Deep Convolutional Neural Network Model for Predicting MHC I Binding Affinity in Peptide-Based Therapeutics

سال انتشار: 1402
محل انتشار: دوازدهمین همایش ملی و سومین همایش بین المللی بیوانفورماتیک
کد COI اختصاصی: IBIS12_185
زبان مقاله: انگلیسی
تعداد مشاهده: 147

نویسندگان

Department of Shahid Beheshti University of Medical Sciences, Tehran, Iran

چکیده

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

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.