Identification and Evaluation of Neoantigens in Melanoma Patients Using Data Fusion

سال انتشار: 1402
محل انتشار: دوازدهمین همایش ملی و سومین همایش بین المللی بیوانفورماتیک
کد COI اختصاصی: IBIS12_201
زبان مقاله: انگلیسی
تعداد مشاهده: 80

نویسندگان

Immunology Asthma and Allergy Research Institute, Tehran University of Medical Sciences, Tehran, Iran

Laboratory of Complex Biological Systems and Bioinformatics (CBB), Department of Bioinformatics, Institute of Biochemistry and Biophysics (IBB), University of Tehran, Tehran, Iran

B Negahdari

Department of Medical Biotechnology, School of Advanced Technologies in Medicine, Tehran University of Medical Sciences, Tehran, Iran

G.A Kardar

Immunology Asthma and Allergy Research Institute, Tehran University of Medical Sciences, Tehran, Iran

چکیده

Melanoma is a deadly type of skin cancer, and conventional therapies like chemotherapyhave many side effects and are often ineffective due to melanoma cell resistance. Neoantigens, specificpeptides derived from tumor mutations, offer hope for cancer treatment, but predicting neoantigens ischallenging. Machine learning algorithms are recommended to accurately predict neoantigens.Therefore, the aim of this study is to create a new model based on data fusion on different immunogenicfeatures to predict melanoma cancer neoantigens and test the predicted neoantigens in vitro.Methods consist of three phases. Phase ۱: Construction of machine model in three stages: a. Training:Using experimentally confirmed peptides. b. Validation. c. Test: by mutated melanoma s peptides. Phase۲: Identification of genetic changes in melanoma (WES and RNA-Seq from TCGA database). Phase ۳:in vitro evaluation of candidate peptides.The model was constructed and fitted on ۲۶۳ features. Different tools have been used to evaluate andfind peptides features. The netCTLpan was used to find the features related to the binding affinity ofMHC and peptides (like MHC_prediction, TAP prediction score, Cleavage prediction score, percentilerank, netMHCstab). physicochemical features of peptides gained by Peptide master package in R (PI,MW, aIndex, Boman, Charge, Hydrophobicity, instaIndex and ۹ Features related to composition ofamino acids). Also, we obtained the features related to the peptide sequence using the iLearnPlus and pfeature packages. Different classifiers such as Logistic Regression, Random Forest, Gaussian NB,XGBoost, Support vector machine, Linear SVC, KNeighbors, SGD, Gradient Boosting, Extra TreeClassifier, Decision Tree, MLP Classifier were evaluated and tested in this machine. Finally, on nineclassifiers, weighting and voting methods of data fusion applied. The accuracy of this machine was ۶۵percent.

کلیدواژه ها

Data Fusion; Machine Learning; Melanoma; Neoantigens; Immunotherapy

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.