FCNGRU: Locating Transcription Factor Binding Sites by combing Fully Convolutional Neural Network with Gated Recurrent Unit

Deciphering the relationship between transcription factors (TFs) and DNA sequences is very helpful for computational inference of gene regulation and a comprehensive understanding of gene regulation mechanisms. Transcription factor binding sites (TFBSs) are specific DNA short sequences that play a pivotal role in controlling gene expression through interaction with TF proteins. Although recently many computational and deep learning methods have been proposed to predict TFBSs aiming to predict sequence specificity of TF-DNA binding, there is still a lack of effective methods to directly locate TFBSs. In order to address this problem, we propose FCNGRU combing a fully convolutional neural network (FCN) with the gated recurrent unit (GRU) to directly locate TFBSs in this paper. Furthermore, we present a two-task framework (FCNGRU-double): one is a classification task at nucleotide level which predicts the probability of each nucleotide and locates TFBSs, and the other is a regression task at sequence level which predicts the intensity of each sequence. A series of experiments are conducted on 45 in-vitro datasets collected from the UniPROBE database derived from universal protein binding microarrays (uPBMs). Compared with competing methods, FCNGRU-double achieves much better results on these datasets. Moreover, FCNGRU-double has an advantage over a single-task framework, FCNGRU-single, which only contains the branch of locating TFBSs. In additionwe combine with in vivo datasets to make a further analysis and discussion. The source codes are avaiable at https://github.com/wangguoguoa/FCNGRU.

Mapping Biomolecular Sequences: Graphical Representations - their Origins, Applications and Future Prospects

The exponential growth in the depositories of biological sequence data have generated an urgent need to store, retrieve and analyse the data efficiently and effectively for which the standard practice of using alignment procedures are not adequate due to high demand on computing resources and time. Graphical representation of sequences has become one of the most popular alignment-free strategies to analyse the biological sequences where each basic unit of the sequences - the bases adenine, cytosine, guanine and thymine for DNA/RNA, and the 20 amino acids for proteins - are plotted on a multi-dimensional grid. The resulting curve in 2D and 3D space and the implied graph in higher dimensions provide a perception of the underlying information of the sequences through visual inspection; numerical analyses, in geometrical or matrix terms, of the plots provide a measure of comparison between sequences and thus enable study of sequence hierarchies. The new approach has also enabled studies of comparisons of DNA sequences over many thousands of bases and provided new insights into the structure of the base compositions of DNA sequences In this article we review in brief the origins and applications of graphical representations and highlight the future perspectives in this field.

Genetic Similarity Analysis Based on Positive and Negative Sequence Patterns of DNA

Similarity analysis of DNA sequences can clarify the homology between sequences and predict the structure of, and relationship between, them. At the same time, the frequent patterns of biological sequences explain not only the genetic characteristics of the organism, but they also serve as relevant markers for certain events of biological sequences. However, most of the aforementioned biological sequence similarity analysis methods are targeted at the entire sequential pattern, which ignores the missing gene fragment that may induce potential disease. The similarity analysis of such sequences containing a missing gene item is a blank. Consequently, some sequences with missing bases are ignored or not effectively analyzed. Thus, this paper presents a new method for DNA sequence similarity analysis. Using this method, we first mined not only positive sequential patterns, but also sequential patterns that were missing some of the base terms (collectively referred to as negative sequential patterns). Subsequently, we used these frequent patterns for similarity analysis on a two-dimensional plane. Several experiments were conducted in order to verify the effectiveness of this algorithm. The experimental results demonstrated that the algorithm can obtain various results through the selection of frequent sequential patterns and that accuracy and time efficiency was improved.

Mapping sequence to feature vector using numerical representation of codons targeted to amino acids for alignment-free sequence analysis

The phylogenetic analysis based on sequence similarity targeted to real biological taxa is one of the major challenging tasks. In this paper, we propose a novel alignment-free method, CoFASA (Codon Feature based Amino acid Sequence Analyser), for similarity analysis of nucleotide sequences. At first, we assign numerical weights to the four nucleotides. We then calculate a score of each codon based on the numerical value of the constituent nucleotides, termed as degree of codons. Accordingly, we obtain the degree of each amino acid based on the degree of codons targeted towards a specific amino acid. Utilizing the degree of twenty amino acids and their relative abundance within a given sequence, we generate 20-dimensional features for every coding DNA sequence or protein sequence. We use the features for performing phylogenetic analysis of the set of candidate sequences. We use multiple protein sequences derived from Beta-globin (BG), NADH dehydrogenase subunit 5 (ND5), Transferrins (TFs), Xylanases, low identity (<40%) and high identity (⩾40%) protein sequences (encompassing 533 and 1064 protein families) for experimental assessments. We compare our results with sixteen (16) well-known methods, including both alignment-based and alignment-free methods. Various assessment indices are used, such as the Pearson correlation coefficient, RF (Robinson-Foulds) distance and ROC score for performance analysis. While comparing the performance of CoFASA with alignment-based methods (ClustalW, ClustalΩ, MAFFT, and MUSCLE), it shows very similar results. Further, CoFASA shows better performance in comparison to well-known alignment-free methods, including LZW-Kernal, jD2Stat, FFP, spaced, and AFKS-D2s in predicting taxonomic relationship among candidate taxa. Overall, we observe that the features derived by CoFASA are very much useful in isolating the sequences according to their taxonomic labels. While our method is cost-effective, at the same time, produces consistent and satisfactory outcomes.

Efficient Classification of Hot Spots and Hub Protein Interfaces by Recursive Feature Elimination and Gradient Boosting

Proteins are not isolated biological molecules, which have the specific three-dimensional structures and interact with other proteins to perform functions. A small number of residues (hot spots) in protein-protein interactions (PPIs) play the vital role in bioinformatics to influence and control of biological processes. This paper uses the boosting algorithm and gradient boosting algorithm based on two feature selection strategies to classify hot spots with three common datasets and two hub protein datasets. First, the correlation-based feature selection is used to remove the highly related features for improving accuracy of prediction. Then, the recursive feature elimination based on support vector machine (SVM-RFE) is adopted to select the optimal feature subset to improve the training performance. Finally, boosting and gradient boosting (G-boosting) methods are invoked to generate classification results. Gradient boosting is capable of obtaining an excellent model by reducing the loss function in the gradient direction to avoid overfitting. Five datasets from different protein databases are used to verify our models in the experiments. Experimental results show that our proposed classification models have the competitive performance compared with existing classification methods.

Using Random Forest Model Combined With Gabor Feature to Predict Protein-Protein Interaction From Protein Sequence

Protein-protein interactions (PPIs) play a crucial role in the life cycles of living cells. Thus, it is important to understand the underlying mechanisms of PPIs. Although many high-throughput technologies have generated large amounts of PPI data in different organisms, the experiments for detecting PPIs are still costly and time-consuming. Therefore, novel computational methods are urgently needed for predicting PPIs. For this reason, developing a new computational method for predicting PPIs is drawing more and more attention. In this study, we proposed a novel computational method based on texture feature of protein sequence for predicting PPIs. Especially, the Gabor feature is used to extract texture feature and protein evolutionary information from Position-Specific Scoring Matrix, which is generated by Position-Specific Iterated Basic Local Alignment Search Tool. Then, random forest–based classifiers are used to infer the protein interactions. When performed on PPI data sets of yeast, human, and Helicobacter pylori, we obtained good results with average accuracies of 92.10%, 97.03%, and 86.45%, respectively. To better evaluate the proposed method, we compared Gabor feature, Discrete Cosine Transform, and Local Phase Quantization. Our results show that the proposed method is both feasible and stable and the Gabor feature descriptor is reliable in extracting protein sequence information. Furthermore, additional experiments have been conducted to predict PPIs of other 4 species data sets. The promising results indicate that our proposed method is both powerful and robust.

Efficiently Predicting Hot Spots in PPIs by Combining Random Forest and Synthetic Minority Over-Sampling Technique

Hot spot residues bring into play the vital function in bioinformatics to find new medications such as drug design. However, current datasets are predominately composed of non-hot spots with merely a tiny percentage of hot spots. Conventional hot spots prediction methods may face great challenges towards the problem of imbalance training samples. This paper presents a classification method combining with random forest classification and oversampling strategy to improve the training performance. A strategy with an oversampling ability is used to generate hot spots data to balance the given training set. Random forest classification is then invoked to generate a set of forest trees for this oversampled training set. The final prediction performance can be computed recursively after the oversampling and training process. This proposed method is capable of randomly selecting features and constructing a robust random forest to avoid overfitting the training set. Experimental results from three data sets indicate that the performance of hot spots prediction has been significantly improved compared with existing classification methods.

A Stochastic Phylogenetic Algorithm for Mitochondrial DNA Analysis

This paper presents an exploratory analysis of the mitochondrial DNA (mtDNA) of 32 species in the subphylum Vertebrata, divided in 7 taxonomic classes. Multiple stochastic parameters, such as the Hurst and detrended fluctuation analysis (DFA) exponents, Shannon entropy, and Chargaff ratio are computed for each DNA sequence. The biological interpretation of these parameters leads to defining a triplet of novel indices. These new functions incorporate the long-range correlations, the probability of occurrence of nucleic bases, and the ratio of pyrimidines-to-purines. Results suggest that relevant regions in mtDNA can be located using the proposed indices. Furthermore, early results from clustering algorithms indicate that the indices introduced might be useful in phylogenetic studies.

Mutli-Features Prediction of Protein Translational Modification Sites

Post translational modification plays a significiant role in the biological processing. The potential post translational modification is composed of the center sites and the adjacent amino acid residues which are fundamental protein sequence residues. It can be helpful to perform their biological functions and contribute to understanding the molecular mechanisms that are the foundations of protein design and drug design. The existing algorithms of predicting modified sites often have some shortcomings, such as lower stability and accuracy. In this paper, a combination of physical, chemical, statistical, and biological properties of a protein have been ulitized as the features, and a novel framework is proposed to predict a protein's post translational modification sites. The multi-layer neural network and support vector machine are invoked to predict the potential modified sites with the selected features that include the compositions of amino acid residues, the E-H description of protein segments, and several properties from the AAIndex database. Being aware of the possible redundant information, the feature selection is proposed in the propocessing step in this research. The experimental results show that the proposed method has the ability to improve the accuracy in this classification issue.

New 3D graphical representation for RNA structure analysis and its application in the pre-miRNA identification of plants

MicroRNAs (miRNAs) are a family of short non-coding RNAs that play significant roles as post-transcriptional regulators. Consequently, various methods have been proposed to identify precursor miRNAs (pre-miRNAs), among which the comparative studies of miRNA structures are the most important. To measure and classify the structural similarity of miRNAs, we propose a new three-dimensional (3D) graphical representation of the secondary structure of miRNAs, in which an miRNA secondary structure is initially transformed into a characteristic sequence based on physicochemical properties and frequency of base. A numerical characterization of the 3D graph is used to represent the miRNA secondary structure. We then utilize a novel Euclidean distance method based on this expression to compute the distance of different miRNA sequences for the sequence similarity analysis. Finally, we use this sequence similarity analysis method to identify plant pre-miRNAs among three commonly used datasets. Results show that the method is reasonable and effective.

A novel scaffolding algorithm based on contig error correction and path extension

The sequence assembly process can be divided into three stages: contigs extension, scaffolding, and gap filling. The scaffolding method is an essential step during the process to infer the direction and sequence relationships between the contigs. However, scaffolding still faces the challenges of uneven sequencing depth, genome repetitive regions, and sequencing errors, which often leads to many false relationships between contigs. The performance of scaffolding can be improved by removing potential false conjunctions between contigs. In this study, a novel scaffolding algorithm which is on the basis of path extension Loose-Strict-Loose strategy and contig error correction, called iLSLS. iLSLS helps reduce the false relationships between contigs, and improve the accuracy of subsequent steps. iLSLS utilizes a scoring function, which estimates the correctness of candidate paths by the distribution of paired reads, and try to conduction the extension with the path which is scored the highest. What's more, iLSLS can precisely estimate the gap size. We conduct experiments on two real datasets, and the results show that LSLS strategy is efficient to increase the correctness of scaffolds, and iLSLS performs better than other scaffolding methods.

One novel representation of DNA sequence based on the global and local position information

One novel representation of DNA sequence combining the global and local position information of the original sequence has been proposed to distinguish the different species. First, for the sufficient exploitation of global information, one graphical representation of DNA sequence has been formulated according to the curve of Fermat spiral. Then, for the consideration of local characteristics of DNA sequence, attaching each point in the curve of Fermat spiral with the related mass has been applied based on the relationships of neighboring four nucleotides. In this paper, the normalized moments of inertia of the curve of Fermat spiral which composed by the points with mass has been calculated as the numerical description of the corresponding DNA sequence on the first exons of beta-global genes. Choosing the Euclidean distance as the measurement of the numerical descriptions, the similarity between species has shown the performance of proposed method.

Regularized Non-Negative Matrix Factorization for Identifying Differentially Expressed Genes and Clustering Samples: A Survey

Non-negative Matrix Factorization (NMF), a classical method for dimensionality reduction, has been applied in many fields. It is based on the idea that negative numbers are physically meaningless in various data-processing tasks. Apart from its contribution to conventional data analysis, the recent overwhelming interest in NMF is due to its newly discovered ability to solve challenging data mining and machine learning problems, especially in relation to gene expression data. This survey paper mainly focuses on research examining the application of NMF to identify differentially expressed genes and to cluster samples, and the main NMF models, properties, principles, and algorithms with its various generalizations, extensions, and modifications are summarized. The experimental results demonstrate the performance of the various NMF algorithms in identifying differentially expressed genes and clustering samples.

CIPPN: computational identification of protein pupylation sites by using neural network

Recently, experiments revealed the pupylation to be a signal for the selective regulation of proteins in several serious human diseases. As one of the most significant post translational modification in the field of biology and disease, pupylation has the ability to playing the key role in the regulation various diseases’ biological processes. Meanwhile, effectively identification such type modification will be helpful for proteins to perform their biological functions and contribute to understanding the molecular mechanism, which is the foundation of drug design. The existing algorithms of identification such types of modified sites often have some defects, such as low accuracy and time-consuming. In this research, the pupylation sites’ identification model, CIPPN, demonstrates better performance than other existing approaches in this field. The proposed predictor achieves Acc value of 89.12 and Mcc value of 0.7949 in 10-fold cross-validation tests in the Pupdb Database (http://cwtung.kmu.edu.tw/pupdb). Significantly, such algorithm not only investigates the sequential, structural and evolutionary hallmarks around pupylation sites but also compares the differences of pupylation from the environmental, conservative and functional characterization of substrates. Therefore, the proposed feature description approach and algorithm results prove to be useful for further experimental investigation of such modification’s identification.

Classification of Protein Structure Classes on Flexible Neutral Tree

Accurate classification on protein structural is playing an important role in Bioinformatics. An increase in evidence demonstrates that a variety of classification methods have been employed in such a field. In this research, the features of amino acids composition, secondary structure's feature, and correlation coefficient of amino acid dimers and amino acid triplets have been used. Flexible neutral tree (FNT), a particular tree structure neutral network, has been employed as the classification model in the protein structures' classification framework. Considering different feature groups owing diverse roles in the model, impact factors of different groups have been put forward in this research. In order to evaluate different impact factors, Impact Factors Scaling (IFS) algorithm, which aim at reducing redundant information of the selected features in some degree, have been put forward. To examine the performance of such framework, the 640, 1189, and ASTRAL datasets are employed as the low-homology protein structure benchmark datasets. Experimental results demonstrate that the performance of the proposed method is better than the other methods in the low-homology protein tertiary structures.

Predicting protein-protein interactions from primary protein sequences using a novel multi-scale local feature representation scheme and the random forest

The study of protein-protein interactions (PPIs) can be very important for the understanding of biological cellular functions. However, detecting PPIs in the laboratories are both time-consuming and expensive. For this reason, there has been much recent effort to develop techniques for computational prediction of PPIs as this can complement laboratory procedures and provide an inexpensive way of predicting the most likely set of interactions at the entire proteome scale. Although much progress has already been achieved in this direction, the problem is still far from being solved. More effective approaches are still required to overcome the limitations of the current ones. In this study, a novel Multi-scale Local Descriptor (MLD) feature representation scheme is proposed to extract features from a protein sequence. This scheme can capture multi-scale local information by varying the length of protein-sequence segments. Based on the MLD, an ensemble learning method, the Random Forest (RF) method, is used as classifier. The MLD feature representation scheme facilitates the mining of interaction information from multi-scale continuous amino acid segments, making it easier to capture multiple overlapping continuous binding patterns within a protein sequence. When the proposed method is tested with the PPI data of Saccharomyces cerevisiae, it achieves a prediction accuracy of 94.72% with 94.34% sensitivity at the precision of 98.91%. Extensive experiments are performed to compare our method with existing sequence-based method. Experimental results show that the performance of our predictor is better than several other state-of-the-art predictors also with the H. pylori dataset. The reason why such good results are achieved can largely be credited to the learning capabilities of the RF model and the novel MLD feature representation scheme. The experiment results show that the proposed approach can be very promising for predicting PPIs and can be a useful tool for future proteomic studies.

Similarity evaluation of DNA sequences based on frequent patterns and entropy

BACKGROUND

DNA sequence analysis is an important research topic in bioinformatics. Evaluating the similarity between sequences, which is crucial for sequence analysis, has attracted much research effort in the last two decades, and a dozen of algorithms and tools have been developed. These methods are based on alignment, word frequency and geometric representation respectively, each of which has its advantage and disadvantage.

RESULTS

In this paper, for effectively computing the similarity between DNA sequences, we introduce a novel method based on frequency patterns and entropy to construct representative vectors of DNA sequences. Experiments are conducted to evaluate the proposed method, which is compared with two recently-developed alignment-free methods and the BLASTN tool. When testing on the β-globin genes of 11 species and using the results from MEGA as the baseline, our method achieves higher correlation coefficients than the two alignment-free methods and the BLASTN tool.

CONCLUSIONS

Our method is not only able to capture fine-granularity information (location and ordering) of DNA sequences via sequence blocking, but also insensitive to noise and sequence rearrangement due to considering only the maximal frequent patterns. It outperforms major existing methods or tools.

Prediction of protein-protein interactions from amino acid sequences using a novel multi-scale continuous and discontinuous feature set

BACKGROUND

Identifying protein-protein interactions (PPIs) is essential for elucidating protein functions and understanding the molecular mechanisms inside the cell. However, the experimental methods for detecting PPIs are both time-consuming and expensive. Therefore, computational prediction of protein interactions are becoming increasingly popular, which can provide an inexpensive way of predicting the most likely set of interactions at the entire proteome scale, and can be used to complement experimental approaches. Although much progress has already been achieved in this direction, the problem is still far from being solved and new approaches are still required to overcome the limitations of the current prediction models.

RESULTS

In this work, a sequence-based approach is developed by combining a novel Multi-scale Continuous and Discontinuous (MCD) feature representation and Support Vector Machine (SVM). The MCD representation gives adequate consideration to the interactions between sequentially distant but spatially close amino acid residues, thus it can sufficiently capture multiple overlapping continuous and discontinuous binding patterns within a protein sequence. An effective feature selection method mRMR was employed to construct an optimized and more discriminative feature set by excluding redundant features. Finally, a prediction model is trained and tested based on SVM algorithm to predict the interaction probability of protein pairs.

CONCLUSIONS

When performed on the yeast PPIs data set, the proposed approach achieved 91.36% prediction accuracy with 91.94% precision at the sensitivity of 90.67%. Extensive experiments are conducted to compare our method with the existing sequence-based method. Experimental results show that the performance of our predictor is better than several other state-of-the-art predictors, whose average prediction accuracy is 84.91%, sensitivity is 83.24%, and precision is 86.12%. Achieved results show that the proposed approach is very promising for predicting PPI, so it can be a useful supplementary tool for future proteomics studies. The source code and the datasets are freely available at http://csse.szu.edu.cn/staff/youzh/MCDPPI.zip for academic use.