Search

The existing methods for clustering of gene expression profile data either require manual inspection and other biological knowledge or require some cut-off value which can not be directly calculated from the given data set. Thus, the problem of systematic and efficient determination of cluster boundaries of clusters in gene expression profile data still remains demanding. In this context, we have developed a procedure for automatic and systematic determination of the boundaries of clusters in the hierarchical clustering of gene expression data based on the ratio of with-in class variance and between-class variance, which can be fully calculated from the given expression data. After the determination of dendrogram based on agglomerative hierarchical clustering, this ratio is used to determine the cluster boundary. Except this ratio which can be completely calculated from the given expression profile data, unlike other existing approaches, our approach does not require any manual inspection or biological knowledge. Our results are favorably comparable and in some of cases better than existing method which does not utilize prior information or manual inspection. Moreover, gene expression profile data are often contaminated with various type of noise and in order to reduce this noise content, we have also applied image enhancing technique called discrete wavelet transform. We tested a number of mother wavelet functions to smooth the noise in the gene expression data set and obtained some improvements in the quality of the results.

Risk factors for hepatocarcinogenesis include chronic inflammation due to viral infection, liver fibrosis, and aging. In this study, we separated carcinogenic and non-carcinogenic cases due to hepatitis C virus (HCV) infection, aiming to comprehensively analyze miRNA expression in liver tissues by age, and identify factors that contribute to carcinogenesis. Total RNA was extracted from 360 chronic hepatitis C (CH), 43 HCV infected hepatocellular carcinoma (HCC), and surrounding non-tumor (SNT) tissues. MicroRNA (miRNA) expression patterns were analyzed using microarray. Using machine learning, we extracted characteristic miRNA expression patterns for each disease and age. There were no age-dependent changes in miRNA expression in the disease-specific comparisons; however, miRNA expression differed among the age groups of 50, 60, and 70 years of age between CH and SNT. The expression of miRNA was different between SNT and HCC only in patients in their 70s. Of the 55 miRNAs with significant differences in expression between CH and SNT, 34 miRNAs showed significant differences in expression even in the degree of liver fibrosis. The observation that miRNAs involved in hepatocarcinogenesis differ at different ages suggests that the mechanisms of carcinogenesis differ by age group as well. We also found that many miRNAs whose expression did not affect liver fibrosis were involved in carcinogenesis. These findings are expected to define biomarkers for detection of HCC at early stage, and develop novel therapeutic targets for HCC. [ABSTRACT FROM AUTHOR]

Background: MicroRNAs (miRNAs) are a class of non-coding RNAs that play a pivotal role as gene expression regulators. These miRNAs are typically approximately 20 to 25 nucleotides long. The maturation of miRNAs requires Dicer cleavage at specific sites within the precursor miRNAs (pre-miRNAs). Recent advances in machine learning-based approaches for cleavage site prediction, such as PHDcleav and LBSizeCleav, have been reported. ReCGBM, a gradient boosting-based model, demonstrates superior performance compared with existing methods. Nonetheless, ReCGBM operates solely as a binary classifier despite the presence of two cleavage sites in a typical pre-miRNA. Previous approaches have focused on utilizing only a fraction of the structural information in pre-miRNAs, often overlooking comprehensive secondary structure information. There is a compelling need for the development of a novel model to address these limitations. Results: In this study, we developed a deep learning model for predicting the presence of a Dicer cleavage site within a pre-miRNA segment. This model was enhanced by an autoencoder that learned the secondary structure embeddings of pre-miRNA. Benchmarking experiments demonstrated that the performance of our model was comparable to that of ReCGBM in the binary classification tasks. In addition, our model excelled in multi-class classification tasks, making it a more versatile and practical solution than ReCGBM. Conclusions: Our proposed model exhibited superior performance compared with the current state-of-the-art model, underscoring the effectiveness of a deep learning approach in predicting Dicer cleavage sites. Furthermore, our model could be trained using only sequence and secondary structure information. Its capacity to accommodate multi-class classification tasks has enhanced the practical utility of our model. [ABSTRACT FROM AUTHOR]

Background: Recently, many computational methods have been proposed to predict cancer genes. One typical kind of method is to find the differentially expressed genes between tumour and normal samples. However, there are also some genes, for example, 'dark' genes, that play important roles at the network level but are difficult to find by traditional differential gene expression analysis. In addition, network controllability methods, such as the minimum feedback vertex set (MFVS) method, have been used frequently in cancer gene prediction. However, the weights of vertices (or genes) are ignored in the traditional MFVS methods, leading to difficulty in finding the optimal solution because of the existence of many possible MFVSs. Results: Here, we introduce a novel method, called weighted MFVS (WMFVS), which integrates the gene differential expression value with MFVS to select the maximum-weighted MFVS from all possible MFVSs in a protein interaction network. Our experimental results show that WMFVS achieves better performance than using traditional bio-data or network-data analyses alone. Conclusion: This method balances the advantage of differential gene expression analyses and network analyses, improves the low accuracy of differential gene expression analyses and decreases the instability of pure network analyses. Furthermore, WMFVS can be easily applied to various kinds of networks, providing a useful framework for data analysis and prediction. [ABSTRACT FROM AUTHOR]

Deep learning technologies are permeating every field from image and speech recognition to computational and systems biology. However, the application of convolutional neural networks (CCNs) to "omics" data poses some difficulties, such as the processing of complex networks structures as well as its integration with transcriptome data. Here, we propose a CNN approach that combines spectral clustering information processing to classify lung cancer. The developed spectral-convolutional neural network based method achieves success in integrating protein interaction network data and gene expression profiles to classify lung cancer. The performed computational experiments suggest that in terms of accuracy the predictive performance of our proposed method was better than those of other machine learning methods such as SVM or Random Forest. Moreover, the computational results also indicate that the underlying protein network structure assists to enhance the predictions. Data and CNN code can be downloaded from the link: https://sites.google.com/site/nacherlab/analysis [ABSTRACT FROM AUTHOR]

Cancer subtype identification is an unmet need in precision diagnosis. Recently, evolutionary conservation has been indicated to contain informative signatures for functional significance in cancers. However, the importance of evolutionary conservation in distinguishing cancer subtypes remains largely unclear. Here, we identified the evolutionarily conserved genes (i.e. core genes) and observed that they are primarily involved in cellular pathways relevant to cell growth and metabolisms. By using these core genes, we developed two novel strategies, namely a feature-based strategy (FES) and an image-based strategy (IMS) by integrating their evolutionary and genomic profiles with the deep learning algorithm. In comparison with the FES using the random set and the strategy using the PAM50 classifier, the core gene set-based FES achieved a higher accuracy for identifying breast cancer subtypes. The IMS and FES using the core gene set yielded better performances than the other strategies, in terms of classifying both breast cancer subtypes and multiple cancer types. Moreover, the IMS is reproducible even using different gene expression data (i.e. RNA-seq and microarray). Comprehensive analysis of eight cancer types demonstrates that our evolutionary conservation-based models represent a valid and helpful approach for identifying cancer subtypes and the core gene set offers distinguishable clues of cancer subtypes. [ABSTRACT FROM AUTHOR]

Motivation Protein cleavage is an important cellular event, involved in a myriad of processes, from apoptosis to immune response. Bioinformatics provides in silico tools, such as machine learning-based models, to guide the discovery of targets for the proteases responsible for protein cleavage. State-of-the-art models have a scope limited to specific protease families (such as Caspases), and do not explicitly include biological or medical knowledge (such as the hierarchical protein domain similarity or gene–gene interactions). To fill this gap, we present a novel approach for protease target prediction based on data integration. Results By representing protease-protein target information in the form of relational matrices, we design a model (i) that is general and not limited to a single protease family, and (b) leverages on the available knowledge, managing extremely sparse data from heterogeneous data sources, including primary sequence, pathways, domains and interactions. When compared with other algorithms on test data, our approach provides a better performance even for models specifically focusing on a single protease family. Availability and implementation https://gitlab.com/smarini/MaDDA/ (Matlab code and utilized data.) Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

We tackle the problem of completing and inferring genetic networks under stationary conditions from static data, where network completion is to make the minimum amount of modifications to an initial network so that the completed network is most consistent with the expression data in which addition of edges and deletion of edges are basic modification operations. For this problem, we present a new method for network completion using dynamic programming and least-squares fitting. This method can find an optimal solution in polynomial time if the maximum indegree of the network is bounded by a constant. We evaluate the effectiveness of our method through computational experiments using synthetic data. Furthermore, we demonstrate that our proposed method can distinguish the differences between two types of genetic networks under stationary conditions from lung cancer and normal gene expression data. [ABSTRACT FROM AUTHOR]

Since many proteins express their functional activity by interacting with other proteins and forming protein complexes, it is very useful to identify sets of proteins that form complexes. For that purpose, many prediction methods for protein complexes from protein-protein interactions have been developed such as MCL, MCODE, RNSC, PCP, RRW, and NWE. These methods have dealt with only complexes with size of more than three because the methods often are based on some density of subgraphs. However, heterodimeric protein complexes that consist of two distinct proteins occupy a large part according to several comprehensive databases of known complexes. In this paper, we propose several feature space mappings from protein-protein interaction data, in which each interaction is weighted based on reliability. Furthermore, we make use of prior knowledge on protein domains to develop feature space mappings, domain composition kernel and its combination kernel with our proposed features. We perform ten-fold cross-validation computational experiments. These results suggest that our proposed kernel considerably outperforms the naive Bayes-based method, which is the best existing method for predicting heterodimeric protein complexes. [ABSTRACT FROM AUTHOR]

Abstract: Much attention has been paid to RNA–RNA interaction involved in posttranscriptional regulation of gene expression. Although there have been a few studies on secondary structure prediction of interacting RNAs using dynamic programming (DP) algorithms, no grammar-based approach has been proposed. This paper provides a new modeling for RNA–RNA interaction based on multiple context-free grammar (MCFG). We present a polynomial time parsing (prediction) algorithm of the stochastic version of MCFG. Experimental results show that our approach is comparable to an existing work based on DP. The MCFG-based approach is more flexible than other DP-based methods. [Copyright &y& Elsevier]

Reconstruction of genetic regulatory networks from time series data of gene expression patterns is an important research topic in bioinformatics. Probabilistic Boolean Networks (PBNs) have been proposed as an effective model for gene regulatory networks. PBNs are able to cope with uncertainty, corporate rule-based dependencies between genes and discover the sensitivity of genes in their interactions with other genes. However, PBNs are unlikely to use directly in practice because of huge amount of computational cost for obtaining predictors and their corresponding probabilities. In this paper, we propose a multivariate Markov model for approximating PBNs and describing the dynamics of a genetic network for gene expression sequences. The main contribution of the new model is to preserve the strength of PBNs and reduce the complexity of the networks. The number of parameters of our proposed model is O(n2) where n is the number of genes involved. We also develop efficient estimation methods for solving the model parameters. Numerical examples on synthetic data sets and practical yeast data sequences are given to demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Analysis of the interactions between genes by systematic gene disruptions and gene overexpressions is an important topic in molecular biology. This paper analyses the problem of identifying a genetic network from the data obtained by multiple gene disruptions and overexpressions in regard to the number of experiments and the complexity of experiments. An experiment consists of simultaneous gene disruptions and overexpressions and the complexity of an experiment is the number of genes disrupted or overexpressed. We define a genetic network as a boolean network and show a series of algorithms which describe methods for identifying the underlying genetic network by such experiments. Some lower bounds on the number of experiments required for the identification are also proved for some cases. [Copyright &y& Elsevier]

Recently, network controllability studies have proposed several frameworks for the control of large complex biological networks using a small number of life molecules. However, age-related changes in the brain have not been investigated from a controllability perspective. In this study, we compiled the gene expression profiles of four normal brain regions from individuals aged 20–99 years and generated dynamic probabilistic protein networks across their lifespan. We developed a new algorithm that efficiently identified critical proteins in probabilistic complex networks, in the context of a minimum dominating set controllability model. The results showed that the identified critical proteins were significantly enriched with well-known ageing genes collected from the GenAge database. In particular, the enrichment observed in replicative and premature senescence biological processes with critical proteins for male samples in the hippocampal region led to the identification of possible new ageing gene candidates. [ABSTRACT FROM AUTHOR]

The reconstruction of gene regulatory networks based on gene expression data can effectively uncover regulatory relationships between genes and provide a deeper understanding of biological control processes. Non-linear dependence is a common problem in the regulatory mechanisms of gene regulatory networks. Various methods based on information theory have been developed to infer networks. However, the methods have introduced many redundant regulatory relationships in the network inference process. A recent measurement method called distance correlation has, in many cases, shown strong and computationally efficient non-linear correlations. In this paper, we propose a novel regulatory network inference method called the distance-correlation and network topology centrality network (DCNTC) method. The method is based on and extends the Local Density Measurement of Network Node Centrality (LDCNET) algorithm, which has the same choice of network centrality ranking as the LDCNET algorithm, but uses a simpler and more efficient distance correlation measure of association between genes. In this work, we integrate distance correlation and network topological centrality into the reasoning about the structure of gene regulatory networks. We will select optimal thresholds based on the characteristics of the distribution of each gene pair in relation to distance correlation. Experiments were carried out on four network datasets and their performance was compared. [ABSTRACT FROM AUTHOR]

The article discusses various reports published within the issue, including on which discusses the alignment of mini-satellite maps, one on the analysis and modeling of genome rearrangement and one which analyzes the gene expression time series data.