A Genetic Algorithm for the Selection of Features Used in the Prediction of Protein Function

Leijoto, Larissa Fernandes; Rodrigues, Thiago Assis de Oliveira; Zaratey, Luis Enrique; Nobre, Cristiane Neri

doi:10.1109/bibe.2014.42

Cited by 14 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Borro et al [31] employed Bayesian classification to extract features from protein structure and achieves an accuracy of 45% in predicting enzyme classes. Leijoto [32] based their work on [31] and proposed an evolutionary system combining GA with Support Vector Machines (SVM) for the same purpose, achieving an accuracy of 71% and outperforming the previous classification methods. Wu et al [33] proposed an ML-DE technique in which a combination of KNN, Linear Regression (LR), Decision Trees, Random Forests and Multi-Layer Perceptron (MLP) (from scikit library [34]) approaches are used to generate sequence-function models able to predict how fit a protein is concerning a specified task.…”

Section: Related Workmentioning

confidence: 99%

Using Genetic Programming to Predict and Optimize Protein Function

Miralavy¹,

Bricco²,

Gilad³

et al. 2022

Preprint

View full text Add to dashboard Cite

Protein engineers conventionally use tools such as Directed Evolution to find new proteins with better functionalities and traits. More recently, computational techniques and especially machine learning approaches have been recruited to assist Directed Evolution, showing promising results. In this paper, we propose POET, a computational Genetic Programming tool based on evolutionary computation methods to enhance screening and mutagenesis in Directed Evolution and help protein engineers to find proteins that have better functionality. As a proof-of-concept we use peptides that generate MRI contrast detected by the Chemical Exchange Saturation Transfer contrast mechanism. The evolutionary methods used in POET are described, and the performance of POET in different epochs of our experiments with Chemical Exchange Saturation Transfer contrast are studied. Our results indicate that a computational modelling tool like POET can help to find peptides with 400% better functionality than used before.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Genetic Programming to Predict and Optimize Protein Function

Miralavy¹,

Bricco²,

Gilad³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They were combined with SVM and used in a bioinformatic application -classification of array-based multiclass tumor [15]. They have also been used for predicting protein function [13], where a GA was used to select some variables before they were used further by SVM. Their prediction results were compared to those of Borro et al [22] and found to be clearly better, demonstrating that using a GA to select a small number of significant variables was more effective, than Borro et al's technique.…”

Section: Genetic Algorithmmentioning

confidence: 99%

“…[9] and Flower Pollination algorithm [10] that proposed using Bat algorithm, in combination with an optimum-path forest classifier. GA has been applied for pattern recognition [11,12], investigation of protein function [13] and SNP selection [14]. Peng et al [15] and Li et al [16,17] used GA with SVM in bioinformatics.…”

Section: Introductionmentioning

confidence: 99%

SELECTION OF A MINIMAL NUMBER OF SIGNIFICANT PORCINE SNPs BY AN INFORMATION GAIN AND GENETIC ALGORITHM HYBRID MODEL

Rathasamuth

Pasupa

Tongsima

2019

MJCS

View full text Add to dashboard Cite

A panel of a large number of common Single Nucleotide Polymorphisms (SNPs) distributed across an entire porcine genome has been widely used to represent genetic variability of pigs. With the advent of SNP-array technology, a genome-wide genetic profile of a specimen can be easily observed. Among the large number of such variations, there exists a much smaller subset of the SNP panel that could equally be used to correctly identify the corresponding breed. This work presents a SNP selection heuristic that can still be used effectively in the breed classification. The features were selected by combining a filter method and a wrapper methodâ€“information gain method and genetic algorithma“plus a feature frequency selection step, while classification used a support vector machine. We were able to reduce the number of significant SNPs to 0.86 % of the total number of SNPs in a swine dataset with 94.80 % classification accuracy.

show abstract

“…It was combined with SVM and used in a bioinformatic application [15], classification of array-based multiclass tumor. It was also used for predicting protein function in [13] where GA was used to select some variables before they were used further by SVM. Their prediction results were compared to those obtained by Borro et al [22] and found to be clearly better, demonstrating that using GA to select a small number of significant variables was more effective that the technique used by Borro et al In [23], GA was used to find the optimum parameters, including hyper-parameters, for SVM operation.…”

Section: Genetic Algorithmmentioning

confidence: 99%

“…There are also several studies that proposed nature-inspired techniques for bioinformatics such as [8,9], and [10] that proposed using Bat algorithm, Cuckoo search algorithm, and Flower Pollination algorithm, respectively, in combination with Optimum-Path Forest classifier. GA has been applied to many fields of study such as pattern recognition [11,12], investigation of protein function [13], and SNP selection [14]. In [15,16,17], GA was used with SVM in bioinformatics.…”

Section: Introductionmentioning

confidence: 99%

Selection of a Minimal Number of Significant Porcine SNPs by an Information Gain and Genetic Algorithm Hybrid Model

Rathasamuth¹,

Pasupa²,

Tongsima³

2019

Preprint

View full text Add to dashboard Cite

A panel of large number of common Single Nucleotide Polymorphisms (SNPs) distributed across an entire porcine genome has been widely used to represent genetic variability of pig. With the advent of SNP-array technology, a genome-wide genetic profile of a specimen can be easily observed. Among the large number of such variations, there exist a much smaller subset of the SNP panel that could equally be used to correctly identify the corresponding breed. This work presents a SNP selection heuristic that can still be used effectively in the breed classification process. The proposed feature selection was done by the approach of combining a filter method and a wrapper method-information gain method and genetic algorithm-plus a feature frequency selection step, while classification was done by support vector machine. The approach was able to reduce the number of significant SNPs to 0.86 % of the total number of SNPs in a swine dataset and provided a high classification accuracy of 94.80 %.

show abstract

A Genetic Algorithm for the Selection of Features Used in the Prediction of Protein Function

Cited by 14 publications

References 16 publications

Using Genetic Programming to Predict and Optimize Protein Function

Using Genetic Programming to Predict and Optimize Protein Function

SELECTION OF A MINIMAL NUMBER OF SIGNIFICANT PORCINE SNPs BY AN INFORMATION GAIN AND GENETIC ALGORITHM HYBRID MODEL

Selection of a Minimal Number of Significant Porcine SNPs by an Information Gain and Genetic Algorithm Hybrid Model

Contact Info

Product

Resources

About