Dual-Signal Feature Spaces Map Protein Subcellular Locations Based on Immunohistochemistry Image and Protein Sequence

Abstract

Protein is one of the primary biochemical macromolecular regulators in the compartmental cellular structure, and the subcellular locations of proteins can therefore provide information on the function of subcellular structures and physiological environments. Recently, data-driven systems have been developed to predict the subcellular location of proteins based on protein sequence, immunohistochemistry (IHC) images, or immunofluorescence (IF) images. However, the research on the fusion of multiple protein signals has received little attention. In this study, we developed a dual-signal computational protocol by incorporating IHC images into protein sequences to learn protein subcellular localization. Three major steps can be summarized as follows in this protocol: first, a benchmark database that includes 281 proteins sorted out from 4722 proteins of the Human Protein Atlas (HPA) and Swiss-Prot database, which is involved in the endoplasmic reticulum (ER), Golgi apparatus, cytosol, and nucleoplasm; second, discriminative feature operators were first employed to quantitate protein image-sequence samples that include IHC images and protein sequence; finally, the feature subspace of different protein signals is absorbed to construct multiple sub-classifiers via dimensionality reduction and binary relevance (BR), and multiple confidence derived from multiple sub-classifiers is adopted to decide subcellular location by the centralized voting mechanism at the decision layer. The experimental results indicated that the dual-signal model embedded IHC images and protein sequences outperformed the single-signal models with accuracy, precision, and recall of 75.41%, 80.38%, and 74.38%, respectively. It is enlightening for further research on protein subcellular location prediction under multi-signal fusion of protein.

Keywords: benchmark database; discriminative feature operators; dual signal; protein subcellular location prediction.

Figure 1

The flowchart of dual-signal model. Abbreviation definitions: ER: endoplasmic reticulum; Golgi: Golgi apparatus; Cyto.: cytosol; Nucl.: nucleoplasm.

Figure 2

Experimental results for different shallow features of protein sequence.

Figure 3

Performance of shallow features fusion of protein sequences.

Figure 4

Experimental results of 10 dbs Daubechies filters in protein channel patch images. (a) Line plot of Haralick feature performance fluctuations in different Daubechies filters; (b) experimental results of Haralick and LBP concatenating.

Figure 5

Performance comparison of IHC image in the abstract and concatenate features.

Figure 6

The multi-classifier outputs result and visualization by centralized voting mechanism. (a) Multi-classifier ensemble with five-fold cross-validation; (b) performance fluctuations of different protein subcellular locations in the five-fold cross-validation; (c–g) visualization of confusion matrix in four categories.

Figure 7

The experimental results of different feature space based on Leave-One-Out.