Unleashing a cascade of machine learning for turbocharged sequence alignment in discrete mathematical sciences using GPU

Kaur, Karamjeet; Chakraborty, Sudeshna; Sagar, Anil Kumar

doi:10.47974/JDMSC-1968

Open Access Research Article

Unleashing a cascade of machine learning for turbocharged sequence alignment in discrete mathematical sciences using GPU

^*Karamjeet KaurCorresponding authorkaram_7378@yahoo.comSchool of Engineering and Technology Sharda University Greater Noida, Uttar Pradesh, 201306, IndiaView full profile → , Sudeshna Chakrabortysudeshna2529@gmail.comSchool of Computing Science & Engineering Galgotias University Greater Noida, Uttar Pradesh, 203201, IndiaView full profile → , Anil Kumar Sagaraksagar22@gmail.comSchool of Engineering and Technology Sharda UniversityGreater Noida, Uttar Pradesh, 201306, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 1129–1138Vol. 27Issue 4June 2024DOI: 10.47974/JDMSC-1968 Crossmark XML

Published Online:: 26 Jun 2024
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-1968
Pages:: 1129–1138

Abstract

Prediction and alignment of multiple sequences is the core methodology for information extraction in proteins. The sequence of grouping accuracy predicts the match score of proteins. In recent years, protein sequence alignment has emerged as a critical task in bioinformatics studies. There are two main methods for sequence alignment: pair-wise and multiple sequence alignment. MSA methods have some limitations which were revealed by prior benchmark studies. We have proposed a new benchmark framework for protein grouping based on a machine-learning algorithm. The proposed algorithm is a cascaded vector machine with three levels for data sampling and normalization of protein data. The proposed algorithm was simulated in MATLAB tools and analyzed using the standard parameters of prediction. The analysis of the results suggests that proposed algorithm is efficient than CNN and RNN.

Keywords

MSA Deep learning Protein RNA/DNA Machine learning Prediction

Subject Classifications

Primary 93A30Secondary 49K15

References

[1] Suvorov, Anton, Joshua Hochuli, and Daniel R. Schrider, Accurate inference of tree topologies from multiple sequence alignments using deep learning, Systematic Biology 69, no. 2, 221-233, (2020).
[2] Kuang, Mengmeng, Yong Liu, and Lufei Gao, DLPAlign: A Deep Learning based Progressive Alignment Method for Multiple Protein Sequences, In CSBio’20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics, pp. 83-92, (2020).
[3] Jain, Aashish, Genki Terashi, Yuki Kagaya, Sai Raghavendra Maddhuri Venkata Subramaniya, Charles Christoffer, and Daisuke Kihara, AttentiveDist: Protein Inter-Residue Distance Prediction Using Deep Learning with Attention on Quadruple Multiple Sequence Alignments, bioRxiv, (2020).
[4] Quadir, Farhan, Raj S. Roy, Randal Halfmann, and Jianlin Cheng, DNCON2_Inter: predicting interchain contacts for homodimeric and homomultimeric protein complexes using multiple sequence alignments of monomers and deep learning, Scientific reports 11, no. 1, 1-10, (2021).
[5] Jain, Aashish, Genki Terashi, Yuki Kagaya, Sai Raghavendra Maddhuri Venkata Subramaniya, Charles Christoffer, and Daisuke Kihara, Analyzing the effect of quadruple multiple sequence alignments on deep learning based protein inter-residue distance prediction, Scientific Reports 11, no. 1, 1-13, (2021).
[6] Chen, Zhen, Pei Zhao, Fuyi Li, Tatiana T. Marquez-Lago, André Leier, Jerico Revote, Yan Zhu et al., iLearn: an integrated platform and meta-learner for feature engineering, machine-learning analysis and modeling of DNA, RNA, and protein sequence data, Briefings in Bioinformatics 21, no. 3, 1047-1057, (2020).
[7] Liu, Xuyang, Lei Jin, Shenghua Gao, and Suwen Zhao, Protein contact map prediction using multiple sequence alignment dropout and consistency learning for sequences with fewer homologs, bioRxiv (2021).
[8] Perera, Gamage Kokila Kasuni, and Champi Thusangi Wannige, A hybrid algorithm for identifying partially conserved regions in multiple sequence alignment, International Journal of Computers and Applications 43, no. 10, 979-986, (2021).
[9] Zhang, Chao, Yiming Zhao, Edward L. Braun, and Siavash Mirarab, TAPER: Pinpointing errors in multiple sequence alignments despite varying rates of evolution, Methods in Ecology and Evolution 12, no. 11, 2145-2158, (2021).
[10] Dabba, Ali, Abdelkamel Tari, and Djaafar Zouache, Multiobjective artificial fish swarm algorithm for multiple sequence alignment, INFOR: Information Systems and Operational Research 58, no. 1, 38-59, (2020).
[11] Rehman, Hafiz Asadul, Kashif Zafar, Ayesha Khan, and Abdullah Imtiaz, Multiple sequence alignment using enhanced bird swarm align algorithm, Journal of Intelligent & Fuzzy Systems Preprint, 1-18, (2021).
[12] Pujari, Jeevana Jyothi, and Kanadam Karteeka Pavan, Multiple Sequence Alignment based on Enhanced Brainstorm Optimization Algorithm with dynamic population size (EBSODP), Annals of the Romanian Society for Cell Biology, 10033-10042, (2021).
[13] Poonia, Ramesh C., and Linesh Raja. “On-demand routing protocols for vehicular cloud computing.” In Research Anthology on
Architectures, Frameworks, and Integration Strategies for Distributed and Cloud Computing, pp. 96-122. IGI Global, (2021).
[14] Fukuda, Hiroyuki, and Kentaro Tomii, DeepECA: an end-to-end learning framework for protein contact prediction from a multiple sequence alignment, BMC bioinformatics 21, no. 1, 1-15, (2020).
[15] Zafalon, Geraldo Francisco Donega, Vitoria Zanon Gomes, Anderson Rici Amorim & Carlos Roberto Valencio, A Hybrid Approach using Progressive and Genetic Algorithms for Improvements in Multiple Sequence Alignments, In ICEIS (2), pp. 384-391, (2021).
[16] Sharma, Shilpa, et al. “Hybrid HOG-SVM encrypted face detection and recognition model.” Journal of Discrete Mathematical Sciences and Cryptography 25.1 (2022): 205-218.

Views: 237Downloads: 4Citations: 0