Search

Protein-protein interaction (PPI) not only plays a critical role in cell life activities, but also plays an important role in discovering the mechanism of biological activity, protein function, and disease states. Developing computational methods is of great significance for PPIs prediction since experimental methods are time-consuming and laborious. In this paper, we proposed a PPI prediction algorithm called GRNN-PPI only using the amino acid sequence information based on general regression neural network and two feature extraction methods. Specifically, we designed a new feature extraction method named Mutation Spectral Radius (MSR) to extract evolutionary information by the BLOSUM62 matrix. Meanwhile, we integrated another feature extraction method, autocorrelation description, which can completely extract information on physicochemical properties and protein sequences. The principal component analysis was applied to eliminate noise, and the general regression neural network was adopted as a classifier. The prediction accuracy of the yeast, human, and Helicobacter pylori1 (H. pylori1) data sets were 97.47%, 99.63%, and 99.97%, respectively. In addition, we also conducted experiments on two important PPI networks and six independent data sets. All results were significantly higher than some state-of-the-art methods used for comparison, showing that our method is feasible and robust.

Campylobacter jejuniis a leading cause of bacterial gastroenteritis in humans around the world. The emergence of bacterial resistance is becoming more serious; therefore, development of new vaccines is considered to be an alternative strategy against drug-resistant pathogen. In this study, we investigated the pangenome of 173C. jejunistrains and analyzed the phylogenesis and the virulence factor genes. In order to acquire a high-quality pangenome, genomic relatedness was firstly performed with average nucleotide identity (ANI) analyses, and an open pangenome of 8,041 gene families was obtained with the correct taxonomy genomes. Subsequently, the virulence property of the core genome was analyzed and 145 core virulence factor (VF) genes were obtained. Upon functional genomics and immunological analyses, five core VF proteins with high antigenicity were selected as potential core vaccine targets for humans. Furthermore, functional annotations indicated that these proteins are involved in important molecular functions and biological processes, such as adhesion, regulation, and secretion. In addition, transcriptome analysis in human cells and pig intestinal loop proved that these vaccine target genes are important in the virulence ofC. jejuniin different hosts. Comprehensive pangenome and relevant animal experiments will facilitate discovering the potential core vaccine targets with improved efficiency in reverse vaccinology. Likewise, this study provided some insights into the genetic polymorphism and phylogeny ofC. jejuniand discovered potential vaccine candidates for humans. Prospective development of new vaccines using the targets will be an alternative to the use of antibiotics and prevent the development of multidrug-resistantC. jejuniin humans and even other animals.

Background Microbes are closely related to human health and diseases. Identification of disease-related microbes is of great significance for revealing the pathological mechanism of human diseases and understanding the interaction mechanisms between microbes and humans, which is also useful for the prevention, diagnosis and treatment of human diseases. Considering the known disease-related microbes are still insufficient, it is necessary to develop effective computational methods and reduce the time and cost of biological experiments. Methods In this work, we developed a novel computational method called MDAKRLS to discover potential microbe-disease associations (MDAs) based on the Kronecker regularized least squares. Specifically, we introduced the Hamming interaction profile similarity to measure the similarities of microbes and diseases besides Gaussian interaction profile kernel similarity. In addition, we introduced the Kronecker product to construct two kinds of Kronecker similarities between microbe-disease pairs. Then, we designed the Kronecker regularized least squares with different Kronecker similarities to obtain prediction scores, respectively, and calculated the final prediction scores by integrating the contributions of different similarities. Results The AUCs value of global leave-one-out cross-validation and 5-fold cross-validation achieved by MDAKRLS were 0.9327 and 0.9023 ± 0.0015, which were significantly higher than five state-of-the-art methods used for comparison. Comparison results demonstrate that MDAKRLS has faster computing speed under two kinds of frameworks. In addition, case studies of inflammatory bowel disease (IBD) and asthma further showed 19 (IBD), 19 (asthma) of the top 20 prediction disease-related microbes could be verified by previously published biological or medical literature. Conclusions All the evaluation results adequately demonstrated that MDAKRLS has an effective and reliable prediction performance. It may be a useful tool to seek disease-related new microbes and help biomedical researchers to carry out follow-up studies.

mRNA m5C, which has recently been implicated in the regulation of mRNA mobility, metabolism, and translation, plays important regulatory roles in various biological events. Two types of m5C sites are found in mRNAs. Type I m5C sites, which contain a downstream G-rich triplet motif and are computationally predicted to locate in the 5’ end of putative hairpin structures, are methylated by NSUN2. Type II m5C sites contain a downstream UCCA motif and are computationally predicted to locate in the loops of putative hairpin structures. However, their biogenesis remains unknown. Here we identified NSUN6, a methyltransferase that is known to methylate C72 of tRNAThr and tRNACys, as an mRNA methyltransferase that targets Type II m5C sites. Combining the RNA secondary structure prediction, miCLIP, and results from a high-throughput mutagenesis analysis, we determined the RNA sequence and structural features governing the specificity of NSUN6-mediated mRNA methylation. Integrating these features into an NSUN6-RNA structural model, we identified an NSUN6 variant that largely loses tRNA methylation but retains mRNA methylation ability. Finally, we revealed a negative correlation between m5C methylation and translation efficiency. Our findings uncover that mRNA m5C is tightly controlled by an elaborate two-enzyme system, and the protein-RNA structure analysis strategy established may be applied to other RNA modification writers to distinguish the functions of different RNA substrates of a writer protein.

Cancer is a highly heterogeneous disease caused by dysregulation in different cell types and tissues. However, different cancers may share common mechanisms. It is critical to identify decisive genes involved in the development and progression of cancer, and joint analysis of multiple cancers may help to discover overlapping mechanisms among different cancers. In this study, we proposed a fusion feature selection framework attributed to ensemble method named Fisher score and Gradient Boosting Decision Tree (FS–GBDT) to select robust and decisive feature genes in high-dimensional gene expression datasets. Joint analysis of 11 human cancers types was conducted to explore the key feature genes subset of cancer. To verify the efficacy of FS–GBDT, we compared it with four other common feature selection algorithms by Support Vector Machine (SVM) classifier. The algorithm achieved highest indicators, outperforms other four methods. In addition, we performed gene ontology analysis and literature validation of the key gene subset, and this subset were classified into several functional modules. Functional modules can be used as markers of disease to replace single gene which is difficult to be found repeatedly in applications of gene chip, and to study the core mechanisms of cancer.

Identification of protein-protein interactions (PPIs) plays an essential role in the understanding of protein functions and cellular biological activities. However, the traditional experiment-based methods are time-consuming and laborious. Therefore, developing new reliable computational approaches has great practical significance for the identification of PPIs. In this paper, a novel prediction method is proposed for predicting PPIs using graph energy, named PPI-GE. Particularly, in the process of feature extraction, we designed two new feature extraction methods, the physicochemical graph energy based on the ionization equilibrium constant and isoelectric point and the contact graph energy based on the contact information of amino acids. The dipeptide composition method was used for order information of amino acids. After multi-information fusion, principal component analysis (PCA) was implemented for eliminating noise and a robust weighted sparse representation-based classification (WSRC) classifier was applied for sample classification. The prediction accuracies based on the five-fold cross-validation of the human, Helicobacter pylori (H. pylori), and yeast data sets were 99.49%, 97.15%, and 99.56%, respectively. In addition, in five independent data sets and two significant PPI networks, the comparative experimental results also demonstrate that PPI-GE obtained better performance than the compared methods.

Background Using knowledge-based interpretation to analyze omics data can not only obtain essential information regarding various biological processes, but also reflect the current physiological status of cells and tissue. The major challenge to analyze gene expression data, with a large number of genes and small samples, is to extract disease-related information from a massive amount of redundant data and noise. Gene selection, eliminating redundant and irrelevant genes, has been a key step to address this problem. Results The modified method was tested on four benchmark datasets with either two-class phenotypes or multiclass phenotypes, outperforming previous methods, with relatively higher accuracy, true positive rate, false positive rate and reduced runtime. Conclusions This paper proposes an effective feature selection method, combining double RBF-kernels with weighted analysis, to extract feature genes from gene expression data, by exploring its nonlinear mapping ability. Electronic supplementary material The online version of this article (10.1186/s12859-018-2400-2) contains supplementary material, which is available to authorized users.

Microorganisms resided in human body play a vital role in metabolism, immune defense, nutrition absorption, cancer control and protection against pathogen colonization. The changes of microbial communities can cause human diseases. Based on the known microbe-disease association, we presented a novel computational model employing Random Walking with Restart optimized by Particle Swarm Optimization (PSO) on the heterogeneous interlinked network of Human Microbe-Disease Associations (PRWHMDA) (see Figure 1). Based on the known human microbe-disease associations, we constructed the heterogeneous interlinked network with Cosine similarity. The extended random walk with restart (RWR) method was derived to get the potential microbe-disease associations. PSO was utilized to get the optimal parameters of RWR. To evaluate the prediction effectiveness, we performed leave one out cross validation (LOOCV) and 5-fold cross validation (CV), which got the AUC (The area under ROC curve) of 0.915 (LOOCV) and the average AUCs of 0.8875 ± 0.0046 (5-fold CV). Moreover, we carried out three case studies of asthma, inflammatory bowel disease (IBD) and type 1 diabetes (T1D) for the further evaluation. The result showed that 10, 10 and 9 of top-10 predicted microbes were verified by previously published experimental results, respectively. It is anticipated that PRWHMDA can be effective to identify the disease-related microbes and maybe helpful to disclose the relationship between microorganisms and their human host.

As therapeutic peptides have been taken into consideration in disease therapy in recent years, many biologists spent time and labor to verify various functional peptides from a large number of peptide sequences. In order to reduce the workload and increase the efficiency of identification of functional proteins, we propose a sequence-based model, q-FP (functional peptide prediction based on the q-Wiener Index), capable of recognizing potentially functional proteins. We extract three types of features by mixing graphic representation and statistical indices based on the q-Wiener index and physicochemical properties of amino acids. Our support-vector-machine-based model achieves an accuracy of 96.71%, 93.34%, 98.40%, and 91.40% for anticancer, virulent, and allergenic proteins datasets, respectively, by using 5-fold cross validation.

Adenosine deaminases acting on RNA (ADARs) convert adenosines to inosines in double-stranded RNA (dsRNA) in animals. Despite their importance, ADAR RNA substrates have not been mapped extensively in vivo. Here we develop irCLASH to map RNA substrates recognized by human ADARs and uncover features that determine their binding affinity and editing efficiency. We also observe a dominance of long-range interactions within ADAR substrates and analyze differences between ADAR1 and ADAR2 editing substrates. Moreover, we unexpectedly discovered that ADAR proteins bind dsRNA substrates tandemly in vivo, each with a 50-bp footprint. Using RNA duplexes recognized by ADARs as readout of pre-messenger RNA structures, we reveal distinct higher-order architectures between pre-messenger RNAs and mRNAs. Our transcriptome-wide atlas of ADAR substrates and the features governing RNA editing observed in our study will assist in the rational design of guide RNAs for ADAR-mediated RNA base editing.

* Background In the search for therapeutic peptides for disease treatments, many efforts have been made to identify various functional peptides from large numbers of peptide sequence databases. In this paper, we propose an effective computational model that uses deep learning and word2vec to predict therapeutic peptides (PTPD). * Results Representation vectors of all k-mers were obtained through word2vec based on k-mer co-existence information. The original peptide sequences were then divided into k-mers using the windowing method. The peptide sequences were mapped to the input layer by the embedding vector obtained by word2vec. Three types of filters in the convolutional layers, as well as dropout and max-pooling operations, were applied to construct feature maps. These feature maps were concatenated into a fully connected dense layer, and rectified linear units (ReLU) and dropout operations were included to avoid over-fitting of PTPD. The classification probabilities were generated by a sigmoid function. PTPD was then validated using two datasets: an independent anticancer peptide dataset and a virulent protein dataset, on which it achieved accuracies of 96% and 94%, respectively. * Conclusions PTPD identified novel therapeutic peptides efficiently, and it is suitable for application as a useful tool in therapeutic peptide design.

Lysine malonylation is one of the important post-translational modification (PTM) of proteins. Malonylated proteins can affect various cell functions of eukaryotes and prokaryotes, which play an important role in metabolic pathways, mitochondrial functions, fatty acid oxidation and other life activities. However, accurate identification of the malonylation sites is the key to further understand the molecular mechanism of malonylation. Currently, experimental identification is still a challenging task, which usually requires a large amount of laboratory work and considerable cost. Regarding this situation, there is an urgent need to establish useful calculation methods and develop effective predictors. We propose a new deep learning network model called DeepMal. Firstly, features are extracted by enhanced amino acid composition (EAAC), enhanced grouped amino acid composition (EGAAC), dipeptide deviation from the expected mean (DDE), K nearest neighbors (KNN) and BLOSUM62 matrix. Secondly, the linear convolutional neural network is used to extract the specific features of malonylation sites, select the relevant features and reduce the feature dimension through maximum pooling. Finally, malonylation sites and non-malonylation sites are classified by a multilayer neural network. And an independent dataset is used to assess the predictive ability of the model DeepMal. On the independent datasets Escherichia coli (E. coli), Homo sapiens (H. sapiens), Mus musculus (M. musculus), the AUC values are 0.974, 0.956 and 0.944, and the accuracies are 96.5%, 95.5% and 94.5%, respectively. Compared with other prediction models, the prediction accuracy is increased by 9.5%–18.5%, and this indicates the effectiveness of the prediction model DeepMal. Using deep learning network can enhance the robustness of DeepMal model for predicting malonylation sites. The source codes and all datasets are publicly available at https://github.com/QUST-AIBBDRC/DeepMal/ .

Apoptosis is associated with some human diseases, including cancer, autoimmune disease, neurodegenerative disease and ischemic damage, etc. Apoptosis proteins subcellular localization information is very important for understanding the mechanism of programmed cell death and the development of drugs. Therefore, the prediction of subcellular localization of apoptosis protein is still a challenging task. In this paper, we propose a novel method for predicting apoptosis protein subcellular localization, called PsePSSM-DCCA-LFDA. Firstly, the protein sequences are extracted by combining pseudo-position specific scoring matrix (PsePSSM) and detrended cross-correlation analysis coefficient (DCCA coefficient), then the extracted feature information is reduced dimensionality by LFDA (local Fisher discriminant analysis). Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of the apoptosis proteins. The overall prediction accuracy of 99.7, 99.6 and 100% are achieved respectively on the three benchmark datasets by the most rigorous jackknife test, which is better than other state-of-the-art methods. The experimental results indicate that our method can significantly improve the prediction accuracy of subcellular localization of apoptosis proteins, which is quite high to be able to become a promising tool for further proteomics studies. The source code and all datasets are available at https://github.com/QUST-BSBRC/PsePSSM-DCCA-LFDA/ .

We generalize chaos game representation (CGR) to higher dimensional spaces while maintaining its bijection, keeping such method sufficiently representative and mathematically rigorous compare to previous attempts. We first state and prove the asymptotic property of CGR and our generalized chaos game representation (GCGR) method. The prediction follows that the dissimilarity of sequences which possess identical subsequences but distinct positions would be lowered exponentially by the length of the identical subsequence; this effect was taking place unbeknownst to researchers. By shining a spotlight on it now, we show the effect fundamentally supports (G)CGR as a similarity measure or feature extraction technique. We develop two feature extraction techniques: GCGR-Centroid and GCGR-Variance. We use the GCGR-Centroid to analyze the similarity between protein sequences by using the datasets 9 ND5, 24 TF and 50 beta-globin proteins. We obtain consistent results compared with previous studies which proves the significance thereof. Finally, by utilizing support vector machines, we train the anticancer peptide prediction model by using both GCGR-Centroid and GCGR-Variance, and achieve a significantly higher prediction performance by employing the 3 well-studied anticancer peptide datasets.

Analysis of drug–target interactions (DTIs) is of great importance in developing new drug candidates for known protein targets or discovering new targets for old drugs. However, the experimental approaches for identifying DTIs are expensive, laborious and challenging. In this study, we report a novel computational method for predicting DTIs using the highly discriminative information of drug-target interactions and our newly developed discriminative vector machine (DVM) classifier. More specifically, each target protein sequence is transformed as the position-specific scoring matrix (PSSM), in which the evolutionary information is retained; then the local binary pattern (LBP) operator is used to calculate the LBP histogram descriptor. For a drug molecule, a novel fingerprint representation is utilized to describe its chemical structure information representing existence of certain functional groups or fragments. When applying the proposed method to the four datasets (Enzyme, GPCR, Ion Channel and Nuclear Receptor) for predicting DTIs, we obtained good average accuracies of 93.16%, 89.37%, 91.73% and 92.22%, respectively. Furthermore, we compared the performance of the proposed model with that of the state-of-the-art SVM model and other previous methods. The achieved results demonstrate that our method is effective and robust and can be taken as a useful tool for predicting DTIs.

Transcription factors (TF) are proteins that control the first step of gene expression, the transcription of DNA into RNA sequences. The mechanism of transcriptional regulatory can be much better understood if the category of transcription factors is known. We developed a new method for predicting the classification of transcription factors by incorporating their binding site properties into a novel mode of Chou's pseudo amino acid composition. The properties include the length of TFBSs for a TF, a new_PWM value, the proportion of not conservative TFBSs, the proportion of nonucleosome of TFBSs, the proportion of conserved-nucleosome of TFBSs, and the GC content of TFBSs. We construct a vector with these properties to represent a TF. Then the vectors which stand for TFs were classified with SVMs. The high accuracy obtained shows that these properties are of great significance for a TF.

In this paper a novel method for phylogenetic analysis of H5N1 avian influenza virus has been proposed. At first we provide a mapping of virus protein sequence. Based on this mapping, we propose a new distance measure and make use of the corresponding similarity matrix to construct phylogenic tree without requiring multiple alignment. As an application, we construct phylogenic tree for 123 species of H5N1 avian influenza virus. The phylogeny obtained is generally consistent with evolutionary trees constructed in previous studies.

In this paper we (1) introduce a new 3D graphical representation of DNA sequences; (2) visualize DNA sequences based on 3DD-Curves; (3) provide a new invariant of DNA sequences based on our 3DD-Curve. All this represents a new development of graphical representation and numerical characterization for DNA sequences.

We develop a novel method of asserting the similarity between two biological sequences without the need for alignment. The proposed method uses free energy of nearest-neighbor interactions as a simple measure of dissimilarity. It is used to perform a search for similarities of a query sequence against three complex datasets. The sensitivity and selectivity are computed and evaluated and the performance of the proposed distance measure is compared. Real data analysis shows that is a very efficient, sensitive and high-selective algorithm in comparing large dataset of DNA sequences.

This paper proposes a novel method for analyzing similarities of protein sequences based on features generated from the hydropathy properties of amino acid sequences. At first using the hydropathy characteristics, the protein sequences are converted into fixed-dimensional feature vectors. Based on these feature vectors, we analyze nine ND5 proteins and construct a phylogenic tree as an application. The phylogeny obtained is generally consistent with the phylogenic tree constructed by MEGA4 software. The experimental results show the utility of our approach.

As the fundamental unit of eukaryotic chromatin structure, nucleosome plays critical roles in gene expression and regulation by controlling physical access to transcription factors. In this paper, based on the geometrically transformed Tsallis entropy and two index-vectors, a valid nucleosome positioning information model is developed to describe the distribution of A/T-riched and G/C-riched dimeric and trimeric motifs along the DNA duplex. When applied to train the support vector machine, the model achieves high AUCs across five organisms, which have significantly outperformed the previous studies. Besides, we adopt the concept of relative distance to describe the probability of arbitrary DNA sequence covered by nucleosome. Thus, the average nucleosome occupancy profile over the S.cerevisiae genome is calculated. With our peak detection model, the isolated nucleosomes along genome sequence are located. When compared with some published results, it shows that our model is effective for nucleosome positioning. The index-vector component [Formula in text] is identified to be an important influencing factor of nucleosome organizations.

In this paper we propose a matrix depiction and two new invariants of DNA sequences. This approach is illustrated on the primate mitochondrial DNA sequences for 11 different species and 80 different H5N1 avian influenza virus DNA sequences. We also construct the dendrogram tree for them. These phylogenies obtained are generally consistent with evolutionary trees constructed in previous studies.