Search

A protein contact map is a simplified, two-dimensional version of the three-dimensional protein structure. Protein contact map is proved to be crucial in forming the three-dimensional structure. Contact map prediction has now become an indispensable and promising intermediate step towards final three-dimensional structure prediction, while directed sequence-structure prediction hits its bottlenecks. In this article, different evaluation scores of prediction efficiency are compared. Next, the state of the art and future perspectives of contact map methods are reviewed and special attention is paid to those relying on machine learning algorithms. Details of neural network based methods as well as a list of machine learning based methods are given. Finally, bottlenecks and potential improvements of contact map predictions are discussed.

Backgrounds: Despite continuing progress in X-ray crystallography and high-field NMR spectroscopy for determination of three-dimensional protein structures, the number of unsolved and newly discovered sequences grows much faster than that of determined structures. Protein modeling methods can possibly bridge this huge sequence-structure gap with the development of computational science. A grand challenging problem is to predict three-dimensional protein structure from its primary structure (residues sequence) alone. However, predicting residue contact maps is a crucial and promising intermediate step towards final three-dimensional structure prediction. Better predictions of local and non-local contacts between residues can transform protein sequence alignment to structure alignment, which can finally improve template based three-dimensional protein structure predictors greatly., Methods: CNNcon, an improved multiple neural networks based contact map predictor using six sub-networks and one final cascade-network, was developed in this paper. Both the sub-networks and the final cascade-network were trained and tested with their corresponding data sets. While for testing, the target protein was first coded and then input to its corresponding sub-networks for prediction. After that, the intermediate results were input to the cascade-network to finish the final prediction., Results: The CNNcon can accurately predict 58.86% in average of contacts at a distance cutoff of 8 Å for proteins with lengths ranging from 51 to 450. The comparison results show that the present method performs better than the compared state-of-the-art predictors. Particularly, the prediction accuracy keeps steady with the increase of protein sequence length. It indicates that the CNNcon overcomes the thin density problem, with which other current predictors have trouble. This advantage makes the method valuable to the prediction of long length proteins. As a result, the effective prediction of long length proteins could be possible by the CNNcon.

Detection of protein families in large scale database is a difficult but important biological problem. Computational clustering methods can effectively address the problem. Although there exist many clustering algorithms, most of them are just based on the threshold. Their computational performances are affected by the weight distribution greatly, and they are only valid for some special networks. A new network clustering algorithm, Markov Finding and Clustering (MFC), is proposed to cluster the proteins into their functionally specific families accurately in this paper. The MFC algorithm makes an improvement in the random walk process and reduces the affection of the noise on the clustering result. It has a good performance on these networks which are not well addressed by existing algorithms sensitive to the noise. Finally, experiments on the protein sequence datasets demonstrate that the algorithm is effective in the detection of protein families and has a better performance than the current algorithms.

Network alignment is an important bridge to understanding human protein-protein interactions (PPIs) and functions through model organisms. However, the underlying subgraph isomorphism problem complicates and increases the time required to align protein interaction networks (PINs). Parallel computing technology is an effective solution to the challenge of aligning large-scale networks via sequential computing. In this study, the typical Hungarian-Greedy Algorithm (HGA) is used as an example for PIN alignment. The authors propose a HGA with 2-nearest neighbours (HGA-2N) and implement its graphics processing unit (GPU) acceleration. Numerical experiments demonstrate that HGA-2N can find alignments that are close to those found by HGA while dramatically reducing computing time. The GPU implementation of HGA-2N optimises the parallel pattern, computing mode and storage mode and it improves the computing time ratio between the CPU and GPU compared with HGA when large-scale networks are considered. By using HGA-2N in GPUs, conserved PPIs can be observed, and potential PPIs can be predicted. Among the predictions based on 25 common Gene Ontology terms, 42.8% can be found in the Human Protein Reference Database. Furthermore, a new method of reconstructing phylogenetic trees is introduced, which shows the same relationships among five herpes viruses that are obtained using other methods.

Identifying essential genes in comparison states (EGS) is vital to understanding cell differentiation, performing drug discovery, and identifying disease causes. Here, we present a machine learning method termed Prediction of Essential Genes in Comparison States (PreEGS). To capture the alteration of the network in comparison states, PreEGS extracts topological and gene expression features of each gene in a five-dimensional vector. PreEGS also recruits a positive sample expansion method to address the problem of unbalanced positive and negative samples, which is often encountered in practical applications. Different classifiers are applied to the simulated datasets, and the PreEGS based on the random forests model (PreEGSRF) was chosen for optimal performance. PreEGSRF was then compared with six other methods, including three machine learning methods, to predict EGS in a specific state. On real datasets with four gene regulatory networks, PreEGSRF predicted five essential genes related to leukemia and five enriched KEGG pathways. Four of the predicted essential genes and all predicted pathways were consistent with previous studies and highly correlated with leukemia. With high prediction accuracy and generalization ability, PreEGSRF is broadly applicable for the discovery of disease-causing genes, driver genes for cell fate decisions, and complex biomarkers of biological systems. [ABSTRACT FROM AUTHOR]

Understanding the molecular mechanisms underlying cell migration, which plays an important role in tumor growth and progression, is critical for the development of novel tumor therapeutics. Overexpression of transmembrane protein 30A (TMEM30A) has been shown to initiate tumor cell migration, however, the molecular mechanisms through which this takes place have not yet been reported. Thus, we propose the integration of computational and experimental approaches by first predicting potential signaling networks regulated by TMEM30A using a) computational biology methods, b) our previous mass spectrometry results of the TMEM30A complex in mouse tissue, and c) a number of migration-related genes manually collected from the literature, and subsequently performing molecular biology experiments including the in vitro scratch assay and real-time quantitative polymerase chain reaction (qPCR) to validate the reliability of the predicted network. The results verify that the genes identified in the computational signaling network are indeed regulated by TMEM30A during cell migration, indicating the effectiveness of our proposed method and shedding light on the regulatory mechanisms underlying tumor migration, which facilitates the understanding of the molecular basis of tumor invasion. [ABSTRACT FROM AUTHOR]

Drought is the one of the most important environment stresses that restricts crop yield worldwide. Cassava (Manihot esculenta Crantz) is an important food and energy crop that has many desirable traits such as drought, heat and low nutrients tolerance. However, the mechanisms underlying drought tolerance in cassava are unclear. Ethylene signaling pathway, from the upstream receptors to the downstream transcription factors, plays important roles in environmental stress responses during plant growth and development. In this study, we used bioinformatics approaches to identify and characterize candidate Manihot esculenta ethylene receptor genes and transcription factor genes. Using computational methods, we localized these genes on cassava chromosomes, constructed phylogenetic trees and identified stress-responsive cis-elements within their 5’ upstream regions. Additionally, we measured the trehalose and proline contents in cassava fresh leaves after drought, osmotic, and salt stress treatments, and then it was found that the regulation patterns of contents of proline and trehalose in response to various dehydration stresses were differential, or even the opposite, which shows that plant may take different coping strategies to deal with different stresses, when stresses come. Furthermore, expression profiles of these genes in different organs and tissues under non-stress and abiotic stress were investigated through quantitative real-time PCR (qRT-PCR) analyses in cassava. Expression profiles exhibited clear differences among different tissues under non-stress and various dehydration stress conditions. We found that the leaf and tuberous root tissues had the greatest and least responses, respectively, to drought stress through the ethylene signaling pathway in cassava. Moreover, tuber and root tissues had the greatest and least reponses to osmotic and salt stresses through ethylene signaling in cassava, respectively. These results show that these plant tissues had differential expression levels of genes involved in ethylene signaling in response to the stresses tested. Moreover, after several gene duplication events, the spatiotemporally differential expression pattern of homologous genes in response to abiotic and biotic stresses may imply their functional diversity as a mechanism for adapting to the environment. Our data provide a framework for further research on the molecular mechanisms of cassava resistance to drought stress and provide a foundation for breeding drought-resistant new cultivars. [ABSTRACT FROM AUTHOR]

It is challenging to obtain reliable and optimal mapping between networks for alignment algorithms when both nodal and topological structures are taken into consideration due to the underlying NP-hard problem. Here, we introduce an adaptive hybrid algorithm that combines the classical Hungarian algorithm and the Greedy algorithm (HGA) for the global alignment of biomolecular networks. With this hybrid algorithm, every pair of nodes with one in each network is first aligned based on node information (e.g., their sequence attributes) and then followed by an adaptive and convergent iteration procedure for aligning the topological connections in the networks. For four well-studied protein interaction networks, i.e., C.elegans, yeast, D.melanogaster, and human, applications of HGA lead to improved alignments in acceptable running time. The mapping between yeast and human PINs obtained by the new algorithm has the largest value of common gene ontology (GO) terms compared to those obtained by other existing algorithms, while it still has lower Mean normalized entropy (MNE) and good performances on several other measures. Overall, the adaptive HGA is effective and capable of providing good mappings between aligned networks in which the biological properties of both the nodes and the connections are important. [ABSTRACT FROM PUBLISHER]