Multi-Approach Bioinformatics Analysis of Curated Omics Data Provides a Gene Expression Panorama for Multiple Cancer Types

Abstract

Studies describing the expression patterns and biomarkers for the tumoral process increase in number every year. The availability of new datasets, although essential, also creates a confusing landscape where common or critical mechanisms are obscured amidst the divergent and heterogeneous nature of such results. In this work, we manually curated the Gene Expression Omnibus using rigorous filtering criteria to select the most homogeneous and highest quality microarray and RNA-seq datasets from multiple types of cancer. By applying systems biology approaches, combined with machine learning analysis, we investigated possible frequently deregulated molecular mechanisms underlying the tumoral process. Our multi-approach analysis of 99 curated datasets, composed of 5,406 samples, revealed 47 differentially expressed genes in all analyzed cancer types, which were all in agreement with the validation using TCGA data. Results suggest that the tumoral process is more related to the overexpression of core deregulated machinery than the underexpression of a given gene set. Additionally, we identified gene expression similarities between different cancer types not described before and performed an overall survival analysis using 20 cancer types. Finally, we were able to suggest a core regulatory mechanism that could be frequently deregulated.

Bioinformatic analysis of methyltransferase-like protein family reveals clinical and functional outcomes in human cancer

“…Furthermore, low METTL7A expression and high METTL7B expression are associated with worse overall and progressive survival in various tumors, including LUAD (Figure 3). These data are in congruence with recent reports on the clinical signi cance of METTL7A and 7B in human cancer 12,[48][49][50] . METTL7A is reported as an integral membrane protein anchored into the endoplasmic reticulum membrane and has roles in lipid droplet formation 51,52 .…”

A Gene-Based Machine Learning Classifier Associated to the Colorectal Adenoma—Carcinoma Sequence

“…Luo et al hypothesized that, since TEX11 is an X-linked gene, its differential expression may be a genetic cause that could explain the higher incidence of CRC in males. Methyltransferase-like protein 7A (METTL7A) belongs to the human methyltransferase-like protein family, and the low METTL7A expression has been associated to cancer aggressiveness and progression in various tumors, including CRC [ 50 , 51 , 52 , 53 ]. Vascular endothelial growth factor A (VEGFA) and its receptors have been identified as major mediators of angiogenesis, which is crucial for tumor invasiveness [ 54 ].…”

Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets

“…Class imbalance is common in many real-world applications and affects the quality and reliability of ML approaches (Leevy et al, 2018;Johnson & Khoshgoftaar, 2019;López et al, 2013). Most importantly, class imbalance is the reality of almost all biological datasets, as we demonstrated in previous works after the manual curation of more than 30.000 cancer datasets (Feltes et al, 2019;Feltes, Poloni & Dorn, 2021;Feltes et al, 2020). Imbalanced data refers to classification problems where we have an unequal number of instances for different classes.…”

“…Among several ML applications in real-world situations, classification tasks stand up as one of the most relevant applications, ranging from classification of types of plants and animals to the identification of different diseases prognoses, such as cancer (Feltes et al, 2019;Feltes, Poloni & Dorn, 2021;Feltes et al, 2020;, H1N1 Flu (Chaurasia & Dixit, 2021), Dengue (Zhao et al, 2020), and COVID-19 (Table 5). The use of these algorithms in the context of hemogram data from COVID-19 patients is summarized in Table 5.…”