Feature selection enhances peptide binding predictions for TCR-specific interactions
IntroductionT-cell receptors (TCRs) play a critical role in the immune response by recognizing specific ligand peptides presented by major histocompatibility complex (MHC) molecules. Accurate prediction of peptide binding to TCRs is essential for advancing immunotherapy, vaccine design, and understa...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Immunology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fimmu.2024.1510435/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590846602510336 |
|---|---|
| author | Hamid Teimouri Hamid Teimouri Zahra S. Ghoreyshi Zahra S. Ghoreyshi Anatoly B. Kolomeisky Anatoly B. Kolomeisky Anatoly B. Kolomeisky Jason T. George Jason T. George Jason T. George Jason T. George |
| author_facet | Hamid Teimouri Hamid Teimouri Zahra S. Ghoreyshi Zahra S. Ghoreyshi Anatoly B. Kolomeisky Anatoly B. Kolomeisky Anatoly B. Kolomeisky Jason T. George Jason T. George Jason T. George Jason T. George |
| author_sort | Hamid Teimouri |
| collection | DOAJ |
| description | IntroductionT-cell receptors (TCRs) play a critical role in the immune response by recognizing specific ligand peptides presented by major histocompatibility complex (MHC) molecules. Accurate prediction of peptide binding to TCRs is essential for advancing immunotherapy, vaccine design, and understanding mechanisms of autoimmune disorders.MethodsThis study presents a theoretical approach that explores the impact of feature selection techniques on enhancing the predictive accuracy of peptide binding models tailored for specific TCRs. To evaluate our approach across different TCR systems, we utilized a dataset that includes peptide libraries tested against three distinct murine TCRs. A broad range of physicochemical properties, including amino acid composition, dipeptide composition, and tripeptide features, were integrated into the machine learning-based feature selection framework to identify key properties contributing to binding affinity.ResultsOur analysis reveals that leveraging optimized feature subsets not only simplifies the model complexity but also enhances predictive performance, enabling more precise identification of TCR peptide interactions. The results of our feature selection method are consistent with findings from hybrid approaches that utilize both sequence and structural data as input as well as experimental data.DiscussionOur theoretical approach highlights the role of feature selection in peptide-TCR interactions, providing a quantitative tool for uncovering the molecular mechanisms of the T-cell response and assisting in the design of more advanced targeted therapeutics. |
| format | Article |
| id | doaj-art-ce21519cc26844cba45e58d044deb61d |
| institution | Kabale University |
| issn | 1664-3224 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Immunology |
| spelling | doaj-art-ce21519cc26844cba45e58d044deb61d2025-01-23T06:56:31ZengFrontiers Media S.A.Frontiers in Immunology1664-32242025-01-011510.3389/fimmu.2024.15104351510435Feature selection enhances peptide binding predictions for TCR-specific interactionsHamid Teimouri0Hamid Teimouri1Zahra S. Ghoreyshi2Zahra S. Ghoreyshi3Anatoly B. Kolomeisky4Anatoly B. Kolomeisky5Anatoly B. Kolomeisky6Jason T. George7Jason T. George8Jason T. George9Jason T. George10Department of Chemistry, Rice University, Houston, TX, United StatesCenter for Theoretical Biological Physics, Rice University, Houston, TX, United StatesCenter for Theoretical Biological Physics, Rice University, Houston, TX, United StatesDepartment of Biomedical Engineering, Texas A&M University, College Station, TX, United StatesDepartment of Chemistry, Rice University, Houston, TX, United StatesCenter for Theoretical Biological Physics, Rice University, Houston, TX, United StatesDepartment of Chemical and Biomolecular Engineering, Rice University, Houston, TX, United StatesCenter for Theoretical Biological Physics, Rice University, Houston, TX, United StatesDepartment of Biomedical Engineering, Texas A&M University, College Station, TX, United StatesDepartment of Hematopoietic Biology and Malignancy, MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Translational Medical Sciences, Texas A&M Health Science Center, Houston, TX, United StatesIntroductionT-cell receptors (TCRs) play a critical role in the immune response by recognizing specific ligand peptides presented by major histocompatibility complex (MHC) molecules. Accurate prediction of peptide binding to TCRs is essential for advancing immunotherapy, vaccine design, and understanding mechanisms of autoimmune disorders.MethodsThis study presents a theoretical approach that explores the impact of feature selection techniques on enhancing the predictive accuracy of peptide binding models tailored for specific TCRs. To evaluate our approach across different TCR systems, we utilized a dataset that includes peptide libraries tested against three distinct murine TCRs. A broad range of physicochemical properties, including amino acid composition, dipeptide composition, and tripeptide features, were integrated into the machine learning-based feature selection framework to identify key properties contributing to binding affinity.ResultsOur analysis reveals that leveraging optimized feature subsets not only simplifies the model complexity but also enhances predictive performance, enabling more precise identification of TCR peptide interactions. The results of our feature selection method are consistent with findings from hybrid approaches that utilize both sequence and structural data as input as well as experimental data.DiscussionOur theoretical approach highlights the role of feature selection in peptide-TCR interactions, providing a quantitative tool for uncovering the molecular mechanisms of the T-cell response and assisting in the design of more advanced targeted therapeutics.https://www.frontiersin.org/articles/10.3389/fimmu.2024.1510435/fullimmune responsefeature selectionphysicochemical propertiesTCR-peptide interactionsbinding affinity |
| spellingShingle | Hamid Teimouri Hamid Teimouri Zahra S. Ghoreyshi Zahra S. Ghoreyshi Anatoly B. Kolomeisky Anatoly B. Kolomeisky Anatoly B. Kolomeisky Jason T. George Jason T. George Jason T. George Jason T. George Feature selection enhances peptide binding predictions for TCR-specific interactions Frontiers in Immunology immune response feature selection physicochemical properties TCR-peptide interactions binding affinity |
| title | Feature selection enhances peptide binding predictions for TCR-specific interactions |
| title_full | Feature selection enhances peptide binding predictions for TCR-specific interactions |
| title_fullStr | Feature selection enhances peptide binding predictions for TCR-specific interactions |
| title_full_unstemmed | Feature selection enhances peptide binding predictions for TCR-specific interactions |
| title_short | Feature selection enhances peptide binding predictions for TCR-specific interactions |
| title_sort | feature selection enhances peptide binding predictions for tcr specific interactions |
| topic | immune response feature selection physicochemical properties TCR-peptide interactions binding affinity |
| url | https://www.frontiersin.org/articles/10.3389/fimmu.2024.1510435/full |
| work_keys_str_mv | AT hamidteimouri featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT hamidteimouri featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT zahrasghoreyshi featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT zahrasghoreyshi featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT anatolybkolomeisky featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT anatolybkolomeisky featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT anatolybkolomeisky featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT jasontgeorge featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT jasontgeorge featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT jasontgeorge featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions AT jasontgeorge featureselectionenhancespeptidebindingpredictionsfortcrspecificinteractions |