Cancer is a standout amongst the most widely recognized and complex infections of the present century
since it happens because of numerous organic and physical responses. One of the amplest and most boundless
growths for the ladies today is Breast tumor, while prostate malignancy is a worry for some men. Computational
models of disease are being created to help both biological invention and clinical prescription. The In silico models
encourage the accumulation and utilization of trials to break down and separate rich organic data from vast natural
database. In this study, a total of seven data sets is used, that is, five data sets from the Universal Mutation Database
(UMD) TP53 database and two datasets from the International Agency for Research on Cancer (IARC) TP53 
database, are used to assess the work. Back propagation neural network with hybrid model of 5-fold cross-validation
and validation sets was used to classify and predict breast and prostate cancers in patients based on molecular
mutations located in the TP53 gene. The performance of the proposed system in the network testing phase was
determined to be satisfactory based on the average values for all folds of five indices (i.e., sensitivity = 97 and 96.5;
specificity = 96.6 and 97.3; accuracy = 98 and 96.7; F-measure = 98.1 and 97.1; and Matthew’s correlation
coefficient = 0.93 and 0.91) for breast and prostate cancers, respectively.
[In Silico Molecular Classification of Breast and Prostate Cancers using Back Propagation Neural Network.