Search

The early symptoms of hepatocellular carcinoma patients are often subtle and easily overlooked. By the time patients exhibit noticeable symptoms, the disease has typically progressed to middle or late stages, missing optimal treatment opportunities. Therefore, discovering biomarkers is essential for elucidating their functions for the early diagnosis and prevention. In practical research, challenges such as high-dimensional features, low sample size, and the complexity of gene interactions impact the reliability of biomarker discovery and disease diagnosis when using single-omics approaches. To address these challenges, we thus propose, Multi-level attention graph neural network (MLA-GNN) model for analyzing integrated multi-omics data related to liver cancer. The proposed protocol are using feature selection strategy by removing the noise and redundant information from gene expression and DNA methylation data. Additionally, it employs the Cartesian product method to integrate multi-omics datasets. The study also analyzes gene interactions using WGCNA and identifies potential genes through the MLA-GNN model, offering innovative approaches to resolve these issues. Furthermore, this paper identifies FOXL2 as a promising liver cancer marker through gene ontology and survival analysis. Validation using box plots showed that the expression of the gene FOXL2 was higher in patients with hepatocellular carcinoma than in normal individuals. The drug sensitivity correlation and molecular docking results of FOXL2 with the liver cancer-targeting agent lenvatinib emphasized its potential role in hepatocellular carcinoma treatment and highlighted the importance of FOXL2 in hepatocellular carcinoma treatment. [ABSTRACT FROM AUTHOR]

Malignancies such as bladder urothelial carcinoma, colon adenocarcinoma, liver hepatocellular carcinoma, lung adenocarcinoma and prostate adenocarcinoma significantly impact men's well-being. Accurate cancer classification is vital in determining treatment strategies and improving patient prognosis. This study introduced an innovative method that utilizes gene selection from high-dimensional datasets to enhance the performance of the male tumor classification algorithm. The method assesses the reliability of DNA methylation data to distinguish the five most prevalent types of male cancers from normal tissues by employing DNA methylation 450K data obtained from The Cancer Genome Atlas (TCGA) database. First, the chi-square test is used for dimensionality reduction and second, L1 penalized logistic regression is used for feature selection. Furthermore, the stacking ensemble learning technique was employed to integrate seven common multiclassification models. Experimental results demonstrated that the ensemble learning model utilizing multiple classification models outperformed any base classification model. The proposed ensemble model achieved an astonishing overall accuracy (ACC) of 99.2% in independent testing data. Moreover, it may present novel ideas and pathways for the early detection and treatment of future diseases. [ABSTRACT FROM AUTHOR]

Protein phosphorylation plays a critical role in human body by altering the structural conformation of a protein, causing it to become activated/deactivated, or functional modification. Given an uncharacterized protein sequence, can we predict whether it may be phosphorylated or may not? This is no doubt a very meaningful problem for both basic research and drug development. Unfortunately, to our best knowledge, so far no high throughput bioinformatics tool whatsoever has been developed to address such a very basic but important problem due to its extremely complexity and lacking sufficient training data. Here we proposed a predictor called iPhos-PseEvo by (1) incorporating the protein sequence evolutionary information into the general pseudo amino acid composition (PseAAC) via the grey system theory, (2) balancing out the skewed training datasets by the asymmetric bootstrap approach, and (3) constructing an ensemble predictor by fusing an array of individual random forest classifiers thru a voting system. Rigorous jackknife tests have indicated that very promising success rates have been achieved by iPhos-PseEvo even for such a difficult problem. A user-friendly web-server for iPhos-PseEvo has been established at , by which users can easily obtain their desired results without the need to go through the complicated mathematical equations involved. It has not escaped our notice that the formulation and approach presented here can be used to analyze many other problems in protein science as well. [ABSTRACT FROM AUTHOR]

Predicting phosphorylation protein is a challenging problem, particularly when query proteins have multi-label features meaning that they may be phosphorylated at two or more different type amino acids. In fact, human protein usually be phosphorylated at serine, threonine and tyrosine. By introducing the 'multi-label learning' approach, a novel predictor has been developed that can be used to deal with the systems containing both single- and multi-label phosphorylation protein. Here we proposed a predictor called Multi-iPPseEvo by (1) incorporating the protein sequence evolutionary information into the general pseudo amino acid composition (PseAAC) via the grey system theory, (2) balancing out the skewed training datasets by the asymmetric bootstrap approach, and (3) constructing an ensemble predictor by fusing an array of individual random forest classifiers thru a voting system. Rigorous cross-validations via a set of multi-label metrics indicate that the multi-label phosphorylation predictor is very promising and encouraging. The current approach represents a new strategy to deal with the multi-label biological problems, and the software is freely available for academic use at http://www.jci-bioinfo.cn/Multi-iPPseEvo. [ABSTRACT FROM AUTHOR]