Fast Statistical Alignment Export

@article{citeulike:4674821, abstract = {We describe a new program for the alignment of multiple biological sequences that is both statistically motivated and fast enough for problem sizes that arise in practice. Our F ast S tatistical A lignment program is based on pair hidden Markov models which approximate an insertion/deletion process on a tree and uses a sequence annealing algorithm to combine the posterior probabilities estimated from these models into a multiple alignment. FSA uses its explicit statistical model to produce multiple alignments which are accompanied by estimates of the alignment accuracy and uncertainty for every column and character of the alignment\^{a}€”previously available only with alignment programs which use computationally-expensive Markov Chain Monte Carlo approaches\^{a}€”yet can align thousands of long sequences. Moreover, FSA utilizes an unsupervised query-specific learning procedure for parameter estimation which leads to improved accuracy on benchmark reference alignments in comparison to existing programs. The centroid alignment approach taken by FSA, in combination with its learning procedure, drastically reduces the amount of false-positive alignment on biological data in comparison to that given by other methods. The FSA program and a companion visualization tool for exploring uncertainty in alignments can be used via a web interface at http://orangutan.math.berkeley.edu/fsa/ , and the source code is available at http://fsa.sourceforge.net/ .}, author = {Bradley, Robert K. and Roberts, Adam and Smoot, Michael and Juvekar, Sudeep and Do, Jaeyoung and Dewey, Colin and Holmes, Ian and Pachter, Lior}, citeulike-article-id = {4674821}, citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pcbi.1000392}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19478997}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19478997}, day = {29}, doi = {10.1371/journal.pcbi.1000392}, issn = {1553-7358}, journal = {PLoS Comput Biol}, keywords = {alignment, berkeley, fsa, good-stuff, pachter}, month = {May}, number = {5}, pages = {e1000392+}, posted-at = {2009-11-07 22:26:02}, priority = {2}, publisher = {Public Library of Science}, title = {Fast Statistical Alignment}, url = {http://dx.doi.org/10.1371/journal.pcbi.1000392}, volume = {5}, year = {2009} }

TY - JOUR ID - citeulike:4674821 L3 - citeulike-article-id:4674821 N2 - We describe a new program for the alignment of multiple biological sequences that is both statistically motivated and fast enough for problem sizes that arise in practice. Our F ast S tatistical A lignment program is based on pair hidden Markov models which approximate an insertion/deletion process on a tree and uses a sequence annealing algorithm to combine the posterior probabilities estimated from these models into a multiple alignment. FSA uses its explicit statistical model to produce multiple alignments which are accompanied by estimates of the alignment accuracy and uncertainty for every column and character of the alignment—previously available only with alignment programs which use computationally-expensive Markov Chain Monte Carlo approaches—yet can align thousands of long sequences. Moreover, FSA utilizes an unsupervised query-specific learning procedure for parameter estimation which leads to improved accuracy on benchmark reference alignments in comparison to existing programs. The centroid alignment approach taken by FSA, in combination with its learning procedure, drastically reduces the amount of false-positive alignment on biological data in comparison to that given by other methods. The FSA program and a companion visualization tool for exploring uncertainty in alignments can be used via a web interface at http://orangutan.math.berkeley.edu/fsa/ , and the source code is available at http://fsa.sourceforge.net/ . IS - 5 JF - PLoS Comput Biol SN - 1553-7358 TI - Fast Statistical Alignment PB - Public Library of Science VL - 5 SP - e1000392 KW - alignment KW - berkeley KW - fsa KW - good-stuff KW - pachter AU - Bradley, Robert AU - Roberts, Adam AU - Smoot, Michael AU - Juvekar, Sudeep AU - Do, Jaeyoung AU - Dewey, Colin AU - Holmes, Ian AU - Pachter, Lior PY - 2009/05/29/ UR - http://dx.doi.org/10.1371/journal.pcbi.1000392 ER -