Predicting, designing, characterization and evaluation of a new novel anticancer peptide SSVAM-9 against the lung carcinoma, an in-silico approach

Sindhu Kalajirao, Sivaa Arumugam Ramakrishnan, Vasanth Raj Palanimuthu

Department of Pharmaceutical Biotechnology, JSS College of Pharmacy, JSS Academy of Higher Education & Research, Ooty, Nilgiris, Tamil Nadu, India

Refer this article

Sindhu Kalajirao, Sivaa Arumugam Ramakrishnan, Vasanth Raj Palanimuthu, 2023. Predicting, designing, characterization and evaluation of a new novel anticancer peptide ssvam-9 against the lung carcinoma, an insilico approach. Journal of medical pharmaceutical and allied sciences, V 12 - I 2, Pages - 5706 – 5712. Doi: 10.55522/jmpas.V12I2.4768.

ABSTRACT

Several anticancer drugs are getting resisted by the cancer cell and treatment like chemotherapy, radiation causes serious side effects. In immunomodulatory treatment the efficiency is less and CAR-T cells, CAR-NK cells require enormous time to get adopt to the in vitro and may cause seizures, dilemma, concussion in prolonged use against the cancer. Even the production of CAR-T cells and NK cells are tedious process. To overcome this situation, anticancer peptides can be used, as they don’t have any drug resistance and they can be highly potent, with good cell penetration. The advantages of these peptides are easy to modify, produce and formulate. This pandemic showed us that, identifying and characterizing a novel anticancer peptide (ACP) is an extremely time and labor consuming process. To reduce the time and labor, this study uses several in silico tools and algorithms like SVM, RF, XGBoost and KNN to predict a novel anticancer peptide. After several studies, with the collected data, a novel anticancer peptide – SSVAM-9 was predicted, which acts against the lung carcinoma. In this, anticancer activity prediction, cell permeation prediction with all 4 algorithms; stability prediction, allergenicity prediction and activity on lung carcinoma prediction were carried out in in silico model. Considering all the parameters, one best novel ACP was selected (SSVAM-9), and it can be easily formulated as the peptide is a stable one. This approach is an advantageous one as it is cost-efficient and less-time consuming which can be studied in vivo and in vitro in future.

Keywords:

Anticancer peptides, Machine Learning, Lung carcinoma, A549, In-silico

Full Text Article