{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:11:40Z","timestamp":1780765900051,"version":"3.54.1"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04258-w","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T12:00:59Z","timestamp":1754481659000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Random Variable Based Alignment-Free Approach for Protein Sequence Comparison"],"prefix":"10.1007","volume":"6","author":[{"given":"Debrupa","family":"Pal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Papri","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2899-4433","authenticated-orcid":false,"given":"Subhram","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bansibadan","family":"Maji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"issue":"5","key":"4258_CR1","doi-asserted-by":"publisher","first-page":"2781","DOI":"10.1016\/S0006-3495(02)75287-9","volume":"83","author":"HH Gan","year":"2002","unstructured":"Gan HH, Perlow RA, Roy S, Ko J, Wu M, Huang J, Schlick T. Analysis of protein sequence\/structure similarity relationships. Biophys J. 2002;83(5):2781\u201391.","journal-title":"Biophys J"},{"issue":"5","key":"4258_CR2","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.compbiomed.2012.01.011","volume":"42","author":"ZH Qi","year":"2012","unstructured":"Qi ZH, Feng J, Qi XQ, Li L. Application of 2D graphic representation of protein sequence based on Huffman tree method. Comput Biol Med. 2012;42(5):556\u201363.","journal-title":"Comput Biol Med"},{"issue":"2","key":"4258_CR3","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/TCBB.2013.10","volume":"10","author":"DS Huang","year":"2013","unstructured":"Huang DS, Yu HJ. Normalized feature vectors: a novel alignment-free sequence comparison method based on the numbers of adjacent amino acids. IEEE\/ACM Trans Comput Biol Bioinf. 2013;10(2):457\u201367.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinf"},{"issue":"1","key":"4258_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"AK Saw","year":"2019","unstructured":"Saw AK, Tripathy BC, Nandi S. Alignment-free similarity analysis for protein sequences based on fuzzy integral. Sci Rep. 2019;9(1):1\u201313.","journal-title":"Sci Rep"},{"key":"4258_CR5","doi-asserted-by":"publisher","unstructured":"Armen Abnousi SL, Broschat A, Kalyanaraman. 2015. An alignment-free approach to cluster proteins using frequency of conserved k-mers. In Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics (BCB \u201815). Association for Computing Machinery, New York, NY, USA, 597\u2013606. https:\/\/doi.org\/10.1145\/2808719.2812223","DOI":"10.1145\/2808719.2812223"},{"key":"4258_CR6","doi-asserted-by":"crossref","unstructured":"Abo-Elkhier MM, AbdElwahaab MA, Maaty AE. M. I. (2019). Measuring similarity among protein sequences using a new descriptor. BioMed Research International, 2019.","DOI":"10.1155\/2019\/2796971"},{"issue":"3","key":"4258_CR7","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1016\/0022-2836(82)90398-9","volume":"162","author":"O Gotoh","year":"1982","unstructured":"Gotoh O. An improved algorithm for matching biological sequences. J Mol Biol. 1982;162(3):705\u20138.","journal-title":"J Mol Biol"},{"key":"4258_CR8","doi-asserted-by":"crossref","unstructured":"Chakraborty, A., & Bandyopadhyay, S. (2013). FOGSAA: Fast optimal global sequence alignment algorithm. Scientific reports, 3(1), 1\u20139.","DOI":"10.1038\/srep01746"},{"key":"4258_CR9","doi-asserted-by":"crossref","unstructured":"Feng, D. F., & Doolittle, R. F. (1987). Progressive sequence alignment is a a prerequisite to correct phylogenetic trees. Journal of molecular evolution, 25(4),351\u2013360.","DOI":"10.1007\/BF02603120"},{"issue":"4","key":"4258_CR10","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.1016\/S0006-3495(95)80325-5","volume":"68","author":"RS Rahman","year":"1995","unstructured":"Rahman RS, Rackovsky S. Protein sequence randomness and sequence\/structure correlations. Biophys J. 1995;68(4):1531\u20139.","journal-title":"Biophys J"},{"issue":"1","key":"4258_CR11","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1186\/s13059-017-1319-7","volume":"18","author":"A Zielezinski","year":"2017","unstructured":"Zielezinski A, Vinga S, Almeida J, Karlowski WM. Alignment-free sequence comparison: benefits, applications, and tools. Genome Biol. 2017;18(1):186. https:\/\/doi.org\/10.1186\/s13059-017-1319-7.","journal-title":"Genome Biol"},{"key":"4258_CR12","doi-asserted-by":"crossref","unstructured":"Bernard, G., Chan, C. X., Chan, Y. B., Chua, X. Y., Cong, Y., Hogan, J. M.,. & Ragan, M. A. (2019). Alignment-free inference of hierarchical and reticulate phylogenomic relationships. Briefings in Bioinformatics, 20(2), 426\u2013435.","DOI":"10.1093\/bib\/bbx067"},{"issue":"3","key":"4258_CR13","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. Basic local alignment search tool. J Mol Biol. 1990;215(3):403\u201310.","journal-title":"J Mol Biol"},{"key":"4258_CR14","doi-asserted-by":"crossref","unstructured":"Pearson, W. R., & Lipman, D. J. (1988). Improved tools for biological sequence comparison. Proceedings of the National Academy of Sciences, 85(8), 2444\u20132448.","DOI":"10.1073\/pnas.85.8.2444"},{"key":"4258_CR15","doi-asserted-by":"crossref","unstructured":"Thompson, J. D., Higgins, D. G., & Gibson, T. J. (1994). CLUSTAL W: improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice. Nucleic acids research, 22(22), 4673\u20134680.","DOI":"10.1093\/nar\/22.22.4673"},{"key":"4258_CR16","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1186\/1471-2105-5-113","volume":"5","author":"RC Edgar","year":"2004","unstructured":"Edgar RC. MUSCLE: a multiple sequence alignment method with reduced time and space complexity. BMC Bioinformatics. 2004;5:113. https:\/\/doi.org\/10.1186\/1471-2105-5-113.","journal-title":"BMC Bioinformatics"},{"key":"4258_CR17","doi-asserted-by":"crossref","unstructured":"Katoh, K., Misawa, K., Kuma, K. I., & Miyata, T. (2002). MAFFT: a novel method for rapid multiple sequence alignment based on fast Fourier transform. Nucleic acids research, 30(14), 3059\u20133066.","DOI":"10.1093\/nar\/gkf436"},{"issue":"17","key":"4258_CR18","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul SF, Madden TL, Sch\u00e4ffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 1997;25(17):3389\u2013402.","journal-title":"Nucleic Acids Res"},{"issue":"Database issue","key":"4258_CR19","doi-asserted-by":"publisher","first-page":"D222","DOI":"10.1093\/nar\/gkt1223","volume":"42","author":"RD Finn","year":"2014","unstructured":"Finn RD, Bateman A, Clements J, Coggill P, Eberhardt RY, Eddy SR, Heger A, Hetherington K, Holm L, Mistry J, Sonnhammer EL, Tate J, Punta M. Pfam: the protein families database. Nucleic Acids Res. 2014;42(Database issue):D222\u201330. https:\/\/doi.org\/10.1093\/nar\/gkt1223.","journal-title":"Nucleic Acids Res"},{"key":"4258_CR20","doi-asserted-by":"crossref","unstructured":"Schwartz, S., Kent, W. J., Smit, A., Zhang, Z., Baertsch, R., Hardison, R. C.,. & Miller, W. (2003). Human\u2013mouse alignments with BLASTZ. Genome research, 13(1), 103\u2013107.","DOI":"10.1101\/gr.809403"},{"key":"4258_CR21","doi-asserted-by":"crossref","unstructured":"Blanchette, M., Kent, W. J., Riemer, C., Elnitski, L., Smit, A. F., Roskin, K. M.,. & Miller, W. (2004). Aligning multiple genomic sequences with the threaded blockset aligner. Genome research, 14(4), 708\u2013715.","DOI":"10.1101\/gr.1933104"},{"issue":"6","key":"4258_CR22","doi-asserted-by":"publisher","first-page":"e11147","DOI":"10.1371\/journal.pone.0011147","volume":"5","author":"AE Darling","year":"2010","unstructured":"Darling AE, Mau B, Perna NT. Progressive mauve: multiple genome alignment with gene gain, loss and rearrangement. PLoS ONE. 2010;5(6):e11147. https:\/\/doi.org\/10.1371\/journal.pone.0011147.","journal-title":"PLoS ONE"},{"issue":"4","key":"4258_CR23","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1093\/bioinformatics\/btg005","volume":"19","author":"S Vinga","year":"2003","unstructured":"Vinga S, Almeida J. Alignment-free sequence comparison-a review. Bioinf (Oxford England). 2003;19(4):513\u201323. https:\/\/doi.org\/10.1093\/bioinformatics\/btg005.","journal-title":"Bioinf (Oxford England)"},{"issue":"1","key":"4258_CR24","doi-asserted-by":"publisher","first-page":"bbab340","DOI":"10.1093\/bib\/bbab340","volume":"23","author":"HC Yi","year":"2022","unstructured":"Yi HC, You ZH, Huang DS, Kwoh CK. Graph representation learning in bioinformatics: trends, methods and applications. Brief Bioinform. 2022;23(1):bbab340.","journal-title":"Brief Bioinform"},{"issue":"2","key":"4258_CR25","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.jtbi.2005.11.023","volume":"241","author":"C Li","year":"2006","unstructured":"Li C, Tang N, Wang J. Directed graphs of DNA sequences and their numerical characterization. J Theor Biol. 2006;241(2):173\u20137.","journal-title":"J Theor Biol"},{"issue":"2","key":"4258_CR26","first-page":"445","volume":"65","author":"PA He","year":"2011","unstructured":"He PA, Li XF, Yang JL, Wang J. A novel descriptor for protein similarity analysis. MATCH Commun Math Comput Chem. 2011;65(2):445\u201358.","journal-title":"MATCH Commun Math Comput Chem"},{"issue":"12","key":"4258_CR27","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1002\/qua.22709","volume":"111","author":"JF Yu","year":"2011","unstructured":"Yu JF, Sun X, Wang JH. A novel 2D graphical representation of protein sequence based on individual amino acid. Int J Quantum Chem. 2011;111(12):2835\u201343.","journal-title":"Int J Quantum Chem"},{"issue":"1","key":"4258_CR28","first-page":"451","volume":"70","author":"YX Liu","year":"2013","unstructured":"Liu YX, Li D, Lu K, Jiao YD, He PA. P\u2013H curve, a graphical representation of protein sequences for similarities analysis. MATCH Commun Math Comput Chem. 2013;70(1):451\u201366.","journal-title":"MATCH Commun Math Comput Chem"},{"issue":"1","key":"4258_CR29","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.jtbi.2010.08.007","volume":"267","author":"ZC Wu","year":"2010","unstructured":"Wu ZC, Xiao X, Chou KC. 2D-MH: A web-server for generating graphic representation of protein sequences based on the physicochemical properties of their constituent amino acids. J Theor Biol. 2010;267(1):29\u201334.","journal-title":"J Theor Biol"},{"key":"4258_CR30","doi-asserted-by":"crossref","unstructured":"Ma T, Liu Y, Dai Q, Yao Y, He PA. (2014). A graphical representation of protein based on a novel iterated function system. Physica A: Statistical Mechanics and its Applications, 403, 21\u201328.","DOI":"10.1016\/j.physa.2014.01.067"},{"issue":"5","key":"4258_CR31","doi-asserted-by":"publisher","first-page":"539","DOI":"10.2174\/1574893611308050003","volume":"8","author":"G Huang","year":"2013","unstructured":"Huang G, Hu J. Similarity\/dissimilarity analysis of protein sequences by a new graphical representation. Curr Bioinform. 2013;8(5):539\u201344.","journal-title":"Curr Bioinform"},{"key":"4258_CR32","first-page":"213","volume":"71","author":"Z Li","year":"2014","unstructured":"Li Z, Geng C, He P, Yao Y. A novel method of 3D graphical representation and similarity analysis for proteins. MATCH Commun Math ComputChem. 2014;71:213\u201326.","journal-title":"MATCH Commun Math ComputChem"},{"key":"4258_CR33","doi-asserted-by":"crossref","unstructured":"Ao C, Jiao S, Wang Y, Yu L, Zou Q. (2022). Biological sequence classification: A review on data and general methods. Research, 2022, 0011.","DOI":"10.34133\/research.0011"},{"issue":"2","key":"4258_CR34","doi-asserted-by":"publisher","first-page":"100","DOI":"10.2174\/1386207321666180130100838","volume":"21","author":"C Li","year":"2018","unstructured":"Li C, Zhao J, Wang C, Yao Y. Protein sequence comparison and DNA-binding protein identification with generalized PseAAC and graphical representation. Comb Chem High Throughput Screen. 2018;21(2):100\u201310.","journal-title":"Comb Chem High Throughput Screen"},{"issue":"22","key":"4258_CR35","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1002\/qua.24479","volume":"113","author":"M Randi\u0107","year":"2013","unstructured":"Randi\u0107 M, Novi\u010d M, Plav\u0161i\u0107 D. Milestones in graphical bioinformatics. Int J Quantum Chem. 2013;113(22):2413\u201346.","journal-title":"Int J Quantum Chem"},{"issue":"1\u20132","key":"4258_CR36","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/S0009-2614(03)00244-6","volume":"371","author":"M Randi\u0107","year":"2003","unstructured":"Randi\u0107 M, Vra\u010dko M, Ler\u0161 N, Plav\u0161i\u0107 D. Analysis of similarity\/dissimilarity of DNA sequences based on novel 2-D graphical representation. Chem Phys Lett. 2003;371(1\u20132):202\u20137.","journal-title":"Chem Phys Lett"},{"issue":"5\u20136","key":"4258_CR37","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1080\/1062936X.2010.510481","volume":"21","author":"P He","year":"2010","unstructured":"He P. A new graphical representation of similarity\/dissimilarity studies of protein sequences. SAR QSAR Environ Res. 2010;21(5\u20136):571\u201380.","journal-title":"SAR QSAR Environ Res"},{"issue":"5","key":"4258_CR38","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1021\/ci000034q","volume":"40","author":"M Randi\u0107","year":"2000","unstructured":"Randi\u0107 M, Vracko M, Nandy A, Basak SC. On 3-D graphical representation of DNA primary sequences and their numerical characterization. J Chem Inf Comput Sci. 2000;40(5):1235\u201344.","journal-title":"J Chem Inf Comput Sci"},{"issue":"11","key":"4258_CR39","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1002\/jcc.20060","volume":"25","author":"B Liao","year":"2004","unstructured":"Liao B, Wang TM. New 2D graphical representation of DNA sequences. J Comput Chem. 2004;25(11):1364\u20138.","journal-title":"J Comput Chem"},{"issue":"12","key":"4258_CR40","doi-asserted-by":"publisher","first-page":"406","DOI":"10.3390\/app6120406","volume":"6","author":"C Li","year":"2016","unstructured":"Li C, Li X, Lin YX. Numerical characterization of protein sequences based on the generalized chou\u2019s Pseudo amino acid composition. Appl Sci. 2016;6(12):406.","journal-title":"Appl Sci"},{"issue":"3","key":"4258_CR41","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.jtbi.2003.09.009","volume":"226","author":"ZG Yu","year":"2004","unstructured":"Yu ZG, Anh V, Lau KS. Chaos game representation of protein sequences based on the detailed HP model and their multifractal and correlation analyses. J Theor Biol. 2004;226(3):341\u20138.","journal-title":"J Theor Biol"},{"key":"4258_CR42","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1016\/j.csbj.2020.07.004","volume":"18","author":"Z Sun","year":"2020","unstructured":"Sun Z, Pei S, He RL, Yau SST. A novel numerical representation for proteins: three-dimensional chaos game representation and its extended natural vector. Comput Struct Biotechnol J. 2020;18:1904\u201313.","journal-title":"Comput Struct Biotechnol J"},{"issue":"6","key":"4258_CR43","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1002\/qua.25068","volume":"116","author":"PA He","year":"2016","unstructured":"He PA, Xu S, Dai Q, Yao Y. A generalization of CGR representation for analyzing and comparing protein sequences. Int J Quantum Chem. 2016;116(6):476\u201382.","journal-title":"Int J Quantum Chem"},{"key":"4258_CR44","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.jtbi.2014.01.001","volume":"347","author":"Y Yao","year":"2014","unstructured":"Yao Y, Yan S, Han J, Dai Q, He PA. A novel descriptor of protein sequences and its application. J Theor Biol. 2014;347:109\u201317.","journal-title":"J Theor Biol"},{"issue":"5","key":"4258_CR45","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/S1093-3263(97)00106-X","volume":"15","author":"S Basu","year":"1997","unstructured":"Basu S, Pan A, Dutta C, Das J. Chaos game representation of proteins. J Mol Graph Model. 1997;15(5):279\u201389.","journal-title":"J Mol Graph Model"},{"issue":"3","key":"4258_CR46","doi-asserted-by":"publisher","first-page":"217","DOI":"10.5483\/BMBRep.2008.41.3.217","volume":"41","author":"C Li","year":"2008","unstructured":"Li C, Xing L, Wang X. 2-D graphical representation of protein sequences and its application to coronavirus phylogeny. BMB Rep. 2008;41(3):217\u201322.","journal-title":"BMB Rep"},{"key":"4258_CR47","doi-asserted-by":"crossref","unstructured":"Yu JF, Qu A, Tang HC, Wang FH, Wang CL, Wang HM, Zhu HQ. (2019). A novel numerical model for protein sequences analysis based on spherical coordinates and multiple physicochemical properties of amino acids. Biopolymers, 110(8), e23282.","DOI":"10.1002\/bip.23282"},{"issue":"17","key":"4258_CR48","doi-asserted-by":"publisher","first-page":"9341","DOI":"10.1007\/s00500-024-09834-5","volume":"28","author":"L Hooshyar","year":"2024","unstructured":"Hooshyar L, Hern\u00e1ndez-Jim\u00e9nez MB, Khastan A, Vasighi M. An efficient and accurate approach to identify similarities between biological sequences using pair amino acid composition and physicochemical properties. Soft Comput. 2024;28(17):9341\u201357.","journal-title":"Soft Comput"},{"key":"4258_CR49","doi-asserted-by":"publisher","unstructured":"Pal D, Dey S, Ghosh P, Das S, Maji B. (2023, June). A New Method for Protein Sequence Comparison Using Chaos Game Representation. In International Conference on Data Analytics & Management (pp. 389\u2013397). Singapore: Springer Nature Singapore. https:\/\/doi.org\/10.1007\/978-981-99-6553-3_30","DOI":"10.1007\/978-981-99-6553-3_30"},{"issue":"5","key":"4258_CR50","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.ygeno.2017.11.003","volume":"110","author":"S Das","year":"2018","unstructured":"Das S, Deb T, Dey N, Ashour AS, Bhattacharya DK, Tibarewala DN. Optimal choice of k-mer in composition vector method for genome sequence comparison. Genomics. 2018;110(5):263\u201373.","journal-title":"Genomics"},{"issue":"12","key":"4258_CR51","doi-asserted-by":"publisher","first-page":"6425","DOI":"10.1080\/07391102.2023.2268719","volume":"42","author":"S Ghosh","year":"2023","unstructured":"Ghosh S, Pal J, Cattani C, Maji B, Bhattacharya DK. Protein sequence comparison based on representation on a finite dimensional unit hypercube. J Biomol Struct Dynamics. 2023;42(12):6425\u201339. https:\/\/doi.org\/10.1080\/07391102.2023.2268719.","journal-title":"J Biomol Struct Dynamics"},{"key":"4258_CR52","doi-asserted-by":"publisher","first-page":"204201882210866","DOI":"10.1177\/20420188221086693","volume":"13","author":"AS Abdalrada","year":"2022","unstructured":"Abdalrada AS, Abawajy J, Al-Quraishi T, Islam SMS. Prediction of cardiac autonomic neuropathy using a machine learning model in patients with diabetes. Therapeutic Adv Endocrinol Metabolism. 2022;13:20420188221086693.","journal-title":"Therapeutic Adv Endocrinol Metabolism"},{"issue":"1","key":"4258_CR53","doi-asserted-by":"publisher","first-page":"008","DOI":"10.29328\/journal.jgmgt.1001010","volume":"7","author":"DK Bhattacharya","year":"2024","unstructured":"Bhattacharya DK. A critical review on some recent developments in comparison of biological sequences. J Genetic Med Gene Therapy. 2024;7(1):008\u201314. https:\/\/doi.org\/10.29328\/journal.jgmgt.1001010.","journal-title":"J Genetic Med Gene Therapy"},{"issue":"12","key":"4258_CR54","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.3390\/genes11121431","volume":"11","author":"V Singh","year":"2020","unstructured":"Singh V, Sharma A, Dehzangi A, Tsunoda T. PupStruct: prediction of pupylated lysine residues using structural properties of amino acids. Genes. 2020;11(12):1431.","journal-title":"Genes"},{"issue":"8","key":"4258_CR55","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1109\/TNB.2015.2500186","volume":"14","author":"R Sharma","year":"2015","unstructured":"Sharma R, Dehzangi A, Lyons J, Paliwal K, Tsunoda T, Sharma A. Predict gram-positive and gram-negative subcellular localization via incorporating evolutionary information and physicochemical features into chou\u2019s general PseAAC. IEEE Trans Nanobiosci. 2015;14(8):915\u201326.","journal-title":"IEEE Trans Nanobiosci"},{"key":"4258_CR56","doi-asserted-by":"publisher","first-page":"107494","DOI":"10.1016\/j.compbiolchem.2021.107494","volume":"92","author":"ST Sara","year":"2021","unstructured":"Sara ST, Hasan MM, Ahmad A, Shatabda S. Convolutional neural networks with image representation of amino acid sequences for protein function prediction. Comput Biol Chem. 2021;92:107494.","journal-title":"Comput Biol Chem"},{"issue":"W1","key":"4258_CR57","doi-asserted-by":"publisher","first-page":"W78","DOI":"10.1093\/nar\/gkae268","volume":"52","author":"I Letunic","year":"2024","unstructured":"Letunic I, Bork P. Interactive tree of life (iTOL) v6: recent updates to the phylogenetic tree display and annotation tool. Nucleic Acids Res. 2024;52(W1):W78\u201382.","journal-title":"Nucleic Acids Res"},{"issue":"1\u20132","key":"4258_CR58","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.gene.2011.07.002","volume":"486","author":"C Yu","year":"2011","unstructured":"Yu C, Cheng SY, He RL, Yau SST. Protein map: an alignment-free sequence comparison method based on various properties of amino acids. Gene. 2011;486(1\u20132):110\u20138.","journal-title":"Gene"},{"issue":"1","key":"4258_CR59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-016-0028-x","volume":"7","author":"L Yu","year":"2017","unstructured":"Yu L, Zhang Y, Gutman I, Shi Y, Dehmer M. Protein sequence comparison based on physicochemical properties and the position-feature energy matrix. Sci Rep. 2017;7(1):1\u20139.","journal-title":"Sci Rep"},{"key":"4258_CR60","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.jtbi.2016.06.034","volume":"406","author":"C Xu","year":"2016","unstructured":"Xu C, Sun D, Liu S, Zhang Y. Protein sequence analysis by incorporating modified chaos game and physicochemical properties into chou\u2019s general Pseudo amino acid composition. J Theor Biol. 2016;406:105\u201315.","journal-title":"J Theor Biol"},{"issue":"5","key":"4258_CR61","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1089\/dna.2007.0676","volume":"27","author":"SST Yau","year":"2008","unstructured":"Yau SST, Yu C, He R. A protein map and its application. DNA Cell Biol. 2008;27(5):241\u201350.","journal-title":"DNA Cell Biol"},{"key":"4258_CR62","doi-asserted-by":"crossref","unstructured":"Yu C, He RL, Stephen S-T, Yau. (2013). Protein sequence comparison based on K-string dictionary. Gene 529.2 (2013): 250\u2013256.","DOI":"10.1016\/j.gene.2013.07.092"},{"key":"4258_CR63","doi-asserted-by":"publisher","unstructured":"Czerniecka, A., Bieli\u0144ska-W\u0105\u017c, D., W\u0105\u017c, P., & Clark, T. (2016). 20D-dynamic representation of protein sequences. Genomics, 107(1), 16\u201323. https:\/\/doi.org\/10.1016\/j.ygeno.2015.12.003.","DOI":"10.1016\/j.ygeno.2015.12.003"},{"issue":"1\u20133","key":"4258_CR64","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.cplett.2005.06.005","volume":"411","author":"Y Zhang","year":"2005","unstructured":"Zhang Y, Liao B, Ding K. On 2D graphical representation of DNA sequence of nondegeneracy. Chem Phys Lett. 2005;411(1\u20133):28\u201332.","journal-title":"Chem Phys Lett"},{"issue":"6","key":"4258_CR65","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1021\/ci500577m","volume":"55","author":"JF Yu","year":"2015","unstructured":"Yu JF, Dou XH, Wang HB, Sun X, Zhao HY, Wang JH. A novel cylindrical representation for characterizing intrinsic properties of protein sequences. J Chem Inf Model. 2015;55(6):1261\u201370.","journal-title":"J Chem Inf Model"},{"key":"4258_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04223-3","volume":"22","author":"Z Mu","year":"2021","unstructured":"Mu Z, Yu T, Liu X, Zheng H, Wei L, Liu J. FEGS: a novel feature extraction model for protein sequences and its applications. BMC Bioinformatics. 2021;22:1\u201315.","journal-title":"BMC Bioinformatics"},{"key":"4258_CR67","doi-asserted-by":"publisher","first-page":"107284","DOI":"10.1016\/j.compbiolchem.2020.107284","volume":"87","author":"M Hayati","year":"2020","unstructured":"Hayati M, Chindelevitch L. Computing the distribution of the Robinson-Foulds distance. Comput Biol Chem. 2020;87:107284.","journal-title":"Comput Biol Chem"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04258-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04258-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04258-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T21:26:38Z","timestamp":1757366798000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04258-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":67,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["4258"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04258-w","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,6]]},"assertion":[{"value":"4 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original online version of this article was revised due to city name \"Durgapur\" was incorrectly published in the affiliation 2. Now, the city name has been corrected to Kolkata from Durgapur.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research Involving Human and \/or Animals"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"722"}}