Use of Chou’s 5-steps rule to predict the subcellular localization of gram-negative and gram-positive bacterial proteins by multi-label learning based on gene ontology annotation and profile alignment

Abstract

<jats:title>Abstract</jats:title><jats:p>To date, many proteins generated by large-scale genome sequencing projects are still uncharacterized and subject to intensive investigations by both experimental and computational means. Knowledge of protein subcellular localization (SCL) is of key importance for protein function elucidation. However, it remains a challenging task, especially for multiple sites proteins known to shuttle between cell compartments to perform their proper biological functions and proteins which do not have significant homology to proteins of known subcellular locations. Due to their low-cost and reasonable accuracy, machine learning-based methods have gained much attention in this context with the availability of a plethora of biological databases and annotated proteins for analysis and benchmarking. Various predictive models have been proposed to tackle the SCL problem, using different protein sequence features pertaining to the subcellular localization, however, the overwhelming majority of them focuses on single localization and cover very limited cellular locations. The prediction was basically established on sorting signals, amino acids compositions, and homology. To improve the prediction quality, focus is actually on knowledge information extracted from annotation databases, such as protein–protein interactions and Gene Ontology (GO) functional domains annotation which has been recently a widely adopted and essential information for learning systems. To deal with such problem, in the present study, we considered SCL prediction task as a multi-label learning problem and tried to label both single site and multiple sites unannotated bacterial protein sequences by mining proteins homology relationships using both GO terms of protein homologs and PSI-BLAST profiles. The experiments using 5-fold cross-validation tests on the benchmark datasets showed a significant improvement on the results obtained by the proposed consensus multi-label prediction model which discriminates six compartments for Gram-negative and five compartments for Gram-positive bacterial proteins.</jats:p>

Identification and characterization of inulinases by bioinformatics analysis of bacterial glycoside hydrolases family 32 (GH32)

“…One of the essential elements of cell survival is proteins, whose presence in specific cell sites determines their function and biological nature. After synthesizing proteins in the cytosol, they are directed to particular parts of the cell, including organelles, based on their biological function [ 25 ]. Prediction of subcellular protein localization is based on sorting signals, amino acids composition, and homology [ 25 ].…”

“…After synthesizing proteins in the cytosol, they are directed to particular parts of the cell, including organelles, based on their biological function [ 25 ]. Prediction of subcellular protein localization is based on sorting signals, amino acids composition, and homology [ 25 ]. Protein sorting is a complex biological mechanism often driven by specific signal sequences in nascent proteins.…”

Multilocation proteins in organelle communication: Based on protein–protein interactions

“…At present, research pertaining to subcellular localization is divided mainly into experimental evidence and software predictions. The experimental methods include immunofluorescence (Stadler et al, 2013 ) and expression of green fluorescent protein fusion proteins (Cui et al, 2016 ), and software performed predictions are based mainly on bioinformatics (Bouziane & Chouarfia, 2020 ; Chou, 2019 ; Chou et al, 2019a ). The application of these experimental methods can provide more accurate information on protein subcellular localization, and the present research is based mainly on this type of method.…”

A Multilabel Learning-Based Automatic Annotation Method for Semantic Roles in English Text

“…The literature [19] analyzes the label dependency and partial multi-label dependency problems based on extracting sample relations from input features based on positive and negative labels respectively and obtaining label information from the output space, which provides a broad idea for the introduction of multi-label association relations. There are also many approaches to introduce sample relations and label correlations in multi-label learning.…”