Gelato: a new hybrid deep learning-based Informer model for multivariate air pollution prediction

The increase in air pollutants and its adverse effects on human health and the environment has raised significant concerns. This implies the necessity of predicting air pollutant levels. Numerous studies have aimed to provide new models for more accurate prediction of air pollutants such as CO2, O3, and PM2.5. Most of the models used in the literature are deep learning models with Transformers being the best for time series prediction. However, there is still a need to enhance accuracy in air pollution prediction using Transformers. Alongside the need for increased accuracy, there is a significant demand for predicting a broader spectrum of air pollutants. To encounter this challenge, this paper proposes a new hybrid deep learning-based Informer model called "Gelato" for multivariate air pollution prediction. Gelato takes a leap forward by taking several air pollutants into consideration simultaneously. Besides introducing new changes to the Informer structure as the base model, Gelato utilizes Particle Swarm Optimization for hyperparameter optimization. Moreover, XGBoost is used at the final stage to achieve minimal errors. Applying the proposed model on a dataset containing eight important air pollutants, including CO2, O3, NO, NO2, SO2, PM10, NH3, and PM2.5, the Gelato performance is assessed. Comparing the results of Gelato with other models shows Gelato's superiority over them, proving it is a high-confidence model for multivariate air pollution prediction.

miR-17-92 host gene, uderexpressed in gastric cancer and its expression was negatively correlated with the metastasis

BACKGROUND

This study aimed to evaluate the expression of miR-17-92 host gene (MIR17HG), in gastric cancer and paired normal adjacent tissues for the 1st time.

METHODS

Using quantitative real-time-polymerase chain reaction, the MIR17HG expression was assessed in 30 paired tumoral and nontumoral gastric tissue samples.

RESULTS

Our results showed that this transcript was significantly underexpressed in gastric tumors compared with normal ones. Furthermore, there was an association between the expression levels of MIR17HG and gastric cancer grades and stages. Moreover, the expression level of MIR17HG was conversely associated with the size of tumoral specimens in early stages (stages I and II). We also observed an association between the presence of metastasis and lower expression of MIR17HG.

CONCLUSION

Our results suggest that MIR17HG gene expression is dysregulated in gastric cancer in which it may indicate a tumor suppressive function of this miRNA cluster host gene in gastric cancer.

The stem cell self-renewal gene, Musashi 1, is highly expressed in tumor and non-tumor samples of human bladder

CONTEXT

The stem cell model for cancer assumes that a key event in tumorigenesis is the deregulation of genes involved in the regulation of stem cell self-renewal. The Musashi family is an evolutionarily conserved group of neural RNA-binding proteins. In mammals, the family consists of two individual genes, Musashi 1 (MSI1) and MSI2, encoding the Musashi 1 and Musashi 2 proteins. Musashi 1 is involved in the regulation of self-renewal of stem cells. Recently, its over-expression has also been reported in a variety of human tumors.

AIMS

To investigate a potential expression of the stem cell self-renewal gene, Musashi 1, in human bladder cancer, we examined its gene expression in a series of tumor and non-tumor tissue samples of bladder.

MATERIALS AND METHODS

Relative expression of MSI1 was determined by the real-time quantitative reverse transcription polymerase chain reaction (qRT-PCR) in 70 surgical samples of bladder.

RESULTS

Using specific primers for MSI1 and TBP (as an internal control) for qRT-PCR technique, we found a relatively high expression level of MSI1 in all examined tumor and non-tumor bladder tissue specimens. However, our data did not show any correlation between the level of gene expression and tumor/non-tumor states of the samples (P>0.05).

CONCLUSIONS

All together, our data demonstrated that Musashi 1 is highly and un-differentially expressed in both examined tumoral and apparently normal bladder tissues.

Differential effects of Nucleostemin suppression on cell cycle arrest and apoptosis in the bladder cancer cell lines 5637 and SW1710

OBJECTIVES

The Nucleostemin (NS) gene encodes a nucleolar protein enriched in adult and embryonic stem cells. NS is thought to regulate cancer cell proliferation, but the mechanisms involved are poorly understood. In this study, we have investigated the role of NS in bladder cancer.

MATERIALS AND METHODS

Expression of NS was determined by quantitative reverse transcription-polymerase chain reaction in bladder carcinoma cell lines and in normal uro-epithelial cell cultures. We used an RNAi strategy to investigate the function of NS in two selected carcinoma cell lines.

RESULTS

High NS expression was found in most bladder carcinoma cell lines and normal uro-epithelial cells. Knockdown of NS expression induced a severe decline in cell proliferation in 5637 and SW1710 cell lines, both with mutant p53. Apoptosis was more strongly enhanced in 5637 cells lacking RB1 than in SW1710 cells lacking p16(INK4A). Moreover, NS-siRNA-treated 5637 cells accumulated mainly in G(2)/M, whereas SW1710 cells arrested in G(0)/G(1).

CONCLUSION

Our data indicate that NS expression is necessary for cell proliferation and evasion of apoptosis in bladder cancer cells, independent of its effect on p53. Also, we speculate that the precise effect of NS on cell cycle regulation may relate to functional status of RB1 and CDKN2A/p16(INK4A).