SVM and SVR-based MHC-binding prediction using a mathematical presentation of peptide sequences
Само за регистроване кориснике
2016
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
At present, there are a number of methods for the prediction of T-cell epitopes and major histocompatibility complex (MHC)-binding peptides. Despite numerous methods for predicting T-cell epitopes, there still exist limitations that affect the reliability of prevailing methods. For this reason, the development of models with high accuracy are crucial. An accurate prediction of the peptides that bind to specific major histocompatibility complex class I and II (MHC-I and MHC-II) molecules is important for an understanding of the functioning of the immune system and the development of peptide-based vaccines. Peptide binding is the most selective step in identifying T-cell epitopes. In this paper, we present a new approach to predicting MHC-binding ligands that takes into account new weighting schemes for position-based amino acid frequencies, BLOSUM and VOGG substitution of amino acids, and the physicochemical and molecular properties of amino acids. We have made models for quantitatively... and qualitatively predicting MHC-binding ligands. Our models are based on two machine learning methods support vector machine (SVM) and support vector regression (SVR), where our models have used for feature selection, several different encoding and weighting schemes for peptides. The resulting models showed comparable, and in some cases better, performance than the best existing predictors. The obtained results indicate that the physicochemical and molecular properties of amino acids (AA) contribute significantly to the peptide-binding affinity.
Кључне речи:
T-cell epitope / Support vector machine / MHC I binding prediction / Encoding scheme / Data miningИзвор:
Computational Biology and Chemistry, 2016, 65, 117-127Издавач:
- Elsevier Sci Ltd, Oxford
Финансирање / пројекти:
- Методе нумеричке и нелинеарне анализе са применама (RS-MESTD-Basic Research (BR or ON)-174002)
DOI: 10.1016/j.compbiolchem.2016.10.011
ISSN: 1476-9271
PubMed: 27816828
WoS: 000390498000015
Scopus: 2-s2.0-84994663339
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Jandrlić, Davorka PY - 2016 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2335 AB - At present, there are a number of methods for the prediction of T-cell epitopes and major histocompatibility complex (MHC)-binding peptides. Despite numerous methods for predicting T-cell epitopes, there still exist limitations that affect the reliability of prevailing methods. For this reason, the development of models with high accuracy are crucial. An accurate prediction of the peptides that bind to specific major histocompatibility complex class I and II (MHC-I and MHC-II) molecules is important for an understanding of the functioning of the immune system and the development of peptide-based vaccines. Peptide binding is the most selective step in identifying T-cell epitopes. In this paper, we present a new approach to predicting MHC-binding ligands that takes into account new weighting schemes for position-based amino acid frequencies, BLOSUM and VOGG substitution of amino acids, and the physicochemical and molecular properties of amino acids. We have made models for quantitatively and qualitatively predicting MHC-binding ligands. Our models are based on two machine learning methods support vector machine (SVM) and support vector regression (SVR), where our models have used for feature selection, several different encoding and weighting schemes for peptides. The resulting models showed comparable, and in some cases better, performance than the best existing predictors. The obtained results indicate that the physicochemical and molecular properties of amino acids (AA) contribute significantly to the peptide-binding affinity. PB - Elsevier Sci Ltd, Oxford T2 - Computational Biology and Chemistry T1 - SVM and SVR-based MHC-binding prediction using a mathematical presentation of peptide sequences EP - 127 SP - 117 VL - 65 DO - 10.1016/j.compbiolchem.2016.10.011 ER -
@article{ author = "Jandrlić, Davorka", year = "2016", abstract = "At present, there are a number of methods for the prediction of T-cell epitopes and major histocompatibility complex (MHC)-binding peptides. Despite numerous methods for predicting T-cell epitopes, there still exist limitations that affect the reliability of prevailing methods. For this reason, the development of models with high accuracy are crucial. An accurate prediction of the peptides that bind to specific major histocompatibility complex class I and II (MHC-I and MHC-II) molecules is important for an understanding of the functioning of the immune system and the development of peptide-based vaccines. Peptide binding is the most selective step in identifying T-cell epitopes. In this paper, we present a new approach to predicting MHC-binding ligands that takes into account new weighting schemes for position-based amino acid frequencies, BLOSUM and VOGG substitution of amino acids, and the physicochemical and molecular properties of amino acids. We have made models for quantitatively and qualitatively predicting MHC-binding ligands. Our models are based on two machine learning methods support vector machine (SVM) and support vector regression (SVR), where our models have used for feature selection, several different encoding and weighting schemes for peptides. The resulting models showed comparable, and in some cases better, performance than the best existing predictors. The obtained results indicate that the physicochemical and molecular properties of amino acids (AA) contribute significantly to the peptide-binding affinity.", publisher = "Elsevier Sci Ltd, Oxford", journal = "Computational Biology and Chemistry", title = "SVM and SVR-based MHC-binding prediction using a mathematical presentation of peptide sequences", pages = "127-117", volume = "65", doi = "10.1016/j.compbiolchem.2016.10.011" }
Jandrlić, D.. (2016). SVM and SVR-based MHC-binding prediction using a mathematical presentation of peptide sequences. in Computational Biology and Chemistry Elsevier Sci Ltd, Oxford., 65, 117-127. https://doi.org/10.1016/j.compbiolchem.2016.10.011
Jandrlić D. SVM and SVR-based MHC-binding prediction using a mathematical presentation of peptide sequences. in Computational Biology and Chemistry. 2016;65:117-127. doi:10.1016/j.compbiolchem.2016.10.011 .
Jandrlić, Davorka, "SVM and SVR-based MHC-binding prediction using a mathematical presentation of peptide sequences" in Computational Biology and Chemistry, 65 (2016):117-127, https://doi.org/10.1016/j.compbiolchem.2016.10.011 . .