Soft computing methods for the prediction of protein tertiary structures: A survey

Chamorro, Alfonso E. Márquez; Asencio-Cortés, Gualberto; Santiesteban-Toca, Cosme E.; Aguilar–Ruiz, Jesús S.

doi:10.1016/j.asoc.2015.06.024

Cited by 30 publications

(17 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As aforementioned in the introduction, the prediction of contact maps is a very complex problem. But it is a much simpler alternative for the prediction of protein structures since it can be treated as a classification problem [10].…”

Section: Related Workmentioning

confidence: 99%

“…First, the general inter-residual prediction capacity (for the entire sequence) of the implemented method was analyzed. Where we take into account the SCOP classification, the best performance is reached in all-β proteins, with 49% accuracy (a state-of-art average standard [10]).…”

Section: Internal Validationmentioning

confidence: 99%

“…Another problem is that most of the methods employed are practically black boxes [10], so their result is not easily interpreted by biologists specialists, which makes it difficult to understand the process of folding proteins.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tree-based Secondary Structure Interactions Predictor Method for Protein Contact Maps

Quintana-Zaez

Ruiz

Santiesteban-Toca

2018

CyS

View full text Add to dashboard Cite

Understanding the folding of proteins is one of the most interesting research field for the Bioinformatics. The contact maps constitute an intermediate step in the prediction of the 3D structure of the proteins and allow to represent folding patterns. Currently, the methods used to predict contact maps achieve low precision results, only about 25% of long-range (L/5) contacts are correctly predicted, and their knowledge base is not humanly interpretable. In this paper, we propose an easy implementation multiple classifier for contact maps, which is based on patterns of interaction between secondary structures and employed decision trees as base classifiers. This method is able to naturally reduce the level of imbalance between contact/non-contact classes. In addition, a set of interpretable rules are extracted as a complement to the prediction. The validation of method performance shows that an average of 45% of general contacts are correctly predicted. Moreover, a Z-score comparison of its longrange contacts predictions (L/5) with participant methods in CASP11 competition shows that it is competitive with the state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Internal Validationmentioning

confidence: 99%

See 1 more Smart Citation

Tree-based Secondary Structure Interactions Predictor Method for Protein Contact Maps

Quintana-Zaez

Ruiz

Santiesteban-Toca

2018

CyS

View full text Add to dashboard Cite

show abstract

“…The integration of computational sciences into the pharmaceutical and biomedical industry has yielded several applications and technological advances during the last decades [1,2]. The pharmaceutical industry is primarily headed towards improving the long and costly process of discovery and development of new drugs, which involves several stages including in vitro and in vivo wet-lab experiments.…”

Section: Introductionmentioning

confidence: 99%

Neural-based approaches to overcome feature selection and applicability domain in drug-related property prediction

Sabando

Ponzoni

Soto

2019

Applied Soft Computing

View full text Add to dashboard Cite

In the fields of pharmaceutical research and biomedical sciences, QSAR modeling is an established approach during drug discovery for prediction of biological activity of drug candidates. Yet, QSAR modeling poses a series of open challenges. First, chemical compounds are represented on a high-dimensional space and thus feature selection is typically applied, although this task entails a challenging combinatorial problem with potential loss of information. Second, the definition of the applicability domain of a QSAR model is a desirable aspect to determine the reliability of predictions on unseen chemicals, which is often difficult to assess due to the extent of the chemical space. Finally, interpretability of these models is also a critical issue for drug designers. The purpose of this work is to thoroughly assess the application of neural-based methods and recent advances deep learning for QSAR modeling. We hypothesize that neural-based methods can overcome the need to perform a descriptor selection phase. We developed three QSAR models based on neural networks for prediction of relevant chemical and biomedical properties that, in the absence of any feature selection step, can outperform the state-of-the-art models for such properties. We also implemented an embedded applicability domain technique based on network output probabilities that proved to be effective; its application improved the predictive performance of the model. Finally, we proposed the use of a post hoc feature analysis technique based on an aggregation of network weights, which enabled effective detection of relevant features in the model.

show abstract

“…São listadas diversas tecnologias em Redes Neurais Artificiais e suas aplicações, além dos diversos desafios em aberto. Na mesma linha um survey é apresentado em (MARQUEZ-CHAMORRO et al, 2015), que discute 90 técnicas diferentes e sua aplicação em PSP. O foco dessa revisão é comparar as técnicas de predição, entretanto dela também se extraem informações de ambiente de processamento e necessidades em geral, devido à complexidade e ao volume de dados.…”

Section: Estado Da Arte De Pspunclassified

MDAPSP - Uma arquitetura modular distribuída para auxílio à predição de estruturas de proteínas

Oliveira¹

View full text Add to dashboard Cite

Agradeço primeiramente à minha família pela paciência, compreensão e apoio desde sempre. Ao prof. Júlio pelas oportunidades e pela orientação nessa caminhada acadêmica. Agradeço aos demais professores que contribuíram para minha formação e desenvolvimento dessa pesquisa, àqueles que integram o LaSDPC, ao prof. Alexandre Delbem pela colaboração e ao prof. Stephan Reiff-Marganiec pela orientação no período na Universidade de Leicester-Inglaterra. Aos meus amigos, dos quais destaco quatro que auxiliaram diretamente na construção dessa tese, Alexandre Defelicibus, Fausto Costa, Mário Pardo e Juliano Ferreira. Aos companheiros de laboratório pelas conversas, risadas e trocas de conhecimento. Aos amigos com quem convivi nesses anos, compartilhando teto, experiências, alegrias e dificuldades. Aos amigos de toda a vida de Machado, Poços de Caldas, São Carlos, Leicester e demais lugares que tive o prazer de conhecer. Muito obrigado. "O que sabemos é uma gota, o que ignoramos é um oceano." (Isaac Newton) Palavras-chave: Arquiteturas orientadas a serviço, predição de estruturas de proteínas, gateways científicos, workflows científicos, WorkflowSim.

show abstract

Soft computing methods for the prediction of protein tertiary structures: A survey

Cited by 30 publications

References 93 publications

Tree-based Secondary Structure Interactions Predictor Method for Protein Contact Maps

Tree-based Secondary Structure Interactions Predictor Method for Protein Contact Maps

Neural-based approaches to overcome feature selection and applicability domain in drug-related property prediction

MDAPSP - Uma arquitetura modular distribuída para auxílio à predição de estruturas de proteínas

Contact Info

Product

Resources

About