Shanghai, China
Shanghai, China

Time filter

Source Type

Xiaoqi Z.,Shanghai Normal University | Chun L.I.,Bohai University | Jun W.,Shanghai Normal University | Jun W.,Shanghai Universities
Journal of Computational Chemistry | Year: 2010

An information-theoretical approach, which combines a sequence decomposition technique and a fuzzy clustering algorithm, is proposed for prediction of protein structural class. This approach could bypass the process of selecting and comparing sequence features as done previously. First, distances between each pair of protein sequences are estimated using a conditional decomposition technique in information theory. Then, the fuzzy k-nearest neighbor algorithm is used to identify the structural class of a protein given as set of sample sequences. To verify the strength of our method, we choose three widely used datasete constructed by Chou and Zhou. It is shown by the Jackknife test that our approach represents an improvement in the prediction of accuracy over existing methods. © 2009 Wiley Periodicals, Inc.


Wu S.-F.,CAS Shanghai Institutes for Biological Sciences | Huang Y.,Shanghai Universities | Hou J.-K.,CAS Shanghai Institutes for Biological Sciences | Yuan T.-T.,CAS Shanghai Institutes for Biological Sciences | And 4 more authors.
Leukemia | Year: 2010

Onzin is a small, novel, and highly conserved protein with unique structure and tissue-restricted expression. The regulation of its expression and biological roles remain greatly elusive. Here, we provide the first demonstration that onzin expression is significantly downregulated during differentiation induction of acute myeloid leukemic (AML) cell lines and primary cells by all-trans retinoic acid (ATRA) and especially by phorbol 12-myristate 13-acetate (PMA). Applying chemical inhibitions, RNA interferences, and transfected expressions of dominant negative mutants or constitutive catalytic forms of the related kinases, we show that protein kinase C-(PKC)-extracellular signal-regulated protein kinase 2 (ERK2) signaling axis is required for PMA-induced downregulation of onzin expression. The ectopic expression of onzin partially inhibits PMA-induced monocytic differentiation of AML cells, whereas suppression of onzin by specific short hairpin RNAs enhances PMA-induced differentiation to a degree. Furthermore, onzin partially inhibits the transcriptional activity of hematopoiesis-related important transcription factor PU.1 via their interaction. Taken together, our results show that PMA downregulates onzin expression through PKC-ERK2 signaling pathway, which favors monocytic differentiation of leukemic cells. © 2010 Macmillan Publishers Limited All rights reserved.


Dou Y.,Dalian University of Technology | Zheng X.,Shanghai Normal University | Wang J.,Shanghai Normal University | Wang J.,Shanghai Universities
Journal of Theoretical Biology | Year: 2010

Amino acid background distribution is an important factor for entropy-based methods which extract sequence conservation information from protein multiple sequence alignments (MSAs). However, MSAs are usually not large enough to allow a reliable observed background distribution. In this paper, we propose two new estimations of background distribution. One is an integration of the observed background distribution and the position-specific residue distribution, and the other is a normalized square root of observed background frequency. To validate these new background distributions, they are applied to the relative entropy model to find catalytic sites and ligand binding sites from protein MSAs. Experimental results show that they are superior to the observed background distribution in predicting functionally important residues. © 2009.


Peng X.,Shanghai Normal University | Peng X.,Shanghai Universities
Neural Networks | Year: 2010

The learning speed of classical Support Vector Regression (SVR) is low, since it is constructed based on the minimization of a convex quadratic function subject to the pair groups of linear inequality constraints for all training samples. In this paper we propose Twin Support Vector Regression (TSVR), a novel regressor that determines a pair of ε{lunate}-insensitive up- and down-bound functions by solving two related SVM-type problems, each of which is smaller than that in a classical SVR. The TSVR formulation is in the spirit of Twin Support Vector Machine (TSVM) via two nonparallel planes. The experimental results on several artificial and benchmark datasets indicate that the proposed TSVR is not only fast, but also shows good generalization performance. © 2009 Elsevier Ltd. All rights reserved.


Peng X.,Shanghai Normal University | Peng X.,Shanghai Universities
Pattern Recognition | Year: 2011

A novel twin parametric-margin support vector machine (TPMSVM) for classification is proposed in this paper. This TPMSVM, in the spirit of the twin support vector machine (TWSVM), determines indirectly the separating hyperplane through a pair of nonparallel parametric-margin hyperplanes solved by two smaller sized support vector machine (SVM)-type problems. Similar to the parametric-margin νsupport vector machine (par-νSVM), this TPMSVM is suitable for many cases, especially when the data has heteroscedastic error structure, that is, the noise strongly depends on the input value. But there is an advantage in the learning speed compared with the par-νSVM. The experimental results on several artificial and benchmark datasets indicate that the TPMSVM not only obtains fast learning speed, but also shows good generalization. © 2011 Elsevier Ltd. All rights reserved.


Peng X.,Shanghai Normal University | Peng X.,Shanghai Universities | Xu D.,Shanghai Normal University | Xu D.,Shanghai Universities
Information Sciences | Year: 2012

Twin support vector machines (TSVMs) achieve fast training speed and good performance for data classification. However, TSVMs do not take full advantage of the statistical information in data, such as the covariance of each class of data. This paper proposes a new twin Mahalanobis distance-based support vector machine (TMSVM) classifier, in which two Mahalanobis distance-based kernels are constructed according to the covariance matrices of two classes of data for optimizing the nonparallel hyperplanes. TMSVMs have a special case of TSVMs when the covariance matrices in a reproducing kernel Hilbert space are degenerated to the identity ones. TMSVMs are suitable for many real problems, especially for the case that the covariance matrices of two classes of data are obviously different. The experimental results on several artificial and benchmark datasets indicate that TMSVMs not only possess fast learning speed, but also obtain better generalization than TSVMs and other methods. © 2012 Elsevier Inc. All rights reserved.


Li L.-Q.,Chongqing Medical University | Zhang Y.,Chongqing Medical University | Zou L.-Y.,Chongqing Medical University | Zhou Y.,Chongqing Medical University | And 2 more authors.
Protein and Peptide Letters | Year: 2012

Many proteins bear multi-locational characteristics, and this phenomenon is closely related to biological function. However, most of the existing methods can only deal with single-location proteins. Therefore, an automatic and reliable ensemble classifier for protein subcellular multi-localization is needed. We propose a new ensemble classifier combining the KNN (K-nearest neighbour) and SVM (support vector machine) algorithms to predict the subcellular localization of eukaryotic, Gram-negative bacterial and viral proteins based on the general form of Chou's pseudo amino acid composition, i.e., GO (gene ontology) annotations, dipeptide composition and AmPseAAC (Amphiphilic pseudo amino acid composition). This ensemble classifier was developed by fusing many basic individual classifiers through a voting system. The overall prediction accuracies obtained by the KNN-SVM ensemble classifier are 95.22, 93.47 and 80.72% for the eukaryotic, Gram-negative bacterial and viral proteins, respectively. Our prediction accuracies are significantly higher than those by previous methods and reveal that our strategy better predicts subcellular locations of multi-location proteins. © 2012 Bentham Science Publishers.


Peng X.,Shanghai Normal University | Peng X.,Shanghai Universities
Information Sciences | Year: 2010

In this paper, a ν-twin support vector machine (ν-TSVM) is presented, improving upon the recently proposed twin support vector machine (TSVM). This ν-TSVM introduces a pair of parameters (ν) to control the bounds of the fractions of the support vectors and the error margins. The theoretical analysis shows that this ν-TSVM can be interpreted as a pair of minimum generalized Mahalanobis-norm problems on two reduced convex hulls (RCHs). Based on the well-known Gilbert's algorithm, a geometric algorithm for TSVM (GA-TSVM) and its probabilistic speed-up version, named PGA-TSVM, are presented. Computational results on several synthetic as well as benchmark datasets demonstrate the significant advantages of the proposed algorithms in terms of both computation complexity and classification accuracy. © 2010 Elsevier Inc. All rights reserved.


Liu T.,Shandong Agricultural University | Geng X.,Dalian University of Technology | Zheng X.,Shanghai Normal University | Zheng X.,Shanghai Universities | And 3 more authors.
Amino Acids | Year: 2012

Computational prediction of protein structural class based solely on sequence data remains a challenging problem in protein science. Existing methods differ in the protein sequence representation models and prediction engines adopted. In this study, a powerful feature extraction method, which combines position-specific score matrix (PSSM) with auto covariance (AC) transformation, is introduced. Thus, a sample protein is represented by a series of discrete components, which could partially incorporate the long-range sequence order information and evolutionary information reflected from the PSI-BLAST profile. To verify the performance of our method, jackknife cross-validation tests are performed on four widely used benchmark datasets. Comparison of our results with existing methods shows that our method provides the state-of-the-art performance for structural class prediction. A Web server that implements the proposed method is freely available at http://202.194.133.5/xinxi/AAC-PSSM-AC/ index.htm . © 2011 Springer-Verlag.


Guo B.-Y.,Shanghai Normal University | Guo B.-Y.,Shanghai Universities | Wang T.-J.,Henan University of Science and Technology
Journal of Scientific Computing | Year: 2010

In this paper, we investigate composite Laguerre-Legendre spectral method for fourth-order exterior problems. Some results on composite Laguerre-Legendre approximation are established, which is a set of piecewise mixed approximations coupled with domain decomposition. These results play an important role in spectral method for fourth-order exterior problems with rectangle obstacle. As examples of applications, composite spectral schemes are provided for two model problems, with convergence analysis. Efficient algorithms are implemented. Numerical results demonstrate their high accuracy, and confirm theoretical analysis well. © Springer Science+Business Media, LLC 2010.

Loading Shanghai Universities collaborators
Loading Shanghai Universities collaborators