Feature Selection via Swarm Intelligence for Determining Protein Essentiality.

Ming Fang,Fang-Xiang Wu,Xiujuan Lei,Yuhui Shi,Shi Cheng

doi:10.3390/molecules23071569

Abstract

Protein essentiality is fundamental to comprehend the function and evolution of genes. The prediction of protein essentiality is pivotal in identifying disease genes and potential drug targets. Since the experimental methods need many investments in time and funds, it is of great value to predict protein essentiality with high accuracy using computational methods. In this study, we present a novel feature selection named Elite Search mechanism-based Flower Pollination Algorithm (ESFPA) to determine protein essentiality. Unlike other protein essentiality prediction methods, ESFPA uses an improved swarm intelligence–based algorithm for feature selection and selects optimal features for protein essentiality prediction. The first step is to collect numerous features with the highly predictive characteristics of essentiality. The second step is to develop a feature selection strategy based on a swarm intelligence algorithm to obtain the optimal feature subset. Furthermore, an elite search mechanism is adopted to further improve the quality of feature subset. Subsequently a hybrid classifier is applied to evaluate the essentiality for each protein. Finally, the experimental results show that our method is competitive to some well-known feature selection methods. The proposed method aims to provide a new perspective for protein essentiality determination.

Highlights

Essential proteins are required for the viability of an organism
Recall, F-Measure, and AUC scores, all four values of Elite Search mechanism-based Flower Pollination Algorithm (ESFPA) are higher than those of other feature selection methods, which indicates that its performancethose outperforms those by some methods, which indicates that its performance outperforms obtained by obtained some state-of-the-art state-of-the-art feature presented selection methods presented here
The values of Precision, Recall, and F-Measure for each feature subset are listed in Table 3, and it shows that the performance of the and F-Measure for each feature subset are listed in Table 3, and it shows that the performance of the feature subset selected from our ESFPA algorithm is superior to those that consider only individual feature subset selected from our ESFPA algorithm is superior to those that consider only individual features

Summary

Introduction

Essential proteins are required for the viability of an organism. The ability to predict essential proteins has the potential to influence the understanding of minimal requirements for a cell and the search for drug targets [1]. The prediction of protein essentiality has been supported by a large number of experimental methods like gene knockouts [3], RNA interference [4], and conditional knockouts [5]. The execution of each of these methods needs a large amount of time and funds. Taking these constraints into account, more and more researches on the identification of protein essentiality have been carried out using computational methods, especially with the growth and development of available data

Methods

Results

Conclusion