quality single-cell Raman spectra of normal hepatocytes (HL-7702) and liver cancer cell lines (SMMC-7721, Hep3B, HepG2, SK-Hep1 and Huh7). The tentative assignment of Raman peaks indicated that arginine content was elevated and phenylalanine, glutathione and glutamate content was decreased in liver cancer cells. Subsequently, we randomly selected 300 spectra from each cell line for DNN model analysis, achieving a mean accuracy of 99.2%, a mean sensitivity of 99.2% and a mean specificity of 99.8% for the identification and classification of multiple LC cells and hepatocyte cells. These results demonstrate the combination of LTRS and DNN is a promising method for rapid and accurate cancer cell identification at single cell level.

Highly Efficient Blood Protein Analysis Using Membrane Purification Technique and Super-Hydrophobic SERS Platform for Precise Screening and Staging of Nasopharyngeal Carcinoma.

Early screening and precise staging are crucial for reducing mortality in patients with nasopharyngeal carcinoma (NPC). This study aimed to assess the performance of blood protein surface-enhanced Raman scattering (SERS) spectroscopy, combined with deep learning, for the precise detection of NPC. A highly efficient protein SERS analysis, based on a membrane purification technique and super-hydrophobic platform, was developed and applied to blood samples from 1164 subjects, including 225 healthy volunteers, 120 stage I, 249 stage II, 291 stage III, and 279 stage IV NPC patients. The proteins were rapidly purified from only 10 µL of blood plasma using the membrane purification technique. Then, the super-hydrophobic platform was prepared to pre-concentrate tiny amounts of proteins by forming a uniform deposition to provide repeatable SERS spectra. A total of 1164 high-quality protein SERS spectra were rapidly collected using a self-developed macro-Raman system. A convolutional neural network-based deep-learning algorithm was used to classify the spectra. An accuracy of 100% was achieved for distinguishing between the healthy and NPC groups, and accuracies of 96%, 96%, 100%, and 100% were found for the differential classification among the four NPC stages. This study demonstrated the great promise of SERS- and deep-learning-based blood protein testing for rapid, non-invasive, and precise screening and staging of NPC.

Adsorption behavior and performance of ammonium onto sorghum straw biochar from water.

Sorghum has been widely used for liquor production and brewing, but how to make efficiently utilize sorghum straw (SS) has become an urgent problem. Meanwhile, the wastewater produced by winemaking is typical organic wastewater with a high ammonium concentration. To solve the problem of resource utilization of SS and remove ammonium from water, SS was used to prepare biochar as an adsorbent for ammonium adsorption. Batch adsorption experiments were carried out to study the influencing factors and adsorption mechanisms of ammonium onto sorghum straw biochar (SSB). The results showed that the adsorption capacity of SSB was much higher than that of SS. The SSB pyrolyzed at 300 °C had the highest adsorption capacity. The favorable pH was 6-10, and the optimal dosage was 2.5 g/L. The adsorption process and behavior conformed to the pseudo-second-order kinetic and Langmuir isotherm adsorption models. The maximum ammonium adsorption capacity of SSB at 45 °C was 7.09 mg/g, which was equivalent to 7.60 times of SS. The ammonium adsorption of SS and SSB was mainly chemical adsorption. The regeneration test indicated that SSB had good regeneration performance after three adsorption-regeneration cycles. This work suggests that SSB could be potentially applied to sewage treatment containing ammonium to achieve the purpose of resource recycling.