iTTCA-MFF: identifying tumor T cell antigens based on multiple feature fusion
Hongliang Zou1, Fan Yang2, Zhijian Yin2
1School of Communications and Electronics, Jiangxi Science and Technology Normal University, Nanchang, 330003, China. hongliangzou@126.com.
Abstract:
Cancer is a terrible disease, recent studies reported that tumor T cell antigens (TTCAs) may play a promising role in cancer treatment. Since experimental methods are still expensive and time-consuming, it is highly desirable to develop automatic computational methods to identify tumor T cell antigens from the huge amount of natural and synthetic peptides. Hence, in this study, a novel computational model called iTTCA-MFF was proposed to identify TTCAs. In order to describe the sequence effectively, the physicochemical (PC) properties of amino acid and residue pairwise energy content matrix (RECM) were firstly employed to encode peptide sequences. Then, two different approaches including covariance and Pearson's correlation coefficient (PCC) were used to collect discriminative information from PC and RECM matrixes. Next, an effective feature selection approach called the least absolute shrinkage and selection operator (LAASO) was adopted to select the optimal features. These selected optimal features were fed into support vector machine (SVM) for identifying TTCAs. We performed experiments on two different datasets, experimental results indicated that the proposed method is promising and may play a complementary role to the existing methods for identifying TTCAs. The datasets and codes can be available at https://figshare.com/articles/online_resource/iTTCA-MFF/17636120 .
Insights
A new computational model, iTTCA-MFF, effectively identifies tumor T cell antigens (TTCAs) using physicochemical properties and machine learning. This method offers a faster, automated approach for cancer research, complementing existing experimental techniques.
Area of Science:
- Computational Biology
- Immunology
- Bioinformatics
Background:
- Tumor T cell antigens (TTCAs) show promise in cancer treatment.
- Experimental identification of TTCAs is costly and time-consuming.
- Automated computational methods are needed to identify TTCAs from peptide sequences.
Purpose of the Study:
- To propose a novel computational model, iTTCA-MFF, for identifying tumor T cell antigens.
- To develop an efficient and accurate method for predicting TTCAs.
Main Methods:
- Encoding peptide sequences using physicochemical (PC) properties and residue pairwise energy content matrix (RECM).
- Utilizing covariance and Pearson's correlation coefficient (PCC) for feature extraction.
- Applying least absolute shrinkage and selection operator (LAASO) for optimal feature selection.
- Employing support vector machine (SVM) for TTCAs identification.
Main Results:
- The iTTCA-MFF model demonstrated promising performance in identifying TTCAs on two independent datasets.
- The combination of PC properties, RECM, and advanced feature selection/classification techniques proved effective.
- Experimental results suggest the model's utility in cancer research.
Conclusions:
- The proposed iTTCA-MFF model provides an effective computational approach for TTCAs identification.
- This method can serve as a valuable complement to traditional experimental techniques.
- The developed model contributes to advancing automated peptide analysis in cancer immunology.
More Related Videos
Related Concept Videos
01:27Tumor Immunotherapy
01:22T Cell Activation and Clonal Selection
Naive T cells that have not yet encountered an antigen express two primary CD...