Search

Most oral squamous cell carcinoma (OSCC) tumors arise from oral premalignant lesions. Oral submucous fibrosis (OSF), usually occurring in male chewers of betel quid, is a premalignant stromal disease characterized by a high malignant transformation rate and high prevalence. Although a relationship between the inhabited microbiome and carcinogenesis has been proposed, no detailed information regarding the oral microbiome of patients with OSF exists; the changes of the salivary microbiome during cancer formation remain unclear. This study compared the salivary microbiomes of male patients with OSCC and a predisposing OSF background (OSCC-OSF group) and those with OSF only (OSF group). The results of high-throughput sequencing of the bacterial 16S rRNA gene indicated that OSF-related carcinogenesis and smoking status significantly contributed to phylogenetic composition variations in the salivary microbiome, leading to considerable reductions in species richness and phylogenetic diversity. The microbiome profile of OSF-related malignancy was associated with increased microbial stochastic fluctuation, which dominated the salivary microbiome assembly and caused species co-occurrence network collapse. Artificial intelligence selection algorithms consistently identified 5 key species in the OSCC-OSF group: Porphyromonas catoniae, Prevotella multisaccharivorax, Prevotella sp. HMT-300, Mitsuokella sp. HMT-131, and Treponema sp. HMT-927. Robust accuracy in predicting oral carcinogenesis was obtained with our exploratory and validation data sets. In functional analysis, the microbiome of the OSCC-OSF group had greater potential for S -adenosyl- l -methionine and norspermidine synthesis but lower potential for l -ornithine and pyrimidine deoxyribonucleotide synthesis and formaldehyde metabolism. These findings indicated that the salivary microbiome plays important roles in modulating microbial metabolites during oral carcinogenesis. In conclusion, our results provided new insights into salivary microbiome alterations during the malignant transformation of OSF. [ABSTRACT FROM AUTHOR]

• A novel hybrid approach (DFN-AI) integrating complex network theory and AI algorithms is proposed to enhance the accuracy of the Baltic Dry Index (BDI) forecasting. • DFN-AI models outperform their corresponding single AI forecasting models with lower absolute value, variance of errors, and also higher directional matching rates. • The accuracy improvements of DFN-AI models are robust for different time-scale BDI datasets as well as in the respect of random sampling cases and challenging situations. Enhancing the accuracy of freight rate forecasting is crucial when agents in the shipping industry make their business decisions and strive to avoid or reduce possible risks. Although there has been a lot of freight rate trend analysis in the literature, the time-varying and volatile nature of the shipping market makes the accurate prediction of it extremely difficult, if not impossible. In this research, we first propose the use of a dynamic fluctuation network (DFN) to transform a time series data set into an evolving directed network, which removes the noise in the data and allows us to extract time-varying features in it. We then develop a hybrid approach that combines the DFN and artificial intelligence (AI) techniques to forecast the Baltic Dry Index (BDI), which is new to the literature. The utilization of DFN with AI enables the non-linear, cyclical and dynamic features of the BDI to be extracted effectively and the prediction accuracy is not impacted by the length and time-scale of sample selection either in long-term or short-term forecasting. These advantages of DFN offset the well-known limitations of traditional AI-based algorithms and econometric models in BDI forecasting. The empirical results from applying the resultant model to multi-time-scale datasets in a random sampling case show that the model is more accurate than the model based on the AI technique only. We test the accuracy of the DFN-AI model in three challenging cases which respectively contain a sudden rise, a decline, or frequent fluctuations of the BDI. The DFN-AI model has fewer errors and a higher trend matching rate than the corresponding AI-based model. Our hybrid approach also shows its superiority in working with data containing an extreme market downturn, which shed light on the predictability of BDI. This study has important implications for overall business, commercial, and hedging strategies in the shipping industry. [ABSTRACT FROM AUTHOR]