Deep Convolutional Neural Network Model for Predicting MHC I Binding Affinity in Peptide-Based Therapeutics
سال انتشار: 1402
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 27
نسخه کامل این مقاله ارائه نشده است و در دسترس نمی باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
IBIS12_185
تاریخ نمایه سازی: 12 آبان 1403
چکیده مقاله:
The intricate interactions between human leukocyte antigens (HLAs) and peptides arefundamental to the human immune system's functionality. A key application of understanding theseinteractions is in the realm of peptide drug discovery and the development of therapeutic mRNA. Thisstudy introduces a pioneering deep convolutional neural network model (DCNN) designed to predictMajor Histocompatibility Complex Class I (MHC I) peptide binding affinities. Notably, this modelautonomously learns the encoding of MHC sequences and their binding contexts, circumventing theneed for explicit MHC-peptide bound structure data.A distinctive feature of the proposed DCNN model is its ability to adapt to peptides of variable lengths,enhancing its robustness and applicability across a diverse range of peptide sequences. This adaptabilityis crucial given the inherent length variance in naturally occurring peptides. The performance of themodel was rigorously evaluated using a test set comprising ۳۰% of the total data, ensuring acomprehensive assessment of its predictive capabilities.The evaluation metrics underscore the model's high efficacy and reliability: it achieved an accuracy of۹۱.۲۱۶%, precision of ۷۱.۴۹۹%, recall rate of ۹۳.۲۴۳%, and an F۱-score of ۸۰.۹۳۶%. Moreover, themodel demonstrated exceptional discriminative ability, as evidenced by an Area under the ReceiverOperating Characteristic Curve (AUC) of ۰.۹۷۵. These metrics collectively highlight the model'spotential as a significant tool in peptide-based therapeutic research.In conclusion, this DCNN model stands as a significant advancement in computational immunology,offering a potent tool for predicting HLA-peptide interactions. Its implications extend to enhancingpeptide drug discovery and the design of therapeutic mRNA, marking a noteworthy contribution tobiomedical research and healthcare innovation.
کلیدواژه ها:
Deep Convolutional Neural Network (DCNN) ، Major Histocompatibility Complex(MHC) I ، Peptide Binding Affinity ، Therapeutic mRNA ، Peptide-Based Therapeutics
نویسندگان
Narges Sangarani Pour
Department of Shahid Beheshti University of Medical Sciences, Tehran, Iran