MpsLDA-ProSVM: Predicting multi-label protein subcellular localization by wMLDAe dimensionality reduction and ProSVM classifier

Mull-label proteins play a significant role in life processes such as cell growth, development, and reproduction. Exploring protein subcellular localization (SCL) is a direct way to better understand the function of mull-label proteins in cells. This paper firstly presents a new prediction model named MpsLDA-ProSVM which predicts the SCL of mull-label proteins. Firstly, we utilize four coding algorithms including pseudo position-specific scoring matrix (PsePSSM), gene ontology (GO), conjoint triad (CT) and pseudo amino acid composition (PseAAC) to draw the feature information from protein sequences. Then, for the first time, we use a weighted mull-label linear discriminant analysis framework based on entropy weight form (wMLDAe) to refine and purify features. Finally, we input the optimal feature subset into the mull-label learning with label-specific features (LIFT) and mull-label k-nearest neighbor (ML-KNN) algorithms to obtain a synthetic ranking of relevant labels, and then use Prediction and Relevance Ordering based SVM (ProSVM) classifier to predict the SCLs. Tested by leave-one-out cross-validation (LOOCV), the overall actual accuracy on virus, plant, Gram-positive bacteria and Gram-negative bacteria datasets are 98.06%, 98.97%, 99.81% and 98.49%, which are 0.56%-9.16%, 1.07%30.87%, 0.21%-6.91% and 3.99%-8.59% higher than other advanced methods respectively. By comparison, the model MpsLDA-ProSVM can effectively predict the specific location of mull-label proteins in cells.

Automated summary

The paper introduces a new prediction model, MpsLDA-ProSVM, which accurately predicts the specific subcellular localization of multi-label proteins in cells. By utilizing various coding algorithms and a weighted multi-label linear discriminant analysis framework, the model demonstrates high accuracy in virus, plant, Gram-positive bacteria, and Gram-negative bacteria datasets.