CQAPaper.bib

%% This BibTeX bibliography file was created using BibDesk.
%% http://bibdesk.sourceforge.net/


%% Created for Paul Edlefsen at 2015-10-23 13:42:42 +0200 


%% Saved with string encoding Unicode (UTF-8) 



@article{Rumelhart:1986,
	Author = {Rumelhart, D.E. and Hintont, G.E. and Williams, R.J.},
	Date-Added = {2011-05-01 17:33:41 -0700},
	Date-Modified = {2011-05-01 17:34:07 -0700},
	Issn = {0028-0836},
	Journal = {Nature},
	Number = {6088},
	Pages = {533--536},
	Title = {{Learning representations by back-propagating errors}},
	Volume = {323},
	Year = {1986}}

@article{Mamitsuka:1998,
	Author = {Mamitsuka, H.},
	Date-Added = {2011-05-01 17:13:48 -0700},
	Date-Modified = {2011-05-01 17:14:14 -0700},
	Issn = {0887-3585},
	Journal = {Proteins Structure Function and Genetics},
	Number = {4},
	Pages = {460--474},
	Title = {{Predicting peptides that bind to MHC molecules using supervised learning of hidden Markov models}},
	Volume = {33},
	Year = {1998}}

@article{Baldi:1994,
	Abstract = {Hidden Markov model (HMM) techniques are used to model families of biological sequences. A smooth and convergent algorithm is introduced to iteratively adapt the transition and emission parameters of the models from the examples in a given family. The HMM approach is applied to three protein families: globins, immunoglobulins, and kinases. In all cases, the models derived capture the important statistical characteristics of the family and can be used for a number of tasks, including multiple alignments, motif detection, and classification. For K sequences of average length N, this approach yields an effective multiple-alignment algorithm which requires O(KN2) operations, linear in the number of sequences.},
	Author = {Baldi, P and Chauvin, Y and Hunkapiller, T and McClure, M A},
	Date-Added = {2011-05-01 16:52:59 -0700},
	Date-Modified = {2011-05-01 16:53:33 -0700},
	Eprint = {http://www.pnas.org/content/91/3/1059.full.pdf+html},
	Journal = {Proceedings of the National Academy of Sciences},
	Number = {3},
	Pages = {1059-1063},
	Title = {Hidden Markov models of biological primary sequence information},
	Volume = {91},
	Year = {1994},
	Bdsk-Url-1 = {http://www.pnas.org/content/91/3/1059.abstract}}

@article{baldi1994smooth,
	Author = {Baldi, Pierre and Chauvin, Yves},
	Journal = {Neural Computation},
	Number = {2},
	Pages = {307--318},
	Title = {Smooth on-line learning algorithms for hidden Markov models},
	Volume = {6},
	Year = {1994}}

@article{Hunter:2004,
	Author = {Hunter, D.R. and Lange, K.},
	Date-Added = {2011-05-01 16:42:53 -0700},
	Date-Modified = {2011-05-01 16:43:29 -0700},
	Issn = {0003-1305},
	Journal = {The American Statistician},
	Number = {1},
	Pages = {30--37},
	Publisher = {ASA},
	Title = {{A tutorial on MM algorithms}},
	Volume = {58},
	Year = {2004}}

@article{Mamitsuka:1996,
	Author = {Mamitsuka, Hiroshi},
	Date-Added = {2011-05-01 16:38:30 -0700},
	Date-Modified = {2011-05-01 16:39:52 -0700},
	Doi = {10.1089/cmb.1996.3.361},
	Eprint = {http://www.liebertonline.com/doi/pdf/10.1089/cmb.1996.3.361},
	Journal = {Journal of Computational Biology},
	Number = {3},
	Pages = {361-373},
	Title = {A Learning Method of Hidden Markov Models for Sequence Discrimination},
	Volume = {3},
	Year = {1996},
	Bdsk-Url-1 = {http://www.liebertonline.com/doi/abs/10.1089/cmb.1996.3.361},
	Bdsk-Url-2 = {http://dx.doi.org/10.1089/cmb.1996.3.361}}

@article{meng:1997aof,
	Author = {Meng, X.L. and van Dyk, D.},
	Date-Added = {2009-05-18 20:01:43 -0400},
	Date-Modified = {2009-05-18 20:01:43 -0400},
	Journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
	Pages = {511--567},
	Publisher = {Blackwell Publishers},
	Title = {{The EM algorithm--an old folk-song sung to a fast new tune}},
	Year = {1997}}

@unpublished{PreCBW,
	Author = {Edlefsen, Paul T. and Siegel, Andrew F and Kolker, Eugene},
	Date-Added = {2009-05-18 19:45:42 -0400},
	Date-Modified = {2009-05-18 21:13:45 -0400},
	Note = {unpublished},
	Title = {{A conditional maximization procedure for Profile hidden Markov models}},
	Year = {2003}}

@misc{ronquist:2003,
	Author = {Ronquist, F. and Huelsenbeck, J.P.},
	Date-Added = {2009-05-12 13:17:32 -0400},
	Date-Modified = {2009-05-12 13:17:32 -0400},
	Journal = {Bioinformatics},
	Number = {12},
	Pages = {1572--1574},
	Publisher = {Oxford Univ Press},
	Title = {{MrBayes 3: Bayesian phylogenetic inference under mixed models}},
	Volume = {19},
	Year = {2003}}

@article{heinrich-2004,
	Adsnote = {Provided by the Smithsonian/NASA Astrophysics Data System},
	Adsurl = {http://adsabs.harvard.edu/abs/2004physics...9129H},
	Author = {{Heinrich}, J. and {Blocker}, C. and {Conway}, J. and {Demortier}, L. and {Lyons}, L. and {Punzi}, G. and {Sinervo}, P.~K.},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Eprint = {physics/0409129},
	Journal = {ArXiv Physics e-prints},
	Month = sep,
	Title = {{Interval estimation in the presence of nuisance parameters. 1. Bayesian approach}},
	Year = 2004}

@article{Dempster:IJAR,
	Abstract = { The Dempster-Shafer (DS) theory of probabilistic reasoning is presented in terms of a semantics whereby every meaningful formal assertion is associated with a triple (p, q, r) where p is the probability "for" the assertion, q is the probability "against" the assertion, and r is the probability of "don't know". Arguments are presented for the necessity of "don't know". Elements of the calculus are sketched, including the extension of a DS model from a margin to a full state space, and DS combination of independent DS uncertainty assessments on the full space. The methodology is applied to inference and prediction from Poisson counts, including an introduction to the use of join-tree model structure to simplify and shorten computation. The relation of DS theory to statistical significance testing is elaborated, introducing along the way the new concept of "dull" null hypothesis.},
	Author = {Dempster, A. P.},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:11:08 -0400},
	Journal = {International Journal of Approximate Reasoning},
	Keywords = {Dempster-Shafer; Belief functions; State space; Poisson model; Join-tree computation; Statistical significance; Dull null hypothesis},
	Pages = {365--377},
	Title = {{The Dempster-Shafer calculus for statisticians}},
	Ty = {JOUR},
	Volume = {48},
	Year = {2008},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6V07-4NF7Y50-1/2/93422a4d194c97649d5a67f034772acf}}

@article{Shenoy:1986,
	Author = {P. P. Shenoy and G. Shafer},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Journal = {IEEE Expert},
	Number = {3},
	Pages = {43-52},
	Title = {Propagating belief functions with local computations},
	Volume = {1},
	Year = {1986}}

@article{Dempster:196712,
	Abstract = {This paper provides detailed formulae for upper and lower probability inferences, based on a sample from a finite population with a discrete univariate observable characteristic, and directed towards the unknown parameters of the population or properties of a future sample. The model is set up in $\S2$ and the detailed formulae are given in $\S3$. Section 4 demonstrates a limited relationship with confidence statements and $\S5$ explores some special cases.},
	Author = {Dempster, A. P.},
	Bdsk-Url-1 = {http://links.jstor.org/sici?sici=0006-3444\%5C(196712\%5C)54\%5C:3\%5C/4\%5C\%3C515\%5C:UALPIB\%5C\%3E2.0.CO\%5C;2-A},
	Bdsk-Url-2 = {http://links.jstor.org/sici?sici=0006-3444\%5C\%28196712\%5C\%2954\%5C\%3A3\%5C\%2F4\%5C\%3C515\%5C\%3AUALPIB\%5C\%3E2.0.CO\%5C\%3B2-A},
	Copyright = {Copyright 1967 Biometrika Trust},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Issn = {0006-3444},
	Journal = {Biometrika},
	Jstor_Articletype = {Full Length Article},
	Jstor_Date = {196712},
	Jstor_Formatteddate = {Dec., 1967},
	Month = {dec},
	Number = {3/4},
	Pages = {515--528},
	Publisher = {Biometrika Trust},
	Title = {Upper and Lower Probability Inferences Based on a Sample from a Finite Univariate Population},
	Volume = {54},
	Year = {1967}}

@article{Dempster:196704,
	Abstract = {A multivalued mapping from a space $X$ to a space $S$ carries a probability measure defined over subsets of $X$ into a system of upper and lower probabilities over subsets of $S$. Some basic properties of such systems are explored in Sections 1 and 2. Other approaches to upper and lower probabilities are possible and some of these are related to the present approach in Section 3. A distinctive feature of the present approach is a rule for conditioning, or more generally, a rule for combining sources of information, as discussed in Sections 4 and 5. Finally, the context in statistical inference from which the present theory arose is sketched briefly in Section 6.},
	Author = {Dempster, A. P.},
	Bdsk-Url-1 = {http://links.jstor.org/sici?sici=0003-4851\%5C(196704\%5C)38\%5C:2\%5C\%3C325\%5C:UALPIB\%5C\%3E2.0.CO\%5C;2-A},
	Bdsk-Url-2 = {http://links.jstor.org/sici?sici=0003-4851\%5C\%28196704\%5C\%2938\%5C\%3A2\%5C\%3C325\%5C\%3AUALPIB\%5C\%3E2.0.CO\%5C\%3B2-A},
	Copyright = {Copyright 1967 Institute of Mathematical Statistics},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Issn = {0003-4851},
	Journal = {The Annals of Mathematical Statistics},
	Jstor_Articletype = {Full Length Article},
	Jstor_Date = {196704},
	Jstor_Formatteddate = {Apr., 1967},
	Month = {apr},
	Number = {2},
	Pages = {325--339},
	Publisher = {Institute of Mathematical Statistics},
	Title = {Upper and Lower Probabilities Induced by a Multivalued Mapping},
	Volume = {38},
	Year = {1967}}

@article{Dempster:196806,
	Abstract = {Within the class of models producing upper and lower probability systems, as discussed in Dempster (1967a), a simple and important subclass may be characterized by random intervals on the line. Detailed expressions are given here for the upper and lower probabilities of a general fixed closed interval determined by a general random closed interval. Such random closed intervals occur in the applications of the general class of models to statistical inference described in Dempster (1966, 1967b, 1968). The illustration given here concerns inference about binomial $p$ and stresses the flexibility allowed in the introduction of prior information.},
	Author = {Dempster, A. P.},
	Bdsk-Url-1 = {http://links.jstor.org/sici?sici=0003-4851\%5C(196806\%5C)39\%5C:3\%5C\%3C957\%5C:UALPGB\%5C\%3E2.0.CO\%5C;2-L},
	Bdsk-Url-2 = {http://links.jstor.org/sici?sici=0003-4851\%5C\%28196806\%5C\%2939\%5C\%3A3\%5C\%3C957\%5C\%3AUALPGB\%5C\%3E2.0.CO\%5C\%3B2-L},
	Copyright = {Copyright 1968 Institute of Mathematical Statistics},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Issn = {0003-4851},
	Journal = {The Annals of Mathematical Statistics},
	Jstor_Articletype = {Full Length Article},
	Jstor_Date = {196806},
	Jstor_Formatteddate = {Jun., 1968},
	Month = {jun},
	Number = {3},
	Pages = {957--966},
	Publisher = {Institute of Mathematical Statistics},
	Title = {Upper and Lower Probabilities Generated by a Random Closed Interval},
	Volume = {39},
	Year = {1968}}

@article{Dempster:1968,
	Abstract = {Procedures of statistical inference are described which generalize Bayesian inference in specific ways. Probability is used in such a way that in general only bounds may be placed on the probabilities of given events, and probability systems of this kind are suggested both for sample information and for prior information. These systems are then combined using a specified rule. Illustrations are given for inferences about trinomial probabilities, and for inferences about a monotone sequence of binomial $p_i$. Finally, some comments are made on the general class of models which produce upper and lower probabilities, and on the specific models which underlie the suggested inference procedures.},
	Author = {Dempster, A. P.},
	Bdsk-Url-1 = {http://links.jstor.org/sici?sici=0035-9246\%5C(1968\%5C)30\%5C:2\%5C\%3C205\%5C:AGOBI\%5C\%3E2.0.CO\%5C;2-J},
	Bdsk-Url-2 = {http://links.jstor.org/sici?sici=0035-9246\%5C\%281968\%5C\%2930\%5C\%3A2\%5C\%3C205\%5C\%3AAGOBI\%5C\%3E2.0.CO\%5C\%3B2-J},
	Copyright = {Copyright 1968 Royal Statistical Society},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:09:12 -0400},
	Issn = {0035-9246},
	Journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
	Jstor_Articletype = {Full Length Article},
	Jstor_Date = {1968},
	Jstor_Formatteddate = {1968},
	Number = {2},
	Pages = {205--247},
	Publisher = {Royal Statistical Society},
	Title = {A Generalization of {Bayesian} Inference},
	Volume = {30},
	Year = {1968}}

@article{Kohlas:1994fk,
	Abstract = {The mathematical theory of evidence has been introduced by Glenn Shafer in 1976 as a new approach to the representation of uncertainty. This theory can be represented under several distinct but more or less equivalent forms. Probabilistic interpretations of evidence theory have their roots in Arthur Dempster's multivalued mappings of probability spaces. This leads to random set and more generally to random filter models of evidence. In this probabilistic view evidence is seen as more or less probable arguments for certain hypotheses and they can be used to support those hypotheses to certain degrees. These degrees of support are in fact the reliabilities with which the hypotheses can be derived from the evidence. Alternatively, the mathematical theory of evidence can be founded axiomatically on the notion of belief functions or on the allocation of belief masses to subsets of a frame of discernment. These approaches aim to present evidence theory as an extension of probability theory. Evidence theory has been used to represent uncertainty in expert systems, especially in the domain of diagnostics. It can be applied to decision analysis and it gives a new perspective for statistical analysis. Among its further applications are image processing, project planning and scheduling and risk analysis. The computational problems of evidence theory are well understood and even though the problem is complex, efficient methods are available.},
	Author = {Kohlas, J{\"u}rg and Monney, Paul-Andr{\'e}},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Journal = {Mathematical Methods of Operations Research},
	M3 = {10.1007/BF01440734},
	Number = {1},
	Pages = {35--68},
	Title = {Theory of evidence: A survey of its mathematical foundations, applications and computational aspects},
	Ty = {JOUR},
	Volume = {39},
	Year = {1994},
	Bdsk-Url-1 = {http://dx.doi.org/10.1007/BF01440734}}

@article{Kennes:1992lr,
	Author = {Kennes, R.},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Isbn = {0018-9472},
	Journal = {Systems, Man and Cybernetics, IEEE Transactions on},
	Journal1 = {Systems, Man and Cybernetics, IEEE Transactions on},
	Keywords = {Boolean algebra; directed graphs; Boolean lattice; Dempster's rule; Dempster-Shafer theory; Mobius transformation; directed graphs; general binary relations},
	Number = {2},
	Pages = {201--223},
	Title = {Computational aspects of the Mobius transformation of graphs},
	Title1 = {Systems, Man and Cybernetics, IEEE Transactions on},
	Ty = {JOUR},
	Volume = {22},
	Year = {1992}}

@article{searches_bosons,
	Author = {P. Igo-Kemenes},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:23:18 -0400},
	Editor = {W.-M. Yao et al.},
	Journal = {Journal of Physics G},
	Number = {1},
	Series = {The Review of Particle Physics},
	Title = {{Searches for Higgs bosons}},
	Volume = {33},
	Year = {2006},
	Bdsk-Url-1 = {http://pdg.lbl.gov/2006/reviews/higgs_s055.pdf}}

@article{rolke-2005-551,
	Author = {Wolfgang A. Rolke and Angel M. Lopez and Jan Conrad},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Journal = {NUCL.INSTRUM.METH.A},
	Pages = {493},
	Title = {Limits and Confidence Intervals in the Presence of Nuisance Parameters},
	Volume = {551},
	Year = {2005},
	Bdsk-Url-1 = {http://www.citebase.org/abstract?id=oai:arXiv.org:physics/0403059}}

@article{Cobb:2006,
	Author = {Barry R. Cobb and Prakash P. Shenoy},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Journal = {International Journal of Approximate Reasoning},
	Month = apr,
	Pages = {314--330},
	Title = {On the Plausibility Transformation Method for Translating Belief Function Models to Probability Models},
	Volume = {41(3)},
	Year = {2006}}

@book{Almond:1995,
	Address = {London},
	Author = {Almond, Russell G.},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-10 14:45:35 -0400},
	Db = {WorldCat},
	Id = {31374056},
	Isbn = {0412066610 9780412066610},
	Language = {English},
	Publisher = {Chapman \& Hall},
	Title = {Graphical belief modeling},
	Ty = {BOOK},
	Year = {1995},
	Bdsk-Url-1 = {http://worldcat.org}}

@book{Kohlas:uq,
	Author = {Kohlas, J{\"u}rg and Monney, Paul-Andr{\'e}},
	Call-Number = {QA273},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Dewey-Call-Number = {519.5/4},
	Genre = {Probabilities},
	Publisher = {Springer},
	Title = {A mathematical theory of hints : an approach to the Dempster-Shafer theory of evidence},
	Volume = {425},
	Year = {1995}}

@book{Shafer:1976qy,
	Address = {Princeton, N.J.},
	Author = {Shafer, Glenn},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Genre = {Probabilities},
	Publisher = {Princeton University Press},
	Title = {A mathematical theory of evidence},
	Year = {1976}}

@incollection{Thoma:1991,
	Address = {Amsterdam},
	Author = {H. M. Thoma},
	Booktitle = {Conditional Logic in Expert Systems},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Editor = {I. R. Goodman and M. M. Gupta and H. T. Nguyen and G. S. Rogers},
	Pages = {269-308},
	Publisher = {North-Holland},
	Title = {Belief Function Computations},
	Year = 1991}

@inproceedings{Pearl:1982,
	Author = {{Pearl}, J.},
	Booktitle = {Proceedings American Association of Artificial Intelligence National Conference on AI},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Pages = {133-136},
	Title = {{Reverend Bayes on inference engines: A distributed hierarchical approach}},
	Year = 1982}

@inproceedings{Punzi,
	Adsnote = {Provided by the Smithsonian/NASA Astrophysics Data System},
	Adsurl = {http://adsabs.harvard.edu/abs/2006sppp.conf...88P},
	Author = {{Punzi}, G.},
	Booktitle = {Statistical Problems in Particle Physics, Astrophysics and Cosmology},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Editor = {{Lyons}, L. and {Karag{\"o}z {\"U}nel}, M.},
	Pages = {88-+},
	Title = {{Ordering Algorithms and Confidence Intervals in the Presence of Nuisance Parameters}},
	Year = 2006}

@inproceedings{Demortier,
	Adsnote = {Provided by the Smithsonian/NASA Astrophysics Data System},
	Adsurl = {http://adsabs.harvard.edu/abs/2006sppp.conf...11D},
	Author = {{Demortier}, L.},
	Booktitle = {Statistical Problems in Particle Physics, Astrophysics and Cosmology},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Editor = {{Lyons}, L. and {Karag{\"o}z {\"U}nel}, M.},
	Pages = {11-+},
	Title = {{Bayesian Reference Analysis}},
	Year = 2006}

@inproceedings{Cranmer,
	Adsnote = {Provided by the Smithsonian/NASA Astrophysics Data System},
	Adsurl = {http://adsabs.harvard.edu/abs/2003sppp.conf..261C},
	Author = {{Cranmer}, K.},
	Booktitle = {Statistical Problems in Particle Physics, Astrophysics, and Cosmology},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Editor = {{Lyons}, L. and {Mount}, R. and {Reitmeyer}, R.},
	Pages = {261-+},
	Title = {{Frequentist Hypothesis Testing with Background Uncertainty}},
	Year = 2003}

@inproceedings{conrad-2006,
	Adsnote = {Provided by the Smithsonian/NASA Astrophysics Data System},
	Adsurl = {http://adsabs.harvard.edu/abs/2006sppp.conf...93C},
	Author = {{Conrad}, J. and {Tegenfeldt}, F.},
	Booktitle = {Statistical Problems in Particle Physics, Astrophysics and Cosmology},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Editor = {{Lyons}, L. and {Karag{\"o}z {\"U}nel}, M.},
	Pages = {93-+},
	Title = {{Likelihood Ratio Intervals with Bayesian Treatment of Uncertainties: Coverage, Power and Combined Experiments}},
	Year = 2006}

@inproceedings{Cousins,
	Author = {Robert D. Cousins},
	Booktitle = {PHYSTAT 05},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Title = {Treatment of Nuisance Parameters in High Energy Physics, and Possible Justifications and Improvements in the Statistics Literature},
	Year = {2005},
	Bdsk-Url-1 = {http://www.physics.ox.ac.uk/phystat05/proceedings/files/oxford_cousins_final.pdf}}

@inproceedings{Reid,
	Author = {N. Reid},
	Booktitle = {PHYSTAT 05},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Title = {Response (to Cousins)},
	Year = {2005},
	Bdsk-Url-1 = {http://www.physics.ox.ac.uk/phystat05/proceedings/files/Reid-response.pdf}}

@inproceedings{heinrich-2007,
	Author = {Joel Heinrich},
	Booktitle = {Proceedings of the 2007 PHYSTAT LHC Workshop on Statistical Issues for LHC Physics},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Editor = {{Prosper}, H. B. and {Lyons}, L. and {De Roeck}, A.},
	Pages = {133--142},
	Title = {Review of the Banff Challenge on Upper Limits},
	Year = {2008},
	Bdsk-Url-1 = {http://physics.rockefeller.edu/~luc/proceedings/phystat2007_heinrich.pdf}}

@misc{Atlas,
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-10 14:46:41 -0400},
	Title = {The ATLAS Experiment},
	Bdsk-Url-1 = {http://atlas.ch/}}

@unpublished{a1_project_site,
	Author = {Joel Heinrich},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:28:09 -0400},
	Month = jul,
	Note = {http://newton.hep.upenn.edu/~heinrich/birs/},
	Title = {{BIRS A1 Limits Project}},
	Year = {2006},
	Bdsk-Url-1 = {http://newton.hep.upenn.edu/~heinrich/birs/}}

@unpublished{a1,
	Author = {Joel Heinrich},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:22:37 -0400},
	Month = jul,
	Note = {http://newton.hep.upenn.edu/~heinrich/birs/project.pdf},
	Title = {Limits Comparison Project},
	Year = {2006},
	Bdsk-Url-1 = {http://newton.hep.upenn.edu/~heinrich/birs/project.pdf}}

@phdthesis{Kong:thesis,
	Author = {A. Kong},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	School = {Department of Statistics, Harvard University},
	Title = {Multivariate Belief Functions and Graphical Models},
	Year = {1986}}

@phdthesis{Almond:thesis,
	Author = {Almond, Russell G.},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	School = {Harvard University},
	Title = {Fusion and Propagation of Graphical Belief Models: An Implementation and an Example},
	Year = {1989}}

@phdthesis{Thoma:thesis,
	Address = {Cambridge, MA},
	Author = {H. M. Thoma},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	School = {Statistics Department, Harvard University},
	Title = {Factorization of belief functions},
	Year = {1989}}

@techreport{Almond:1988,
	Author = {Almond, Russell G.},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Institution = {Statistics Department, Harvard University},
	Month = {June},
	Number = {S-121},
	Title = {Fusion and Propagation in Graphical Belief Models},
	Year = {1988},
	Bdsk-Url-1 = {http://ralmond.net/pubs/captain.pdf}}

@techreport{blimitguide,
	Author = {Joel Heinrich},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:10:14 -0400},
	Month = oct,
	Number = {7232},
	Title = {{User Guide to Bayesian-Limit Software Package}},
	Year = {2004},
	Bdsk-Url-1 = {http://www-cdf.fnal.gov/publications/cdf7232_blimitguide.pdf}}

@techreport{genlimit,
	Author = {Joel Heinrich},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Institution = {The Collider Detector at Fermilab},
	Month = apr,
	Number = {7587},
	Title = {Bayesian limit software: multi-channel with correlated backgrounds and efficiencies},
	Year = {2005},
	Bdsk-Url-1 = {http://www-cdf.fnal.gov/publications/cdf7587_genlimit.pdf}}

@unpublished{birs_workshop_objectives,
	Author = {James Linnemann and Louis Lyons and Nancy Reid},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-18 21:28:32 -0400},
	Month = jul,
	Note = {http://www.birs.ca/workshops/2006/06w5054/Objectives06w5054.html},
	Title = {{BIRS} Workshop on Statistical Inference Problems in High Energy Physics and Astronomy Objectives Document},
	Year = {2006},
	Bdsk-Url-1 = {http://www.birs.ca/workshops/2006/06w5054/Objectives06w5054.html}}

@article{PaulsPosterAtHIVDynamics2015,
Author = {Edlefsen, Paul T},
Title = {{P}oster {A}bstract: Identifying within-host {HIV-1} subpopulations by cosegregation of {P}rofile {H}idden {M}arkov {M}odel update vectors},
Journal = {{HIV} Dynamics and Evolution}, 
Month = {May},
Year = {2015}}

@unpublished{birs_workshop_report,
	Author = {James Linnemann and Louis Lyons and Nancy Reid},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Month = feb,
	Note = {http://www.birs.ca/workshops/2006/06w5054/report06w5054.pdf},
	Title = {Report for Workshop 06w5054: Statistical inference Problems in High Energy Physics and Astronomy},
	Year = {2007},
	Bdsk-Url-1 = {http://www.birs.ca/workshops/2006/06w5054/report06w5054.pdf}}

@unpublished{a1_slides,
	Author = {Joel Heinrich},
	Date-Added = {2009-05-09 14:19:07 -0400},
	Date-Modified = {2009-05-09 14:19:07 -0400},
	Month = jul,
	Note = {http://newton.hep.upenn.edu/~heinrich/birs/a1.pdf},
	Title = {Setting the Scene for Limits and Nuisance Parameters},
	Year = {2006},
	Bdsk-Url-1 = {http://newton.hep.upenn.edu/~heinrich/birs/a1.pdf}}

@article{Karplus1998,
	Author = {Karplus, K and Barrett, C and Hughey, R},
	Doi = {10.1093/bioinformatics/14.10.846},
	Journal = {Bioinformatics},
	Pages = {846-856},
	Pubmedid = {9927713},
	Title = {Hidden Markov models for detecting remote protein homologies},
	Volume = {14},
	Year = {1998},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/14.10.846}}

@techreport{SAMDocumentation,
	Author = {Hughey, R. and Karplus, K. and Krogh, A.},
	Date-Added = {2009-05-06 06:15:02 -0400},
	Date-Modified = {2009-05-06 06:18:02 -0400},
	Institution = {Baskin School of Engineering. University of California Santa Cruz},
	Number = {UCSC-CRL-99-11, updated for SAM Version 3.4},
	Title = {{SAM Sequence Alignment and Modeling Software System}},
	Year = {2003}}

@article{KullbackLeibler,
	Author = {Kullback, S and Leibler, RA},
	Doi = {10.1214/aoms/1177729694},
	Journal = {Ann Math Stat},
	Pages = {79-86},
	Title = {On information and sufficiency},
	Volume = {22},
	Year = {1951},
	Bdsk-Url-1 = {http://dx.doi.org/10.1214/aoms/1177729694}}

@unpublished{HMMerUsersGuide,
	Author = {Eddy, SR},
	Date-Added = {2009-05-06 06:11:52 -0400},
	Date-Modified = {2009-05-06 06:11:52 -0400},
	Note = {St Louis, MO: Washington University School of Medicine},
	Title = {{HMMER User's Guide: Biological sequence analysis using profile hidden Markov models}},
	Year = {1998}}

@unpublished{HMMerUsersGuide3.1,
	Author = {Eddy, SR and Wheeler, TJ},
	Note = {http://hmmer.janelia.org/},
	Title = {HMMER User's Guide, version 3.1},
	Year = {2013}}

@article{PHMMLogos,
	Abstract = {BACKGROUND:Profile Hidden Markov Models (pHMMs) are a widely used tool for protein family research. Up to now, however, there exists no method to visualize all of their central aspects graphically in an intuitively understandable way.RESULTS:We present a visualization method that incorporates both emission and transition probabilities of the pHMM, thus extending sequence logos introduced by Schneider and Stephens. For each emitting state of the pHMM, we display a stack of letters. The stack height is determined by the deviation of the position's letter emission frequencies from the background frequencies. The stack width visualizes both the probability of reaching the state (the hitting probability) and the expected number of letters the state emits during a pass through the model (the state's expected contribution).A web interface offering online creation of HMM Logos and the corresponding source code can be found at the Logos web server of the Max Planck Institute for Molecular Genetics http://logos.molgen.mpg.de.CONCLUSIONS:We demonstrate that HMM Logos can be a useful tool for the biologist: We use them to highlight differences between two homologous subfamilies of GTPases, Rab and Ras, and we show that they are able to indicate structural elements of Ras.},
	Author = {Schuster-Bockler, Benjamin and Schultz, Jorg and Rahmann, Sven},
	Date-Added = {2009-05-05 12:28:31 -0400},
	Date-Modified = {2009-05-18 21:21:51 -0400},
	Doi = {10.1186/1471-2105-5-7},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {7},
	Pubmedid = {14736340},
	Title = {{HMM Logos for visualization of protein families}},
	Volume = {5},
	Year = {2004},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/5/7},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-5-7}}

@article{letunic2006sdc,
	Annote = {Uses HMMer},
	Author = {Letunic, I. and Copley, R.R. and Pils, B. and Pinkert, S. and Schultz, J. and Bork, P.},
	Date-Added = {2009-05-05 07:51:56 -0400},
	Date-Modified = {2009-05-05 07:52:08 -0400},
	Journal = {Nucleic Acids Research},
	Keywords = {HMMer},
	Number = {Database Issue},
	Pages = {D257},
	Publisher = {Oxford Univ Press},
	Title = {{SMART 5: domains in the context of genomes and networks}},
	Volume = {34},
	Year = {2006}}

@article{haft2003tdp,
	Annote = {Uses HMMer},
	Author = {Haft, D.H. and Selengut, J.D. and White, O.},
	Date-Added = {2009-05-05 07:49:57 -0400},
	Date-Modified = {2009-05-05 07:50:30 -0400},
	Journal = {Nucleic Acids Research},
	Keywords = {HMMer},
	Number = {1},
	Pages = {371},
	Publisher = {Oxford Univ Press},
	Title = {{The TIGRFAMs database of protein families}},
	Volume = {31},
	Year = {2003}}

@article{madera2002cph,
	Author = {Madera, M. and Gough, J.},
	Date-Added = {2009-05-05 07:42:02 -0400},
	Date-Modified = {2009-05-05 07:42:02 -0400},
	Journal = {Nucleic acids research},
	Number = {19},
	Pages = {4321},
	Publisher = {Oxford Univ Press},
	Title = {{A comparison of profile hidden Markov model procedures for remote homology detection}},
	Volume = {30},
	Year = {2002}}

@article{coin:2003,
	Author = {Coin, L. and Bateman, A. and Durbin, R.},
	Date-Added = {2009-05-05 07:40:15 -0400},
	Date-Modified = {2009-05-05 07:40:15 -0400},
	Journal = {Proceedings of the National Academy of Sciences},
	Number = {8},
	Pages = {4516--4520},
	Publisher = {National Acad Sciences},
	Title = {{Enhanced protein domain discovery by using language modeling techniques from speech recognition}},
	Volume = {100},
	Year = {2003}}

@article{coin:2004,
	Author = {Coin, L. and Bateman, A. and Durbin, R.},
	Date-Added = {2009-05-05 07:38:24 -0400},
	Date-Modified = {2009-05-05 07:38:24 -0400},
	Journal = {BMC bioinformatics},
	Number = {1},
	Pages = {56},
	Publisher = {BioMed Central Ltd},
	Title = {{Enhanced protein domain discovery using taxonomy}},
	Volume = {5},
	Year = {2004}}

@article{hargbo:1999,
	Author = {Hargbo, J. and Elofsson, A.},
	Date-Added = {2009-05-05 07:36:05 -0400},
	Date-Modified = {2009-05-05 07:36:05 -0400},
	Journal = {Proteins: Structure, Function, and Genetics},
	Number = {1},
	Publisher = {John Wiley \& Sons, Inc. New York},
	Title = {{Hidden Markov models that use predicted secondary structures for fold recognition}},
	Volume = {36},
	Year = {1999}}

@article{karchin:2003,
	Author = {Karchin, R. and Cline, M. and Mandel-Gutfreund, Y. and Karplus, K.},
	Date-Added = {2009-05-05 07:34:34 -0400},
	Date-Modified = {2009-05-05 07:34:34 -0400},
	Journal = {Proteins: Structure, Function, and Genetics},
	Number = {4},
	Pages = {504--514},
	Publisher = {Wiley Subscription Services, Inc., A Wiley Company New York},
	Title = {{Hidden Markov models that use predicted local structure for fold recognition: alphabets of backbone geometry}},
	Volume = {51},
	Year = {2003}}

@article{qian:2003,
	Author = {Qian, B. and Goldstein, R.A.},
	Date-Added = {2009-05-05 07:31:28 -0400},
	Date-Modified = {2009-05-05 07:31:28 -0400},
	Journal = {Proteins: Structure, Function, and Genetics},
	Number = {3},
	Publisher = {Wiley Subscription Services, Inc., A Wiley Company Hoboken},
	Title = {{Detecting distant homologs using phylogenetic tree-based HMMs}},
	Volume = {52},
	Year = {2003}}

@article{mitchison:1995,
	Author = {Mitchison, G. and Durbin, R.},
	Date-Added = {2009-05-05 07:27:41 -0400},
	Date-Modified = {2009-05-05 07:27:41 -0400},
	Journal = {Journal of Molecular Evolution},
	Number = {6},
	Pages = {1139--1151},
	Publisher = {Springer},
	Title = {{Tree-based maximal likelihood substitution matrices and hidden Markov models}},
	Volume = {41},
	Year = {1995}}

@conference{eddy:1995,
	Author = {Eddy, S.R.},
	Booktitle = {Proc Int Conf Intell Syst Mol Biol},
	Date-Added = {2009-05-04 16:44:18 -0400},
	Date-Modified = {2009-05-04 16:44:18 -0400},
	Pages = {114--120},
	Title = {{Multiple alignment using hidden Markov models}},
	Volume = {3},
	Year = {1995}}

@article{scott:2002,
	Author = {Scott, S.L.},
	Date-Added = {2009-05-02 12:22:56 -0400},
	Date-Modified = {2009-05-02 12:22:56 -0400},
	Journal = {Journal of the American Statistical Association},
	Number = {457},
	Pages = {337--352},
	Publisher = {ASA},
	Title = {{Bayesian methods for hidden Markov models: Recursive computing in the 21st century}},
	Volume = {97},
	Year = {2002}}

@article{edlefsen2010transposon,
	Author = {Edlefsen, Paul T and Liu, Jun S},
	Journal = {BMC genomics},
	Number = {Suppl 1},
	Pages = {S10},
	Publisher = {BioMed Central Ltd},
	Title = {Transposon identification using {Profile HMMs}},
	Volume = {11},
	Year = {2010}}

@article{sonnhammer:1997,
	Author = {Sonnhammer, E.L.L. and Eddy, S.R. and Durbin, R.},
	Date-Added = {2009-05-01 12:48:45 -0400},
	Date-Modified = {2009-05-01 12:48:45 -0400},
	Journal = {Proteins: Structure, Function, and Genetics},
	Number = {3},
	Pages = {405--420},
	Publisher = {Wiley Subscription Services, Inc., A Wiley Company Hoboken},
	Title = {{Pfam: a comprehensive database of protein domain families based on seed alignments}},
	Volume = {28},
	Year = {1997}}

@article{schwartz:2003,
	Author = {Schwartz, S. and Kent, W.J. and Smit, A. and Zhang, Z. and Baertsch, R. and Hardison, R.C. and Haussler, D. and Miller, W.},
	Date-Added = {2009-04-29 16:27:02 -0400},
	Date-Modified = {2009-05-10 14:47:14 -0400},
	Journal = {Genome Research},
	Number = {1},
	Pages = {103--107},
	Publisher = {Cold Spring Harbor Laboratory Press},
	Title = {{Human-mouse alignments with BLASTZ}},
	Volume = {13},
	Year = {2003}}

@article{rosenbloom:2008,
	Author = {Rosenbloom, K. and Taylor, J. and Schaeffer, S. and Kent, J. and Haussler, D. and Miller, W.},
	Date-Added = {2009-04-29 16:25:18 -0400},
	Date-Modified = {2009-04-29 16:25:18 -0400},
	Journal = {METHODS IN MOLECULAR BIOLOGY-CLIFTON THEN TOTOWA-},
	Pages = {133},
	Publisher = {Springer},
	Title = {{Phylogenomic resources at the UCSC Genome Browser}},
	Volume = {422},
	Year = {2008}}

@article{kent:2003,
	Author = {Kent, W.J. and Baertsch, R. and Hinrichs, A. and Miller, W. and Haussler, D.},
	Date-Added = {2009-04-29 16:23:44 -0400},
	Date-Modified = {2009-04-29 16:23:44 -0400},
	Journal = {Proceedings of the National Academy of Sciences},
	Number = {20},
	Pages = {11484--11489},
	Publisher = {National Acad Sciences},
	Title = {{Evolution's cauldron: Duplication, deletion, and rearrangement in the mouse and human genomes}},
	Volume = {100},
	Year = {2003}}

@book{eddy:1992,
	Author = {Eddy, S. and {School of Medicine and Dept. of Genetics and National Human Genome Research Institute (US)}},
	Date-Added = {2009-04-28 14:47:10 -0400},
	Date-Modified = {2009-04-28 14:47:10 -0400},
	Publisher = {Washington University School of Medicine},
	Title = {{HMMER profile hidden Markov models for biological sequence analysis}},
	Year = {1992}}

@article{hughey:1996,
	Author = {Hughey, R. and Krogh, A.},
	Date-Added = {2009-04-28 14:44:54 -0400},
	Date-Modified = {2009-04-28 14:44:54 -0400},
	Journal = {Bioinformatics},
	Number = {2},
	Pages = {95--107},
	Publisher = {Oxford Univ Press},
	Title = {{Hidden Markov models for sequence analysis: extension and analysis of the basic method}},
	Volume = {12},
	Year = {1996}}

@unpublished{SAM,
	Author = {Hughey, R and Krogh, A},
	Note = {Santa Cruz: University of California},
	Title = {SAM: Sequence alignment and modeling software system},
	Year = {1995}}

@article{Needleman:1970,
	Author = {Needleman, S.B. and Wunsch, C.D.},
	Date-Added = {2009-04-28 13:17:15 -0400},
	Date-Modified = {2009-04-28 14:04:42 -0400},
	Journal = {J. Mol. Biol.},
	Pages = {443---453},
	Title = {A general method applicable to the search for similarities in the amino acid sequence of two proteins},
	Volume = {48},
	Year = {1970}}

@article{altschul:1990,
	Author = {Altschul, S.F. and Gish, W. and Miller, W. and Myers, E.W. and Lipman, D.J.},
	Date-Added = {2009-04-28 13:16:02 -0400},
	Date-Modified = {2009-04-28 13:16:02 -0400},
	Journal = {J. mol. Biol},
	Number = {3},
	Pages = {403--410},
	Title = {{Basic local alignment search tool}},
	Volume = {215},
	Year = {1990}}

@article{smith:1981,
	Author = {Smith, TF and Waterman, MS},
	Date-Added = {2009-04-28 13:06:53 -0400},
	Date-Modified = {2009-04-28 13:06:53 -0400},
	Journal = {J. Mol. Bwl},
	Pages = {195--197},
	Title = {{Identification of common molecular subsequences}},
	Volume = {147},
	Year = {1981}}

@article{Wong:2008wj,
	Abstract = {The statistical methods applied to the analysis of genomic data do not account for uncertainty in the sequence alignment. Indeed, the alignment is treated as an observation, and all of the subsequent inferences depend on the alignment being correct. This may not have been too problematic for many phylogenetic studies, in which the gene is carefully chosen for, among other things, ease of alignment. However, in a comparative genomics study, the same statistical methods are applied repeatedly on thousands of genes, many of which will be difficult to align. Using genomic data from seven yeast species, we show that uncertainty in the alignment can lead to several problems, including different alignment methods resulting in different conclusions. },
	Annote = {10.1126/science.1151532},
	Author = {Wong, Karen M. and Suchard, Marc A. and Huelsenbeck, John P.},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-04-28 11:57:31 -0400},
	Journal = {Science},
	Journal1 = {Science},
	Number = {5862},
	Pages = {473--476},
	Title = {Alignment Uncertainty and Genomic Analysis},
	Ty = {JOUR},
	Volume = {319},
	Year = {2008},
	Bdsk-Url-1 = {http://www.sciencemag.org/cgi/content/abstract/319/5862/473}}

@article{thompson:1994,
	Author = {Thompson, JD and Higgins, DG and Gibson, TJ and Clustal, W.},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-04-28 11:57:31 -0400},
	Journal = {Nucleic Acids Res},
	Number = {22},
	Pages = {4673--4680},
	Title = {{Improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice}},
	Volume = {22},
	Year = {1994}}

@article{katoh:2005,
	Author = {Katoh, K. and Kuma, K. and Toh, H. and Miyata, T.},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-04-28 11:57:31 -0400},
	Journal = {Nucleic acids research},
	Number = {2},
	Pages = {511},
	Publisher = {Oxford Univ Press},
	Title = {{MAFFT version 5: improvement in accuracy of multiple sequence alignment}},
	Volume = {33},
	Year = {2005}}

@article{Edgar:2004bmc,
	Abstract = {BACKGROUND:In a previous paper, we introduced MUSCLE, a new program for creating multiple alignments of protein sequences, giving a brief summary of the algorithm and showing MUSCLE to achieve the highest scores reported to date on four alignment accuracy benchmarks. Here we present a more complete discussion of the algorithm, describing several previously unpublished techniques that improve biological accuracy and / or computational complexity. We introduce a new option, MUSCLE-fast, designed for high-throughput applications. We also describe a new protocol for evaluating objective functions that align two profiles.RESULTS:We compare the speed and accuracy of MUSCLE with CLUSTALW, Progressive POA and the MAFFT script FFTNS1, the fastest previously published program known to the author. Accuracy is measured using four benchmarks: BAliBASE, PREFAB, SABmark and SMART. We test three variants that offer highest accuracy (MUSCLE with default settings), highest speed (MUSCLE-fast), and a carefully chosen compromise between the two (MUSCLE-prog). We find MUSCLE-fast to be the fastest algorithm on all test sets, achieving average alignment accuracy similar to CLUSTALW in times that are typically two to three orders of magnitude less. MUSCLE-fast is able to align 1,000 sequences of average length 282 in 21 seconds on a current desktop computer.CONCLUSIONS:MUSCLE offers a range of options that provide improved speed and / or alignment accuracy compared with currently available programs. MUSCLE is freely available at http://www.drive5.com/muscle.},
	Author = {Edgar, Robert},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-05-18 21:26:28 -0400},
	Doi = {10.1186/1471-2105-5-113},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {113},
	Pubmedid = {15318951},
	Title = {{MUSCLE: a multiple sequence alignment method with reduced time and space complexity}},
	Volume = {5},
	Year = {2004},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/5/113},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-5-113}}

@article{Edgar:2004sf,
	Abstract = {We describe MUSCLE, a new computer program for creating multiple alignments of protein sequences. Elements of the algorithm include fast distance estimation using kmer counting, progressive alignment using a new profile function we call the log-expectation score, and refinement using tree-dependent restricted partitioning. The speed and accuracy of MUSCLE are compared with T-Coffee, MAFFT and CLUSTALW on four test sets of reference alignments: BAliBASE, SABmark, SMART and a new benchmark, PREFAB. MUSCLE achieves the highest, or joint highest, rank in accuracy on each of these sets. Without refinement, MUSCLE achieves average accuracy statistically indistinguishable from T-Coffee and MAFFT, and is the fastest of the tested methods for large numbers of sequences, aligning 5000 sequences of average length 350 in 7 min on a current desktop computer. The MUSCLE program, source code and PREFAB test data are freely available at http://www.drive5. com/muscle. },
	Annote = {10.1093/nar/gkh340},
	Author = {Edgar, Robert C.},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-05-18 21:26:07 -0400},
	Journal = {Nucleic Acids Research},
	Journal1 = {Nucl. Acids Res.},
	Number = {5},
	Pages = {1792--1797},
	Title = {{MUSCLE: multiple sequence alignment with high accuracy and high throughput}},
	Ty = {JOUR},
	Volume = {32},
	Year = {2004},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/cgi/content/abstract/32/5/1792}}

@article{notredame:2000,
	Author = {Notredame, C. and Higgins, D.G. and Heringa, J.},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-04-28 11:57:31 -0400},
	Journal = {Journal of molecular biology},
	Number = {1},
	Pages = {205--217},
	Publisher = {Elsevier},
	Title = {{T-Coffee: A novel method for fast and accurate multiple sequence alignment}},
	Volume = {302},
	Year = {2000}}

@article{Lunter:2008fj,
	Abstract = {Sequence alignment underpins all of comparative genomics, yet it remains an incompletely solved problem. In particular, the statistical uncertainty within inferred alignments is often disregarded, while parametric or phylogenetic inferences are considered meaningless without confidence estimates. Here, we report on a theoretical and simulation study of pairwise alignments of genomic DNA at humanmouse divergence. We find that >15{\%} of aligned bases are incorrect in existing whole-genome alignments, and we identify three types of alignment error, each leading to systematic biases in all algorithms considered. Careful modeling of the evolutionary process improves alignment quality; however, these improvements are modest compared with the remaining alignment errors, even with exact knowledge of the evolutionary model, emphasizing the need for statistical approaches to account for uncertainty. We develop a new algorithm, Marginalized Posterior Decoding (MPD), which explicitly accounts for uncertainties, is less biased and more accurate than other algorithms we consider, and reduces the proportion of misaligned bases by a third compared with the best existing algorithm. To our knowledge, this is the first nonheuristic algorithm for DNA sequence alignment to show robust improvements over the classic NeedlemanWunsch algorithm. Despite this, considerable uncertainty remains even in the improved alignments. We conclude that a probabilistic treatment is essential, both to improve alignment quality and to quantify the remaining uncertainty. This is becoming increasingly relevant with the growing appreciation of the importance of noncoding DNA, whose study relies heavily on alignments. Alignment errors are inevitable, and should be considered when drawing conclusions from alignments. Software and alignments to assist researchers in doing this are provided at http://genserv.anat.ox.ac.uk/grape/. },
	Annote = {10.1101/gr.6725608},
	Author = {Lunter, Gerton and Rocco, Andrea and Mimouni, Naila and Heger, Andreas and Caldeira, Alexandre and Hein, Jotun},
	Date-Added = {2009-04-28 11:57:31 -0400},
	Date-Modified = {2009-04-28 11:57:31 -0400},
	Journal = {Genome Research},
	Journal1 = {Genome Res.},
	Number = {2},
	Pages = {298--309},
	Title = {Uncertainty in homology inferences: Assessing and improving genomic sequence alignment},
	Ty = {JOUR},
	Volume = {18},
	Year = {2008},
	Bdsk-Url-1 = {http://www.genome.org/cgi/content/abstract/18/2/298}}

@article{iupaciub:1983,
	Author = {IUPAC-IUB},
	Date-Added = {2009-04-28 10:29:59 -0400},
	Date-Modified = {2009-04-28 10:29:59 -0400},
	Journal = {Eur. J. Biochem.},
	Pages = {9--15},
	Title = {{IUPAC-IUB, Joint Commision on Biochemical Nomenclature}},
	Volume = {131},
	Year = {1983}}

@article{altschul:1997,
	Author = {Altschul, SF and Madden, TL and Schaffer, AA and Zhang, J. and Zhang, Z. and Miller, W. and Lipman, DJ},
	Date-Added = {2009-04-27 17:33:50 -0400},
	Date-Modified = {2009-04-27 17:33:50 -0400},
	Journal = {Nucleic acids research},
	Number = {17},
	Pages = {3389},
	Publisher = {Oxford Univ Press},
	Title = {{Gapped BLAST and PSI-BLAST: a new generation of protein database search programs}},
	Volume = {25},
	Year = {1997}}

@unpublished{Crossmatch,
	Author = {Green, P.},
	Date-Added = {2009-04-27 17:29:19 -0400},
	Date-Modified = {2009-05-18 21:30:45 -0400},
	Note = {At http://bozeman.mbt.washington.edu/phrap.docs/swat.html},
	Title = {{Crossmatch}},
	Year = {1994}}

@unpublished{WU-BLAST,
	Author = {Gish, W.},
	Date-Added = {2009-04-27 17:25:37 -0400},
	Date-Modified = {2009-05-18 21:14:27 -0400},
	Note = {http://blast.wustl.edu},
	Title = {{WU-BLAST}},
	Year = {1990},
	Bdsk-Url-1 = {http://blast.wustl.edu}}

@article{fiebig2003dynamics,
  title={Dynamics of HIV viremia and antibody seroconversion in plasma donors: implications for diagnosis and staging of primary HIV infection},
  author={Fiebig, Eberhard W and Wright, David J and Rawal, Bhupat D and Garrett, Patricia E and Schumacher, Richard T and Peddada, Lorraine and Heldebrant, Charles and Smith, Richard and Conrad, Andrew and Kleinman, Steven H and others},
  journal={Aids},
  volume={17},
  number={13},
  pages={1871--1879},
  year={2003},
  publisher={LWW}
}

@article{TravissBenchmarksPaper,
year={2015},
journal={Mobile DNA},
eid={13},
volume={6},
number={1},
doi={10.1186/s13100-015-0044-6},
title={A call for benchmarking transposable element annotation methods},
url={http://dx.doi.org/10.1186/s13100-015-0044-6},
publisher={BioMed Central},
author={Hoen, DouglasR. and Hickey, Glenn and Bourque, Guillaume and Casacuberta, Josep and Cordaux, Richard and Feschotte, Cédric and Fiston-Lavier, Anna-Sophie and Hua-Van, Aurélie and Hubley, Robert and Kapusta, Aurélie and Lerat, Emmanuelle and Maumus, Florian and Pollock, DavidD. and Quesneville, Hadi and Smit, Arian and Wheeler, TravisJ. and Bureau, ThomasE. and Blanchette, Mathieu},
language={English}
}

@unpublished{RAPBeta,
	Author = {{Los Alamos National Labs}},
	Note = {http://www.hiv.lanl.gov/content/sequence/RAP/RAP.html},
	Title = {{RAP Beta}},
	Year = {2015},
	Bdsk-Url-1 = {http://www.hiv.lanl.gov/content/sequence/RAP/RAP.html}}

@unpublished{LANL,
	Author = {{Los Alamos National Labs}},
	Note = {http://www.hiv.lanl.gov},
	Title = {{LANL HIV-1 Sequence Database}},
	Year = 2015,
	Bdsk-Url-1 = {http://www.hiv.lanl.gov}}

@unpublished{ProfillicSimulation,
	Author = {Edlefsen, Paul T},
	Note = {https://github.com/tedholzman/profillicSimulation},
	Title = {{Profillic Simulation Software}},
	Year = {2015},
	Bdsk-Url-1 = {https://github.com/tedholzman/profillicSimulation}}

@unpublished{Profillic,
	Author = {Edlefsen, Paul T},
	Note = {https://github.com/galosh/profillic},
	Title = {{Profillic Software}},
	Year = 2015,
	Bdsk-Url-1 = {https://github.com/galosh/profillic}}

@article{bedell:2000,
	Author = {Bedell, J.A. and Korf, I. and Gish, W.},
	Date-Added = {2009-04-27 17:23:36 -0400},
	Date-Modified = {2009-05-10 14:46:57 -0400},
	Journal = {Bioinformatics},
	Number = 11,
	Pages = {1040--1041},
	Publisher = {Oxford Univ Press},
	Title = {{MaskerAid: a performance enhancement to RepeatMasker}},
	Volume = 16,
	Year = 2000}

@unpublished{RepeatMasker,
	Author = {Smit, AFA AND Hubley, R AND Green, P.},
	Date-Added = {2009-04-27 17:10:19 -0400},
	Date-Modified = {2009-04-28 11:58:45 -0400},
	Note = {http://www.repeatmasker.org},
	Title = {RepeatMasker {Open-3.0}},
	Year = {1996-2004},
	Bdsk-Url-1 = {http://www.repeatmasker.org}}

@article{Jurka:2005,
	Author = {Jurka, J. and Kapitonov, VV and Pavlicek, A. and Klonowski, P. and Kohany, O. and Walichiewicz, J.},
	Date-Added = {2009-04-27 17:08:55 -0400},
	Date-Modified = {2009-04-27 17:09:13 -0400},
	Journal = {Cytogenet Genome Res},
	Number = {1-4},
	Pages = {462--467},
	Publisher = {S. Karger AG},
	Title = {{Repbase Update, a database of eukaryotic repetitive elements}},
	Volume = {110},
	Year = {2005}}

@article{Glusman:2006,
	Abstract = {<p>The identification and characterization of the complete ensemble of genes is a main goal of deciphering the digital information stored in the human genome. Many algorithms for computational gene prediction have been described, ultimately derived from two basic concepts: (1) modeling gene structure and (2) recognizing sequence similarity. Successful hybrid methods combining these two concepts have also been developed. We present a third orthogonal approach to gene prediction, based on detecting the genomic signatures of transcription, accumulated over evolutionary time. We discuss four algorithms based on this third concept: Greens and CHOWDER, which quantify mutational strand biases caused by transcription-coupled DNA repair, and ROAST and PASTA, which are based on strand-specific selection against polyadenylation signals. We combined these algorithms into an integrated method called FEAST, which we used to predict the location and orientation of thousands of putative transcription units not overlapping known genes. Many of the newly predicted transcriptional units do not appear to code for proteins. The new algorithms are particularly apt at detecting genes with long introns and lacking sequence conservation. They therefore complement existing gene prediction methods and will help identify functional transcripts within many apparent ``genomic deserts.''</p>},
	Author = {Glusman, Gustavo AND Qin, Shizhen AND El-Gewely, M. Raafat AND Siegel, Andrew F AND Roach, Jared C AND Hood, Leroy AND Smit, Arian F. A},
	Bdsk-Url-1 = {http://dx.plos.org/10.1371\%2Fjournal.pcbi.0020018},
	Date-Added = {2009-04-27 16:52:48 -0400},
	Date-Modified = {2009-04-27 16:52:48 -0400},
	Doi = {10.1371/journal.pcbi.0020018},
	Journal = {PLoS Comput Biol},
	Month = {03},
	Number = {3},
	Pages = {e18},
	Publisher = {Public Library of Science},
	Title = {A Third Approach to Gene Prediction Suggests Thousands of Additional Human Transcribed Regions},
	Volume = {2},
	Year = {2006},
	Bdsk-Url-2 = {http://dx.plos.org/10.1371/journal.pcbi.0020018},
	Bdsk-Url-3 = {http://dx.doi.org/10.1371/journal.pcbi.0020018}}

@article{wilson:2007,
	Author = {Wilson, M.H. and Coates, C.J. and George, A.L.},
	Date-Added = {2009-04-27 16:45:41 -0400},
	Date-Modified = {2009-04-27 16:45:50 -0400},
	Journal = {Molecular Therapy},
	Number = {1},
	Pages = {139--145},
	Publisher = {Nature Publishing Group},
	Title = {{PiggyBac transposon-mediated gene transfer in human cells}},
	Volume = {15},
	Year = {2007}}

@article{Jordan:2003,
	Abstract = {
Transposable elements (TEs) are abundant in mammalian genomes and have potentially contributed to their hosts' evolution by providing novel regulatory or coding sequences. We surveyed different classes of regulatory region in the human genome to assess systematically the potential contribution of TEs to gene regulation. Almost 25\% of the analyzed promoter regions contain TE-derived sequences, including many experimentally characterized cis-regulatory elements. Scaffold/matrix attachment regions (S/MARs) and locus control regions (LCRs) that are involved in the simultaneous regulation of multiple genes also contain numerous TE-derived sequences. Thus, TEs have probably contributed substantially to the evolution of both gene-specific and global patterns of human gene regulation.},
	Author = {I. King Jordan and Igor B. Rogozin and Galina V. Glazko and Eugene V. Koonin},
	Date-Added = {2009-04-27 16:38:26 -0400},
	Date-Modified = {2009-04-27 16:38:26 -0400},
	Doi = {DOI: 10.1016/S0168-9525(02)00006-9},
	Issn = {0168-9525},
	Journal = {Trends in Genetics},
	Number = {2},
	Pages = {68 - 72},
	Title = {Origin of a substantial fraction of human regulatory sequences from transposable elements},
	Volume = {19},
	Year = {2003},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6TCY-47DT7P2-1/2/b66308c198ebb74738ce4a981fba3be7},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/S0168-9525(02)00006-9}}

@article{Piriyapongsa:2007,
	Abstract = {We sought to evaluate the extent of the contribution of transposable elements (TEs) to human microRNA (miRNA) genes along with the evolutionary dynamics of TE-derived human miRNAs. We found 55 experimentally characterized human miRNA genes that are derived from TEs, and these TE-derived miRNAs have the potential to regulate thousands of human genes. Sequence comparisons revealed that TE-derived human miRNAs are less conserved, on average, than non-TE-derived miRNAs. However, there are 18 TE-derived miRNAs that are relatively conserved, and 14 of these are related to the ancient L2 and MIR families. Comparison of miRNA vs. mRNA expression patterns for TE-derived miRNAs and their putative target genes showed numerous cases of anti-correlated expression that are consistent with regulation via mRNA degradation. In addition to the known human miRNAs that we show to be derived from TE sequences, we predict an additional 85 novel TE-derived miRNA genes. TE sequences are typically disregarded in genomic surveys for miRNA genes and target sites; this is a mistake. Our results indicate that TEs provide a natural mechanism for the origination miRNAs that can contribute to regulatory divergence between species as well as a rich source for the discovery of as yet unknown miRNA genes.
},
	Author = {Piriyapongsa, Jittima and Marino-Ramirez, Leonardo and Jordan, I. King},
	Date-Added = {2009-04-27 16:27:03 -0400},
	Date-Modified = {2009-04-27 16:27:03 -0400},
	Doi = {10.1534/genetics.107.072553},
	Eprint = {http://www.genetics.org/cgi/reprint/176/2/1323.pdf},
	Journal = {Genetics},
	Number = {2},
	Pages = {1323-1337},
	Title = {{Origin and Evolution of Human microRNAs From Transposable Elements}},
	Volume = {176},
	Year = {2007},
	Bdsk-Url-1 = {http://www.genetics.org/cgi/content/abstract/176/2/1323},
	Bdsk-Url-2 = {http://dx.doi.org/10.1534/genetics.107.072553}}

@book{lupski:2006,
	Author = {Lupski, J.R. and Stankiewicz, P.},
	Date-Added = {2009-04-27 16:17:20 -0400},
	Date-Modified = {2009-04-27 16:17:40 -0400},
	Publisher = {Humana Press},
	Title = {{Genomic disorders: the genomic basis of disease}},
	Year = {2006}}

@article{deininger:1999,
	Author = {Deininger, P.L. and Batzer, M.A.},
	Date-Added = {2009-04-27 16:08:46 -0400},
	Date-Modified = {2009-04-27 16:16:58 -0400},
	Journal = {Molecular Genetics and Metabolism},
	Number = {3},
	Pages = {183--193},
	Publisher = {Elsevier},
	Title = {{Alu repeats and human disease}},
	Volume = {67},
	Year = {1999}}

@article{NatureMouseGenome:2002,
	Author = {Waterston, R.H. and Lindblad-Toh, K. and Birney, E. and Rogers, J. and Abril, J.F. and Agarwal, P. and Agarwala, R. and Ainscough, R. and Alexandersson, M. and An, P. and others},
	Date-Added = {2009-04-27 15:23:11 -0400},
	Date-Modified = {2009-04-27 15:23:33 -0400},
	Journal = {Nature},
	Number = {6915},
	Pages = {520--562},
	Title = {{Initial sequencing and comparative analysis of the mouse genome}},
	Volume = {420},
	Year = {2002}}

@article{NatureHumanGenome:2001,
	Annote = {10.1038/35057062},
	Author = {Venter, J.C.},
	Date-Added = {2009-04-27 15:10:56 -0400},
	Date-Modified = {2009-04-27 15:14:50 -0400},
	Isbn = {0028-0836},
	Journal = {Nature},
	L3 = {http://www.nature.com/nature/journal/v409/n6822/suppinfo/409860a0_S1.html},
	M3 = {10.1038/35057062},
	Month = {Jan},
	Number = {6822},
	Pages = {860--921},
	Publisher = {Macmillian Magazines Ltd.},
	Title = {Initial sequencing and analysis of the human genome},
	Ty = {JOUR},
	Volume = {409},
	Year = {2001},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/35057062}}

@article{Medstrand:2002,
	Abstract = {Remnants of more than 3 million transposable elements, primarily retroelements, comprise nearly half of the human genome and have generated much speculation concerning their evolutionary significance. We have exploited the draft human genome sequence to examine the distributions of retroelements on a genome-wide scale. Here we show that genomic densities of 10 major classes of human retroelements are distributed differently with respect to surrounding GC content and also show that the oldest elements are preferentially found in regions of lower GC compared with their younger relatives. In addition, we determined whether retroelement densities with respect to genes could be accurately predicted based on surrounding GC content or if genes exert independent effects on the density distributions. This analysis revealed that all classes of long terminal repeat (LTR) retroelements and L1 elements, particularly those in the same orientation as the nearest gene, are significantly underrepresented within genes and older LTR elements are also underrepresented in regions within 5 kb of genes. Thus, LTR elements have been excluded from gene regions, likely because of their potential to affect gene transcription. In contrast, the density of Alu sequences in the proximity of genes is significantly greater than that predicted based on the surrounding GC content. Furthermore, we show that the previously described density shift of Alu repeats with age to domains of higher GC was markedly delayed on the Y chromosome, suggesting that recombination between chromosome pairs greatly facilitates genomic redistributions of retroelements. These findings suggest that retroelements can be removed from the genome, possibly through recombination resulting in re-creation of insert-free alleles. Such a process may provide an explanation for the shifting distributions of retroelements with time.
},
	Author = {Medstrand, Patrik and van de Lagemaat, Louie N. and Mager, Dixie L.},
	Date-Added = {2009-04-27 14:06:12 -0400},
	Date-Modified = {2009-04-27 15:28:04 -0400},
	Doi = {10.1101/gr.388902},
	Eprint = {http://genome.cshlp.org/content/12/10/1483.full.pdf+html},
	Journal = {Genome Research},
	Number = {10},
	Pages = {1483-1495},
	Title = {{Retroelement Distributions in the Human Genome: Variations Associated With Age and Proximity to Genes}},
	Volume = {12},
	Year = {2002},
	Bdsk-Url-1 = {http://genome.cshlp.org/content/12/10/1483.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1101/gr.388902}}

@article{Lerat:2007,
	Abstract = {
Transposable elements (TEs) are genomic sequences able to replicate themselves, and to move from one chromosomal position to another within the genome. Many TEs contain their own regulatory regions, which means that they may influence the expression of neighboring genes. TEs may also be activated and transcribed in various cancers. We therefore tested whether gene expression in normal and tumor tissues is influenced by the neighboring TEs. To do this, we associated all human genes to the nearest TEs. We analyzed the expression of these genes in normal and tumor tissues using SAGE and EST data, and related this to the presence and type of TEs in their vicinity. We confirmed that TEs tend to be located in antisense orientation relative to their hosting genes. We found that the average number of tissues where a gene is expressed varies depending on the type of TEs located near the gene, and that the difference in expression level between normal and tumor tissues is greatest for genes that host SINE elements. This deregulation increases with the number of SINE copies in the gene vicinity. This suggests that SINE elements might contribute to the cascade of gene deregulation in cancer cells.},
	Author = {Emmanuelle Lerat and Marie S\'{e}mon},
	Date-Added = {2009-04-27 13:19:20 -0400},
	Date-Modified = {2009-04-27 15:19:39 -0400},
	Doi = {DOI: 10.1016/j.gene.2007.04.002},
	Issn = {0378-1119},
	Journal = {Gene},
	Keywords = {Gene expression},
	Number = {2},
	Pages = {303 - 311},
	Title = {Influence of the transposable element neighborhood on human gene expression in normal and tumor tissues},
	Volume = {396},
	Year = {2007},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6T39-4NF4F3Y-1/2/3e190f06fec722c498cd36c642a132a8},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.gene.2007.04.002}}

@article{Jurka:1998,
	Abstract = {
For hundreds of millions of years, perhaps from the very beginning of their evolutionary history, eukaryotic cells have been habitats and junkyards for countless generations of transposable elements, preserved in repetitive DNA sequences. Analysis of these sequences, combined with experimental research, reveals a history of complex [`]intracellular ecosystems' of transposable elements that are inseparably associated with genomic evolution.},
	Author = {Jerzy Jurka},
	Date-Added = {2009-04-27 13:13:08 -0400},
	Date-Modified = {2009-05-18 21:07:20 -0400},
	Doi = {DOI: 10.1016/S0959-440X(98)80067-5},
	Issn = {0959-440X},
	Journal = {Current Opinion in Structural Biology},
	Number = {3},
	Pages = {333 - 337},
	Title = {Repeats in genomic {DNA}: mining and meaning},
	Volume = {8},
	Year = {1998},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6VS6-4547FDN-JF/2/de36dd55627cba66517147639fb13184},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/S0959-440X(98)80067-5}}

@article{Walbot:2008,
	Abstract = {:A report on the Maize Genetics Conference held in Washington DC, USA, 27 February-1 March, 2008.},
	Author = {Walbot, Virginia},
	Date-Added = {2009-04-27 12:52:55 -0400},
	Date-Modified = {2009-04-27 12:53:24 -0400},
	Doi = {10.1186/gb-2008-9-4-303},
	Issn = {1465-6906},
	Journal = {Genome Biology},
	Number = {4},
	Pages = {303},
	Pubmedid = {18423056},
	Title = {Maize genome in motion},
	Volume = {9},
	Year = {2008},
	Bdsk-Url-1 = {http://genomebiology.com/2008/9/4/303},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/gb-2008-9-4-303}}

@article{Gribskov,
	Abstract = {Profile analysis is a method for detecting distantly related proteins by sequence comparison. The basis for comparison is not only the customary Dayhoff mutational-distance matrix but also the results of structural studies and information implicit in the alignments of the sequences of families of similar proteins. This information is expressed in a position-specific scoring table (profile), which is created from a group of sequences previously aligned by structural or sequence similarity. The similarity of any other sequence (target) to the group of aligned sequences (probe) can be tested by comparing the target to the profile using dynamic programming algorithms. The profile method differs in two major respects from methods of sequence comparison in common use: (i) Any number of known sequences can be used to construct the profile, allowing more information to be used in the testing of the target than is possible with pairwise alignment methods. (ii) The profile includes the penalties for insertion or deletion at each position, which allow one to include the probe secondary structure in the testing scheme. Tests with globin and immunoglobulin sequences show that profile analysis can distinguish all members of these families from all other sequences in a database containing 3800 protein sequences.
},
	Author = {Gribskov, M and McLachlan, A D and Eisenberg, D},
	Date-Added = {2008-10-22 17:40:38 -0400},
	Date-Modified = {2008-10-22 17:41:03 -0400},
	Eprint = {http://www.pnas.org/content/84/13/4355.full.pdf+html},
	Journal = {Proceedings of the National Academy of Sciences of the United States of America},
	Number = {13},
	Pages = {4355-4358},
	Title = {{Profile analysis: detection of distantly related proteins}},
	Volume = {84},
	Year = {1987},
	Bdsk-Url-1 = {http://www.pnas.org/content/84/13/4355.abstract}}

@article{Lunter:2007uo,
	Abstract = {Summary:Hidden Markov models are widely applied within computational biology. The large datasets and complex models involved demand optimized implementations, while efficient exploration of model space requires rapid prototyping. These requirements are not met by existing solutions, and hand-coding is time-consuming and error-prone. Here, I present a compiler that takes over the mechanical process of implementing HMM algorithms, by translating high-level XML descriptions into efficient C++ implementations. The compiler is highly customizable, produces efficient and bug-free code, and includes several optimizations.  Availability:http://genserv.anat.ox.ac.uk/software  Contact: gerton.lunter{\char64}dpag.ox.ac.uk },
	Annote = {10.1093/bioinformatics/btm350},
	Author = {Lunter, Gerton},
	Date-Added = {2008-03-19 13:47:32 -0400},
	Date-Modified = {2009-05-18 21:18:57 -0400},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Pages = {btm350--},
	Title = {{HMMoC - a compiler for hidden Markov models}},
	Ty = {JOUR},
	Year = {2007},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/btm350v1}}

@article{Vergne:2008qc,
	Author = {Vergne, Nicolas},
	Date-Added = {2008-02-22 11:54:30 -0500},
	Date-Modified = {2009-05-18 21:18:14 -0400},
	Journal = {tatistical Applications in Genetics and Molecular Biology},
	Number = {1},
	Title = {{Drifting Markov models with polynomial drift and applications to DNA sequences}},
	Volume = {7},
	Year = {2008},
	Bdsk-Url-1 = {http://www.bepress.com/sagmb/vol7/iss1/art6}}

@article{15799782,
	Abstract = {BACKGROUND:Cis-regulatory modules are combinations of regulatory elements occurring in close proximity to each other that control the spatial and temporal expression of genes. The ability to identify them in a genome-wide manner depends on the availability of accurate models and of search methods able to detect putative regulatory elements with enhanced sensitivity and specificity.RESULTS:We describe the implementation of a search method for putative transcription factor binding sites (TFBSs) based on hidden Markov models built from alignments of known sites. We built 1,079 models of TFBSs using experimentally determined sequence alignments of sites provided by the TRANSFAC and JASPAR databases and used them to scan sequences of the human, mouse, fly, worm and yeast genomes. In several cases tested the method identified correctly experimentally characterized sites, with better specificity and sensitivity than other similar computational methods. Moreover, a large-scale comparison using synthetic data showed that in the majority of cases our method performed significantly better than a nucleotide weight matrix-based method.CONCLUSION:The search engine, available at http://mapper.chip.org, allows the identification, visualization and selection of putative TFBSs occurring in the promoter or other regions of a gene from the human, mouse, fly, worm and yeast genomes. In addition it allows the user to upload a sequence to query and to build a model by supplying a multiple sequence alignment of binding sites for a transcription factor of interest. Due to its extensive database of models, powerful search engine and flexible interface, MAPPER represents an effective resource for the large-scale computational analysis of transcriptional regulation.},
	Author = {Marinescu, Voichita and Kohane, Isaac and Riva, Alberto},
	Date-Added = {2008-02-22 11:44:54 -0500},
	Date-Modified = {2009-05-18 21:20:15 -0400},
	Doi = {10.1186/1471-2105-6-79},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {79},
	Pubmedid = {15799782},
	Title = {{MAPPER: a search engine for the computational identification of putative transcription factor binding sites in multiple genomes}},
	Volume = {6},
	Year = {2005},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/6/79},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-6-79}}

@article{Sun:2007bq,
	Abstract = {Motivation: Profile HMMs are a powerful tool for modeling conserved motifs in proteins. These models are widely used by search tools to classify new protein sequences into families based on domain architecture. However, the proliferation of known motifs and new proteomic sequence data poses a computational challenge for search, requiring days of CPU time to annotate an organism's proteome.  Results: We use PROSITE-like patterns as a filter to speed up the comparison between protein sequence and profile HMM. A set of patterns is designed starting from the HMM, and only sequences matching one of these patterns are compared to the HMM by full dynamic programming. We give an algorithm to design patterns with maximal sensitivity subject to a bound on the false positive rate. Experiments show that our patterns typically retain at least 90{\%} of the sensitivity of the source HMM while accelerating search by an order of magnitude.  Availability: Contact the first author at the address below.  Contact: yanni{\char64}cse.wustl.edu },
	Annote = {10.1093/bioinformatics/btl323},
	Author = {Sun, Yanni and Buhler, Jeremy},
	Date-Added = {2008-02-22 11:39:52 -0500},
	Date-Modified = {2008-02-22 11:39:52 -0500},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {2},
	Pages = {e36--43},
	Title = {Designing patterns for profile HMM search},
	Ty = {JOUR},
	Volume = {23},
	Year = {2007},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/2/e36}}

@article{Finn:2006le,
	Abstract = {Pfam is a database of protein families that currently contains 7973 entries (release 18.0). A recent development in Pfam has enabled the grouping of related families into clans. Pfam clans are described in detail, together with the new associated web pages. Improvements to the range of Pfam web tools and the first set of Pfam web services that allow programmatic access to the database and associated tools are also presented. Pfam is available on the web in the UK (http://www.sanger.ac.uk/Software/Pfam/), the USA (http://pfam.wustl.edu/), France (http://pfam.jouy.inra.fr/) and Sweden (http://pfam.cgb.ki.se/). },
	Annote = {10.1093/nar/gkj149},
	Author = {Finn, Robert D. and Mistry, Jaina and Schuster-Bockler, Benjamin and Griffiths-Jones, Sam and Hollich, Volker and Lassmann, Timo and Moxon, Simon and Marshall, Mhairi and Khanna, Ajay and Durbin, Richard and Eddy, Sean R. and Sonnhammer, Erik L. L. and Bateman, Alex},
	Date-Added = {2008-02-18 14:27:20 -0500},
	Date-Modified = {2008-02-18 14:27:20 -0500},
	Journal = {Nucleic Acids Research},
	Journal1 = {Nucl. Acids Res.},
	Number = {suppl{\_}1},
	Pages = {D247--251},
	Title = {Pfam: clans, web tools and services},
	Ty = {JOUR},
	Volume = {34},
	Year = {2006},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/cgi/content/abstract/34/suppl_1/D247}}

@article{price2005nir,
	Author = {Price, A.L. and Jones, N.C. and Pevzner, P.A.},
	Date-Added = {2008-02-18 10:49:43 -0500},
	Date-Modified = {2008-02-18 10:49:43 -0500},
	Journal = {Bioinformatics},
	Number = {Suppl 1},
	Pages = {i351--i358},
	Publisher = {Oxford Univ Press},
	Title = {{De novo identification of repeat families in large genomes}},
	Volume = {21},
	Year = {2005}}

@article{bao2002ani,
	Author = {Bao, Z. and Eddy, S.R.},
	Date-Added = {2008-02-18 10:47:35 -0500},
	Date-Modified = {2008-02-18 10:47:35 -0500},
	Journal = {Genome Research},
	Number = {8},
	Pages = {1269},
	Publisher = {Cold Spring Harbor Lab},
	Title = {{Automated De Novo Identification of Repeat Sequence Families in Sequenced Genomes}},
	Volume = {12},
	Year = {2002}}

@article{walters2006ahs,
	Author = {Walters, J.P. and Qudah, B. and Chaudhary, V.},
	Date-Added = {2008-02-18 10:17:18 -0500},
	Date-Modified = {2008-02-18 10:17:18 -0500},
	Journal = {Proceedings of the 20th International Conference on Advanced Information Networking and Applications-Volume 1 (AINA'06)-Volume 01},
	Pages = {289--294},
	Publisher = {IEEE Computer Society Washington, DC, USA},
	Title = {{Accelerating the HMMER Sequence Analysis Suite Using Conventional Processors}},
	Year = {2006}}

@article{Krogh:1994lr,
	Abstract = { Hidden Markov Models (HMMs) are applied to the problems of statistical modeling, database searching and multiple sequence alignment of protein families and protein domains. These methods are demonstrated on the globin family, the protein kinase catalytic domain, and the EF-hand calcium binding motif. In each case the parameters of an HMM are estimated from a training set of unaligned sequences. After the HMM is built, it is used to obtain a multiple alignment of all the training sequences. It is also used to search the SWISS-PROT 22 database for other sequences that are members of the given protein family, or contain the given domain. The HMM produces multiple alignments of good quality that agree closely with the alignments produced by programs that incorporate three-dimensional structural information. When employed in discrimination tests (by examining how closely the sequences in a database fit the globin, kinase and EF-hand HMMs), the HMM is able to distinguish members of these families from non-members with a high degree of accuracy. Both the HMM and PROFILESEARCH (a technique used to search for relationships between a protein sequence and multiply aligned sequences) perform better in these tests than PROSITE (a dictionary of sites and patterns in proteins). The HMM appears to have a slight advantage over PROFILESEARCH in terms of lower rates of false negatives and false positives, even though the HMM is trained using only unaligned sequences, whereas PROFILESEARCH requires aligned training sequences. Our results suggest the presence of an EF-hand calcium binding motif in a highly conserved and evolutionary preserved putative intracellular region of 155 residues in the [alpha]-1 subunit of L-type calcium channels which play an important role in excitation-contraction coupling. This region has been suggested to contain the functional domains that are typical or essential for all L-type calcium channels regardless of whether they couple to ryanodine receptors, conduct ions or both.},
	Author = {Krogh, Anders and Brown, Michael and Mian, I. Saira and Sjolander, Kimmen and Haussler, David},
	Date-Added = {2007-11-28 15:58:12 -0500},
	Date-Modified = {2009-05-18 21:17:14 -0400},
	Journal = {Journal of Molecular Biology},
	Keywords = {hidden Markov models; multiple sequence alignments; globin; kinase; EF-hand},
	Number = {5},
	Pages = {1501--1531},
	Title = {{Hidden Markov models in computational biology : Applications to protein modeling}},
	Ty = {JOUR},
	Volume = {235},
	Year = {1994},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6WK7-45NSKPC-N4/2/9f3b29bcd4f053eef79538ce8e34331b}}

@article{Churchill:1989eu,
	Abstract = { The composition of naturally occurring DNA sequences is often strikingly heterogeneous. In this paper, the DNA sequence is viewed as a stochastic process with local compositional properties determined by the states of a hidden Markov chain. The model used is a discrete-state, discrete-outcome version of a general model for non-stationary time series proposed by Kitagawa (1987). A smoothing algorithm is described which can be used to reconstruct the hidden process and produce graphic displays of the compositional structure of a sequence. The problem of parameter estimation is approached using likelihood methods and an EM algorithm for approximating the maximum likelihood estimate is derived. The methods are applied to sequences from yeast mitochondrial DNA, human and mouse mitochondrial DNAs, a human X chromosomal fragment and the complete genome of bacteriophage lambda.},
	Author = {Churchill, Gary A.},
	Date-Added = {2007-11-28 15:43:32 -0500},
	Date-Modified = {2009-05-18 21:08:13 -0400},
	Journal = {Bulletin of Mathematical Biology},
	Number = {1},
	Pages = {79--94},
	Title = {Stochastic models for heterogeneous {DNA} sequences},
	Ty = {JOUR},
	Volume = {51},
	Year = {1989},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6WC7-4GP24Y4-5/2/f56111f3f586bc139d36535e521fa523}}

@article{17389042,
	Abstract = {BACKGROUND:Profile Hidden Markov Models (HMM) are statistical representations of protein families derived from patterns of sequence conservation in multiple alignments and have been used in identifying remote homologues with considerable success. These conservation patterns arise from fold specific signals, shared across multiple families, and function specific signals unique to the families. The availability of sequences pre-classified according to their function permits the use of negative training sequences to improve the specificity of the HMM, both by optimizing the threshold cutoff and by modifying emission probabilities to minimize the influence of fold-specific signals. A protocol to generate family specific HMMs is described that first constructs a profile HMM from an alignment of the family's sequences and then uses this model to identify sequences belonging to other classes that score above the default threshold (false positives). Ten-fold cross validation is used to optimise the discrimination threshold score for the model. The advent of fast multiple alignment methods enables the use of the profile alignments to align the true and false positive sequences, and the resulting alignments are used to modify the emission probabilities in the original model.RESULTS:The protocol, called HMM-ModE, was validated on a set of sequences belonging to six sub-families of the AGC family of kinases. These sequences have an average sequence similarity of 63\% among the group though each sub-group has a different substrate specificity. The optimisation of discrimination threshold, by using negative sequences scored against the model improves specificity in test cases from an average of 21\% to 98\%. Further discrimination by the HMM after modifying model probabilities using negative training sequences is provided in a few cases, the average specificity rising to 99\%. Similar improvements were obtained with a sample of G-Protein coupled receptors sub-classified with respect to their substrate specificity, though the average sequence identity across the sub-families is just 20.6\%. The protocol is applied in a high-throughput classification exercise on protein kinases.CONCLUSION:The protocol has the potential to maximise the contributions of discriminating residues to classify proteins based on their molecular function, using pre-classified positive and negative sequence training data. The high specificity of the method, and increasing availability of pre-classified sequence data holds the potential for its application in sequence annotation.},
	Author = {Srivastava, Prashant and Desai, Dhwani and Nandi, Soumyadeep and Lynn, Andrew},
	Date-Added = {2007-11-27 17:49:48 -0500},
	Date-Modified = {2009-05-18 21:15:02 -0400},
	Doi = {10.1186/1471-2105-8-104},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {104},
	Pubmedid = {17389042},
	Title = {{HMM-ModE - Improved classification using profile hidden Markov models by optimising the discrimination threshold and modifying emission probabilities with negative training sequences}},
	Volume = {8},
	Year = {2007},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/8/104},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-8-104}}

@article{Becker:2007fj,
	Abstract = {Summary: Recent development of strategies using multiple sequence alignments (MSA) or profiles to detect remote homologies between proteins has led to a significant increase in the number of proteins whose structures can be generated by comparative modeling methods. However, prediction of the optimal alignment between these highly divergent homologous proteins remains a difficult issue. We present a tool based on a generalized Viterbi algorithm that generates optimal and sub-optimal alignments between a sequence and a Hidden Markov Model. The tool is implemented as a new function within the HMMER package called hmmkalign.  Availability:http://www-spider.cea.fr/Groups/hk3039/view.html  Supplementary information: Supplementary data are available at Bioinformatics online. },
	Annote = {10.1093/bioinformatics/btm492},
	Author = {Becker, Emmanuelle and Cotillard, Aurelie and Meyer, Vincent and Madaoui, Hocine and Guerois, Raphael},
	Date-Added = {2007-11-27 15:53:27 -0500},
	Date-Modified = {2009-05-18 21:21:16 -0400},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {22},
	Pages = {3095--3097},
	Title = {{HMM-Kalign: a tool for generating sub-optimal HMM alignments}},
	Ty = {JOUR},
	Volume = {23},
	Year = {2007},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/22/3095}}

@article{Griffiths-Jones:2002fu,
	Abstract = {Motivation: The best quality multiple sequence alignments are  generally considered to derive from structural superposition. However, no previous work has studied the relative performance of profile hidden Markov models (HMMs) derived from such alignments. Therefore several alignment methods have been used to generate multiple sequence alignments from 348 structurally aligned families in the HOMSTRAD database. The performance of profile HMMs derived from the structural and sequence-based alignments has been assessed for homologue detection.  Results: The best alignment methods studied here correctly align  nearly 80{\%} of residues with respect to structure alignments. Alignment quality and model sensitivity are found to be dependent on average number, length, and identity of sequences in the alignment. The striking conclusion is that, although structural data may improve the quality of multiple sequence alignments, this does not add to the ability of the derived profile HMMs to find sequence homologues.  Supplementary information: A list of HOMSTRAD families used in this study and the corresponding Pfam families is available at http://www.sanger.ac.uk/Users/sgj/alignments/map.html  Contact: sgj{\char64}sanger.ac.uk },
	Annote = {10.1093/bioinformatics/18.9.1243},
	Author = {Griffiths-Jones, Sam and Bateman, Alex},
	Date-Added = {2007-11-24 17:54:02 -0500},
	Date-Modified = {2009-05-18 21:19:37 -0400},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {9},
	Pages = {1243--1249},
	Title = {{The use of structure information to increase alignment accuracy does not aid homologue detection with profile HMMs}},
	Ty = {JOUR},
	Volume = {18},
	Year = {2002},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/18/9/1243}}

@article{Edgar:2003la,
	Abstract = {Motivation:Aligning multiple proteins based on sequence information alone is challenging if sequence identity is low or there is a significant degree of structural divergence. We present a novel algorithm (SATCHMO) that is designed to address this challenge. SATCHMO simultaneously constructs a tree and a set of multiple sequence alignments, one for each internal node of the tree. The alignment at a given node contains all sequences within its sub-tree, and predicts which positions in those  sequences are alignable and which are not. Aligned regions therefore  typically get shorter on a path from a leaf to the root as sequences diverge in structure. Current methods either regard all positions as alignable (e.g. ClustalW), or align only those positions believed to be homologous across all sequences (e.g. profile HMM methods); by contrast SATCHMO makes different predictions of alignable regions in different subgroups. SATCHMO generates profile hidden Markov models at each node; these are used to  determine branching order, to align sequences and to predict structurally alignable regions.  Results: In experiments on the BAliBASE benchmark alignment  database, SATCHMO is shown to perform comparably to ClustalW and the UCSC SAM HMM software. Results using SATCHMO to identify protein domains are demonstrated on potassium channels, with implications for the mechanism by which tumor necrosis factor alpha affects potassium current.  Availability: The software is available for download from http://www.drive5.com/lobster/index.htm  Contact: bob{\char64}drive5.com },
	Annote = {10.1093/bioinformatics/btg158},
	Author = {Edgar, Robert C. and Sjolander, Kimmen},
	Date-Added = {2007-11-24 17:51:30 -0500},
	Date-Modified = {2009-05-18 21:20:28 -0400},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {11},
	Pages = {1404--1411},
	Title = {{SATCHMO: sequence alignment and tree construction using hidden Markov models}},
	Ty = {JOUR},
	Volume = {19},
	Year = {2003},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/19/11/1404}}

@article{Gough:2001bs,
	Abstract = { Of the sequence comparison methods, profile-based methods perform with greater selectively than those that use pairwise comparisons. Of the profile methods, hidden Markov models (HMMs) are apparently the best. The first part of this paper describes calculations that (i) improve the performance of HMMs and (ii) determine a good procedure for creating HMMs for sequences of proteins of known structure. For a family of related proteins, more homologues are detected using multiple models built from diverse single seed sequences than from one model built from a good alignment of those sequences. A new procedure is described for detecting and correcting those errors that arise at the model-building stage of the procedure. These two improvements greatly increase selectivity and coverage. The second part of the paper describes the construction of a library of HMMs, called SUPERFAMILY, that represent essentially all proteins of known structure. The sequences of the domains in proteins of known structure, that have identities less than 95 \%, are used as seeds to build the models. Using the current data, this gives a library with 4894 models. The third part of the paper describes the use of the SUPERFAMILY model library to annotate the sequences of over 50 genomes. The models match twice as many target sequences as are matched by pairwise sequence comparison methods. For each genome, close to half of the sequences are matched in all or in part and, overall, the matches cover 35 \% of eukaryotic genomes and 45 \% of bacterial genomes. On average roughly 15\% of genome sequences are labelled as being hypothetical yet homologous to proteins of known structure. The annotations derived from these matches are available from a public web server at: http://stash.mrc-lmb.cam.ac.uk/SUPERFAMILY. This server also enables users to match their own sequences against the SUPERFAMILY model library.},
	Author = {Gough, Julian and Karplus, Kevin and Hughey, Richard and Chothia, Cyrus},
	Date-Added = {2007-11-24 17:49:09 -0500},
	Date-Modified = {2009-05-18 21:20:52 -0400},
	Journal = {Journal of Molecular Biology},
	Keywords = {genome; superfamily; hidden Markov model; structure; homology},
	Number = {4},
	Pages = {903--919},
	Title = {{Assignment of homology to genome sequences using a library of hidden Markov models that represent all proteins of known structure}},
	Ty = {JOUR},
	Volume = {313},
	Year = {2001},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6WK7-457CXWM-3D/2/4d2d71fa096ca47cc00b2bd491f15642}}

@article{Edgar:2004sp,
	Abstract = {Motivation:In recent years, several methods have been proposed for aligning two protein sequence profiles, with reported improvements in alignment accuracy and homolog discrimination versus sequence-sequence methods (e.g. BLAST) and profile-sequence methods (e.g. PSI-BLAST). Profile-profile alignment is also the iterated step in progressive multiple sequence alignment algorithms such as CLUSTALW. However, little is known about the relative performance of different profile-profile scoring functions. In this work, we evaluate the alignment accuracy of 23 different profile-profile scoring functions by comparing alignments of 488 pairs of sequences with identity {$[$}<={$]$}30{\%} against structural alignments. We optimize parameters for all scoring functions on the same training set and use profiles of alignments from both PSI-BLAST and SAM-T99. Structural alignments are constructed from a consensus between the FSSP database and CE structural aligner. We compare the results with sequence-sequence and sequence-profile methods, including BLAST and PSI-BLAST.  Results: We find that profile-profile alignment gives an average improvement over our test set of typically 2-3{\%} over profile-sequence alignment and {$[$}\~{}{$]$}40{\%} over sequence-sequence alignment. No statistically significant difference is seen in the relative performance of most of the scoring functions tested. Significantly better results are obtained with profiles constructed from SAM-T99 alignments than from PSI-BLAST alignments.  Availability: Source code, reference alignments and more detailed results are freely available at http://phylogenomics.berkeley.edu/profilealignment/ },
	Annote = {10.1093/bioinformatics/bth090},
	Author = {Edgar, Robert C. and Sjolander, Kimmen},
	Date-Added = {2007-11-24 17:46:03 -0500},
	Date-Modified = {2007-11-24 17:46:03 -0500},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {8},
	Pages = {1301--1308},
	Title = {A comparison of scoring functions for protein sequence profile alignment},
	Ty = {JOUR},
	Volume = {20},
	Year = {2004},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/20/8/1301}}

@article{Edgar:2004tg,
	Abstract = {Motivation: Alignments of two multiple-sequence alignments, or statistical models of such alignments (profiles), have important applications in computational biology. The increased amount of information in a profile versus a single sequence can lead to more accurate alignments and more sensitive homolog detection in database searches. Several profile-profile alignment methods have been proposed and have been shown to improve sensitivity and alignment quality compared with sequence-sequence methods (such as BLAST) and profile-sequence methods (e.g. PSI-BLAST). Here we present a new approach to profile-profile alignment we call Comparison of Alignments by Constructing Hidden Markov Models (HMMs) (COACH). COACH aligns two multiple sequence alignments by constructing a profile HMM from one alignment and aligning the other to that HMM.  Results: We compare the alignment accuracy of COACH with two recently published methods: Yona and Levitt's prof{\_}sim and Sadreyev and Grishin's COMPASS. On two sets of reference alignments selected from the FSSP database, we find that COACH is able, on average, to produce alignments giving the best coverage or the fewest errors, depending on the chosen parameter settings.  Availability: COACH is freely available from www.drive5.com/lobster },
	Annote = {10.1093/bioinformatics/bth091},
	Author = {Edgar, Robert C. and Sjolander, Kimmen},
	Date-Added = {2007-11-24 17:43:48 -0500},
	Date-Modified = {2009-05-18 21:17:30 -0400},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {8},
	Pages = {1309--1318},
	Title = {{COACH: profile-profile alignment of protein families using hidden Markov models}},
	Ty = {JOUR},
	Volume = {20},
	Year = {2004},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/20/8/1309}}

@article{kececioglu2010aligning,
	Author = {Kececioglu, John and Kim, Eagu and Wheeler, Travis},
	Journal = {Journal of Computational Biology},
	Number = {3},
	Pages = {561--580},
	Publisher = {Mary Ann Liebert, Inc. 140 Huguenot Street, 3rd Floor New Rochelle, NY 10801 USA},
	Title = {Aligning protein sequences with predicted secondary structure},
	Volume = {17},
	Year = {2010}}

@article{Soding:2005qe,
	Abstract = {Motivation: Protein homology detection and sequence alignment are at the basis of protein structure prediction, function prediction and evolution.  Results: We have generalized the alignment of protein sequences with a profile hidden Markov model (HMM) to the case of pairwise alignment of profile HMMs. We present a method for detecting distant homologous relationships between proteins based on this approach. The method (HHsearch) is benchmarked together with BLAST, PSI-BLAST, HMMER and the profile-profile comparison tools PROF{\_}SIM and COMPASS, in an all-against-all comparison of a database of 3691 protein domains from SCOP 1.63 with pairwise sequence identities below 20{\%}.  Sensitivity: When the predicted secondary structure is included in the HMMs, HHsearch is able to detect between 2.7 and 4.2 times more homologs than PSI-BLAST or HMMER and between 1.44 and 1.9 times more than COMPASS or PROF{\_}SIM for a rate of false positives of 10{\%}. Approximately half of the improvement over the profile-profile comparison methods is attributable to the use of profile HMMs in place of simple profiles.  Alignment quality: Higher sensitivity is mirrored by an increased alignment quality. HHsearch produced 1.2, 1.7 and 3.3 times more good alignments ( balanced' score >0.3) than the next best method (COMPASS), and 1.6, 2.9 and 9.4 times more than PSI-BLAST, at the family, superfamily and fold level, respectively.  Speed: HHsearch scans a query of 200 residues against 3691 domains in 33 s on an AMD64 2GHz PC. This is 10 times faster than PROF{\_}SIM and 17 times faster than COMPASS.  Availability: HHsearch can be downloaded from http://www.protevo.eb.tuebingen.mpg.de/download/ together with up-to-date versions of SCOP and PFAM. A web server is available at http://www.protevo.eb.tuebingen.mpg.de/toolkit/index.php?view=hhpred  Contact: johannes.soeding{\char64}tuebingen.mpg.de },
	Annote = {10.1093/bioinformatics/bti125},
	Author = {Soding, Johannes},
	Date-Added = {2007-11-24 17:41:49 -0500},
	Date-Modified = {2009-05-18 21:19:47 -0400},
	Journal = {Bioinformatics},
	Journal1 = {Bioinformatics},
	Number = {7},
	Pages = {951--960},
	Title = {{Protein homology detection by HMM-HMM comparison}},
	Ty = {JOUR},
	Volume = {21},
	Year = {2005},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/21/7/951}}

@article{15831105,
	Abstract = {BACKGROUND:Profile hidden Markov model (HMM) techniques are among the most powerful methods for protein homology detection. Yet, the critical features for successful modelling are not fully known. In the present work we approached this by using two of the most popular HMM packages: SAM and HMMER. The programs' abilities to build models and score sequences were compared on a SCOP/Pfam based test set. The comparison was done separately for local and global HMM scoring.RESULTS:Using default settings, SAM was overall more sensitive. SAM's model estimation was superior, while HMMER's model scoring was more accurate. Critical features for model building were then analysed by comparing the two packages' algorithmic choices and parameters. The weighting between prior probabilities and multiple alignment counts held the primary explanation why SAM's model building was superior. Our analysis suggests that HMMER gives too much weight to the sequence counts. SAM's emission prior probabilities were also shown to be more sensitive. The relative sequence weighting schemes are different in the two packages but performed equivalently.CONCLUSION:SAM model estimation was more sensitive, while HMMER model scoring was more accurate. By combining the best algorithmic features from both packages the accuracy was substantially improved compared to their default performance.},
	Author = {Wistrand, Markus and Sonnhammer, Erik},
	Date-Added = {2007-11-24 17:38:46 -0500},
	Date-Modified = {2009-05-18 21:15:31 -0400},
	Doi = {10.1186/1471-2105-6-99},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {99},
	Pubmedid = {15831105},
	Title = {{Improved profile HMM performance by assessment of critical algorithmic features in SAM and HMMER}},
	Volume = {6},
	Year = {2005},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/6/99},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-6-99}}

@article{15504234,
	Abstract = {BACKGROUND:Certain protein families are highly conserved across distantly related organisms and belong to large and functionally diverse superfamilies. The patterns of conservation present in these protein sequences presumably are due to selective constraints maintaining important but unknown structural mechanisms with some constraints specific to each family and others shared by a larger subset or by the entire superfamily. To exploit these patterns as a source of functional information, we recently devised a statistically based approach called contrast hierarchical alignment and interaction network (CHAIN) analysis, which infers the strengths of various categories of selective constraints from co-conserved patterns in a multiple alignment. The power of this approach strongly depends on the quality of the multiple alignments, which thus motivated development of theoretical concepts and strategies to improve alignment of conserved motifs within large sets of distantly related sequences.RESULTS:Here we describe a hidden Markov model (HMM), an algebraic system, and Markov chain Monte Carlo (MCMC) sampling strategies for alignment of multiple sequence motifs. The MCMC sampling strategies are useful both for alignment optimization and for adjusting position specific background amino acid frequencies for alignment uncertainties. Associated statistical formulations provide an objective measure of alignment quality as well as automatic gap penalty optimization. Improved alignments obtained in this way are compared with PSI-BLAST based alignments within the context of CHAIN analysis of three protein families: Gialpha subunits, prolyl oligopeptidases, and transitional endoplasmic reticulum (p97) AAA+ ATPases.CONCLUSION:While not entirely replacing PSI-BLAST based alignments, which likewise may be optimized for CHAIN analysis using this approach, these motif-based methods often more accurately align very distantly related sequences and thus can provide a better measure of selective constraints. In some instances, these new approaches also provide a better understanding of family-specific constraints, as we illustrate for p97 ATPases. Programs implementing these procedures and supplementary information are available from the authors.},
	Author = {Neuwald, Andrew and Liu, Jun},
	Date-Added = {2007-11-24 17:33:42 -0500},
	Date-Modified = {2009-05-18 21:16:07 -0400},
	Doi = {10.1186/1471-2105-5-157},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {157},
	Pubmedid = {15504234},
	Title = {{Gapped alignment of protein sequence motifs through Monte Carlo optimization of a hidden Markov model}},
	Volume = {5},
	Year = {2004},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/5/157},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-5-157}}

@article{Marti-Renom:2004dq,
	Abstract = {The accuracy of an alignment between two protein sequences can be improved by including other detectably related sequences in the comparison. We optimize and benchmark such an approach that relies on aligning two multiple sequence alignments, each one including one of the two protein sequences. Thirteen different protocols for creating and comparing profiles corresponding to the multiple sequence alignments are implemented in the SALIGN command of MODELLER. A test set of 200 pairwise, structure-based alignments with sequence identities below 40{\%} is used to benchmark the 13 protocols as well as a number of previously described sequence alignment methods, including heuristic pairwise sequence alignment by BLAST, pairwise sequence alignment by global dynamic programming with an affine gap penalty function by the ALIGN command of MODELLER, sequence-profile alignment by PSI-BLAST, Hidden Markov Model methods implemented in SAM and LOBSTER, pairwise sequence alignment relying on predicted local structure by SEA, and multiple sequence alignment by CLUSTALW and COMPASS. The alignment accuracies of the best new protocols were significantly better than those of the other tested methods. For example, the fraction of the correctly aligned residues relative to the structure-based alignment by the best protocol is 56{\%}, which can be compared with the accuracies of 26{\%}, 42{\%}, 43{\%}, 48{\%}, 50{\%}, 49{\%}, 43{\%}, and 43{\%} for the other methods, respectively. The new method is currently applied to large-scale comparative protein structure modeling of all known sequences. },
	Annote = {10.1110/ps.03379804},
	Author = {Marti-Renom, Marc A. and Madhusudhan, M. S. and Sali, Andrej},
	Date-Added = {2007-11-24 17:28:26 -0500},
	Date-Modified = {2007-11-24 17:28:26 -0500},
	Journal = {Protein Science},
	Journal1 = {Protein Sci},
	Number = {4},
	Pages = {1071--1087},
	Title = {Alignment of protein sequences by their profiles},
	Ty = {JOUR},
	Volume = {13},
	Year = {2004},
	Bdsk-Url-1 = {http://www.proteinscience.org/cgi/content/abstract/13/4/1071}}

@article{Eddy:1996gf,
	Abstract = { `Profiles' of protein structures and sequence alignments can detect subtle homologies. Profile analysis has been put on firmer mathematical ground by the introduction of hidden Markov model (HMM) methods. During the past year, applications of these powerful new HMM-based profiles have begun to appear in the fields of protein-structure prediction and large-scale genome-sequence analysis.},
	Author = {Eddy, Sean R},
	Date-Added = {2007-11-24 17:05:44 -0500},
	Date-Modified = {2009-05-18 21:15:17 -0400},
	Journal = {Current Opinion in Structural Biology},
	Number = {3},
	Pages = {361--365},
	Title = {{Hidden Markov models}},
	Ty = {JOUR},
	Volume = {6},
	Year = {1996},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6VS6-4547DF9-47/2/75cc022272b19d611988ad48b4aa3c79}}

@article{ChristianBarrett04011997,
	Abstract = {MOTIVATION: Statistical sequence comparison techniques, such as hidden Markov models and generalized profiles, calculate the probability that a sequence was generated by a given model. Log-odds scoring is a means of evaluating this probability by comparing it to a null hypothesis, usually a simpler statistical model intended to represent the universe of sequences as a whole, rather than the group of interest. Such scoring leads to two immediate questions: what should the null model be, and what threshold of log-odds score should be deemed a match to the model.  RESULTS: This paper analyses these two issues experimentally. Within the context of the Sequence Alignment and Modeling software suite (SAM), we consider a variety of null models and suitable thresholds. Additionally, we consider HMMer's log-odds scoring and SAM's original Z-scoring method. Among the null model choices, a simple looping null model that emits characters according to the geometric mean of the character probabilities in the columns modeled by the hidden Markov model (HMM) performs well or best across all four discrimination experiments.  AVAILABILITY: Information on obtaining the SAM program suite (free for academic use), as well as a server interface, is available from http://www.cse.ucsc.edu/research/compbio/sam.html. HMMer is freely available from http://genome.wustl.edu/eddy/hmm.html.  CONTACT: E-mail: rph@cse.ucsc.edu
},
	Author = {Barrett, Christian and Hughey, Richard and Karplus, Kevin},
	Date-Added = {2007-11-24 17:02:02 -0500},
	Date-Modified = {2007-11-24 17:02:02 -0500},
	Doi = {10.1093/bioinformatics/13.2.191},
	Eprint = {http://bioinformatics.oxfordjournals.org/cgi/reprint/13/2/191.pdf},
	Journal = {Comput. Appl. Biosci.},
	Number = {2},
	Pages = {191-199},
	Title = {{Scoring hidden Markov models}},
	Volume = {13},
	Year = {1997},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/13/2/191},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/13.2.191}}

@article{Eddy:1998,
	Author = {Eddy, SR},
	Date-Added = {2007-11-24 16:58:51 -0500},
	Date-Modified = {2009-04-28 13:46:56 -0400},
	Doi = {10.1093/bioinformatics/14.9.755},
	Eprint = {http://bioinformatics.oxfordjournals.org/cgi/reprint/14/9/755.pdf},
	Journal = {Bioinformatics},
	Number = {9},
	Pages = {755-763},
	Title = {{Profile hidden Markov models}},
	Volume = {14},
	Year = {1998},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/14/9/755},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/14.9.755}}

@article{CTarnas06011998,
	Author = {Tarnas, C and Hughey, R},
	Date-Added = {2007-11-24 16:56:26 -0500},
	Date-Modified = {2007-11-24 16:56:26 -0500},
	Doi = {10.1093/bioinformatics/14.5.401},
	Eprint = {http://bioinformatics.oxfordjournals.org/cgi/reprint/14/5/401.pdf},
	Journal = {Bioinformatics},
	Number = {5},
	Pages = {401-406},
	Title = {{Reduced space hidden Markov model training}},
	Volume = {14},
	Year = {1998},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/14/5/401},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/14.5.401}}

@article{Liu:1999,
	Abstract = {The alignment of multiple homologous biopolymer sequences is crucial in research on protein modeling and engineering, molecular evolution, and prediction in terms of both gene function and gene product structure. In this article we provide a coherent view of the two recent models used for multiple sequence alignment-the hidden Markov model (HMM) and the block-based motif model-to develop a set of new algorithms that have both the sensitivity of the block-based model and the flexibility of the HMM. In particular, we decompose the standard HMM into two components: the insertion component, which is captured by the so-called "propagation model," and the deletion component, which is described by a deletion vector. Such a decomposition serves as a basis for rational compromise between biological specificity and model flexibility. Furthermore, we introduce a Bayesian model selection criterion that-in combination with the propagation model, genetic algorithm, and other computational aspects-forms the core of PROBE, a multiple alignment and database search methodology. The application of our method to a GTPase family of protein sequences yields an alignment that is confirmed by comparison with known tertiary structures.},
	Author = {Liu, Jun S. and Neuwald, Andrew F. and Lawrence, Charles E.},
	Bdsk-Url-1 = {http://links.jstor.org/sici?sici=0162-1459(199903)94:445\%3C1:MSIBSA\%3E2.0.CO;2-C},
	Bdsk-Url-2 = {http://links.jstor.org/sici?sici=0162-1459\%28199903\%2994\%3A445\%3C1\%3AMSIBSA\%3E2.0.CO\%3B2-C},
	Copyright = {Copyright 1999 American Statistical Association},
	Date-Added = {2007-11-23 13:00:52 -0500},
	Date-Modified = {2009-05-18 20:17:41 -0400},
	Group = {Applications and Case Studies},
	Issn = {0162-1459},
	Journal = {Journal of the American Statistical Association},
	Jstor_Articletype = {Full Length Article},
	Jstor_Date = {199903},
	Jstor_Formatteddate = {Mar., 1999},
	Keywords = {DNA Sequence, Evolution, Gibbs Sampler, GTPase, Hidden Markov Model, MAP Criterion, Model Selection, Protein Sequence, Sequence Comparisons},
	Month = {mar},
	Number = {445},
	Pages = {1--15},
	Publisher = {American Statistical Association},
	Title = {Markovian Structures in Biological Sequence Alignments},
	Volume = {94},
	Year = {1999}}

@article{DempsterEM:1977,
	Abstract = {A broadly applicable algorithm for computing maximum likelihood estimates from incomplete data is presented at various levels of generality. Theory showing the monotone behaviour of the likelihood and convergence of the algorithm is derived. Many examples are sketched, including missing value situations, applications to grouped, censored or truncated data, finite mixture models, variance component estimation, hyperparameter estimation, iteratively reweighted least squares and factor analysis.},
	Author = {Dempster, A. P. and Laird, N. M. and Rubin, D. B.},
	Bdsk-Url-1 = {http://links.jstor.org/sici?sici=0035-9246(1977)39:1\%3C1:MLFIDV\%3E2.0.CO;2-Z},
	Bdsk-Url-2 = {http://links.jstor.org/sici?sici=0035-9246\%281977\%2939\%3A1\%3C1\%3AMLFIDV\%3E2.0.CO\%3B2-Z},
	Copyright = {Copyright 1977 Royal Statistical Society},
	Date-Added = {2007-10-24 15:54:58 -0400},
	Date-Modified = {2009-05-18 21:11:41 -0400},
	Issn = {0035-9246},
	Journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
	Jstor_Articletype = {Full Length Article},
	Jstor_Date = {1977},
	Jstor_Formatteddate = {1977},
	Keywords = {Maximum Likelihood, Incomplete Data, EM Algorithm, Posterior Mode},
	Number = {1},
	Pages = {1--38},
	Publisher = {Royal Statistical Society},
	Title = {Maximum Likelihood from Incomplete Data via the {EM} Algorithm},
	Volume = {39},
	Year = {1977}}

@article{MengECM:1993,
	Abstract = {Two major reasons for the popularity of the EM algorithm are that its maximum step involves only complete-data maximum likelihood estimation, which is often computationally simple, and that its convergence is stable, with each iteration increasing the likelihood. When the associated complete-data maximum likelihood estimation itself is complicated, EM is less attractive because the M-step is computationally unattractive. In many cases, however, complete-data maximum likelihood estimation is relatively simple when conditional on some function of the parameters being estimated. We introduce a class of generalized EM algorithms, which we call the ECM algorithm, for Expectation/Conditional Maximization (CM), that takes advantage of the simplicity of complete-data conditional maximum likelihood estimation by replacing a complicated M-step of EM with several computationally simpler CM-steps. We show that the ECM algorithm shares all the appealing convergence properties of EM, such as always increasing the likelihood, and present several illustrative examples.
},
	Author = {Meng, Xiao-Li and Rubin, Donald B.},
	Date-Added = {2007-10-24 15:52:44 -0400},
	Date-Modified = {2007-10-24 16:11:09 -0400},
	Doi = {10.1093/biomet/80.2.267},
	Eprint = {http://biomet.oxfordjournals.org/cgi/reprint/80/2/267.pdf},
	Journal = {Biometrika},
	Number = {2},
	Pages = {267-278},
	Title = {{Maximum likelihood estimation via the ECM algorithm: A general framework}},
	Volume = {80},
	Year = {1993},
	Bdsk-Url-1 = {http://biomet.oxfordjournals.org/cgi/content/abstract/80/2/267},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/biomet/80.2.267}}

@article{Johnson2006,
	Author = {Johnson, S},
	Journal = {Remote Protein Homology Detection Using Hidden Markov Models. PhD thesis},
	Publisher = {St. Louis: Washington University},
	Year = {2006}}

@article{Brown1993,
	Author = {Brown, M and Hughey, R and Krogh, A and Mian, IS and Sjolander, K and Haussler, D},
	Journal = {Proceedings of the First International Conference on Intelligent Systems for Molecular Biology},
	Pages = {47-55},
	Title = {Using Dirichlet mixture priors to derive hidden Markov models for protein families},
	Volume = {1},
	Year = {1993}}

@article{Sjolander1996,
	Author = {Sjolander, K and Karplus, K and Brown, M and Hughey, R and Krogh, A and Mian, IS and Haussler, D},
	Doi = {10.1093/bioinformatics/12.4.327},
	Journal = {Bioinformatics},
	Pages = {327-345},
	Title = {Dirichlet mixtures: a method for improved detection of weak but significant protein sequence homology},
	Volume = {12},
	Year = {1996},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/12.4.327}}

@article{Henikoff1994,
	Author = {Henikoff, S and Henikoff, JG},
	Doi = {10.1016/0022-2836(94)90032-9},
	Journal = {J Mol Biol},
	Pages = {574-578},
	Pubmedid = {7966282},
	Title = {Position-based sequence weights},
	Volume = {243},
	Year = {1994},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/0022-2836(94)90032-9}}

@article{Rabiner:1989,
	Author = {Rabiner, L. R.},
	Date-Added = {2007-10-24 15:49:22 -0400},
	Date-Modified = {2009-05-18 21:20:01 -0400},
	Isbn = {0018-9219},
	Journal = {Proceedings of the IEEE},
	Journal1 = {Proceedings of the IEEE},
	Keywords = {Markov processes; speech recognition; balls-in-urns system; coin-tossing; discrete Markov chains; ergodic models; hidden Markov models; hidden states; left-right models; probabilistic function; speech recognition},
	Number = {2},
	Pages = {257--286},
	Title = {{A tutorial on hidden Markov models and selected applications in speech recognition}},
	Title1 = {Proceedings of the IEEE},
	Ty = {JOUR},
	Volume = {77},
	Year = {1989}}

@article{Baum:1972,
	Author = {Baum, L.E.},
	Date-Added = {2007-10-24 15:43:53 -0400},
	Date-Modified = {2009-05-18 21:18:29 -0400},
	Journal = {Inequalities},
	Pages = {1-8},
	Title = {{An equality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes}},
	Volume = {3},
	Year = {1972}}

@article{Jurka,
	Author = {Jerzy Jurka and Vladimir V Kaitonov and Arian FA Smit},
	Date-Added = {2007-10-24 10:27:48 -0400},
	Date-Modified = {2007-10-24 10:29:02 -0400},
	Journal = {Encyclopedia of Life Sciences},
	Title = {Repetitive Elements: Detection},
	Year = {2005}}

@article{KyudongHan04132007,
	Abstract = {The completion of the draft sequence of the rhesus macaque genome allowed us to study the genomic composition and evolution of transposable elements in this representative of the Old World monkey lineage, a group of diverse primates closely related to humans. The L1 family of long interspersed elements appears to have evolved as a single lineage, and Alu elements have evolved into four currently active lineages. We also found evidence of elevated horizontal transmissions of retroviruses and the absence of DNA transposon activity in the Old World monkey lineage. In addition, [~]100 precursors of composite SVA (short interspersed element, variable number of tandem repeat, and Alu) elements were identified, with the majority being shared by the common ancestor of humans and rhesus macaques. Mobile elements compose roughly 50\% of primate genomes, and our findings illustrate their diversity and strong influence on genome evolution between closely related species.
},
	Author = {Han, Kyudong and Konkel, Miriam K. and Xing, Jinchuan and Wang, Hui and Lee, Jungnam and Meyer, Thomas J. and Huang, Charles T. and Sandifer, Erin and Hebert, Kristi and Barnes, Erin W. and Hubley, Robert and Miller, Webb and Smit, Arian F. A. and Ullmer, Brygg and Batzer, Mark A.},
	Date-Added = {2007-10-22 11:07:08 -0400},
	Date-Modified = {2007-10-22 11:07:08 -0400},
	Doi = {10.1126/science.1139462},
	Eprint = {http://www.sciencemag.org/cgi/reprint/316/5822/238.pdf},
	Journal = {Science},
	Number = {5822},
	Pages = {238-240},
	Title = {{Mobile DNA in Old World Monkeys: A Glimpse Through the Rhesus Macaque Genome}},
	Volume = {316},
	Year = {2007},
	Bdsk-Url-1 = {http://www.sciencemag.org/cgi/content/abstract/316/5822/238},
	Bdsk-Url-2 = {http://dx.doi.org/10.1126/science.1139462}}

@article{Smit:1999fk,
	Abstract = { The bulk of the human genome is ultimately derived from transposable elements. Observations in the past year lead to some new and surprising ideas on functions and consequences of these elements and their remnants in our genome. The many new examples of human genes derived from single transposon insertions highlight the large contribution of selfish DNA to genomic evolution.},
	Author = {Smit, Arian FA},
	Date-Added = {2007-10-22 11:03:00 -0400},
	Date-Modified = {2007-10-22 11:03:00 -0400},
	Journal = {Current Opinion in Genetics \& Development},
	Number = {6},
	Pages = {657--663},
	Title = {Interspersed repeats and other mementos of transposable elements in mammalian genomes},
	Ty = {JOUR},
	Volume = {9},
	Year = {1999},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6VS0-3YGD3J0-9/2/9a5ebb730803e93804ebef3e1e34d429}}

@article{Moult:2005lr,
	Abstract = { For the past ten years, CASP (Critical Assessment of Structure Prediction) has monitored the state of the art in modeling protein structure from sequence. During this period, there has been substantial progress in both comparative modeling of structure (using information from an evolutionarily related structural template) and template-free modeling. The quality of comparative models depends on the closeness of the evolutionary relationship on which they are based. Template-free modeling, although still very approximate, now produces topologically near correct models for some small proteins. Current major challenges are refining comparative models so that they match experimental accuracy, obtaining accurate sequence alignments for models based on remote evolutionary relationships, and extending template-free modeling methods so that they produce more accurate models, handle parts of comparative models not available from a template and deal with larger structures.},
	Author = {Moult, John},
	Date-Added = {2007-10-22 10:55:28 -0400},
	Date-Modified = {2007-10-22 10:55:28 -0400},
	Journal = {Current Opinion in Structural Biology},
	Number = {3},
	Pages = {285--289},
	Title = {A decade of CASP: progress, bottlenecks and prognosis in protein structure prediction},
	Title1 = {Sequences and topology/Nucleic acids},
	Ty = {JOUR},
	Volume = {15},
	Year = {2005},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6VS6-4GBD6KT-1/2/08167b756ffa066f3d63f71cbbf97908}}

@article{DFAM,
	Author = {Wheeler, TJ and Clements, J and Eddy, SR and Hubley, R and Jones, TA and Jurka, J and Smit, AFA and Finn, RD},
	Doi = {10.1093/nar/gks1265},
	Journal = {Nucleic Acids Res},
	Pages = {D70-D82},
	Pubmedid = {23203985},
	Title = {Dfam: a database of repetitive DNA based on profile hidden Markov models},
	Volume = {41},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gks1265}}

@article{FinnHMMer3,
	Abstract = {HMMER is a software suite for protein sequence similarity searches using probabilistic methods. Previously, HMMER has mainly been available only as a computationally intensive UNIX command-line tool, restricting its use. Recent advances in the software, HMMER3, have resulted in a 100-fold speed gain relative to previous versions. It is now feasible to make efficient profile hidden Markov model (profile HMM) searches via the web. A HMMER web server (http://hmmer.janelia.org) has been designed and implemented such that most protein database searches return within a few seconds. Methods are available for searching either a single protein sequence, multiple protein sequence alignment or profile HMM against a target sequence database, and for searching a protein sequence against Pfam. The web server is designed to cater to a range of different user expertise and accepts batch uploading of multiple queries at once. All search methods are also available as RESTful web services, thereby allowing them to be readily integrated as remotely executed tasks in locally scripted workflows. We have focused on minimizing search times and the ability to rapidly display tabular results, regardless of the number of matches found, developing graphical summaries of the search results to provide quick, intuitive appraisement of them.},
	Author = {Finn, Robert D. and Clements, Jody and Eddy, Sean R.},
	Doi = {10.1093/nar/gkr367},
	Eprint = {http://nar.oxfordjournals.org/content/early/2011/05/18/nar.gkr367.full.pdf+html},
	Journal = {Nucleic Acids Research},
	Title = {{HMMER} web server: interactive sequence similarity searching},
	Year = {2011},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gkr367}}

@book{Durbin,
	Author = {Durbin, Richard and Eddy, Sean R. and Krogh, Anders and Mitchison, Graeme},
	Date-Added = {2007-10-22 10:45:06 -0400},
	Date-Modified = {2007-10-22 10:53:55 -0400},
	Keywords = {HMM},
	Publisher = {Cambridge University Press},
	Title = {Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids},
	Year = {1998}}

@article{Wheeler2013,
	Author = {Wheeler, TJ and Eddy, SR},
	Doi = {10.1093/bioinformatics/btt403},
	Journal = {Bioinformatics},
	Pages = {2487-2489},
	Pubmedid = {23842809},
	Title = {nhmmer: DNA homology search with profile HMMs},
	Volume = {29},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/btt403}}

@article{Skylign,
	Abstract = {BACKGROUND:Logos are commonly used in molecular biology to provide a compact graphical representation of the conservation pattern of a set of sequences. They render the information contained in sequence alignments or profile hidden Markov models by drawing a stack of letters for each position, where the height of the stack corresponds to the conservation at that position, and the height of each letter within a stack depends on the frequency of that letter at that position.RESULTS:We present a new tool and web server, called Skylign, which provides a unified framework for creating logos for both sequence alignments and profile hidden Markov models. In addition to static image files, Skylign creates a novel interactive logo plot for inclusion in web pages. These interactive logos enable scrolling, zooming, and inspection of underlying values. Skylign can avoid sampling bias in sequence alignments by down-weighting redundant sequences and by combining observed counts with informed priors. It also simplifies the representation of gap parameters, and can optionally scale letter heights based on alternate calculations of the conservation of a position.CONCLUSION:Skylign is available as a website, a scriptable web service with a RESTful interface, and as a software package for download. Skylign's interactive logos are easily incorporated into a web page with just a few lines of HTML markup. Skylign may be found at http://skylign.org webcite.},
	Author = {Wheeler, Travis and Clements, Jody and Finn, Robert},
	Doi = {10.1186/1471-2105-15-7},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Number = {1},
	Pages = {7},
	Pubmedid = {24410852},
	Title = {Skylign: a tool for creating informative, interactive logos representing sequence alignments and profile hidden Markov models},
	Url = {http://www.biomedcentral.com/1471-2105/15/7},
	Volume = {15},
	Year = {2014},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/15/7},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-15-7}}

@article{Domingo01012002,
	Author = {Domingo, Esteban},
	Doi = {10.1128/JVI.76.1.463-465.2002},
	Eprint = {http://jvi.asm.org/content/76/1/463.full.pdf+html},
	Journal = {Journal of Virology},
	Number = {1},
	Pages = {463-465},
	Title = {Quasispecies Theory in Virology},
	Url = {http://jvi.asm.org/content/76/1/463.short},
	Volume = {76},
	Year = {2002},
	Bdsk-Url-1 = {http://jvi.asm.org/content/76/1/463.short},
	Bdsk-Url-2 = {http://dx.doi.org/10.1128/JVI.76.1.463-465.2002}}

@article{vignuzzi2006quasispecies,
	Author = {Vignuzzi, Marco and Stone, Jeffrey K and Arnold, Jamie J and Cameron, Craig E and Andino, Raul},
	Journal = {Nature},
	Number = {7074},
	Pages = {344--348},
	Publisher = {Nature Publishing Group},
	Title = {Quasispecies diversity determines pathogenesis through cooperative interactions in a viral population},
	Volume = {439},
	Year = {2006}}

@article{Langfelder01032008,
	Abstract = {Summary: Hierarchical clustering is a widely used method for detecting clusters in genomic data. Clusters are defined by cutting branches off the dendrogram. A common but inflexible method uses a constant height cutoff value; this method exhibits suboptimal performance on complicated dendrograms. We present the Dynamic Tree Cut R package that implements novel dynamic branch cutting methods for detecting clusters in a dendrogram depending on their shape. Compared to the constant height cutoff method, our techniques offer the following advantages: (1) they are capable of identifying nested clusters; (2) they are flexible---cluster shape parameters can be tuned to suit the application at hand; (3) they are suitable for automation; and (4) they can optionally combine the advantages of hierarchical clustering and partitioning around medoids, giving better detection of outliers. We illustrate the use of these methods by applying them to protein--protein interaction network data and to a simulated gene expression data set.Availability: The Dynamic Tree Cut method is implemented in an R package available at http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/BranchCuttingContact: stevitihit@yahoo.comSupplementary information: Supplementary data are available at Bioinformatics online.},
	Author = {Langfelder, Peter and Zhang, Bin and Horvath, Steve},
	Doi = {10.1093/bioinformatics/btm563},
	Eprint = {http://bioinformatics.oxfordjournals.org/content/24/5/719.full.pdf+html},
	Journal = {Bioinformatics},
	Number = {5},
	Pages = {719-720},
	Title = {Defining clusters from a hierarchical cluster tree: the Dynamic Tree Cut package for R},
	Url = {http://bioinformatics.oxfordjournals.org/content/24/5/719.abstract},
	Volume = {24},
	Year = {2008},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/content/24/5/719.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/btm563}}

@article{Gaschen01052001,
	Abstract = {Motivation: The amount of HIV-1 sequence data generated

  (presently around 42000 sequences, of which more than 22000 are from

  the V3 region of the viral envelope) presents a challenge for anyone

  working on the analysis of these data. A major problem is obtaining

  the region of interest from the stored sequences, which often

  contain but are not limited to that region. In addition, multiple

  alignment programs generally cannot deal with the large numbers of

  sequences that are available for many HIV-1 regions. We set out to

  provide our users with a tool that will retrieve and create an

  initial alignment of the HIV sequences that are available for a

  given genomic region.Results: The MPAlign (Multiple Pairwise

  Alignment) web interface is a collection of Perl scripts that

  retrieves sequences from the Los Alamos HIV sequence database based

  on a number of search parameters. All sequences were

  pairwise-aligned to a model sequence using the Hidden Markov

  Model-based program HMMER. The HMMER model is general enough to

  accommodate virtually all HIV-1 sequences stored in the database. To

  create a multiple sequence alignment, gaps were inserted into the

  sequences during retrieval, so that they are aligned to one another.

  Retrieving and aligning the almost 560 gp120 sequences

  (1500 nt) stored in the database is at least 1500 times

  faster than a similar Clustal alignment.Availability: At http://www.hiv.lanl.gov/Contact: Brian Gaschen at bkg@lanl.gov
        
      },
	Author = {Gaschen, Brian and Kuiken, Carla and Korber, Bette and Foley, Brian},
	Doi = {10.1093/bioinformatics/17.5.415},
	Eprint = {http://bioinformatics.oxfordjournals.org/content/17/5/415.full.pdf+html},
	Journal = {Bioinformatics},
	Number = {5},
	Pages = {415-418},
	Title = {Retrieval and on-the-fly alignment of sequence fragments from the HIV database},
	Url = {http://bioinformatics.oxfordjournals.org/content/17/5/415.abstract},
	Volume = {17},
	Year = {2001},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/content/17/5/415.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/17.5.415}}

@article{rose2000detecting,
	Author = {Rose, Patrick P and Korber, Bette T},
	Date-Added = {2015-09-30 07:46:03 +0000},
	Date-Modified = {2015-09-30 07:46:49 +0000},
	Journal = {Bioinformatics},
	Keywords = {HYPERMUT; apobec},
	Number = {4},
	Pages = {400--401},
	Publisher = {Oxford Univ Press},
	Title = {Detecting hypermutations in viral sequences with an emphasis on G→ A hypermutation},
	Volume = {16},
	Year = {2000}}

@article{Giorgi:2010aa,
	Abstract = {BACKGROUND: The occurrence of a genetic bottleneck in HIV sexual or mother-to-infant transmission has been well documented. This results in a majority of new infections being homogeneous, i.e., initiated by a single genetic strain. Early after infection, prior to the onset of the host immune response, the viral population grows exponentially. In this simple setting, an approach for estimating evolutionary and demographic parameters based on comparison of diversity measures is a feasible alternative to the existing Bayesian methods (e.g., BEAST), which are instead based on the simulation of genealogies. RESULTS: We have devised a web tool that analyzes genetic diversity in acutely infected HIV-1 patients by comparing it to a model of neutral growth. More specifically, we consider a homogeneous infection (i.e., initiated by a unique genetic strain) prior to the onset of host-induced selection, where we can assume a random accumulation of mutations. Previously, we have shown that such a model successfully describes about 80{\%} of sexual HIV-1 transmissions provided the samples are drawn early enough in the infection. Violation of the model is an indicator of either heterogeneous infections or the initiation of selection. CONCLUSIONS: When the underlying assumptions of our model (homogeneous infection prior to selection and fast exponential growth) are met, we are under a very particular scenario for which we can use a forward approach (instead of backwards in time as provided by coalescent methods). This allows for more computationally efficient methods to derive the time since the most recent common ancestor. Furthermore, the tool performs statistical tests on the Hamming distance frequency distribution, and outputs summary statistics (mean of the best fitting Poisson distribution, goodness of fit p-value, etc). The tool runs within minutes and can readily accommodate the tens of thousands of sequences generated through new ultradeep pyrosequencing technologies. The tool is available on the LANL website.},
	An = {PMC2975664},
	Author = {Giorgi, Elena E and Funkhouser, Bob and Athreya, Gayathri and Perelson, Alan S and Korber, Bette T and Bhattacharya, Tanmoy},
	Date-Added = {2015-09-26 17:57:23 +0000},
	Date-Modified = {2015-09-26 21:14:08 +0000},
	Db = {PMC},
	Doi = {10.1186/1471-2105-11-532},
	Isbn = {1471-2105},
	J1 = {BMC Bioinformatics},
	Journal = {BMC Bioinformatics},
	Keywords = {HIV timing estimation; poisson; PoissonFitter; data},
	Pages = {532--532},
	Publisher = {BioMed Central},
	Title = {Estimating time since infection in early homogeneous HIV-1 samples using a poisson model},
	Ty = {JOUR},
	U1 = {1471-2105-11-532{$[$}PII{$]$}; 20973976{$[$}pmid{$]$}; 20973976{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2975664/},
	Volume = {11},
	Year = {2010},
	Year1 = {2010/10/25},
	Year2 = {2010/05/19/received},
	Year3 = {2010/10/25/accepted},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2975664/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-11-532}}

@article{Rossenkhan:2012aa,
	Abstract = {To assess the level of intra-patient diversity and evolution of HIV-1C non-structural genes in primary infection, viral quasispecies obtained by single genome amplification (SGA) at multiple sampling timepoints up to 500 days post-seroconversion (p/s) were analyzed. The mean intra-patient diversity was 0.11{\%} (95{\%} CI; 0.02 to 0.20) for vif, 0.23{\%} (95{\%} CI; 0.08 to 0.38) for vpr, 0.35{\%} (95{\%} CI; −0.05 to 0.75) for vpu, 0.18{\%} (95{\%} CI; 0.01 to 0.35) for tat exon 1 and 0.30{\%} (95{\%} CI; 0.02 to 0.58) for rev exon 1 during the time period 0 to 90 days p/s. The intra-patient diversity increased gradually in all non-structural genes over the first year of HIV-1 infection, which was evident from the vif mean intra-patient diversity of 0.46{\%} (95{\%} CI; 0.28 to 0.64), vpr 0.44{\%} (95{\%} CI; 0.24 to 0.64), vpu 0.84{\%} (95{\%} CI; 0.55 to 1.13), tat exon 1 0.35{\%} (95{\%} CI; 0.14 to 0.56 ) and rev exon 1 0.42{\%} (95{\%} CI; 0.18 to 0.66) during the time period of 181 to 500 days p/s. There was a statistically significant increase in viral diversity for vif (p = 0.013) and vpu (p = 0.002). No associations between levels of viral diversity within the non-structural genes and HIV-1 RNA load during primary infection were found. The study details the dynamics of the non-structural viral genes during the early stages of HIV-1C infection.},
	Address = {San Francisco, USA},
	An = {PMC3348911},
	Author = {Rossenkhan, Raabya and Novitsky, Vladimir and Sebunya, Theresa K and Musonda, Rosemary and Gashe, Berhanu A and Essex, M},
	Date-Added = {2015-09-26 21:25:20 +0000},
	Date-Modified = {2015-09-26 21:28:55 +0000},
	Db = {PMC},
	Doi = {10.1371/journal.pone.0035491},
	Editor = {Le Gall, Sylvie},
	Isbn = {1932-6203},
	J1 = {PLoS One},
	Journal = {PLoS ONE},
	Keywords = {HIV founder detection; HIV evolution rate within host; Raabya; data},
	Number = {5},
	Pages = {e35491},
	Publisher = {Public Library of Science},
	Title = {Viral Diversity and Diversification of Major Non-Structural Genes vif, vpr, vpu, tat exon 1 and rev exon 1 during Primary HIV-1 Subtype C Infection},
	Ty = {JOUR},
	U1 = {PONE-D-12-00440{$[$}PII{$]$}; 22590503{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3348911/},
	Volume = {7},
	Year = {2012},
	Year1 = {2012/05/09},
	Year2 = {2012/01/04/received},
	Year3 = {2012/03/16/accepted},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3348911/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1371/journal.pone.0035491}}

@article{Herbeck:2011aa,
	Abstract = {HIV-1 transmission and viral evolution in the first year of infection were studied in 11 individuals representing four transmitter-recipient pairs and three independent seroconverters. Nine of these individuals were enrolled during acute infection; all were men who have sex with men (MSM) infected with HIV-1 subtype B. A total of 475 nearly full-length HIV-1 genome sequences were generated, representing on average 10 genomes per specimen at 2 to 12 visits over the first year of infection. Single founding variants with nearly homogeneous viral populations were detected in eight of the nine individuals who were enrolled during acute HIV-1 infection. Restriction to a single founder variant was not due to a lack of diversity in the transmitter as homogeneous populations were found in recipients from transmitters with chronic infection. Mutational patterns indicative of rapid viral population growth dominated during the first 5 weeks of infection and included a slight contraction of viral genetic diversity over the first 20 to 40 days. Subsequently, selection dominated, most markedly in env and nef. Mutants were detected in the first week and became consensus as early as day 21 after the onset of symptoms of primary HIV infection. We found multiple indications of cytotoxic T lymphocyte (CTL) escape mutations while reversions appeared limited. Putative escape mutations were often rapidly replaced with mutually exclusive mutations nearby, indicating the existence of a maturational escape process, possibly in adaptation to viral fitness constraints or to immune responses against new variants. We showed that establishment of HIV-1 infection is likely due to a biological mechanism that restricts transmission rather than to early adaptive evolution during acute infection. Furthermore, the diversity of HIV strains coupled with complex and individual-specific patterns of CTL escape did not reveal shared sequence characteristics of acute infection that could be harnessed for vaccine design.},
	Address = {1752 N St., N.W., Washington, DC},
	An = {PMC3147913},
	Author = {Herbeck, Joshua T and Rolland, Morgane and Liu, Yi and McLaughlin, Sherry and McNevin, John and Zhao, Hong and Wong, Kim and Stoddard, Julia N and Raugi, Dana and Sorensen, Stephanie and Genowati, Indira and Birditt, Brian and McKay, Angela and Diem, Kurt and Maust, Brandon S and Deng, Wenjie and Collier, Ann C and Stekler, Joanne D and McElrath, M Juliana and Mullins, James I},
	Date = {2011/08/},
	Date-Added = {2015-09-26 21:38:38 +0000},
	Date-Modified = {2015-09-26 21:41:24 +0000},
	Db = {PMC},
	Doi = {10.1128/JVI.02697-10},
	Isbn = {0022-538X; 1098-5514},
	J1 = {J Virol},
	Journal = {Journal of Virology},
	Keywords = {HIV evolution rate within host; Morgane; Josh; Jim},
	Month = {08},
	Number = {15},
	Pages = {7523--7534},
	Publisher = {American Society for Microbiology},
	Title = {Demographic Processes Affect HIV-1 Evolution in Primary Infection before the Onset of Selective Processes},
	Ty = {JOUR},
	U1 = {21593162{$[$}pmid{$]$}; 2697-10{$[$}PII{$]$}; 21593162{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3147913/},
	Volume = {85},
	Year = {2011},
	Year1 = {2010/12/30/received},
	Year2 = {2011/05/11/accepted},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3147913/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1128/JVI.02697-10}}

@article{edlefsen2013sieve,
	Author = {Edlefsen, Paul T and Gilbert, Peter B and Rolland, Morgane},
	Journal = {Current opinion in HIV and AIDS},
	Number = {5},
	Pages = {432--436},
	Publisher = {NIH Public Access},
	Title = {Sieve analysis in HIV-1 vaccine efficacy trials.},
	Volume = {8},
	Year = {2013}}

@article{Wu:2014aa,
	Abstract = {Trade-offs between throughput, read length, and error rates in high-throughput sequencing limit certain applications such as monitoring viral quasispecies. Here, we describe a molecular-based tag linkage method that allows assemblage of short sequence reads into long DNA fragments. It enables haplotype phasing with high accuracy and sensitivity to interrogate individual viral sequences in a quasispecies. This approach is demonstrated to deduce ∼2000 unique 1.3 kb viral sequences from HIV-1 quasispecies in vivo and after passaging ex vivo with a detection limit of ∼0.005{\%} to ∼0.001{\%}. Reproducibility of the method is validated quantitatively and qualitatively by a technical replicate. This approach can improve monitoring of the genetic architecture and evolution dynamics in any quasispecies population.},
	Address = {San Francisco, USA},
	An = {PMC4026136},
	Author = {Wu, Nicholas C and De La Cruz, Justin and Al-Mawsawi, Laith Q and Olson, C Anders and Qi, Hangfei and Luan, Harding H and Nguyen, Nguyen and Du, Yushen and Le, Shuai and Wu, Ting-Ting and Li, Xinmin and Lewis, Martha J and Yang, Otto O and Sun, Ren},
	Date-Added = {2015-09-28 06:36:07 +0000},
	Date-Modified = {2015-09-28 06:36:07 +0000},
	Db = {PMC},
	Doi = {10.1371/journal.pone.0097505},
	Editor = {Shomron, Noam},
	Isbn = {1932-6203},
	J1 = {PLoS One},
	Journal = {PLoS ONE},
	Number = {5},
	Pages = {e97505},
	Publisher = {Public Library of Science},
	Title = {HIV-1 Quasispecies Delineation by Tag Linkage Deep Sequencing},
	Ty = {JOUR},
	U1 = {PONE-D-14-02705{$[$}PII{$]$}; 24842159{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4026136/},
	Volume = {9},
	Year = {2014},
	Year1 = {2014/05/19},
	Year2 = {2014/01/20/received},
	Year3 = {2014/04/17/accepted},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4026136/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1371/journal.pone.0097505}}

@unpublished{Neher1509.02483v1,
	Abstract = {Many microbial populations rapidly adapt to changing environments with multiple variants competing
for survival. To quantify such complex evolutionary dynamics in vivo, time resolved and
genome wide data including rare variants are essential. We performed whole-genome deep sequencing
of HIV-1 populations in 9 untreated patients, with 6-12 longitudinal samples per patient
spanning 5-8 years of infection. We show that patterns of minor diversity are reproducible between
patients and mirror global HIV-1 diversity, suggesting a universal landscape of fitness costs that
control diversity. Reversions towards the ancestral HIV-1 sequence are observed throughout infection
and account for almost one third of all sequence changes. Reversion rates depend strongly
on conservation. Frequent recombination limits linkage disequilibrium to about 100bp in most of
the genome, but strong hitch-hiking due to short range linkage limits diversity.},
	Author = {Zanini, Fabio and Brodin, Johanna and Thebo, Lina and Lanz, Christa and Bratt, G{\"o}ran and Albert, Jan and Neher, Richard A},
	Date-Added = {2015-10-12 05:27:46 +0000},
	Date-Modified = {2015-10-12 05:30:09 +0000},
	Month = {September},
	Note = {arXiv:1509.02483v1 [q-bio.PE] 8 Sep 2015},
	Title = {Population genomics of intrapatient HIV-1 evolution},
	Year = {2015}}

@article{Gounder:2015aa,
	Abstract = {In chronic HIV infection, CD8+ T cell responses to Gag are associated with lower viral loads, but longitudinal studies of HLA-restricted CD8+ T cell-driven selection pressure in Gag from the time of acute infection are limited. In this study we examined Gag sequence evolution over the first year of infection in 22 patients identified prior to seroconversion. A total of 310 and 337 full-length Gag sequences from the earliest available samples (median = 14 days after infection {$[$}Fiebig stage I/II{$]$}) and at one-year post infection respectively were generated. Six of 22 (27{\%}) individuals were infected with multiple variants. There was a trend towards early intra-patient viral sequence diversity correlating with viral load set point (p = 0.07, r = 0.39). At 14 days post infection, 59.7{\%} of Gag CTL epitopes contained non-consensus polymorphisms and over half of these (35.3{\%}) comprised of previously described CTL escape variants. Consensus and variant CTL epitope proportions were equally distributed irrespective of the selecting host HLA allele and most epitopes remained unchanged over 12 months post infection. These data suggest that intrapatient diversity during acute infection is an indicator of disease outcome. In this setting, there is a high rate of transmitted CTL escape variants and limited immune selection in Gag during the first year of infection. These data have relevance for vaccine strategies designed to elicit effective CD8+ T cell immune responses.},
	Address = {San Francisco, CA USA},
	An = {PMC4363590},
	Author = {Gounder, Kamini and Padayachi, Nagavelli and Mann, Jaclyn K and Radebe, Mopo and Mokgoro, Mammekwa and van der Stok, Mary and Mkhize, Lungile and Mncube, Zenele and Jaggernath, Manjeetha and Reddy, Tarylee and Walker, Bruce D and Ndung'u, Thumbi},
	Date-Added = {2015-09-28 07:16:33 +0000},
	Date-Modified = {2015-09-28 07:16:57 +0000},
	Db = {PMC},
	Doi = {10.1371/journal.pone.0119886},
	Editor = {Gray, Clive M},
	Isbn = {1932-6203},
	J1 = {PLoS One},
	Journal = {PLoS ONE},
	Keywords = {longitudinal; data; HIV founder detection},
	Number = {3},
	Pages = {e0119886},
	Publisher = {Public Library of Science},
	Title = {High Frequency of Transmitted HIV-1 Gag HLA Class I-Driven Immune Escape Variants but Minimal Immune Selection over the First Year of Clade C Infection},
	Ty = {JOUR},
	U1 = {25781986{$[$}pmid{$]$}; PONE-D-14-52860{$[$}PII{$]$}; 25781986{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4363590/},
	Volume = {10},
	Year = {2015},
	Year1 = {2015/03/17},
	Year2 = {2014/11/25/received},
	Year3 = {2015/02/03/accepted},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4363590/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1371/journal.pone.0119886}}

@article{Sterrett:2014aa,
	Abstract = {BACKGROUND:  We performed human immunodeficiency virus type 1 (HIV-1) transmitted/founder (T/F) virus analysis of the VAX003 vaccine efficacy trial participants to characterize the transmission bottleneck and test for vaccine-associated reduction or enhancement of infection in this injection drug user (IDU) cohort. METHODS:  We performed single genome sequencing of plasma vRNA from 50 subjects sampled in early HIV infection. Sequences were analyzed phylogenetically, T/F viruses enumerated, and a sieve analysis performed. RESULTS:  Eight of 19 (42{\%}) placebo recipients were productively infected by more than 1 virus (range 1--5, median 1, mean 1.7). This frequency of multiple virus transmission was greater than reported for heterosexual cohorts (19{\%}, P = .03) but not statistically different from vaccine recipients (22.6{\%}, P > .05), where the range was 1--3, median 1, and mean 1.3 (P > .05 for all comparisons). An atypical sieve effect was detected in Env V2 but was not associated with reduction or enhancement of virus acquisition. CONCLUSIONS:  The number of T/F viruses in IDUs was surprising low, with 95{\%} of individuals infected by only 1--3 viruses. This finding suggests that a successful vaccine or other prevention modality generally needs to protect against only one or a few viruses regardless of risk behavior. T/F analysis identified an atypical genetic sieve in the V2 region of Envelope and found no evidence for vaccine-mediated enhancement in VAX003.},
	An = {PMC4281816},
	Author = {Sterrett, Sarah and Learn, Gerald H and Edlefsen, Paul T and Haynes, Barton F and Hahn, Beatrice H and Shaw, George M and Bar, Katharine J},
	Date = {2014/09/},
	Date-Added = {2015-09-28 04:57:51 +0000},
	Date-Modified = {2015-09-28 05:03:08 +0000},
	Db = {PMC},
	Doi = {10.1093/ofid/ofu056},
	Isbn = {2328-8957},
	J1 = {Open Forum Infect Dis},
	Journal = {Open Forum Infectious Diseases},
	Keywords = {Katie; Paul; HIV founder detection; data},
	Month = {09},
	Number = {2},
	Pages = {ofu056},
	Publisher = {Oxford University Press},
	Title = {Low Multiplicity of HIV-1 Infection and No Vaccine Enhancement in VAX003 Injection Drug Users},
	Ty = {JOUR},
	U1 = {ofu056{$[$}PII{$]$}; 25734126{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4281816/},
	Volume = {1},
	Year = {2014},
	Year1 = {2014/08/14},
	Year2 = {2014/05/13/received},
	Year3 = {2014/06/23/accepted},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4281816/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/ofid/ofu056}}

@article{Li:2010aa,
	Abstract = {Elucidating virus-host interactions responsible for HIV-1 transmission is important for advancing HIV-1 prevention strategies. To this end, single genome amplification (SGA) and sequencing of HIV-1 within the context of a model of random virus evolution has made possible for the first time an unambiguous identification of transmitted/founder viruses and a precise estimation of their numbers. Here, we applied this approach to HIV-1 env analyses in a cohort of acutely infected men who have sex with men (MSM) and found that a high proportion (10 of 28; 36%) had been productively infected by more than one virus. In subjects with multivariant transmission, the minimum number of transmitted viruses ranged from 2 to 10 with viral recombination leading to rapid and extensive genetic shuffling among virus lineages. A combined analysis of these results, together with recently published findings based on identical SGA methods in largely heterosexual (HSX) cohorts, revealed a significantly higher frequency of multivariant transmission in MSM than in HSX [19 of 50 subjects (38%) versus 34 of 175 subjects (19%); Fisher's exact p = 0.008]. To further evaluate the SGA strategy for identifying transmitted/founder viruses, we analyzed 239 overlapping 5' and 3' half genome or env-only sequences from plasma viral RNA (vRNA) and blood mononuclear cell DNA in an MSM subject who had a particularly well-documented virus exposure history 3-6 days before symptom onset and 14-17 days before peak plasma viremia (47,600,000 vRNA molecules/ml). All 239 sequences coalesced to a single transmitted/founder virus genome in a time frame consistent with the clinical history, and a molecular clone of this genome encoded replication competent virus in accord with model predictions. Higher multiplicity of HIV-1 infection in MSM compared with HSX is consistent with the demonstrably higher epidemiological risk of virus acquisition in MSM and could indicate a greater challenge for HIV-1 vaccines than previously recognized.},
	Address = {Department of Medicine, University of Alabama at Birmingham, Birmingham, Alabama, United States of America.},
	Author = {Li, Hui and Bar, Katharine J and Wang, Shuyi and Decker, Julie M and Chen, Yalu and Sun, Chuanxi and Salazar-Gonzalez, Jesus F and Salazar, Maria G and Learn, Gerald H and Morgan, Charity J and Schumacher, Joseph E and Hraber, Peter and Giorgi, Elena E and Bhattacharya, Tanmoy and Korber, Bette T and Perelson, Alan S and Eron, Joseph J and Cohen, Myron S and Hicks, Charles B and Haynes, Barton F and Markowitz, Martin and Keele, Brandon F and Hahn, Beatrice H and Shaw, George M},
	Crdt = {2010/05/21 06:00},
	Da = {20100520},
	Date = {2010 May},
	Date-Added = {2015-09-27 00:15:08 +0000},
	Date-Modified = {2015-09-27 00:17:12 +0000},
	Dcom = {20100825},
	Dep = {20100513},
	Doi = {10.1371/journal.ppat.1000890},
	Edat = {2010/05/21 06:00},
	Gr = {AI27767/AI/NIAID NIH HHS/United States; AI28433/AI/NIAID NIH HHS/United States; AI41534/AI/NIAID NIH HHS/United States; AI67854/AI/NIAID NIH HHS/United States; CA13148/CA/NCI NIH HHS/United States; HHSN266200400088C/PHS HHS/United States; P30 AI050410/AI/NIAID NIH HHS/United States; RR24143/RR/NCRR NIH HHS/United States},
	Issn = {1553-7374 (Electronic); 1553-7366 (Linking)},
	Jid = {101238921},
	Journal = {PLoS Pathog},
	Jt = {PLoS pathogens},
	Keywords = {LANL HIV acute infection studies; data; Katie},
	Language = {eng},
	Lid = {10.1371/journal.ppat.1000890 {$[$}doi{$]$}},
	Lr = {20150409},
	Mh = {Disease Outbreaks/statistics \& numerical data; Evolution, Molecular; Genetic Variation; Genome, Viral; *HIV Infections/epidemiology/prevention \& control/transmission; HIV-1/*genetics/*growth \& development/pathogenicity; Heterosexuality/statistics \& numerical data; Homosexuality, Male/*statistics \& numerical data; Humans; Male; Models, Genetic; Recombination, Genetic/genetics; Risk Factors; Sexual Behavior/*statistics \& numerical data; Virulence; env Gene Products, Human Immunodeficiency Virus/genetics},
	Mhda = {2010/08/26 06:00},
	Month = {May},
	Number = {5},
	Oid = {NLM: PMC2869329},
	Own = {NLM},
	Pages = {e1000890},
	Phst = {2009/12/18 {$[$}received{$]$}; 2010/04/01 {$[$}accepted{$]$}; 2010/05/13 {$[$}epublish{$]$}},
	Pl = {United States},
	Pmc = {PMC2869329},
	Pmid = {20485520},
	Pst = {epublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't},
	Rn = {0 (env Gene Products, Human Immunodeficiency Virus)},
	Sb = {IM},
	Status = {MEDLINE},
	Title = {High Multiplicity Infection by HIV-1 in Men Who Have Sex with Men.},
	Volume = {6},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.ppat.1000890}}

@article{Gottlieb:2008aa,
	Abstract = {Understanding the characteristics of human immunodeficiency virus (HIV) necessary for infection in a new host is a critical goal for acquired immunodeficiency syndrome (AIDS) research. We studied the characteristics of HIV-1 envelope genes in 38 men in the Multicenter AIDS Cohort Study cohort before seroconversion. We found a range of diversity (0.2%-5.6% [median, 0.86%]), V1-V2 loop length (58-93 aa), and potential N-linked glycosylation sites (n = 2-9). However, at least 46% of the men had replicating virus that appeared to have been derived from a single viral variant. Nearly all variants were predicted to be CCR5 tropic. We found no correlation between these viral characteristics and the HIV outcomes of time to clinical AIDS or death and/or a CD4 cell count <200 cells/microL.},
	Address = {Division of Allergy and Infectious Diseases, Department of Medicine, School of Medicine, University of Washington, Seattle 98195, USA. gottlieb@u.washington.edu},
	Author = {Gottlieb, Geoffrey S and Heath, Laura and Nickle, David C and Wong, Kim G and Leach, Stephanie E and Jacobs, Benjamin and Gezahegne, Surafel and van 't Wout, Angelique B and Jacobson, Lisa P and Margolick, Joseph B and Mullins, James I},
	Crdt = {2008/04/19 09:00},
	Da = {20080418},
	Date = {2008 Apr 1},
	Date-Added = {2015-09-27 00:00:43 +0000},
	Date-Modified = {2015-09-27 00:03:31 +0000},
	Dcom = {20080506},
	Doi = {10.1086/529206},
	Edat = {2008/04/19 09:00},
	Gr = {5-M01-RR-00722/RR/NCRR NIH HHS/United States; P01-AI57005/AI/NIAID NIH HHS/United States; P30-AI27757/AI/NIAID NIH HHS/United States; R01 AI047734/AI/NIAID NIH HHS/United States; R01 AI047734-05/AI/NIAID NIH HHS/United States; R01 AI058894/AI/NIAID NIH HHS/United States; R01 AI058894-04/AI/NIAID NIH HHS/United States; R01-AI058894/AI/NIAID NIH HHS/United States; R37 AI047734/AI/NIAID NIH HHS/United States; R37 AI047734-06A1/AI/NIAID NIH HHS/United States; R37-AI047734/AI/NIAID NIH HHS/United States; U01-AI-35039/AI/NIAID NIH HHS/United States; U01-AI-35040/AI/NIAID NIH HHS/United States; U01-AI-35041/AI/NIAID NIH HHS/United States; U01-AI-35042/AI/NIAID NIH HHS/United States; U01-AI-35043/AI/NIAID NIH HHS/United States; U01-AI-37613/AI/NIAID NIH HHS/United States; U01-AI-37984/AI/NIAID NIH HHS/United States},
	Issn = {0022-1899 (Print); 0022-1899 (Linking)},
	Jid = {0413675},
	Journal = {J Infect Dis},
	Jt = {The Journal of infectious diseases},
	Keywords = {LANL HIV acute infection studies; data; Jim; MACS},
	Language = {eng},
	Lid = {10.1086/529206 {$[$}doi{$]$}},
	Lr = {20140922},
	Mh = {Adolescent; Adult; CD4 Lymphocyte Count; Cluster Analysis; Cohort Studies; Genotype; Glycosylation; HIV Infections/*virology; HIV-1/*classification/*isolation \& purification/pathogenicity; Homosexuality; Humans; Male; Middle Aged; Phylogeny; Polymorphism, Genetic; RNA, Viral/genetics; Receptors, CCR5/metabolism; Sequence Analysis, DNA; Sequence Homology; Time Factors; env Gene Products, Human Immunodeficiency Virus/*genetics},
	Mhda = {2008/05/07 09:00},
	Mid = {NIHMS130672},
	Month = {Apr},
	Number = {7},
	Oid = {NLM: NIHMS130672; NLM: PMC3419593},
	Own = {NLM},
	Pages = {1011--1015},
	Pl = {United States},
	Pmc = {PMC3419593},
	Pmid = {18419538},
	Pst = {ppublish},
	Pt = {Journal Article; Multicenter Study; Research Support, N.I.H., Extramural},
	Rn = {0 (RNA, Viral); 0 (Receptors, CCR5); 0 (env Gene Products, Human Immunodeficiency Virus)},
	Sb = {AIM; IM},
	Status = {MEDLINE},
	Title = {HIV-1 variation before seroconversion in men who have sex with men: analysis of acute/early HIV infection in the multicenter AIDS cohort study.},
	Volume = {197},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1086/529206}}

@article{Abrahams:2009aa,
	Abstract = {Identifying the specific genetic characteristics of successfully transmitted variants may prove central to the development of effective vaccine and microbicide interventions. Although human immunodeficiency virus transmission is associated with a population bottleneck, the extent to which different factors influence the diversity of transmitted viruses is unclear. We estimate here the number of transmitted variants in 69 heterosexual men and women with primary subtype C infections. From 1,505 env sequences obtained using a single genome amplification approach we show that 78{\%} of infections involved single variant transmission and 22{\%} involved multiple variant transmissions (median of 3). We found evidence for mutations selected for cytotoxic-T-lymphocyte or antibody escape and a high prevalence of recombination in individuals infected with multiple variants representing another potential escape pathway in these individuals. In a combined analysis of 171 subtype B and C transmission events, we found that infection with more than one variant does not follow a Poisson distribution, indicating that transmission of individual virions cannot be seen as independent events, each occurring with low probability. While most transmissions resulted from a single infectious unit, multiple variant transmissions represent a significant fraction of transmission events, suggesting that there may be important mechanistic differences between these groups that are not yet understood.},
	An = {PMC2663249},
	Author = {Abrahams, M-R and Anderson, J A and Giorgi, E E and Seoighe, C and Mlisana, K and Ping, L-H and Athreya, G S and Treurnicht, F K and Keele, B F and Wood, N and Salazar-Gonzalez, J F and Bhattacharya, T and Chu, H and Hoffman, I and Galvin, S and Mapanje, C and Kazembe, P and Thebus, R and Fiscus, S and Hide, W and Cohen, M S and Karim, S Abdool and Haynes, B F and Shaw, G M and Hahn, B H and Korber, B T and Swanstrom, R and Williamson, C and for the CAPRISA Acute Infection Study Team and the Center for HIV-AIDS Vaccine Immunology Consortium},
	Date = {2009/04/},
	Date-Added = {2015-09-26 20:46:36 +0000},
	Date-Modified = {2015-09-26 20:47:11 +0000},
	Db = {PMC},
	Doi = {10.1128/JVI.02132-08},
	Isbn = {0022-538X; 1098-5514},
	J1 = {J Virol},
	Journal = {Journal of Virology},
	Keywords = {HIV founder detection; non-poisson},
	Month = {04},
	Number = {8},
	Pages = {3556--3567},
	Publisher = {American Society for Microbiology (ASM)},
	Title = {Quantitating the Multiplicity of Infection with Human Immunodeficiency Virus Type 1 Subtype C Reveals a Non-Poisson Distribution of Transmitted Variants},
	Ty = {JOUR},
	U1 = {2132-08{$[$}PII{$]$}; 19193811{$[$}pmid{$]$}; 19193811{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2663249/},
	Volume = {83},
	Year = {2009},
	Year1 = {2009/02/04},
	Year2 = {2008/10/09/received},
	Year3 = {2008/12/24/accepted},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2663249/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1128/JVI.02132-08}}

@article{Keele:2008aa,
	Abstract = {The precise identification of the HIV-1 envelope glycoprotein (Env) responsible for productive clinical infection could be instrumental in elucidating the molecular basis of HIV-1 transmission and in designing effective vaccines. Here, we developed a mathematical model of random viral evolution and, together with phylogenetic tree construction, used it to analyze 3,449 complete env sequences derived by single genome amplification from 102 subjects with acute HIV-1 (clade B) infection. Viral env genes evolving from individual transmitted or founder viruses generally exhibited a Poisson distribution of mutations and star-like phylogeny, which coalesced to an inferred consensus sequence at or near the estimated time of virus transmission. Overall, 78 of 102 subjects had evidence of productive clinical infection by a single virus, and 24 others had evidence of productive clinical infection by a minimum of two to five viruses. Phenotypic analysis of transmitted or early founder Envs revealed a consistent pattern of CCR5 dependence, masking of coreceptor binding regions, and equivalent or modestly enhanced resistance to the fusion inhibitor T1249 and broadly neutralizing antibodies compared with Envs from chronically infected subjects. Low multiplicity infection and limited viral evolution preceding peak viremia suggest a finite window of potential vulnerability of HIV-1 to vaccine-elicited immune responses, although phenotypic properties of transmitted Envs pose a formidable defense.},
	An = {PMC2387184},
	Author = {Keele, Brandon F and Giorgi, Elena E and Salazar-Gonzalez, Jesus F and Decker, Julie M and Pham, Kimmy T and Salazar, Maria G and Sun, Chuanxi and Grayson, Truman and Wang, Shuyi and Li, Hui and Wei, Xiping and Jiang, Chunlai and Kirchherr, Jennifer L and Gao, Feng and Anderson, Jeffery A and Ping, Li-Hua and Swanstrom, Ronald and Tomaras, Georgia D and Blattner, William A and Goepfert, Paul A and Kilby, J Michael and Saag, Michael S and Delwart, Eric L and Busch, Michael P and Cohen, Myron S and Montefiori, David C and Haynes, Barton F and Gaschen, Brian and Athreya, Gayathri S and Lee, Ha Y and Wood, Natasha and Seoighe, Cathal and Perelson, Alan S and Bhattacharya, Tanmoy and Korber, Bette T and Hahn, Beatrice H and Shaw, George M},
	Date = {2008/05/27},
	Date-Added = {2015-09-26 19:40:24 +0000},
	Date-Modified = {2015-09-26 19:50:19 +0000},
	Db = {PMC},
	Doi = {10.1073/pnas.0802203105},
	Isbn = {0027-8424; 1091-6490},
	J1 = {Proc Natl Acad Sci U S A},
	Journal = {Proceedings of the National Academy of Sciences of the United States of America},
	Keywords = {HIV founder detection; HIV timing estimation; poisson},
	Month = {05},
	Number = {21},
	Pages = {7552--7557},
	Publisher = {National Academy of Sciences},
	Title = {Identification and characterization of transmitted and early founder virus envelopes in primary HIV-1 infection},
	Ty = {JOUR},
	U1 = {18490657{$[$}pmid{$]$}; 0166{$[$}PII{$]$}; 18490657{$[$}pmid{$]$}},
	Url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2387184/},
	Volume = {105},
	Year = {2008},
	Year1 = {2008/05/19},
	Year2 = {2007/12/20/received},
	Bdsk-Url-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2387184/},
	Bdsk-Url-2 = {http://dx.doi.org/10.1073/pnas.0802203105}}

@article{FollmannMultiplicityVE,
	Abstract = {
Vaccine clinical trials with active surveillance for infection often use the time to infection as the primary endpoint. A common method of analysis for such trials is to compare the times to infection between the vaccine and placebo groups using a Cox regression model. With new technology, we can sometimes additionally record the precise number of virions that cause infection rather than just the indicator that infection occurred. In this article, we develop a unified approach for vaccine trials that couples the time to infection with the number of infecting or founder viruses. We assume that the instantaneous risk of a potentially infectious exposure for individuals in the placebo and vaccine groups follows the same proportional intensity model. Following exposure, the number of founder viruses X* is assumed to be generated from some distribution on 0,1,{\ldots}, which is allowed to be different for the two groups. Exposures that result in X*=0 are unobservable. We denote the placebo and vaccine means of X* by μ and μΔ so that 1−Δ measures the proportion reduction in the mean number of infecting virions due to vaccination per exposure. We develop different semi-parametric methods of estimating Δ. We allow the distribution of X* to be Poisson or unspecified, and discuss how to incorporate covariates that impact the time to exposure and/or X*. Interestingly Δ, which is a ratio of untruncated means, can be reliably estimated using truncated data (X*>0), even if the placebo and vaccine distributions of X* are completely unspecified. Simulations of vaccine clinical trials show that the method can reliably recover Δ in realistic settings. We apply our methods to an HIV vaccine trial conducted in injecting drug users.
},
	Author = {Follmann, Dean and Huang, Chiung-Yu},
	Doi = {10.1111/biom.12277},
	Issn = {1541-0420},
	Journal = {Biometrics},
	Keywords = {Burden of illness, Competing risks, Cox regression, Empirical process, Infectious disease, Marked process},
	Number = {2},
	Pages = {386--396},
	Title = {Incorporating founder virus information in vaccine field trials},
	Url = {http://dx.doi.org/10.1111/biom.12277},
	Volume = {71},
	Year = {2015},
	Bdsk-Url-1 = {http://dx.doi.org/10.1111/biom.12277}}

@comment{BibDesk URL Groups{
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<array>
	<dict>
		<key>URL</key>
		<string>file://localhost/Users/pedlefse/Downloads/bibtex-citations</string>
		<key>group name</key>
		<string>bibtex-citations</string>
	</dict>
	<dict>
		<key>URL</key>
		<string>file://localhost/Users/pedlefse/Documents/hiatus/hunterMMs.bib</string>
		<key>group name</key>
		<string>hunterMMs.bib</string>
	</dict>
	<dict>
		<key>URL</key>
		<string>file://localhost/Users/pedlefse/Downloads/mal_cmb3_361.bib</string>
		<key>group name</key>
		<string>mal_cmb3_361.bib</string>
	</dict>
	<dict>
		<key>URL</key>
		<string>file://localhost/Users/pedlefse/Documents/hiatus/Mamitsuka1998.bib</string>
		<key>group name</key>
		<string>Mamitsuka1998.bib</string>
	</dict>
	<dict>
		<key>URL</key>
		<string>file://localhost/Users/pedlefse/Documents/hiatus/Rumelhart1986.bib</string>
		<key>group name</key>
		<string>Rumelhart1986.bib</string>
	</dict>
</array>
</plist>
}}