Multiple sequence alignment with affine gap by using multi-objective genetic algorithm

Aligning Molecular Sequences by Wavelet Transform using Cross Correlation Similarity Metric

“…To overcome this drawback, iterative alignment algorithms like improved version of Hidden Markov Model [15] is employed. Many evolutionary algorithms are used for this alignment problem [3] [7]. When considering local alignment, there are many algorithms like EMBOSS [16] which uses the modified version of SW algorithm to improve the speed up, LALIGN [4] which finds the internal duplications by calculating non-interesting local alignments of protein or DNA sequences and BLAST that enables to compare a query sequence with a library of sequences, and identify library sequences that resemble the query sequence above a certain threshold for pair-wise alignment problem.…”

“…Orobitg et al, [14] in 2013 has proposed improved GA using Q score as objective function. Kaya et al, [7] in 2014 has proposed multi-objective GA with affine gap, SP and column score as the objective function for MSA problem. In 2014, Arabi et al [1] has proposed an enhanced dynamic algorithm to align genome sequences.…”

A parallel GWO technique for aligning multiple molecular sequences

“…To overcome this drawback iterative alignment algorithms like [3], [4] are employed. As the MSA is an NP-complete problem [5], evolutionary approaches like [6], [7] are followed in order to find approximate solutions. In recent years, as there is an increase in the databases of the computational biology, the above said algorithms are considered to be time consuming ones.…”

Comparing different machine learning and mathematical regression models to evaluate multiple sequence alignments

“…Also, advanced computational approaches and machine-learning techniques are also widely used to improve the accuracy in MSAs. Thus, genetic algorithms can be implemented to combine different alignment scores in the fitness function and achieve more accurate MSAs [9,10]. Moreover, another well-known technique such as swarm optimization has been recently applied together with hidden Markov models (HMMs) to generate better alignments [11].…”

“…In the same way, other algorithms propose alternative evaluations by adding several features related to secondary structure, gaps and conservation [20,21]. However, most of the previously described alignment approaches still consider suboptimal scores such as PAM and BLOSUM [10,11] or STRIKE [9]. In this work, novel alternative scoring schemes will be proposed to address the MSA evaluation problem by integrating a wide dataset of both other scores and biological features.…”