Prediction of anticancer peptides using by classification algorithms

Cancer is a disease characterized by uncontrolled cell growth, leading to tumor formation and potential metastasis. Conventional cancer treatments like chemotherapy and radiation therapy can cause severe side effects and harm healthy cells. Therefore, researchers are investigating alternative options, including the use of anticancer peptides.Anticancer peptides are specialized molecules that selectively target cancer cells, inhibiting their growth and inducing cell death. They interact with specific targets within cancer cells, potentially halting their proliferation, triggering apoptosis, or enhancing immune recognition. Anticancer peptides offer advantages such as reduced side effects, enhanced specificity for targeting cancer cells, and multifaceted effects on cancer progression.However, developing and applying anticancer peptides face challenges related to stability, target specificity, biological activity, and pharmacokinetics. Thus, alongside experimental studies, statistical models play a crucial role in identifying promising anticancer peptides.The study's objective is to classify anticancer peptides using data from experimental studies in scientific literature and databases. Five model anticancer peptides were classified using various algorithms like logistic regression, random forest, k-nearest neighbor, support vector machine, and linear discriminant analysis, implemented in Python programming.The study highlights that anticancer peptides hold promise as an alternative or complementary approach in cancer treatment. Further peptide development could contribute to more effective and safer cancer therapy. However, advancing in this field requires additional experimental research and comprehensive statistical analyses to fully support the potential of anticancer peptides in combating cancer.