Imbalanced Protein Data Classification Using Ensemble FTM-SVM

Abstract

Classification of protein sequences into functional and structural families based on machine learning methods is a hot research topic in machine learning and Bioinformatics. In fact, the underlying protein classification problem is a huge multiclass problem. Generally, the multiclass problem can be reduced to a set of binary classification problems. The protein in one class are seen as positive examples while those outside the class are seen as negative examples. However, the class imbalance problem will arise in this case because the number of protein in one class is usually much smaller than that of the protein outside the class. To handle the challenge, we propose a novel framework to classify the protein. We firstly use free scores (FS) to perform feature extraction for protein; then, the inverse random under sampling (IRUS) is used to create a large number of distinct training sets; next, we use a new ensemble approach to combine these distinct training sets with a new fuzzy total margin support vector machine (FTM-SVM) that we have constructed. we call the novel ensemble classifier as ensemble fuzzy total margin support vector machine (EnFTM-SVM). We then give a full description of our method, including the details of its derivation. Finally, experimental results on fourteen benchmark protein data sets indicate that the proposed method outperforms many state-of-the-art protein classifying methods.

SVM-Prot 2016: A Web-Server for Machine Learning Prediction of Protein Functional Families from Sequence Irrespective of Similarity

“…This was partly due to the imbalanced training sets with the numbers of non-members greatly surpassing those of the members. Imbalanced training sets were known to adversely affect the machine learning prediction performance, particularly the minority class [ 48 , 49 ]. Moreover, not all functional families were sufficiently covered by the known proteins, particularly those with < 100 known protein members, the inadequate coverage of the respective training sets likely affect SE s to varying degrees.…”

“…One useful strategy for overcoming the imbalanced datasets problem is to re-construct the training sets into more balanced ones by either over sampling the minority class [ 48 ] or under sampling the majority one [ 49 ], which might compromise the training datasets by introducing noises to the minority class or reducing the diversity of the majority one. In SVM-Prot, the training sets of the non-members were constructed from the minimal set of representative proteins from the Pfam domain families.…”

Assessment of Library Users’ Feedback Using Modified Multilayer Perceptron Neural Networks

“…K-means clustering algorithm is applied on books circulation records to analyze readers' characteristics [4]. Artificial neural network techniques are applied for library management models [5]. A neural network based assessment method is developed and applied to assess college library website [6].…”

“…Classification of imbalanced protein data by using ensemble classifier technique EnFTM-SVM is proposed in [5]. This is an ensemble of fuzzy total margin support vector machine (FTN-SVM).…”

Classification of Regions with Endemic Diseases Based on Trace Element Concentrations in Groundwater

“…Here we have applied SVM as a tool to provide classification of endemic disease potential areas. Recently support vector machines, developed by Vapnik [20], have been used for a range of problems including pattern recognition [21,22], bioinformatics [23,24], and text categorization [25,26]. The use of classification in this facet and in medical diagnosis has been gradually increasing [27][28][29][30].…”