Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets. Hughes, A., Ruan, Y., Ekanayake, S., Bae, S., S., Dong, Q., Rho, M., Qiu, J., & Fox, G., C. BMC bioinformatics, 13(2):S9, BioMed Central, 2012. abstract bibtex Modern pyrosequencing techniques make it possible to study complex bacterial populations, such as 16S rRNA, directly from environmental or clinical samples without the need for laboratory purification. Alignment of sequences across the resultant large data sets (100,000+ sequences) is of particular interest for the purpose of identifying potential gene clusters and families, but such analysis represents a daunting computational task. The aim of this work is the development of an efficient pipeline for the clustering of large sequence read sets. Pairwise alignment techniques are used here to calculate genetic distances between sequence pairs. These methods are pleasingly parallel and have been shown to more accurately reflect accurate genetic distances in highly variable regions of rRNA genes than do traditional multiple sequence alignment (MSA) approaches. By utilizing Needleman-Wunsch (NW) pairwise alignment in conjunction with novel implementations of interpolative multidimensional scaling (MDS), we have developed an effective method for visualizing massive biosequence data sets and quickly identifying potential gene clusters. This study demonstrates the use of interpolative MDS to obtain clustering results that are qualitatively similar to those obtained through full MDS, but with substantial cost savings. In particular, the wall clock time required to cluster a set of 100,000 sequences has been reduced from seven hours to less than one hour through the use of interpolative MDS. Although work remains to be done in selecting the optimal training set size for interpolative MDS, substantial computational cost savings will allow us to cluster much larger sequence sets in the future.
@article{
title = {Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets},
type = {article},
year = {2012},
pages = {S9},
volume = {13},
publisher = {BioMed Central},
id = {81adcba1-80d7-3f6e-8a03-9b5c6632e8c6},
created = {2018-01-09T20:30:37.141Z},
file_attached = {false},
profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
last_modified = {2020-05-11T14:43:45.443Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Hughes2012},
source_type = {JOUR},
folder_uuids = {36d8ccf4-7085-47fa-8ab9-897283d082c5},
private_publication = {false},
abstract = {Modern pyrosequencing techniques make it possible to study complex bacterial populations, such as 16S rRNA, directly from environmental or clinical samples without the need for laboratory purification. Alignment of sequences across the resultant large data sets (100,000+ sequences) is of particular interest for the purpose of identifying potential gene clusters and families, but such analysis represents a daunting computational task. The aim of this work is the development of an efficient pipeline for the clustering of large sequence read sets. Pairwise alignment techniques are used here to calculate genetic distances between sequence pairs. These methods are pleasingly parallel and have been shown to more accurately reflect accurate genetic distances in highly variable regions of rRNA genes than do traditional multiple sequence alignment (MSA) approaches. By utilizing Needleman-Wunsch (NW) pairwise alignment in conjunction with novel implementations of interpolative multidimensional scaling (MDS), we have developed an effective method for visualizing massive biosequence data sets and quickly identifying potential gene clusters. This study demonstrates the use of interpolative MDS to obtain clustering results that are qualitatively similar to those obtained through full MDS, but with substantial cost savings. In particular, the wall clock time required to cluster a set of 100,000 sequences has been reduced from seven hours to less than one hour through the use of interpolative MDS. Although work remains to be done in selecting the optimal training set size for interpolative MDS, substantial computational cost savings will allow us to cluster much larger sequence sets in the future.},
bibtype = {article},
author = {Hughes, Adam and Ruan, Yang and Ekanayake, Saliya and Bae, Seung-Hee S.H. and Dong, Qunfeng and Rho, Mina and Qiu, Judy and Fox, Geoffrey Charles},
journal = {BMC bioinformatics},
number = {2}
}
Downloads: 0
{"_id":"5gEqaC9h6Rddzstp2","bibbaseid":"hughes-ruan-ekanayake-bae-dong-rho-qiu-fox-interpolativemultidimensionalscalingtechniquesfortheidentificationofclustersinverylargesequencesets-2012","downloads":0,"creationDate":"2018-03-12T19:10:28.081Z","title":"Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets","author_short":["Hughes, A.","Ruan, Y.","Ekanayake, S.","Bae, S., S.","Dong, Q.","Rho, M.","Qiu, J.","Fox, G., C."],"year":2012,"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibdata":{"title":"Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets","type":"article","year":"2012","pages":"S9","volume":"13","publisher":"BioMed Central","id":"81adcba1-80d7-3f6e-8a03-9b5c6632e8c6","created":"2018-01-09T20:30:37.141Z","file_attached":false,"profile_id":"42d295c0-0737-38d6-8b43-508cab6ea85d","last_modified":"2020-05-11T14:43:45.443Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Hughes2012","source_type":"JOUR","folder_uuids":"36d8ccf4-7085-47fa-8ab9-897283d082c5","private_publication":false,"abstract":"Modern pyrosequencing techniques make it possible to study complex bacterial populations, such as 16S rRNA, directly from environmental or clinical samples without the need for laboratory purification. Alignment of sequences across the resultant large data sets (100,000+ sequences) is of particular interest for the purpose of identifying potential gene clusters and families, but such analysis represents a daunting computational task. The aim of this work is the development of an efficient pipeline for the clustering of large sequence read sets. Pairwise alignment techniques are used here to calculate genetic distances between sequence pairs. These methods are pleasingly parallel and have been shown to more accurately reflect accurate genetic distances in highly variable regions of rRNA genes than do traditional multiple sequence alignment (MSA) approaches. By utilizing Needleman-Wunsch (NW) pairwise alignment in conjunction with novel implementations of interpolative multidimensional scaling (MDS), we have developed an effective method for visualizing massive biosequence data sets and quickly identifying potential gene clusters. This study demonstrates the use of interpolative MDS to obtain clustering results that are qualitatively similar to those obtained through full MDS, but with substantial cost savings. In particular, the wall clock time required to cluster a set of 100,000 sequences has been reduced from seven hours to less than one hour through the use of interpolative MDS. Although work remains to be done in selecting the optimal training set size for interpolative MDS, substantial computational cost savings will allow us to cluster much larger sequence sets in the future.","bibtype":"article","author":"Hughes, Adam and Ruan, Yang and Ekanayake, Saliya and Bae, Seung-Hee S.H. and Dong, Qunfeng and Rho, Mina and Qiu, Judy and Fox, Geoffrey Charles","journal":"BMC bioinformatics","number":"2","bibtex":"@article{\n title = {Interpolative multidimensional scaling techniques for the identification of clusters in very large sequence sets},\n type = {article},\n year = {2012},\n pages = {S9},\n volume = {13},\n publisher = {BioMed Central},\n id = {81adcba1-80d7-3f6e-8a03-9b5c6632e8c6},\n created = {2018-01-09T20:30:37.141Z},\n file_attached = {false},\n profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},\n last_modified = {2020-05-11T14:43:45.443Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Hughes2012},\n source_type = {JOUR},\n folder_uuids = {36d8ccf4-7085-47fa-8ab9-897283d082c5},\n private_publication = {false},\n abstract = {Modern pyrosequencing techniques make it possible to study complex bacterial populations, such as 16S rRNA, directly from environmental or clinical samples without the need for laboratory purification. Alignment of sequences across the resultant large data sets (100,000+ sequences) is of particular interest for the purpose of identifying potential gene clusters and families, but such analysis represents a daunting computational task. The aim of this work is the development of an efficient pipeline for the clustering of large sequence read sets. Pairwise alignment techniques are used here to calculate genetic distances between sequence pairs. These methods are pleasingly parallel and have been shown to more accurately reflect accurate genetic distances in highly variable regions of rRNA genes than do traditional multiple sequence alignment (MSA) approaches. By utilizing Needleman-Wunsch (NW) pairwise alignment in conjunction with novel implementations of interpolative multidimensional scaling (MDS), we have developed an effective method for visualizing massive biosequence data sets and quickly identifying potential gene clusters. This study demonstrates the use of interpolative MDS to obtain clustering results that are qualitatively similar to those obtained through full MDS, but with substantial cost savings. In particular, the wall clock time required to cluster a set of 100,000 sequences has been reduced from seven hours to less than one hour through the use of interpolative MDS. Although work remains to be done in selecting the optimal training set size for interpolative MDS, substantial computational cost savings will allow us to cluster much larger sequence sets in the future.},\n bibtype = {article},\n author = {Hughes, Adam and Ruan, Yang and Ekanayake, Saliya and Bae, Seung-Hee S.H. and Dong, Qunfeng and Rho, Mina and Qiu, Judy and Fox, Geoffrey Charles},\n journal = {BMC bioinformatics},\n number = {2}\n}","author_short":["Hughes, A.","Ruan, Y.","Ekanayake, S.","Bae, S., S.","Dong, Q.","Rho, M.","Qiu, J.","Fox, G., C."],"biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibbaseid":"hughes-ruan-ekanayake-bae-dong-rho-qiu-fox-interpolativemultidimensionalscalingtechniquesfortheidentificationofclustersinverylargesequencesets-2012","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["interpolative","multidimensional","scaling","techniques","identification","clusters","very","large","sequence","sets","hughes","ruan","ekanayake","bae","dong","rho","qiu","fox"],"keywords":[],"authorIDs":[],"dataSources":["zgahneP4uAjKbudrQ","ya2CyA73rpZseyrZ8"]}