Studying toxicology and its relationship to drugs is expected to provide substantial human benefits; however, such benefits demand the ability to recognize and understand drug side effects and prevent them from happening. The proposed model aims to improve toxicity prediction by classifying chemical synthesis using an Artificial Immune Recognition System (AIRS) algorithm. The core of the current approach is its emphasis on constructing a hybrid classification system that achieves an effective performance. This system is achieved by merging three different types of artificial immune recognition system algorithms with a detector-based classifier in a hybrid model and optimizing the final output to improve the overall system performance.
Digital Object Identifier (DOI)
Mahmoud, Amena; Hamza, Taher; and Z. Rashad, M.
"Prediction of Chemical Toxicity for Drug Design Using AIRS Algorithms and Hybrid Classifiers,"
Applied Mathematics & Information Sciences: Vol. 14:
2, Article 18.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol14/iss2/18