Joint Detection of Associations between DNA Methylation and Gene Expression from Multiple Cancers

Identification and segregation of genes with improved recurrent neural network trained with optimal gene level and mutation level features

Even though many different approaches have been employed to address the complex mutational heterogeneity of cancer, finding driver genes is still problematic since other genomic factors cannot be fully integrated for combined analyses. This research paper presents a novel gene identification and segregation model with five key processes (a) pre-processing, (b) treatment of class imbalances, (c) feature extraction, (d) feature selection, and (e) gene classification. To increase the data quality, the gathered initial information is first pre-processed utilizing data cleaning and data normalization. This turns the raw data into something that is both useful and effective. In actuality, the sample is skewed against drivers because passenger mutation markers appear in proportionally less instances than drivers do. To address the Class Imbalance Problem, improved K-Means + SMOTE are applied to the preprocessed data. The most crucial characteristics, including those at the gene and mutation levels, are then extracted from the balanced dataset. To lessen the computational load in terms of time, the best features from the retrieved features are selected using Forensic interpretation tailored hunger food search optimization (FIHFSO). The ideal features are used to train the deep learning classifier that conducts the separation procedure. In this research, an Improved Recurrent Neural Network (I-RNN) is used to make a final decision about genes. At 90% of learning percentage, the accuracy of the proposed method achieves 0.98% of 0.83, 0.81, 0.65, 0.80, 0.92 and 0.63% which is compared to the other methods like HGS, FBIO, AOA, AO, GOA and PRO respectively.

Comprehensive Analysis of FASN in Tumor Immune Infiltration and Prognostic Value for Immunotherapy and Promoter DNA Methylation

Fatty acid synthase (FASN) promotes tumor progression in multiple cancers. In this study, we comprehensively examined the expression, prognostic significance, and promoter methylation of FASN, and its correlation with immune cell infiltration in pan-cancer. Our results demonstrated that elevated FASN expression was significantly associated with an unfavorable prognosis in many cancer types. Furthermore, FASN promoter DNA methylation can be used as a tumor prognosis marker. Importantly, high levels of FASN were significantly negatively correlated with tumor immune infiltration in 35 different cancers. Additionally, FASN was significantly associated with tumor mutational burden (TMB) and microsatellite instability (MSI) in multiple malignancies, suggesting that it may be essential for tumor immunity. We also investigated the effects of FASN expression on immunotherapy efficacy and prognosis. In up to 15 tumors, it was significantly negatively correlated with immunotherapy-related genes, such as PD-1, PD-L1, and CTLA-4. Moreover, we found that tumors with high FASN expression may be more sensitive to immunotherapy and have a good prognosis with PD-L1 treatment. Finally, we confirmed the tumor-suppressive effect of mir-195-5p through FASN. Altogether, our results suggested that FASN may serve as a novel prognostic indicator and immunotherapeutic target in various malignancies.

Bioinformatics identification of CCL8/21 as potential prognostic biomarkers in breast cancer microenvironment

BACKGROUND

Breast cancer (BC) is the most common malignancy among females worldwide. The tumor microenvironment usually prevents effective lymphocyte activation and infiltration, and suppresses infiltrating effector cells, leading to a failure of the host to reject the tumor. CC chemokines play a significant role in inflammation and infection.

METHODS

In our study, we analyzed the expression and survival data of CC chemokines in patients with BC using several bioinformatics analyses tools.

RESULTS

The mRNA expression of CCL2/3/4/5/7/8/11/17/19/20/22 was remarkably increased while CCL14/21/23/28 was significantly down-regulated in BC tissues compared with normal tissues. Methylation could down-regulate expression of CCL2/5/15/17/19/20/22/23/24/25/26/27 in BC. Low expression of CCL3/4/23 was found to be associated with drug resistance in BC. Results from Kaplan-Meier plotter and BC Gene-Expression Miner v4.2 (bcGenExMiner) v4.2 demonstrated that BC patients with high CCL8 and low CCL19/21/22 expression were more likely to have a worse prognosis. CCL8 expression was significantly up-regulated in BC tissues compared with normal tissues. High CCL8 expression was significantly correlated with negative PR, negative ER, positive nodal status, triple-negative BC subtype, basal-like BC subtype, triple-negative and basal-like BC subtype and high grades. CCL21 was down-regulated in BC, while high levels of CCL21 was associated with negative PR, triple-negative subtype, basal-like subtype and low tumor grade. Functional analysis demonstrated that CCL8 and CCL21 were involved in carcinogenesis, tumor immune escape and chemoresistance in BC.

CONCLUSION

Integrative bioinformatics analysis demonstrated CCL8/21 as potential prognostic biomarkers in BC microenvironment.