ABSTRACT
The gut microbiota and cancer have been demonstrated to be closely related. However, few studies have explored the bronchoalveolar lavage fluid (BALF) microbiota in patients with lung cancer (LC), specifically the microbiota related to progression-free survival (PFS) in LC. A total of 216 BALF samples were collected including 166 LC and 50 benign pulmonary disease (N-LC) samples, and further sequenced using 16S rRNA amplicon sequencing. Enrolled LC patients were followed up, the therapeutic efficacy was assessed, and PFS was calculated. The associated clinical and microbiota sequencing data were deeply analysed. Distinct differences in the microbial profiles were evident in the lower airways of patients with LC and N-LC, which was also found between non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). A combined random forest model was built to distinguish NSCLC from SCLC and reached area under curves (AUCs) of 0.919 (95% CI 86.69-97.1%) and 0.893 (95% CI 79.39-99.29%) in the training and test groups, respectively. The lower alpha diversity of the BALF microbiota in NSCLC patients was significantly associated with reduced PFS, although this link was not observed in SCLC. Specifically, NSCLC with a higher abundance of f_Lachnospiraceae, s_Prevotella nigrescens and f_[Mogibacteriaceae] achieved longer PFS. The enrichment of o_Streptophyta and g_Prevotella was observed in SCLC with worse PFS. This study provided a detailed description of the characteristics of BALF microbiota in patients with NSCLC and SCLC simultaneously and provided insights into the role of the diagnosis and prognosis evaluation. Supplementary Information: The online version contains supplementary material available at 10.1007/s43657-023-00135-9.
ABSTRACT
With its low-cost, label-free and non-destructive features, Raman spectroscopy is becoming an attractive technique with high potential to discriminate the causative agent of bacterial infections and bacterial infections per se. However, it is challenging to achieve consistency and accuracy of Raman spectra from numerous bacterial species and phenotypes, which significantly hinders the practical application of the technique. In this study, we analyzed surfaced enhanced Raman spectra (SERS) through machine learning algorithms in order to discriminate bacterial pathogens quickly and accurately. Two unsupervised machine learning methods, K-means Clustering (K-Means) and Agglomerative Nesting (AGNES) were performed for clustering analysis. In addition, eight supervised machine learning methods were compared in terms of bacterial predictions via Raman spectra, which showed that convolutional neural network (CNN) achieved the best prediction accuracy (99.86%) with the highest area (0.9996) under receiver operating characteristic curve (ROC). In sum, machine learning methods can be potentially applied to classify and predict bacterial pathogens via Raman spectra at general level.
ABSTRACT
Raman spectroscopy (RS) is a widely used analytical technique based on the detection of molecular vibrations in a defined system, which generates Raman spectra that contain unique and highly resolved fingerprints of the system. However, the low intensity of normal Raman scattering effect greatly hinders its application. Recently, the newly emerged surface enhanced Raman spectroscopy (SERS) technique overcomes the problem by mixing metal nanoparticles such as gold and silver with samples, which greatly enhances signal intensity of Raman effects by orders of magnitudes when compared with regular RS. In clinical and research laboratories, SERS provides a great potential for fast, sensitive, label-free, and non-destructive microbial detection and identification with the assistance of appropriate machine learning (ML) algorithms. However, choosing an appropriate algorithm for a specific group of bacterial species remains challenging, because with the large volumes of data generated during SERS analysis not all algorithms could achieve a relatively high accuracy. In this study, we compared three unsupervised machine learning methods and 10 supervised machine learning methods, respectively, on 2,752 SERS spectra from 117 Staphylococcus strains belonging to nine clinically important Staphylococcus species in order to test the capacity of different machine learning methods for bacterial rapid differentiation and accurate prediction. According to the results, density-based spatial clustering of applications with noise (DBSCAN) showed the best clustering capacity (Rand index 0.9733) while convolutional neural network (CNN) topped all other supervised machine learning methods as the best model for predicting Staphylococcus species via SERS spectra (ACC 98.21%, AUC 99.93%). Taken together, this study shows that machine learning methods are capable of distinguishing closely related Staphylococcus species and therefore have great application potentials for bacterial pathogen diagnosis in clinical settings.