DMLDA-LocLIFT: Identification of multi-label protein subcellular localization using DMLDA dimensionality reduction and LIFT classifier

Background: Multi-label proteins occur in two or more subcellular locations, which play a vital part in cell development and metabolism. Prediction and analysis of multi-label subcellular localization (SCL) can present new angle with drug target identification and new drug design. However, the prediction of multi-label protein SCL using biological experiments is expensive and labor-intensive. Therefore, predicting large-scale SCL with machine learning methods has turned into a hot study topic in bioinformatics. Methods: In this study, a novel multi-label learning means for protein SCL prediction, called DMLDA-LocLIFT, is proposed. Firstly, the dipeptide composition, encoding based on grouped weight, pseudo amino acid composition, gene ontology and pseudo position specific scoring matrix are employed to encode subcellular protein sequences. Then, direct multi-label linear discriminant analysis (DMLDA) is used to reduce the dimension of the fused feature vector. Lastly, the optimal feature vectors are input into the multi-label learning with Label-specIfic FeaTures (LIFT) classifier to predict the location of multi-label proteins. Results: The jackknife test showed that the overall actual accuracy on Gram-negative bacteria, Gram-positive bacteria, and plant datasets are 98.60%, 99.60%, and 97.90% respectively, which are obviously better than other state-of-the-art prediction methods. Conclusion: The proposed model can effectively predict SCL of multi-label proteins and provide references for experimental identification of SCL. The source codes and data are publicly available at https://github.com/QUST-AIBBDRC/DMLDA-LocLIFT/.