Local Sequence Information-based Support Vector Machine to Classify Voltage-gated Potassium Channels

Abstract

In our previous work, we developed a computational tool, PreK-ClassK-ClassKv, to predict and classify potassium (K+) channels. For K+ channel prediction (PreK) and classification at family level (ClassK), this method performs well. However, it does not perform so well in classifying voltage-gated potassium (Kv) channels (ClassKv). In this paper, a new method based on the local sequence information of Kv channels is introduced to classify Kv channels. Six transmembrane domains of a Kv channel protein are used to define a protein, and the dipeptide composition technique is used to transform an amino acid sequence to a numerical sequence. A Kv channel protein is represented by a vector with 2000 elements, and a support vector machine algorithm is applied to classify Kv channels. This method shows good performance with averages of total accuracy (Acc), sensitivity (SE), specificity (SP), reliability (R) and Matthews correlation coefficient (MCC) of 98.0%, 89.9%, 100%, 0.95 and 0.94 respectively. The results indicate that the local sequence information-based method is better than the global sequence information-based method to classify Kv channels.

Briefing in Application of Machine Learning Methods in Ion Channel Prediction

“…Based on the benchmark dataset S2, Liu et al [ 17 ] predicted the five subfamilies of potassium VGICs by using SVM combined with dipeptide composition ( 2 ). In the jackknife cross-validation, the average Acc of 98.0% was achieved with the average Sn of 89.9%, Sp of 100%, and MCC of 0.94.…”

“…The second nonredundant benchmark dataset S2 [ 17 ] contains 37 Kv1, 16 Kv2, 18 Kv3, 15 Kv4, and 14 Kv7 subfamilies of voltage-gated K+ channels. These data are derived from the VKCDB database.…”

An efficient approach for the prediction of ion channels and their subfamilies

“…The authors of the papers [23,24] have proposed computational intelligence techniques based method to predict the activity of ion channel proteins. In the paper [25] a support vector machine based method has been proposed to predict five types of voltage gated potassium channels and obtained accuracy of 98%. The authors of the paper [26] proposed a support vector machine based method to predict four types of voltage gated ion channels by using amino acid composition and dipeptide composition and obtained overall accuracy of 97.78%.…”

Predicting ion channels and their types by the dipeptide mode of pseudo amino acid composition

“…He et al (2010) and Huang et al (2010) utilized computational approaches to find potential drug targets from ion channels. Liu et al (2006) used support vector machine (SVM) to predict five types of voltage-gated potassium channels and reported a jackknife cross-validated accuracy of 98%. Saha et al (2006) developed a SVM-based method to predict four types of voltage-gated ion channels by using amino acid composition and dipeptide composition.…”