Protein structure prediction with the 3D-HP side-chain model using a master–slave parallel genetic algorithm

Benítez, César Manuel Vargas; Lopes, Heitor Silvério

doi:10.1007/s13173-010-0002-6

Cited by 16 publications

(10 citation statements)

References 20 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By parallelizing a DE implementation using MPI, the computational load is divided and the overall performance is improved. A Master-Slave (MS) topology was proposed for the parallel DE, similarly as proposed by [17]. In this approach a Master process controls the DE algorithm and distributes to several Slave processes a number of individuals to be evaluated, that is, to compute the fitness function.…”

Section: Parallel Implementationmentioning

confidence: 99%

An improved parallel differential evolution approach for protein structure prediction using both 2D and 3D off-lattice models

Kalegari

Lopes

2013

2013 IEEE Symposium on Differential Evolution (SDE)

View full text Add to dashboard Cite

Protein structure prediction (PSP) is a well-known problem in bioinformatics. Identifying protein native conformations makes it possible to predict its function within the organism. Knowing this also helps the development of new drugs and the comprehension of some biological mechanisms. During years some techniques have been developed for this purpose but, due to their high cost, it is necessary to use simplified models of protein structures. However, even the simplest models, with low biological plausibility, are excessively complex from the computational point of view. This paper reports the application of Differential Evolution (DE) to solve the PSP problem using a Toy Model (also known as the AB Model) in both 2D and 3D to represent the protein structure. This work presents two different versions of the DE algorithm (basic and adaptive) using a parallel architecture (master-slave) based on Message Passing Interface in a cluster. Some special operators for DE were developed: explosion and mirror mutation. All tests executed in this work used four benchmark sequences, ranging from 13 to 55 amino acids. The results for both parallel DE algorithms using both 2D and 3D models were compared with other works in the literature. The DE algorithm achieved excellent results. Overall results encourage further research towards the use of knowledgebased operators to improve further the performance of DE.

show abstract

Section: Parallel Implementationmentioning

confidence: 99%

An improved parallel differential evolution approach for protein structure prediction using both 2D and 3D off-lattice models

Kalegari

Lopes

2013

2013 IEEE Symposium on Differential Evolution (SDE)

View full text Add to dashboard Cite

show abstract

“…-escalonamento sigma (sigma scaling), onde a aptidão de um indivíduo leva em conta a aptidão do resto da população e o desvio padrão da população; -crowding, em que indivíduos muito similares são substituídos por novos indivíduos; -sharing, onde indivíduos muito similares tem aptidão reduzida; -Decimation-and-hot-boot (DHB), em que, se o melhor resultado se manter por um número x de gerações, o melhor indivíduo da população é mantido e substitui-se uma parte da população restante por uma nova população (Benítez 2010). Trabalhos futuros podem avaliar a utilização de outras técnicas em adição as do algoritmo genético atual, como por exemplo, o uso de populações evoluindo paralelamente com migração de indivíduos entre elas.…”

Section: Conclusões E Trabalhos Futurosunclassified

Algoritmos Genéticos Na Otimização Da Lapidação De Gemas Coradas

Fiorest¹,

Brusso²

2012

Revista CIATEC-UPF

View full text Add to dashboard Cite

RESUMOEste artigo descreve o uso de algoritmos genéticos na otimização da lapidação de gemas, aprimorando o projeto 3D Gemas existente ao reduzir a interação humana. Será descrito como o algoritmo será usado para evoluir soluções formadas por conjuntos de pontos na gema digitalizada buscando alcançar o modelo com melhor aproveitamento do volume da gema. Palavras Chave: Inteligência Artificial, Algoritmos Genéticos, Otimização, Lapidação, GALIB ABSTRACTThis paper describes the use of genetic algorithms in the optimization of gemstone cutting, improving the existing 3D Gemas Project by reducing human intervention. It will be described how the algorithm will be used to evolve solutions formed by groups of points in the digitalized gem trying to reach a cutting model with the best gemstone volume usage. Keywords: Artificial Intelligence, Genetic Algorithms, Optimization, Gemstone Cutting, GALIB INTRODUÇÃOA lapidação de gemas, processo necessário para realçar os atributos visuais e consequentemente o valor agregado da mesma com finalidade de uso em joalheria, no Brasil ainda segue padrões e métodos antiquados trabalhando praticamente de forma manual. Isso acarreta em um aproveitamento baixo da gema com risco de deixar imperfeições que resultam em perda de seu valor. Em contraste com métodos mais avançados empregados por empresas estrangeiras representa uma grande desvantagem ao mercado de joias do pais (Aspaham, 2006, p. 38).O projeto 3D Gemas fornece um conjunto de ferramentas para auxiliar empresas do setor através do uso de tecnologias para geração de modelos de lapidação otimizados dando a essas empresas um diferencial competitivo.[...] a Tecnologia 3D Gemas é um conjunto de técnicas e ferramentas desenvolvidas com o objetivo de auxiliar o processo de lapidação facetada de gemas coradas, visando encontrar para cada gema o(s) projeto(s) de lapidação que resultem em maior valor agregado, considerando o aproveitamento do volume da gema (peso) e brilho (lapidação) da pedra lapidada resultante.(Brusso et all, 2010 42) O software, ainda sendo aperfeiçoado, já permite observar as vantagens do uso da tecnologia nessa área e o uso de inteligência artificial permitirá reduzir a interação humana, garantindo assim uma maior automação de todo o processo.

show abstract

“…Many computational studies and techniques were conducted for structural protein analysis. Such techniques include the evolutionary algorithm [2,3], Monte carlo [4,5] and HP model [6,7]. Genetic algorithm (GA) can be chosen to solve the Protein Structure Problem (PSP).…”

Section: Introductionmentioning

confidence: 99%

Hidden Markov model and Chapman Kolmogrov for protein structures prediction from images

Kamal

Chowdhury

Khan

et al. 2017

Computational Biology and Chemistry

View full text Add to dashboard Cite

Protein structure prediction and analysis are more significant for living organs to perfect asses the living organ functionalities. Several protein structure prediction methods use neural network (NN). However, the Hidden Markov model is more interpretable and effective for more biological data analysis compared to the NN. It employs statistical data analysis to enhance the prediction accuracy. The current work proposed a protein prediction approach from protein images based on Hidden Markov Model and Chapman Kolmogrov equation. Initially, a preprocessing stage was applied for protein images' binarization using Otsu technique in order to convert the protein image into binary matrix. Subsequently, two counting algorithms, namely the Flood fill and Warshall are employed to classify the protein structures. Finally, Hidden Markov model and Chapman Kolmogrov equation are applied on the classified structures for predicting the protein structure. The execution time and algorithmic performances are measured to evaluate the primary, secondary and tertiary protein structure prediction.

show abstract

Protein structure prediction with the 3D-HP side-chain model using a master–slave parallel genetic algorithm

Cited by 16 publications

References 20 publications

An improved parallel differential evolution approach for protein structure prediction using both 2D and 3D off-lattice models

An improved parallel differential evolution approach for protein structure prediction using both 2D and 3D off-lattice models

Algoritmos Genéticos Na Otimização Da Lapidação De Gemas Coradas

Hidden Markov model and Chapman Kolmogrov for protein structures prediction from images

Contact Info

Product

Resources

About