CyclinPred: a SVM-based method for predicting cyclin protein sequences

Functional annotation of protein sequences with low similarity to well characterized protein sequences is a major challenge of computational biology in the post genomic era. The cyclin protein family is once such important family of proteins which consists of sequences with low sequence similarity making discovery of novel cyclins and establishing orthologous relationships amongst the cyclins, a difficult task. The currently identified cyclin motifs and cyclin associated domains do not represent all of the identified and characterized cyclin sequences. We describe a Support Vector Machine (SVM) based classifier, CyclinPred, which can predict cyclin sequences with high efficiency. The SVM classifier was trained with features of selected cyclin and non cyclin protein sequences. The training features of the protein sequences include amino acid composition, dipeptide composition, secondary structure composition and PSI-BLAST generated Position Specific Scoring Matrix (PSSM) profiles. Results obtained from Leave-One-Out cross validation or jackknife test, self consistency and holdout tests prove that the SVM classifier trained with features of PSSM profile was more accurate than the classifiers based on either of the other features alone or hybrids of these features. A cyclin prediction server--CyclinPred has been setup based on SVM model trained with PSSM profiles. CyclinPred prediction results prove that the method may be used as a cyclin prediction tool, complementing conventional cyclin prediction methods.     

An SVM method using evolutionary information for the identification of allergenic proteins

This study presents an allergenic protein prediction system that appears to be capable of producing high sensitivity and specificity. The proposed system is based on support vector machine (SVM) using evolutionary information in the form of an amino acid position specific scoring matrix (PSSM). The performance of this system is assessed by a 10-fold cross-validation experiment using a dataset consisting of 693 allergens and 1041 non-allergens obtained from Swiss-Prot and Structural Database of Allergenic Proteins (SDAP). The PSSM method produced an accuracy of 90.1% in comparison to the methods based on SVM using amino acid, dipeptide composition, pseudo (5-tier) amino acid composition that achieved an accuracy of 86.3, 86.5 and 82.1% respectively. The results show that evolutionary information can be useful to build more effective and efficient allergen prediction systems.     

基于卷积神经网络的大肠杆菌启动子预测

目的 基于位点特异性打分矩阵（position-specific scoring matrices,PSSM）的预测模型已经取得了良好的效果,基于PSSM的各种优化方法也在不断发展,但准确率相对较低,为了进一步提高预测准确率,本文基于卷积神经网络（convolutional neural networks,CNN）算法做了进一步研究。方法 采用PSSM将启动子序列处理成数值矩阵,通过CNN算法进行分类。大肠杆菌K-12（Escherichia coli K-12,E.coli K-12,下文简称大肠杆菌）的Sigma38、Sigma54和Sigma70 3种启动子序列被作为正集,编码（Coding）区和非编码（Non-coding）区的序列为负集。结果 在预测大肠杆菌启动子的二分类中,准确率达到99%,启动子预测的成功率接近100%;在对Sigma38、Sigma54、Sigma70 3种启动子的三分类中,预测准确率为98%,并且针对每一种序列的预测准确率均可以达到98%以上。最后,本文以Sigma38、Sigma54、Sigma70 3种启动子分别和Coding区或者Non-coding区序列做四分类,预测得到的准确性为0.98,对3种Sigma启动子均衡样本的十交叉检验预测精度均可以达到0.95以上,海明距离为0.016,Kappa系数为0.97。结论 相较于支持向量机（support vector machine,SVM）等其他分类算法,CNN分类算法更具优势,并且基于CNN的分类优势,编码方式亦可以得到简化。     

Functional combination strategy for prioritization of human miRNA target

MicroRNAs (miRNAs) are a class of non-coding RNAs known to play important regulatory roles through targets, which can affect human cell proliferation, differentiation, and metabolism. Overlaps between different miRNA target prediction algorithms (MTPAs) are small, which limit the understanding of miRNA's biological functions. However, the overlaps increase on functional levels, such as Gene Ontology (GO), Protein–Protein Interaction Network (PPIN) and pathways. Here, we performed prioritization on existing predicted target sets for each miRNA by considering all the possible combinations of 7 functional levels. After analyzing the results of both single and multiple functional levels, we found that functional combination strategies including pathways and GO performed better in the prioritization of human miRNA target. The combination which performed best was “Pathway + GO BP + GO MF + GO CC + Target + PPIN”. For the prioritized result of this combination, the valid target had top ranking, and our method performed better than the MTPAs after comparison adopting the validated ranking levels. Top genes in ranking lists generated by this strategy were either validated by experiments or share same functions with the corresponding miRNA/its validated genes in disease related biological processes.     

GNBSL: a new integrative system to predict the subcellular location for Gram-negative bacteria proteins

This paper proposes a new integrative system (GNBSL--Gram-negative bacteria subcellular localization) for subcellular localization specifized on the Gram-negative bacteria proteins. First, the system generates a position-specific frequency matrix (PSFM) and a position-specific scoring matrix (PSSM) for each protein sequence by searching the Swiss-Prot database. Then different features are extracted by four modules from the PSFM and the PSSM. The features include whole-sequence amino acid composition, N- and C-terminus amino acid composition, dipeptide composition, and segment composition. Four probabilistic neural network (PNN) classifiers are used to classify these modules. To further improve the performance, two modules trained by support vector machine (SVM) are added in this system. One module extracts the residue-couple distribution from the amino acid sequence and the other module applies a pairwise profile alignment kernel to measure the local similarity between every two sequences. Finally, an additional SVM is used to fuse the outputs from the six modules. Test on a benchmark dataset shows that the overall success rate of GNBSL is higher than those of PSORT-B, CELLO, and PSLpred. A web server GNBSL can be visited from http://166.111.24.5/webtools/GNBSL/index.htm.     

A novel method for protein secondary structure prediction using dual-layer SVM and profiles

A high-performance method was developed for protein secondary structure prediction based on the dual-layer support vector machine (SVM) and position-specific scoring matrices (PSSMs). SVM is a new machine learning technology that has been successfully applied in solving problems in the field of bioinformatics. The SVM's performance is usually better than that of traditional machine learning approaches. The performance was further improved by combining PSSM profiles with the SVM analysis. The PSSMs were generated from PSI-BLAST profiles, which contain important evolution information. The final prediction results were generated from the second SVM layer output. On the CB513 data set, the three-state overall per-residue accuracy, Q3, reached 75.2%, while segment overlap (SOV) accuracy increased to 80.0%. On the CB396 data set, the Q3 of our method reached 74.0% and the SOV reached 78.1%. A web server utilizing the method has been constructed and is available at http://www.bioinfo.tsinghua.edu.cn/pmsvm.     

Prediction of nicotinamide adenine dinucleotide interacting sites based on ensemble support vector machine

Nicotinamide adenine dinucleotide (NAD) plays an important role in cellular metabolism and acts as hydrideaccepting and hydride-donating coenzymes in energy production. Identification of NAD protein interacting sites can significantly aid in understanding the NAD dependent metabolism and pathways, and it could further contribute useful information for drug development. In this study, a computational method is proposed to predict NAD-protein interacting sites using the sequence information and structure-based information. All models developed in this work are evaluated using the 7-fold cross validation technique. Results show that using the position specific scoring matrix (PSSM) as an input feature is quite encouraging for predicting NAD interacting sites. After considering the unbalance dataset, the ensemble support vector machine (SVM), which is an assembly of many individual SVM classifiers, is developed to predict the NAD interacting sites. It was observed that the overall accuracy (Acc) thus obtained was 87.31% with Matthew's correlation coefficient (MCC) equal to 0.56. In contrast, the corresponding rate by the single SVM approach was only 80.86% with MCC of 0.38. These results indicated that the prediction accuracy could be remarkably improved via the ensemble SVM classifier approach.     

Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments

Background  

β-turn is a secondary protein structure type that plays significant role in protein folding, stability, and molecular recognition. To date, several methods for prediction of β-turns from protein sequences were developed, but they are characterized by relatively poor prediction quality. The novelty of the proposed sequence-based β-turn predictor stems from the usage of a window based information extracted from four predicted three-state secondary structures, which together with a selected set of position specific scoring matrix (PSSM) values serve as an input to the support vector machine (SVM) predictor.     

Predicting the protein SUMO modification sites based on Properties Sequential Forward Selection (PSFS)

Protein SUMO modification is an important post-translational modification and the optimization of prediction methods remains a challenge. Here, by using Support Vector Machines algorithm (SVM), a novel computational method was developed for SUMO modification site prediction based on Sequential Forward Selection (SFS) of hundreds of amino acid properties, which are collected by Amino Acid Index database (http://www.genome.jp/aaindex). Our method also compares with the 0/1 system, in which the 20 amino acids are represented by 20-dimensional vectors (A = 00000000000000000001, C = 00000000000000000010 and so on). The overall accuracy of leave-one-out cross-validation for our method reaches 89.18%, which is higher than 0/1 system. It indicated that the SUMO modification prediction process is highly related to the amino acid property and this approach here provide a helpful tool for further investigation of the SUMO modification and identification of sumoylation sites in proteins. The software is available at http://www.biosino.org/sumo.     

FaaPred: A SVM-Based Prediction Method for Fungal Adhesins and Adhesin-Like Proteins

Adhesion constitutes one of the initial stages of infection in microbial diseases and is mediated by adhesins. Hence, identification and comprehensive knowledge of adhesins and adhesin-like proteins is essential to understand adhesin mediated pathogenesis and how to exploit its therapeutic potential. However, the knowledge about fungal adhesins is rudimentary compared to that of bacterial adhesins. In addition to host cell attachment and mating, the fungal adhesins play a significant role in homotypic and xenotypic aggregation, foraging and biofilm formation. Experimental identification of fungal adhesins is labor- as well as time-intensive. In this work, we present a Support Vector Machine (SVM) based method for the prediction of fungal adhesins and adhesin-like proteins. The SVM models were trained with different compositional features, namely, amino acid, dipeptide, multiplet fractions, charge and hydrophobic compositions, as well as PSI-BLAST derived PSSM matrices. The best classifiers are based on compositional properties as well as PSSM and yield an overall accuracy of 86%. The prediction method based on best classifiers is freely accessible as a world wide web based server at http://bioinfo.icgeb.res.in/faap. This work will aid rapid and rational identification of fungal adhesins, expedite the pace of experimental characterization of novel fungal adhesins and enhance our knowledge about role of adhesins in fungal infections.     

Predicting protein subnuclear localization using GO-amino-acid composition features

The nucleus guides life processes of cells. Many of the nuclear proteins participating in the life processes tend to concentrate on subnuclear compartments. The subnuclear localization of nuclear proteins is hence important for deeply understanding the construction and functions of the nucleus. Recently, Gene Ontology (GO) annotation has been used for prediction of subnuclear localization. However, the effective use of GO terms in solving sequence-based prediction problems remains challenging, especially when query protein sequences have no accession number or annotated GO term. This study obtains homologies of query proteins with known accession numbers using BLAST to retrieve GO terms for sequence-based subnuclear localization prediction. A prediction method PGAC, which involves mining informative GO terms associated with amino acid composition features, is proposed to design a support vector machine-based classifier. PGAC yields 55 informative GO terms with training and test accuracies of 85.7% and 76.3%, respectively, using a data set SNL_35 (561 proteins in 9 localizations) with 35% sequence identity. Upon comparison with Nuc-PLoc, which combines amphiphilic pseudo amino acid composition of a protein with its position-specific scoring matrix, PGAC using the data set SNL_80 yields a leave-one-out cross-validation accuracy of 81.1%, which is better than that of Nuc-PLoc, 67.4%. Experimental results show that the set of informative GO terms are effective features for protein subnuclear localization. The prediction server based on PGAC has been implemented at http://iclab.life.nctu.edu.tw/prolocgac.     

Association of PARP-1, NF-κB,NF-κBIA and IL-6, IL-1β and TNF-α with Graves Disease and Graves Ophthalmopathy

Background

Graves Disease (GD) is an autoimmune disorder affected by an interaction of multiple genes such as Nuclear Factor-κB (NF-κB), Nuclear Factor-κB Inhibitor (NF-κBIA), Poly (ADP-ribose) polymerase-1 (PARP-1) and cytokines like Interleukin-1β (IL-1β), Interleukin-6 (IL-6) and Tumor Necrosis Factor-α (TNF-α) and mostly accompanied by an ocular disorder, Graves Ophthalmopathy (GO). We hypothesize that there is a relationship between GD, GO, polymorphisms of inflammatory related genes and their association with cytokines, which may play important roles in autoimmune and inflammatory processes.

Subjects and methods

To confirm our hypothesis, we studied the polymorphisms and cytokine levels of 120 patients with GD and GO using PCR-RFLP and ELISA methods, respectively.

Results

We found that patients with GG genotype and carriers of G allele of PARP-1 G1672A polymorphism are at risk in the group having GD (p = 0.0007) while having GA genotype may be protective against the disease. PARP-1 C410T polymorphism was found to be associated with GO by increasing the risk by 1.7 times (p = 0.004). Another risk factor for development of GO was the polymorphism of del/ins of NFkB1 gene (p = 0.032) that increases the risk by 39%. Levels of cytokines were also elevated in patients with GD, but no association was found between levels of cytokines and the development of GO as there was no change in levels of cytokines.

Conclusions

We suggest that, PARP-1 and NFkB1 gene polymorphisms may be risk factors for developing Graves Disease and Ophthalmopathy.     

Catalytic and redox properties of glycine oxidase from Bacillus subtilis

Glycine oxidase (GO) from Bacillus subtilis is a homotetrameric flavoprotein oxidase that catalyzes the oxidation of the amine functional group of sarcosine or glycine (and some d-amino acids) to yield the corresponding keto acids, ammonia/amine and H₂O₂. It shows optima at pH 7–8 for stability and pH 9–10 for activity, depending on the substrate. The tetrameric oligomeric state of the holoenzyme is not affected by pH in the 6.5–10 range. Free GO forms the anionic red semiquinone upon photoreduction. This species is thermodynamically stable, as indicated by the large separation of the two single-electron reduction potentials (ΔE ≥ 290 mV). The first potential is pH independent, while the second is dependent. The midpoint reduction potential exhibits a −23.4 mV/pH unit slope, which is consistent with an overall two-electrons/one-proton transfer in the reduction to yield anionic reduced flavin. In the presence of glycolate (a substrate analogue) and at pH 7.5 the potential for the semiquinone-reduced enzyme couple is shifted positively by ∼160 mV: this favors a two-electron transfer compared to the free enzyme. Binding of glycolate and sulfite is also affected by pH, showing dependencies that reflect the ionization of an active site residue with a pK_a ≈ 8.0. These results highlight substantial differences between GO and related flavoenzymes. This knowledge will facilitate biotechnological use of GO, e.g. as an innovative tool for the in vivo detection of the neurotransmitter glycine.     

Prediction of midbody, centrosome and kinetochore proteins based on gene ontology information

In the process of cell division, a great deal of proteins is assembled into three distinct organelles, namely midbody, centrosome and kinetochore. Knowing the localization of microkit (midbody, centrosome and kinetochore) proteins will facilitate drug target discovery and provide novel insights into understanding their functions. In this study, a support vector machine (SVM) model, MicekiPred, was presented to predict the localization of microkit proteins based on gene ontology (GO) information. A total accuracy of 77.51% was achieved using the jackknife cross-validation. This result shows that the model will be an effective complementary tool for future experimental study. The prediction model and dataset used in this article can be freely downloaded from http://cobi.uestc.edu.cn/people/hlin/tools/MicekiPred/.     

Design of accurate predictors for DNA-binding sites in proteins using hybrid SVM-PSSM method

In this paper, we investigate the design of accurate predictors for DNA-binding sites in proteins from amino acid sequences. As a result, we propose a hybrid method using support vector machine (SVM) in conjunction with evolutionary information of amino acid sequences in terms of their position-specific scoring matrices (PSSMs) for prediction of DNA-binding sites. Considering the numbers of binding and non-binding residues in proteins are significantly unequal, two additional weights as well as SVM parameters are analyzed and adopted to maximize net prediction (NP, an average of sensitivity and specificity) accuracy. To evaluate the generalization ability of the proposed method SVM-PSSM, a DNA-binding dataset PDC-59 consisting of 59 protein chains with low sequence identity on each other is additionally established. The SVM-based method using the same six-fold cross-validation procedure and PSSM features has NP=80.15% for the training dataset PDNA-62 and NP=69.54% for the test dataset PDC-59, which are much better than the existing neural network-based method by increasing the NP values for training and test accuracies up to 13.45% and 16.53%, respectively. Simulation results reveal that SVM-PSSM performs well in predicting DNA-binding sites of novel proteins from amino acid sequences.