{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T05:24:38Z","timestamp":1769837078508,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,2,5]],"date-time":"2019-02-05T00:00:00Z","timestamp":1549324800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PD\/BD\/113969\/2015"],"award-info":[{"award-number":["PD\/BD\/113969\/2015"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PTCD\/EEI-SII\/6608\/2014"],"award-info":[{"award-number":["PTCD\/EEI-SII\/6608\/2014"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UID\/CEC\/00127\/2013"],"award-info":[{"award-number":["UID\/CEC\/00127\/2013"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Programa Operacional Factores de Competitividade \u2013 COMPETE"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Interdiscip Sci Comput Life Sci"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s12539-019-00322-1","type":"journal-article","created":{"date-parts":[[2019,2,5]],"date-time":"2019-02-05T04:18:42Z","timestamp":1549340322000},"page":"68-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["AC: A Compression Tool for Amino Acid Sequences"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8962-8985","authenticated-orcid":false,"given":"Morteza","family":"Hosseini","sequence":"first","affiliation":[]},{"given":"Diogo","family":"Pratas","sequence":"additional","affiliation":[]},{"given":"Armando J.","family":"Pinho","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,5]]},"reference":[{"key":"322_CR1","unstructured":"Cao MD, Dix TI, Allison L, Mears C (2007) A simple statistical algorithm for biological sequence compression. In: Proceedings of DCC \u201907: data compression conference, IEEE Computer Society Washington, DC, USA, March 27\u2013 29, 2007, Snowbird, Utah"},{"key":"322_CR2","doi-asserted-by":"publisher","first-page":"46","DOI":"10.9790\/0661-1054651","volume":"10","author":"S Rafizul Haque","year":"2013","unstructured":"Rafizul Haque S, Mallick T, Kabir I (2013) A new approach of protein sequence compression using repeat reduction and ASCII replacement. IOSR J Comput Eng (IOSR-JCE) 10:46\u201351","journal-title":"IOSR J Comput Eng (IOSR-JCE)"},{"key":"322_CR3","volume-title":"Virtual organisms: the startling world of artificial life","author":"M Ward","year":"2014","unstructured":"Ward M (2014) Virtual organisms: the startling world of artificial life. Macmillan, London"},{"key":"322_CR4","doi-asserted-by":"crossref","unstructured":"Baker MS, Ahn SB, Mohamedali A, Islam MT, Cantor D, Verhaert PD, Fanayan S, Sharma S, Nice EC, Connor M et\u00a0al (2017) Accelerating the search for the missing proteins in the human proteome. Nat Commun 8:14271","DOI":"10.1038\/ncomms14271"},{"key":"322_CR5","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.biochi.2015.10.018","volume":"122","author":"U Eckhard","year":"2016","unstructured":"Eckhard U, Marino G, Butler GS, Overall CM (2016) Positional proteomics in the era of the human proteome project on the doorstep of precision medicine. Biochimie 122:110\u2013118","journal-title":"Biochimie"},{"key":"322_CR6","unstructured":"Legrain P, Aebersold R, Archakov A, Bairoch A, Bala K, Beretta L, Bergeron J, Borchers CH, Corthals GL, Costello CE et\u00a0al (2011) The human proteome project: current state and future direction. Mol Cell Proteom 10(7):M111\u2013009993"},{"issue":"3","key":"322_CR7","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1038\/nbt.2152","volume":"30","author":"YK Paik","year":"2012","unstructured":"Paik YK, Jeong SK, Omenn GS, Uhlen M, Hanash S, Cho SY, Lee HJ, Na K, Choi EY, Yan F (2012) The chromosome-centric human proteome project for cataloging proteins encoded in the genome. Nat Biotechnol 30(3):221","journal-title":"Nat Biotechnol"},{"issue":"8","key":"322_CR8","doi-asserted-by":"publisher","first-page":"2703","DOI":"10.1021\/bi00848a001","volume":"7","author":"IUPAC-IUB Comm","year":"1968","unstructured":"Comm IUPAC-IUB (1968) A one-letter notation for amino acid sequences. Tentative rules. Biochemistry 7(8):2703\u20132705","journal-title":"Biochemistry"},{"issue":"D1","key":"322_CR9","first-page":"D158","volume":"45","author":"U Consortium","year":"2016","unstructured":"Consortium U (2016) UniProt: the universal protein knowledgebase. Nucleic Acids Res 45(D1):D158\u2013D169","journal-title":"Nucleic Acids Res"},{"key":"322_CR10","unstructured":"Pratas D, Hosseini M, Pinho AJ (2018) Compression of amino acid sequences. In: Fdez-Riverola F, Mohamad M, Rocha M, De Paz J, Pinto T (eds) 11th International Conference on Practical Applications of Computational Biology & Bioinformatics. PACBB 2017. Advances in Intelligent Systems and Computing, vol 616. Springer, Cham"},{"key":"322_CR11","first-page":"60723","volume":"2007","author":"D Benedetto","year":"2007","unstructured":"Benedetto D, Caglioti E, Chica C (2007) Compressing proteomes: the relevance of medium range correlations. Eur J Bioinform Syst Biol 2007:60723","journal-title":"Eur J Bioinform Syst Biol"},{"issue":"1","key":"322_CR12","doi-asserted-by":"publisher","first-page":"34","DOI":"10.3390\/e12010034","volume":"12","author":"\u00d6U Nalbantoglu","year":"2009","unstructured":"Nalbantoglu \u00d6U, Russell DJ, Sayood K (2009) Data compression concepts and algorithms and their applications to bioinformatics. Entropy 12(1):34\u201352","journal-title":"Entropy"},{"key":"322_CR13","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/0097-8485(94)85023-2","volume":"18","author":"J Wootton","year":"1994","unstructured":"Wootton J (1994) Non-globular domains in protein sequences: automated segmentation using complexity measures. Comput Chem 18:269\u2013285","journal-title":"Comput Chem"},{"key":"322_CR14","doi-asserted-by":"publisher","first-page":"2949","DOI":"10.1007\/s00018-016-2138-9","volume":"73","author":"J Yu","year":"2016","unstructured":"Yu J, Cao Z, Yang Y, Wang C, Su Z, Zhao Y, Wang J, Zhou Y (2016) Natural protein sequences are more intrinsically disordered than random sequences. Cell Mol Life Sci 73:2949\u20132957","journal-title":"Cell Mol Life Sci"},{"key":"322_CR15","doi-asserted-by":"crossref","unstructured":"Nevill-Manning CG, Witten IH (1999) Protein is incompressible. In: Proceedings of DCC \u201999: Data Compression Conference. IEEE Computer Society Washington, DC, USA, March 29\u201331, Snowbird, Utah, USA","DOI":"10.1109\/DCC.1999.755675"},{"key":"322_CR16","unstructured":"Adjeroh D, Nan F (2006) On compressibility of protein sequences. In: Proceedings of DCC \u201906: data compression conference,. IEEE Computer Society Washington, DC, March 28\u201330, Snowbird, Utah, USA"},{"key":"322_CR17","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1093\/bioinformatics\/bty619","volume":"35","author":"S Deorowicz","year":"2018","unstructured":"Deorowicz S, Walczyszyn J, Debudaj-Grabysz A, Hancock J (2018) Comsa: compression of protein multiple sequence alignment files. Bioinformatics 35:227\u2013234","journal-title":"Bioinformatics"},{"key":"322_CR18","unstructured":"Hategan A, Tabus I (2004) Protein is compressible. In: Signal Processing Symposium. NORSIG 2004. In: Proceedings of the 6th Nordic, 11 June 2004, IEEE, Espoo, Finland, Finland, pp 192\u2013195"},{"key":"322_CR19","first-page":"43","volume":"11","author":"T Matsumoto","year":"2000","unstructured":"Matsumoto T, Sadakane K, Imai H (2000) Biological sequence compression algorithms. Genome Inf 11:43\u201352","journal-title":"Genome Inf"},{"key":"322_CR20","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/18.382012","volume":"41","author":"F Willems","year":"1995","unstructured":"Willems F, Shtarkov Y, Tjalkens T (1995) The context tree weighting method: basic properties. IEEE Trans Inf Theory 41:653\u2013664","journal-title":"IEEE Trans Inf Theory"},{"key":"322_CR21","unstructured":"Burrows M, Wheeler DJ (1994) A block-sorting lossless data compression algorithm. Technical Report, Digital Equipment Corporation, Palo Alto, CA"},{"key":"#cr-split#-322_CR22.1","unstructured":"Adjeroh D, Feng J (2003) The SCP and compressed domain analysis of biological sequences. In: Computational Systems Bioinformatics Conference, International IEEE Computer Society (2003)"},{"key":"#cr-split#-322_CR22.2","unstructured":"Stanford, California, Aug 11-14 2003"},{"issue":"4","key":"322_CR23","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/info7040056","volume":"7","author":"M Hosseini","year":"2016","unstructured":"Hosseini M, Pratas D, Pinho AJ (2016) A survey on data compression methods for biological sequences. Information 7(4):56","journal-title":"Information"},{"issue":"15","key":"322_CR24","doi-asserted-by":"publisher","first-page":"7176","DOI":"10.1073\/pnas.90.15.7176","volume":"90","author":"B Korber","year":"1993","unstructured":"Korber B, Farber RM, Wolpert DH, Lapedes AS (1993) Covariation of mutations in the v3 loop of human immunodeficiency virus type 1 envelope protein: an information theoretic analysis. Proc Natl Acad Sci 90(15):7176\u20137180","journal-title":"Proc Natl Acad Sci"},{"key":"322_CR25","doi-asserted-by":"publisher","first-page":"38,383","DOI":"10.1038\/srep38383","volume":"6","author":"F Pereira","year":"2016","unstructured":"Pereira F, Duarte-Pereira S, Silva RM, Da Costa LT, Pereira-Castro I (2016) Evolution of the NET (NocA, Nlz, Elbow, TLP-1) protein family in metazoans: insights from expression data and phylogenetic analysis. Sci Rep 6:38,383","journal-title":"Sci Rep"},{"issue":"3","key":"322_CR26","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1016\/j.ymeth.2014.01.012","volume":"67","author":"M Hayashida","year":"2014","unstructured":"Hayashida M, Ruan P, Akutsu T (2014) Proteome compression via protein domain compositions. Methods 67(3):380\u2013385","journal-title":"Methods"},{"key":"322_CR27","unstructured":"Pelta DA, Gonzalez JR, Krasnogor N (2005) Protein structure comparison through fuzzy contact maps and the universal similarity metric. In: EUSFLAT Conf., pp 1124\u20131129"},{"key":"322_CR28","unstructured":"Rocha J, Rossell\u00f3 F, Segura J (2006) Compression ratios based on the universal similarity metric still yield protein distances far from CATH distances. \n                    arXiv:q-bio\/0603007"},{"issue":"1","key":"322_CR29","first-page":"1","volume":"1","author":"AN Kolmogorov","year":"1965","unstructured":"Kolmogorov AN (1965) Three approaches to the quantitative definition of information. Probl Inf Transm 1(1):1\u20137","journal-title":"Probl Inf Transm"},{"key":"322_CR30","doi-asserted-by":"publisher","first-page":"7208216","DOI":"10.1155\/2017\/7208216","volume":"2017","author":"F Soler-Toscano","year":"2017","unstructured":"Soler-Toscano F, Zenil H (2017) A computable measure of algorithmic probability by finite approximations with an application to integer sequences. Complexity 2017:7208216","journal-title":"Complexity"},{"issue":"8","key":"322_CR31","doi-asserted-by":"publisher","first-page":"605","DOI":"10.3390\/e20080605","volume":"20","author":"H Zenil","year":"2018","unstructured":"Zenil H, Hern\u00e1ndez-Orozco S, Kiani N, Soler-Toscano F, Rueda-Toicen A, Tegn\u00e9r J (2018) A decomposition method for global evaluation of Shannon entropy and local estimations of algorithmic complexity. Entropy 20(8):605","journal-title":"Entropy"},{"issue":"1","key":"322_CR32","doi-asserted-by":"publisher","first-page":"1850,005","DOI":"10.1142\/S0129626418500056","volume":"28","author":"H Zenil","year":"2018","unstructured":"Zenil H, Kiani NA, Shang MM, Tegn\u00e9r J (2018) Algorithmic complexity and reprogrammability of chemical structure networks. Parallel Process Lett 28(1):1850,005","journal-title":"Parallel Process Lett"},{"issue":"6","key":"322_CR33","doi-asserted-by":"publisher","first-page":"e21,588","DOI":"10.1371\/journal.pone.0021588","volume":"6","author":"AJ Pinho","year":"2011","unstructured":"Pinho AJ, Ferreira PJ, Neves AJ, Bastos CA (2011) On the representability of complete genomes by multiple competing finite-context (Markov) models. PLoS One 6(6):e21,588","journal-title":"PLoS One"},{"issue":"1","key":"322_CR34","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1093\/bioinformatics\/btt594","volume":"30","author":"AJ Pinho","year":"2013","unstructured":"Pinho AJ, Pratas D (2013) MFCompress: a compression tool for FASTA and multi-FASTA data. Bioinformatics 30(1):117\u2013118","journal-title":"Bioinformatics"},{"key":"322_CR35","doi-asserted-by":"crossref","unstructured":"Pratas D, Hosseini M, Pinho AJ (2017) Substitutional tolerant Markov models for relative compression of DNA sequences. In: International conference on practical applications of computational biology & bioinformatics (PACBB). Springer, pp 265\u2013272","DOI":"10.1007\/978-3-319-60816-7_32"},{"key":"322_CR36","doi-asserted-by":"crossref","unstructured":"Pratas D, Pinho AJ, Ferreira PJ (2016) Efficient compression of genomic sequences. In: Proceedings of DCC \u201916: data compression conference. IEEE Computer Society Washington, DC, USA, March 30, April 1, Snowbird, Utah,","DOI":"10.1109\/DCC.2016.60"},{"key":"322_CR37","volume-title":"Introduction to data compression","author":"K Sayood","year":"2017","unstructured":"Sayood K (2017) Introduction to data compression. Morgan Kaufmann, Burlington"},{"key":"322_CR38","doi-asserted-by":"publisher","first-page":"10,203","DOI":"10.1038\/srep10203","volume":"5","author":"D Pratas","year":"2015","unstructured":"Pratas D, Silva RM, Pinho AJ, Ferreira PJ (2015) An alignment-free method to find and visualise rearrangements between pairs of DNA sequences. Sci Rep 5:10,203","journal-title":"Sci Rep"},{"issue":"4","key":"322_CR39","doi-asserted-by":"publisher","first-page":"e0119306","DOI":"10.1371\/journal.pone.0119306","volume":"10","author":"RP Bywater","year":"2015","unstructured":"Bywater RP (2015) Prediction of protein structural features from sequence data based on Shannon entropy and Kolmogorov complexity. PLoS One 10(4):e0119306","journal-title":"PLoS One"},{"key":"322_CR40","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1093\/bioinformatics\/bty645","volume":"35","author":"M Hosseini","year":"2018","unstructured":"Hosseini M, Pratas D, Pinho AJ (2018) Cryfa: a secure encryption tool for genomic data. Bioinformatics 35:146\u2013148","journal-title":"Bioinformatics"},{"key":"322_CR41","doi-asserted-by":"crossref","unstructured":"Pratas D, Pinho AJ (2017) On the approximation of the Kolmogorov complexity for DNA sequences. In: Iberian conference on pattern recognition and image analysis\u00a0(IbPRIA), pp 259\u2013266. Springer","DOI":"10.1007\/978-3-319-58838-4_29"}],"container-title":["Interdisciplinary Sciences: Computational Life Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12539-019-00322-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12539-019-00322-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12539-019-00322-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T19:18:08Z","timestamp":1580843888000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12539-019-00322-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,5]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["322"],"URL":"https:\/\/doi.org\/10.1007\/s12539-019-00322-1","relation":{},"ISSN":["1913-2751","1867-1462"],"issn-type":[{"value":"1913-2751","type":"print"},{"value":"1867-1462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,5]]},"assertion":[{"value":"24 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}