Frequent-subsequence-based prediction of outer membrane proteins

Abstract

A number of medically important disease-causing bacteria (collectively called Gram-negative bacteria) are noted for the extra "outer" membrane that surrounds their cell. Proteins resident in this membrane (outer membrane proteins, or OMPs) are of primary research interest for antibiotic and vaccine drug design as they are on the surface of the bacteria and so are the most accessible targets to develop new drugs against. With the development of genome sequencing technology and bioinformatics, biologists can now deduce all the proteins that are likely produced in a given bacteria and have attempted to classify where proteins are located in a bacterial cell. However such protein localization programs are currently least accurate when predicting OMPs, and so there is a current need for the development of a better OMP classifier. Data mining research suggests that the use of frequent patterns has good performance in aiding the development of accurate and efficient classification algorithms. In this paper, we present two methods to identify OMPs based on frequent subsequences and test them on all Gramnegative bacterial proteins whose localizations have been determined by biological experiments. One classifier follows an association rule approach, while the other is based on support vector machines (SVMs). We compare the proposed methods with the state-of-the-art methods in the biological domain. The results demonstrate that our methods are better both in terms of accurately identifying OMPs and providing biological insights that increase our understanding of the structures and functions of these important proteins.

Sequence Classification Based on Delta-Free Sequential Patterns

“…The classification of sequential data has been extensively studied [14]- [16], [41]. Most previous work has combined sequence feature selection and common classification methods.…”

“…Most previous work has combined sequence feature selection and common classification methods. For instance, the authors of [15], [16] study the prediction of outer membrane proteins from protein sequences by combining several feature selection methods and support vector machines (SVMs) [42]. Other methods are based on Hidden Markov Models (HMM) which are stochastic generalizations of finitestate automata have been proposed for sequence classification [43], [44].…”

On top-k closed sequential patterns mining

“…Sequential pattern mining is a necessary data mining project, which has shown extensive applications, including sequencebased classification [10] and clustering [1], mining API specification and API usage from open source repositories [15], analyzing web log data [3], and so on. A lot of effective sequence mining algorithms have been proposed for all kinds of problem formulations, including the general sequential pattern mining [2], [4], [9] and closed sequential pattern mining [14], [17].…”

Subcellular Localization Prediction through Boosting Association Rules

“…She et al [22] constructed a classifier with associative classification rules to target outer membrane proteins of Gram-negative bacteria. Jin et al [23] used AdaBoost to predict subcellular locations based on amino acid compositions.…”