Pairwise Sequence Alignment in Biological Sequences using Machine Learning

Sequence alignment is a method of positioning two (Pairwise Alignment) or more (Multiple Sequence Alignment) biological sequences of characters (such as DNA, RNA, or Protein sequences) in order to find areas of similarity. It’s possible that similarities between these sequences result from their functional or evolutionary connections. The study primarily focuses on the DNA Pairwise Alignment, which reveals the similarities and contrasts between two DNA sequences. The Needleman-Wunsch algorithm and the Smith-Waterman algorithm, two existing pairwise sequence alignment techniques, both have shortcomings in terms of computational accuracy and efficiency. Sequence alignment over enormous databases is unable to give results in a reasonable amount of time, power, or money. Using a Multilayer Perceptron trained with Particle Swarm Optimization (PSO), a novel method for pairwise sequence alignment in DNA has been developed. The PSO algorithm is used to optimize the parameters of the MLP for better alignment performance.