iDPPIV-SI: identifying dipeptidyl peptidase IV inhibitory peptides by using multiple sequence information.

Currently, diabetes has become a great threaten for people's health in the world. Recent study shows that dipeptidyl peptidase IV (DPP-IV) inhibitory peptides may be a potential pharmaceutical agent to treat diabetes. Thus, there is a need to discriminate DPP-IV inhibitory peptides from non-DPP-IV inhibitory peptides. To address this issue, a novel computational model called iDPPIV-SI was developed in this study. In the first, 50 different types of physicochemical (PC) properties were employed to denote the peptide sequences. Three different feature descriptors including the 1-order, 2-order correlation methods and discrete wavelet transform were applied to collect useful information from the PC matrix. Furthermore, the least absolute shrinkage and selection operator (LASSO) algorithm was employed to select these most discriminative features. All of these chosen features were fed into support vector machine (SVM) for identifying DPP-IV inhibitory peptides. The iDPPIV-SI achieved 91.26% and 98.12% classification accuracies on the training and independent dataset, respectively. There is a significantly improvement in the classification performance by the proposed method, as compared with the state-of-the-art predictors. The datasets and MATLAB codes (based on MATLAB2015b) used in current study are available at https://figshare.com/articles/online_resource/iDPPIV-SI/20085878.Communicated by Ramaswamy H. Sarma.

iHBPs-VWDC: variable-length window-based dynamic connectivity approach for identifying hormone-binding proteins.

Hormone-binding proteins (HBPs) are soluble carrier proteins that play a vital role in the growth and development of living organisms. Identifying HBPs accurately is crucial for understanding their functions. However, traditional wet lab experimental methods are labor intensive and cost ineffective. Therefore, there is a need for computational methods to efficiently identify HBPs. In this study, a machine learning method based on support vector machine (SVM) was proposed for the accurate and efficient identification of HBPs. The encoding of protein sequences involved using fifty different physicochemical (PC) properties. A variable-length window-based dynamic connectivity method was applied to capture the connection information between two different PC properties through two distinct strategies. The canonical correlation analysis algorithm was then used to fuse features obtained from these approaches. Feature selection was performed using the F-score approach to choose the most discriminative features. Finally, these selected features were fed into the SVM to discriminate between HBPs and non-HBPs. The proposed method achieved high classification accuracies of 99.19%, 96.77%, and 94.57% on the main dataset and two independent datasets, respectively, as demonstrated in the jackknife test. Comparative results showed that our proposed method outperforms existing approaches on the same datasets, indicating its potential as a useful tool for identifying HBPs. The Matlab codes and datasets used in the current study are freely available at https://figshare.com/articles/online_resource/iHBPs-VWDC/23559834.Communicated by Ramaswamy H. Sarma.

Dual-Signal Feature Spaces Map Protein Subcellular Locations Based on Immunohistochemistry Image and Protein Sequence.

Protein is one of the primary biochemical macromolecular regulators in the compartmental cellular structure, and the subcellular locations of proteins can therefore provide information on the function of subcellular structures and physiological environments. Recently, data-driven systems have been developed to predict the subcellular location of proteins based on protein sequence, immunohistochemistry (IHC) images, or immunofluorescence (IF) images. However, the research on the fusion of multiple protein signals has received little attention. In this study, we developed a dual-signal computational protocol by incorporating IHC images into protein sequences to learn protein subcellular localization. Three major steps can be summarized as follows in this protocol: first, a benchmark database that includes 281 proteins sorted out from 4722 proteins of the Human Protein Atlas (HPA) and Swiss-Prot database, which is involved in the endoplasmic reticulum (ER), Golgi apparatus, cytosol, and nucleoplasm; second, discriminative feature operators were first employed to quantitate protein image-sequence samples that include IHC images and protein sequence; finally, the feature subspace of different protein signals is absorbed to construct multiple sub-classifiers via dimensionality reduction and binary relevance (BR), and multiple confidence derived from multiple sub-classifiers is adopted to decide subcellular location by the centralized voting mechanism at the decision layer. The experimental results indicated that the dual-signal model embedded IHC images and protein sequences outperformed the single-signal models with accuracy, precision, and recall of 75.41%, 80.38%, and 74.38%, respectively. It is enlightening for further research on protein subcellular location prediction under multi-signal fusion of protein.

iAMY-RECMFF: Identifying amyloidgenic peptides by using residue pairwise energy content matrix and features fusion algorithm.

Various diseases, including Huntington's disease, Alzheimer's disease, and Parkinson's disease, have been reported to be linked to amyloid. Therefore, it is crucial to distinguish amyloid from non-amyloid proteins or peptides. While experimental approaches are typically preferred, they are costly and time-consuming. In this study, we have developed a machine learning framework called iAMY-RECMFF to discriminate amyloidgenic from non-amyloidgenic peptides. In our model, we first encoded the peptide sequences using the residue pairwise energy content matrix. We then utilized Pearson's correlation coefficient and distance correlation to extract useful information from this matrix. Additionally, we employed an improved similarity network fusion algorithm to integrate features from different perspectives. The Fisher approach was adopted to select the optimal feature subset. Finally, the selected features were inputted into a support vector machine for identifying amyloidgenic peptides. Experimental results demonstrate that our proposed method significantly improves the identification of amyloidgenic peptides compared to existing predictors. This suggests that our method may serve as a powerful tool in identifying amyloidgenic peptides. To facilitate academic use, the dataset and codes used in the current study are accessible at https://figshare.com/articles/online_resource/iAMY-RECMFF/22816916.

Integrating Low-Order and High-Order Correlation Information for Identifying Phage Virion Proteins.

Phage virion proteins (PVPs) play an important role in the host cell. Fast and accurate identification of PVPs is beneficial for the discovery and development of related drugs. Although wet experimental approaches are the first choice to identify PVPs, they are costly and time-consuming. Thus, researchers have turned their attention to computational models, which can speed up related studies. Therefore, we proposed a novel machine-learning model to identify PVPs in the current study. First, 50 different types of physicochemical properties were used to denote protein sequences. Next, two different approaches, including Pearson's correlation coefficient (PCC) and maximal information coefficient (MIC), were employed to extract discriminative information. Further, to capture the high-order correlation information, we used PCC and MIC once again. After that, we adopted the least absolute shrinkage and selection operator algorithm to select the optimal feature subset. Finally, these chosen features were fed into a support vector machine to discriminate PVPs from phage non-virion proteins. We performed experiments on two different datasets to validate the effectiveness of our proposed method. Experimental results showed a significant improvement in performance compared with state-of-the-art approaches. It indicates that the proposed computational model may become a powerful predictor in identifying PVPs.

Integrating temporal and spatial variabilities for identifying ion binding proteins in phage.

Recent studies reported that ion binding proteins (IBPs) in phage play a key role in developing drugs to treat diseases caused by drug-resistant bacteria. Therefore, correct recognition of IBPs is an urgent task, which is beneficial for understanding their biological functions. To explore this issue, a new computational model was developed to identify IBPs in this study. First, we used the physicochemical (PC) property and Pearson's correlation coefficient (PCC) to denote protein sequences, and the temporal and spatial variabilities were employed to extract features. Next, a similarity network fusion algorithm was employed to capture the correlation characteristics between these two different kinds of features. Then, a feature selection method called F-score was utilized to remove the influence of redundant and irrelative information. Finally, these reserved features were fed into support vector machine (SVM) to discriminate IBPs from non-IBPs. Experimental results showed that the proposed method has significant improvement in the classification performance, as compared with the state-of-the-art approach. The Matlab codes and dataset used in this study are available at https://figshare.com/articles/online_resource/iIBP-TSV/21779567 for academic use.

Identification of tumor homing peptides by utilizing hybrid feature representation.

Cancer is one of the serious diseases, recent studies reported that tumor homing peptides (THPs) play a key role in treatment of cancer. Due to the experimental methods are time-consuming and expensive, it is urgent to develop automatic computational approaches to identify THPs. Hence, in this study, we proposed a novel machine learning methods to distinguish THPs from non-THPs, in which the peptide sequences firstly encoded by pseudo residue pairwise energy content matrix (PseRECM) and pseudo physicochemical property (PsePC). Moreover, the least absolute shrinkage and selection operator (LAASO) was employed to select optimal features from the extracted features. All of these selected features were fed into support vector machine (SVM) for identifying THPs. We achieved 89.02%, 88.49%, and 94.58% classification accuracy on the Main, Small, and Main90 dataset, respectively. Experimental results showed that our proposed method outperforms the existing predictors on the same benchmark datasets. It indicates that the proposed method may be a useful tool in identifying THPs. The datasets and codes used in current study are available at https://figshare.com/articles/online_resource/iTHPs/16778770.Communicated by Ramaswamy H. Sarma.

iRNA5hmC-HOC: High-order correlation information for identifying RNA 5-hydroxymethylcytosine modification.

RNA 5-hydroxymethylcytosine (5 hmC) is an important RNA modification, which plays vital role in several biological processes. Currently, it is a hot topic to identify 5 hmC sites due to its benefit in understanding its biological functions. Therefore, in this study, we developed a predictor called iRNA5 hmC-HOC, which is based on a high-order correlation information method to identify 5 hmC sites. To build the model, 22 different classes of dinucleotide physicochemical (PC) properties were employed to represent RNA sequences, and the least absolute shrinkage and selection operator (LASSO) algorithm was adopted to select the most discriminative features. In the jackknife test, the proposed method achieved 89.80% classification accuracy based on support vector machine (SVM). As compared with the state-of-the-art predictors, our proposed method has significant improvement on the classification performance. It indicates that the proposed method might be a promising tool in identifying RNA 5 hmC modification sites. The dataset and source codes are available at https://figshare.com/articles/online_resource/iRNA5hmC-HOC/15177450.

Origin and Genesis of the Permain Hydrocarbon in the Northeast of the Dongdaohaizi Depression, Junggar Basin, China.

Dongdaohaizi area is an important hydrocarbon-rich depression in the Junggar Basin. Early resource evaluation has revealed that it has superior hydrocarbon generation conditions. No major exploration breakthrough has been observed in the hydrocarbon from the Permian Pingdiquan Formation source rocks, which are widely distributed and have a large sedimentary thickness. The unclear recognition of the genesis, the sources, and the hydrocarbon evolution history of the formation seriously restricted further exploration and development. Sixty-four samples were acquired during the study, consisting of 30 source rocks, 13 crude oil samples, and 21 natural gas samples. Studying the geochemical characteristics of the source rock extract and the surrounding structural crude oil in the Dongdaohaizi Depression, the differences in the stable carbon isotope, the biomarker compound, and the molecular relative composition of the three sets of main source rock products in the research fields are summarized. The results reflect that the drying coefficient of natural gas in the study area is generally low, and the fractional distillation value of methane and ethane is 0.32, which is most likely due to the loss of oil and gas migration and the mixing of different types of natural gases. The carbon isotope value is relatively low, with the Pr/Ph being generally less than 3.0. The content of sterane C29 is the highest in the relative composition of steranes, followed by the content of sterane C28, which together account for more than 80% of the total sterane content, and then followed by a lower content of C27 sterane, accounting for only 5-20% of the total content, which generally conforms to the characteristics of Permian Pingdiquan Formation source rock products. The carbon isotope value of crude oil ranges from -30.94 to -28.31‰, which is different from the characteristics of typical Permian source rocks (values range from -34.49 to -28.21‰), while it is related to typical Carboniferous products (values range from -29.98 to -24.1‰), indicating that small amounts of Carboniferous source rock products were mixed in different degrees in the Dinan fault area. According to the distribution law of oil and gas, the geochemical characteristics and hydrocarbon sources were considered the oil source in the east of the Dongdaohaizi Depression, mainly from the source rocks of the Permian Pingdiquan Formation. The products of the peak period of hydrocarbon generation in the source rocks of the Pingdiquan Formation have not been transported to the high structural positions on a large scale to form reservoirs. They may still exist in the deep part of the Depression and the slope area. The low-amplitude structural and lithologic traps in the slope area of the Dongdahaizi Depression are promising targets for finding the products of the peak period of hydrocarbon generation. This is of great significance to reveal the Permain hydrocarbon evolution in the Junggar Basin and guide further research on the oil-source correlation of natural gas from the paleo-strata.

Integrating multiple sequence features for identifying anticancer peptides.

As one of the most terrible diseases, cancer causes millions of deaths worldwide every year. The popular treatment approaches, such as radiotherapy and chemotherapy, have been used in against cancer cells. However, those traditional therapies have side effects on normal cells, time-consuming and expensive. Recent studies showed that anticancer peptides (ACP) may be a potential choice instead of traditional approaches for treating cancer. Therefore, it is desired to develop a computational method to identify anticancer peptides. In this study, a support vector machine (SVM) based computational model was proposed to discriminate anticancer peptides from non-anticancer peptides. In the model, peptide sequences were firstly encoded by amino acids physicochemical (PC) properties and residue pairwise energy content matrix (RECM). Then, Pearson's correlation coefficient, high-order correlation information, and discrete wavelet transform were employed to extract useful information from PC and RECM matrix. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to select discriminative features. Finally, these selected features were fed into SVM for distinguishing ACP from non-ACP. Experimental results demonstrated that the proposed method is powerful, it indicates that our proposed method may be a hopeful tool in discriminating anticancer peptides from non-anticancer peptides. The codes and datasets used in current work are available at https://figshare.com/articles/online_resource/iACP/16866232.

iTTCA-MFF: identifying tumor T cell antigens based on multiple feature fusion.

Cancer is a terrible disease, recent studies reported that tumor T cell antigens (TTCAs) may play a promising role in cancer treatment. Since experimental methods are still expensive and time-consuming, it is highly desirable to develop automatic computational methods to identify tumor T cell antigens from the huge amount of natural and synthetic peptides. Hence, in this study, a novel computational model called iTTCA-MFF was proposed to identify TTCAs. In order to describe the sequence effectively, the physicochemical (PC) properties of amino acid and residue pairwise energy content matrix (RECM) were firstly employed to encode peptide sequences. Then, two different approaches including covariance and Pearson's correlation coefficient (PCC) were used to collect discriminative information from PC and RECM matrixes. Next, an effective feature selection approach called the least absolute shrinkage and selection operator (LAASO) was adopted to select the optimal features. These selected optimal features were fed into support vector machine (SVM) for identifying TTCAs. We performed experiments on two different datasets, experimental results indicated that the proposed method is promising and may play a complementary role to the existing methods for identifying TTCAs. The datasets and codes can be available at https://figshare.com/articles/online_resource/iTTCA-MFF/17636120 .

iDHS-DT: Identifying DNase I hypersensitive sites by integrating DNA dinucleotide and trinucleotide information.

DNase I hypersensitive sites (DHSs) is important for identifying the location of gene regulatory elements, such as promoters, enhancers, silencers, and so on. Thus, it is crucial for discriminating DHSs from non-DHSs. Although some traditional methods, such as Southern blots and DNase-seq technique, have the ability to identify DHSs, these approaches are time-consuming, laborious, and expensive. To address these issues, researchers paid their attention on computational approaches. Therefore, in this study, we developed a novel predictor called iDHS-DT to identify DHSs. In this predictor, the DNA sequences were firstly denoted by physicochemical properties (PC) of DNA dinucleotide and trinucleotide. Then, three different descriptors, including auto-covariance, cross-covariance, and discrete wavelet transform were used to collect related features from the PC matrix. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was employed to remove these irrelevant and redundant features. Finally, these selected features were fed into support vector machine (SVM) for distinguishing DHSs from non-DHSs. The proposed method achieved 97.64% and 98.22% classification accuracy on dataset S1 and S2, respectively. Compared with the existing predictors, our proposed model has significantly improvement in classification performance. Experimental results demonstrated that the proposed method is powerful in identifying DHSs.

Identifying N7-methylguanosine sites by integrating multiple features.

Recent studies reported that N7-methylguanosine (m7G) plays a vital role in gene expression regulation. As a consequence, determining the distribution of m7G is a crucial step towards further understanding its biological functions. Although biological experimental approaches are capable of accurately locating m7G sites, they are labor-intensive, costly, and time-consuming. Therefore, it is necessary to develop more effective and robust computational methods to replace, or at least complement current experimental methods. In this study, we developed a novel sequence-based computational tool to identify RNA m7G sites. In this model, 22 kinds of dinucleotide physicochemical (PC) properties were employed to encode the RNA sequence. Three types of descriptors, including auto-covariance, cross-covariance, and discrete wavelet transform were adopted to extract effective features from the PC matrix. The least absolute shrinkage and selection operator (LASSO) algorithm was utilized to reduce the influence of irrelevant or redundant features. Finally, these selected features were fed into a support vector machine (SVM) for distinguishing m7G from non-m7G sites. The proposed method significantly outperforms existing predictors across all evaluation metrics. It indicates that the approach is effective in identifying RNA m7G sites.

m7G-DPP: Identifying N7-methylguanosine sites based on dinucleotide physicochemical properties of RNA.

N7-methylguanosine (m7G) modification is one of the most common post-transcriptional RNA modifications, which play vital role in the regulation of gene expression. Dysfunction of m7G may result to developmental defects and the appearance of some serious diseases. Thus, it is an urgent task to fast and accurate identifying m7G sites. In view of experimental approaches are costly and time-consuming, researchers focused their attention on computational models. Hence, in current study, we proposed a novel predictor called m7G-DPP to identify m7G sites. In the predictor, the RNA sequences were firstly encoded by physicochemical (PC) properties of dinucleotide. Then, sliding window approach was adopted to divide PC matrix into multiple matrixes, and Pearson's correlation coefficient (PCC), dynamic time warping (DTW), and distance correlation (DC) were employed to extract classification features at each window. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was applied to select discriminative features. Finally, these selected features were fed into support vector machine to identify m7G sites. Experimental results showed that the proposed method is effective, which may play a complementary role in current m7G sites prediction studies. The MATLAB codes and dataset can be obtained from website at https://figshare.com/articles/online_resource/m7G-DPP/15000348.

Exploring the Brain Lateralization in ADHD Based on Variability of Resting-State fMRI Signal.

Objective: In this study, we investigate the brain lateralization in ADHD patients. Furthermore, we also explore the difference between male and female patients, and the difference among distinct ADHD subtypes, that is, ADHD-inattentive (ADHD-IA) and ADHD-combined (ADHD-C). Method: We employed the standard deviation to quantify the variability of resting-state functional magnetic resonance imaging (fMRI) signal and measure the lateralization index (LI). Results: ADHD patients showed significantly increased rightward lateralization in the inferior frontal gyrus (opercular), precuneus, and paracentral lobule, and decreased rightward lateralization in the insula. Compared with male patients, female patients showed significantly rightward lateralization in the putamen and lobule VII of cerebellar hemisphere. ADHD-C patients exhibited increased rightward lateralization in the inferior frontal gyrus (opercular), and decreased rightward lateralization in the inferior temporal gyrus, as compared with ADHD-IA. The LI was also found to be related to inattentive and hyper/impulsive scores. Conclusion: These key findings may aid in understanding the pathology of ADHD.

Temporal Variability-Based Functional Brain Lateralization Study in ADHD.

Objective: The aim of this work is to explore the relationship between temporal variability and brain lateralization in ADHD. Method: The temporal variabilities of 116 brain regions based on resting-state functional magnetic resonance imaging (rs-fMRI) data were calculated for analysis. Results: Between-group comparison revealed that in comparison with the controls, ADHD participants showed significantly higher temporal variability in the left superior frontal gyrus (medial), left rectus gyrus, left inferior parietal lobule and angular gyrus, and lower temporal variability in the amygdala, left caudate and putamen. Besides, ADHD patients exhibited significantly increased leftward lateralization in the orbitofrontal cortex (inferior), and decreased rightward lateralization in the orbitofrontal cortex (medial) and rectus gyrus, compared with controls. Lateralization indices were also found to be related with clinical characteristics of ADHD patients. Conclusion: Our results may help us deeper in understanding the pathology of ADHD.

Multiple functional connectivity networks fusion for schizophrenia diagnosis.

Accurate diagnosis of schizophrenia is of great importance to patients and clinicians. Recent studies have found that different frequency bands contain complementary information for diagnosis and prognosis. However, conventional multiple frequency functional connectivity (FC) networks using Pearson's correlation coefficient (PCC) are usually based on pairwise correlations among different brain regions on single frequency band, while ignoring the interactions between regions in different frequency bands, the relationship among different networks, and the nonlinear properties of blood-oxygen-level-dependent (BOLD) signal. To take into account these relationships, we propose in this study a multiple networks fusion method for schizophrenia diagnosis. Specifically, we first construct FC networks within the same and across frequency from the resting-state functional magnetic resonance imaging (rs-fMRI) time series by using extended maximal information coefficient (eMIC) based on four frequency bands: slow-5 (0.01-0.027 Hz), slow-4 (0.027-0.073 Hz), slow-3 (0.073-0.198 Hz), and slow-2 (0.198-0.25 Hz). Then, these networks are combined nonlinearly through network fusion, which generates a unified network for each subject. Features extracted from the unified network are used for final classification. Experimental results demonstrated that the interaction between distinct brain regions across different frequency bands can significantly improve the classification performance, comparing with conventional FC analysis based on specific or entire low-frequency band. The promising results suggest that our proposed framework would be a useful tool in computer-aided diagnosis of schizophrenia. Graphical abstract The flowchart of proposed classification framework.

Dynamic thresholding networks for schizophrenia diagnosis.

BACKGROUND AND OBJECTIVE: Functional connectivity (FC) based on resting-state functional magnetic resonance imaging (rs-fMRI) is an effective approach to describe the neural interaction between distributed brain regions. Recent progress in neuroimaging study reported that the connection between regions is time-varying, which may enhance understanding of normal cognition and alterations that result from brain disorders. However, conventional sliding window based dynamic FC (DFC) analysis has several drawbacks, including arbitrary choice of window length, inaccurate descriptor of FC, and the fact that many spurious connections were included in the fully-connected networks due to noise. This study aims to develop an effective dynamic thresholding brain networks method to diagnose schizophrenia. METHODS: In this study, we proposed a time-varying window length DFC method based on dynamic time warping to construct brain functional networks. To further eliminate the influence of spurious connections caused by noise, orthogonal minimum spanning tree was applied in these networks to generate time-varying window length dynamic thresholding FC (TVWDTFC) networks. To validate the effectiveness of our proposed method, experiments were conducted on a dataset, which including 56 individuals with schizophrenia and 74 healthy controls. RESULTS: We achieved a classification accuracy of 0.8077 (p < 0.001, permutation test) using support vector machine. Experimental results demonstrated that the proposed method outperforms several state-of-the-art approaches, which verified the effectiveness of our proposed TVWDTFC method in schizophrenia diagnosis. Additionally, we also found that the selected discriminative features were mostly distributed in frontal, parietal, and limbic area. CONCLUSIONS: The results suggest that our approach may be a promising tool for computer-aided diagnosis of schizophrenia.

Classifying Multifunctional Enzymes by Incorporating Three Different Models into Chou's General Pseudo Amino Acid Composition.

With the avalanche of the newly found protein sequences in the post-genomic epoch, there is an increasing trend for annotating a number of newly discovered enzyme sequences. Among the various proteins, enzyme was considered as the one of the largest kind of proteins. It takes part in most of the biochemical reactions and plays a key role in metabolic pathways. Multifunctional enzyme is enzyme that plays multiple physiological roles. Given a multifunctional enzyme sequence, how can we identify its class? Especially, how can we deal with the multi-classes problem since an enzyme may simultaneously belong to two or more functional classes? To address these problems, which are obviously very important both to basic research and drug development, a multi-label classifier was developed via three different prediction models with multi-label K-nearest algorithm. Experimental results obtained on a stringent benchmark dataset of enzymes by jackknife cross-validation test show that the predicting results were exciting, indicating that the current method could be an effective and promising high throughput method in the enzyme research. We hope it could play an important complementary role to the existing predictors in identifying the classes of enzymes.

Predicting the Functional Types of Singleplex and Multiplex Eukaryotic Membrane Proteins via Different Models of Chou's Pseudo Amino Acid Compositions.

Given a membrane protein sequence, how can we identify its type, particularly when a query protein may have the multiplex character, i.e., simultaneously exist at two or more different types. However, most of the existing predictors or methods can only be used to deal with the single-type or "singleplex" membrane proteins. Actually, multiple-type or "multiplex" membrane proteins should not be ignored because they usually posses some unique biological functions worthy of our special notice. In this study, three different models were developed, which have the ability to deal with the systems containing both singleplex and multiplex membrane proteins. The overall success rate thus obtained was 0.6440, indicating that the study may become a very useful high-throughput tool in identifying the functional types of membrane proteins.