A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2
Proteins are macromolecules essential for living organisms. However, to perform their function, proteins need to achieve their Native Structure (NS). The NS is reached fast in nature. By contrast, in silico, it is obtained by solving the Protein Folding problem (PFP) which currently has a long execu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Axioms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1680/11/12/729 |
| _version_ | 1797461499248115712 |
|---|---|
| author | Juan P. Sánchez-Hernández Juan Frausto-Solís Diego A. Soto-Monterrubio Juan J. González-Barbosa Edgar Roman-Rangel |
| author_facet | Juan P. Sánchez-Hernández Juan Frausto-Solís Diego A. Soto-Monterrubio Juan J. González-Barbosa Edgar Roman-Rangel |
| author_sort | Juan P. Sánchez-Hernández |
| collection | DOAJ |
| description | Proteins are macromolecules essential for living organisms. However, to perform their function, proteins need to achieve their Native Structure (NS). The NS is reached fast in nature. By contrast, in silico, it is obtained by solving the Protein Folding problem (PFP) which currently has a long execution time. PFP is computationally an NP-hard problem and is considered one of the biggest current challenges. There are several methods following different strategies for solving PFP. The most successful combine computational methods and biological information: I-TASSER, Rosetta (Robetta server), AlphaFold2 (CASP14 Champion), QUARK, PEP-FOLD3, TopModel, and GRSA2-SSP. The first three named methods obtained the highest quality at CASP events, and all apply the Simulated Annealing or Monte Carlo method, Neural Network, and fragments assembly methodologies. In the present work, we propose the GRSA2-FCNN methodology, which assembles fragments applied to peptides and is based on the GRSA2 and Convolutional Neural Networks (CNN). We compare GRSA2-FCNN with the best state-of-the-art algorithms for PFP, such as I-TASSER, Rosetta, AlphaFold2, QUARK, PEP-FOLD3, TopModel, and GRSA2-SSP. Our methodology is applied to a dataset of 60 peptides and achieves the best performance of all methods tested based on the common metrics TM-score, RMSD, and GDT-TS of the area. |
| first_indexed | 2024-03-09T17:20:16Z |
| format | Article |
| id | doaj.art-8fb1e2e5d2fa49f5ba8ac9871529beaf |
| institution | Directory Open Access Journal |
| issn | 2075-1680 |
| language | English |
| last_indexed | 2024-03-09T17:20:16Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Axioms |
| spelling | doaj.art-8fb1e2e5d2fa49f5ba8ac9871529beaf2023-11-24T13:16:11ZengMDPI AGAxioms2075-16802022-12-01111272910.3390/axioms11120729A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2Juan P. Sánchez-Hernández0Juan Frausto-Solís1Diego A. Soto-Monterrubio2Juan J. González-Barbosa3Edgar Roman-Rangel4Departamento de Tecnologías de la Información, Universidad Politécnica del Estado de Morelos, Jiutepec 62574, MexicoDivisión de Estudios de Posgrado e investigación, Tecnológico Nacional de México/I.T. Ciudad Madero, Madero 89440, MexicoDivisión de Estudios de Posgrado e investigación, Tecnológico Nacional de México/I.T. Ciudad Madero, Madero 89440, MexicoDivisión de Estudios de Posgrado e investigación, Tecnológico Nacional de México/I.T. Ciudad Madero, Madero 89440, MexicoComputer Science Department, Instituto Tecnológico Autónomo de México, Mexico City 01080, MexicoProteins are macromolecules essential for living organisms. However, to perform their function, proteins need to achieve their Native Structure (NS). The NS is reached fast in nature. By contrast, in silico, it is obtained by solving the Protein Folding problem (PFP) which currently has a long execution time. PFP is computationally an NP-hard problem and is considered one of the biggest current challenges. There are several methods following different strategies for solving PFP. The most successful combine computational methods and biological information: I-TASSER, Rosetta (Robetta server), AlphaFold2 (CASP14 Champion), QUARK, PEP-FOLD3, TopModel, and GRSA2-SSP. The first three named methods obtained the highest quality at CASP events, and all apply the Simulated Annealing or Monte Carlo method, Neural Network, and fragments assembly methodologies. In the present work, we propose the GRSA2-FCNN methodology, which assembles fragments applied to peptides and is based on the GRSA2 and Convolutional Neural Networks (CNN). We compare GRSA2-FCNN with the best state-of-the-art algorithms for PFP, such as I-TASSER, Rosetta, AlphaFold2, QUARK, PEP-FOLD3, TopModel, and GRSA2-SSP. Our methodology is applied to a dataset of 60 peptides and achieves the best performance of all methods tested based on the common metrics TM-score, RMSD, and GDT-TS of the area.https://www.mdpi.com/2075-1680/11/12/729protein folding problemfragments assemblyconvolutional neural networkgolden ratio simulated annealing |
| spellingShingle | Juan P. Sánchez-Hernández Juan Frausto-Solís Diego A. Soto-Monterrubio Juan J. González-Barbosa Edgar Roman-Rangel A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2 Axioms protein folding problem fragments assembly convolutional neural network golden ratio simulated annealing |
| title | A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2 |
| title_full | A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2 |
| title_fullStr | A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2 |
| title_full_unstemmed | A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2 |
| title_short | A Peptides Prediction Methodology with Fragments and CNN for Tertiary Structure Based on GRSA2 |
| title_sort | peptides prediction methodology with fragments and cnn for tertiary structure based on grsa2 |
| topic | protein folding problem fragments assembly convolutional neural network golden ratio simulated annealing |
| url | https://www.mdpi.com/2075-1680/11/12/729 |
| work_keys_str_mv | AT juanpsanchezhernandez apeptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT juanfraustosolis apeptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT diegoasotomonterrubio apeptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT juanjgonzalezbarbosa apeptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT edgarromanrangel apeptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT juanpsanchezhernandez peptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT juanfraustosolis peptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT diegoasotomonterrubio peptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT juanjgonzalezbarbosa peptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 AT edgarromanrangel peptidespredictionmethodologywithfragmentsandcnnfortertiarystructurebasedongrsa2 |