HPSLPred: An Ensemble Multi‐Label Classifier for Human Protein Subcellular Location Prediction with Imbalanced Source

Abstract

Protein subcellular localization prediction is an important and challenging problem. The traditional biology experiments are expensive and time-consuming, so more and more research interests tend to a series of machine learning approaches for predicting protein subcellular location. There are two main difficult problems among the existing state-of-the-art methods. First, most of the existing techniques are designed to deal with the multi-class but not the multi-label classification, which ignores the connection between the multiple labels. In reality, multiple location proteins implicate that there are vital and unique biological significances worthy of special focus, which cannot be ignored. Second, the techniques for handling imbalanced data in multi-label classification problem is significant but less. For solving the two issues, we have developed an ensemble multi-label classifier called HPSLPred which can be applied for the multi-label classification with imbalanced protein source. For the conveniences of users, a user-friendly webserver for HPSLPred was established at http://server.malab.cn/HPSLPred.

<i>In Silico</i> Structural and Functional Annotation of Nine Essential Hypothetical Proteins from <i>Streptococcus pneumoniae</i>

“…Determination of protein subcellular location is significant, especially for target identification [35]. Furthermore, location prediction can give an idea on the role of a query protein and whether it is categorized as a cytoplasmic, membrane, or secretory protein.…”

SecProMTB: Support Vector Machine‐Based Classifier for Secretory Proteins Using Imbalanced Data Sets Applied to Mycobacterium tuberculosis

“…Synthetic minority oversampling technique (SMOTE) [23] is an oversampling approach in which new synthetic samples are generated from the minority class on the basis of interpolation and succeeded in several bioinformatics problems. [24] The k nearest neighbors were identified for each sample under consideration in minority class by Euclidean distance. Synthetic samples were introduced along the line segments from the consideration sample to the selected nearest neighbors.…”

ProLanGO: Protein Function Prediction Using Neural Machine Translation Based on a Recurrent Neural Network

“…Protein function prediction is usually treated as a multi-label classification problem. Researchers have tried different computation methods in the last few decades for this problem [ 6 , 7 , 8 , 9 , 10 , 11 , 12 ]. In general, the following methods are used for protein function prediction.…”