HybridGO-Loc: Mining Hybrid Features on Gene Ontology for Predicting Subcellular Localization of Multi-Location Proteins

Abstract

Protein subcellular localization prediction, as an essential step to elucidate the functions in vivo of proteins and identify drugs targets, has been extensively studied in previous decades. Instead of only determining subcellular localization of single-label proteins, recent studies have focused on predicting both single- and multi-location proteins. Computational methods based on Gene Ontology (GO) have been demonstrated to be superior to methods based on other features. However, existing GO-based methods focus on the occurrences of GO terms and disregard their relationships. This paper proposes a multi-label subcellular-localization predictor, namely HybridGO-Loc, that leverages not only the GO term occurrences but also the inter-term relationships. This is achieved by hybridizing the GO frequencies of occurrences and the semantic similarity between GO terms. Given a protein, a set of GO terms are retrieved by searching against the gene ontology database, using the accession numbers of homologous proteins obtained via BLAST search as the keys. The frequency of GO occurrences and semantic similarity (SS) between GO terms are used to formulate frequency vectors and semantic similarity vectors, respectively, which are subsequently hybridized to construct fusion vectors. An adaptive-decision based multi-label support vector machine (SVM) classifier is proposed to classify the fusion vectors. Experimental results based on recent benchmark datasets and a new dataset containing novel proteins show that the proposed hybrid-feature predictor significantly outperforms predictors based on individual GO features as well as other state-of-the-art predictors. For readers' convenience, the HybridGO-Loc server, which is for predicting virus or plant proteins, is available online at http://bioinfo.eie.polyu.edu.hk/HybridGoServer/.

Transductive Learning for Multi-Label Protein Subchloroplast Localization Prediction

“…Popular multi-label measures include Overall Actual Accuracy (OAA) [36], [60], Accuracy, Precision, Recall, and F1-score (F1) [61], [62]. Specifically, denote L(Q i ) and M(Q i ) as the true label set and the predicted label set for the i-th protein Q i (i = 1, .…”

mLASSO-Hum: A LASSO-based interpretable human-protein subcellular localization predictor

“…For Step 1, given a query protein, its amino acid sequence is presented to BLAST to find its homologs against the ProSeq database, whose ACs are then used as keys to search against the ProSeq-GO database. Compared to our previous works [61,34,62], one of the differences is that instead of using Swiss-Prot and GOA databases, mLASSO-Hum uses ProSeq and ProSeq-GO to retrieve GO terms, which can guarantee that GO terms can always be found for a query protein given its amino acid sequence.…”

“…Recently, several state-of-the-art multi-label predictors have been proposed, such as Hum-mPLoc 2.0 [51], iLoc-Hum [27], mGOASVM [61], HybridGO-Loc [62], R3P-Loc [63], mPLRLoc [64] and other predictors [65,66,67]. They all use the GO information as the features and apply different multi-label classifiers to tackle the multi-label classification problem.…”

Prediction of protein subcellular localization using support vector machine with the choice of proper kernel

“…In recent times, a support vector machine (SVM) (Höglund et al, 2006;Li et al, 2012;Wan et al, 2012;Wan et al, 2014;Hasan et al, 2015,) has been extensively applied to provide potential solutions for the prediction of protein subcellular localization. However, the selection of an appropriate kernel and its parameters for a given classification problem influences the performance of the SVM.…”