Xijun Liang

Design of a multiple kernel learning algorithm for LS-SVM by convex programming

As a kernel based method, the performance of least squares support vector machine (LS-SVM) depends on the selection of the kernel as well as the regularization parameter (Duan, Keerthi, & Poo, 2003). Cross-validation is efficient in selecting a single kernel and the regularization parameter; however, it suffers from heavy computational cost and is not flexible to deal with multiple kernels. In this paper, we address the issue of multiple kernel learning for LS-SVM by formulating it as semidefinite programming (SDP). Furthermore, we show that the regularization parameter can be optimized in a unified framework with the kernel, which leads to an automatic process for model selection. Extensive experimental validations are performed and analyzed.

Peptide identification based on fuzzy classification and clustering

BackgroundThe sequence database searching has been the dominant method for peptide identification, in which a large number of peptide spectra generated from LC/MS/MS experiments are searched using a search engine against theoretical fragmentation spectra derived from a protein sequences database or a spectral library. Selecting trustworthy peptide spectrum matches (PSMs) remains a challenge.ResultsA novel scoring method named FC-Ranker is developed to assign a nonnegative weight to each target PSM based on the possibility of its being correct. Particularly, the scores of PSMs are updated by using a fuzzy SVM classification model and a fuzzy silhouette index iteratively. Trustworthy PSMs will be assigned high scores when the algorithm stops.ConclusionsOur experimental studies show that FC-Ranker outperforms other post-database search algorithms over a variety of datasets, and it can be extended to solve a general classification problem with uncertain labels.

Inference of gene regulatory subnetworks from time course gene expression data

BackgroundIdentifying gene regulatory network (GRN) from time course gene expression data has attracted more and more attentions. Due to the computational complexity, most approaches for GRN reconstruction are limited on a small number of genes and low connectivity of the underlying networks. These approaches can only identify a single network for a given set of genes. However, for a large-scale gene network, there might exist multiple potential sub-networks, in which genes are only functionally related to others in the sub-networks.ResultsWe propose the network and community identification (NCI) method for identifying multiple subnetworks from gene expression data by incorporating community structure information into GRN inference. The proposed algorithm iteratively solves two optimization problems, and can promisingly be applied to large-scale GRNs. Furthermore, we present the efficient Block PCA method for searching communities in GRNs.ConclusionsThe NCI method is effective in identifying multiple subnetworks in a large-scale GRN. With the splitting algorithm, the Block PCA method shows a promosing attempt for exploring communities in a large-scale GRN.

An adaptive classification model for peptide identification

BackgroundPeptide sequence assignment is the central task in protein identification with MS/MS-based strategies. Although a number of post-database search algorithms for filtering target peptide spectrum matches (PSMs) have been developed, the discrepancy among the output PSMs is usually significant, remaining a few disputable PSMs. Current studies show that a number of target PSMs which are close to decoy PSMs can hardly be separated from those decoys by only using the discrimination function.ResultsIn this paper, we assign each target PSM a weight showing its possibility of being correct. We employ a SVM-based learning model to search the optimal weight for each target PSM and develop a new score system, CRanker, to rank all target PSMs. Due to the large PSM datasets generated in routine database searches, we use the Cholesky factorization technique for storing a kernel matrix to reduce the memory requirement.ConclusionsCompared with PeptideProphet and Percolator, CRanker has identified more PSMs under similar false discover rates over different datasets. CRanker has shown consistent performance on different test sets, validated the reasonability the proposed model.

Measure prediction capability of data for collaborative filtering

Collaborative filtering (CF) approaches have been widely been employed in e-commerce to help users find items they like. Whereas most of existing work focuses on improving algorithmic performance, it is important to know whether the recommendation for users and items can be trustworthy. In this paper, we propose a metric, “relatedness,” to measure the potential that a user’s preference on an item can be accurately predicted. The relatedness of a user–item pair is determined by a community which consists of users and items most related to the pair. The relatedness is computed by solving a constrained

𝓁 2 Multiple Kernel Fuzzy SVM-Based Data Fusion for Improving Peptide Identification

\ell _{1}^{}

An efficient ACS algorithm for classification-based peptide identification

ℓ1-regularized least square problem with a generalized homotopy algorithm, and we design the homotopy-based community search algorithm to identify the community by alternately selecting the most related users and items. As an application of the relatedness metric, we develop the data-oriented combination (DOC) method for recommender systems by integrating a group of benchmark CF methods based on the relatedness of user–item pairs. In experimental studies, we examine the effectiveness of the relatedness metric and validate the performance of the DOC method by comparing it with benchmark methods.

Modeling Gene Regulatory Subnetworks from Time Course Gene Expression Data

Although a number of sequence database search tools and post-database search algorithms for filtering target PSMs have been developed, the discrepancy among the output PSMs is usually significant, remaining a few disputable PSMs. We employ a SVM-based learning model to search the optimal weight for each target PSM and develop a new score system, C-Ranker, to rank all target PSMs. Compared with PeptideProphet and Percolator, CRanker has identified more PSMs under similar false discover rates over different datasets.