Identification and Evaluation of Neoantigens in Melanoma Patients Using Data Fusion

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