mainthesis.bbl

\begin{thebibliography}{10}

\bibitem{myers1995}
EW~Myers.
\newblock Toward simplifying and accurately formulating fragment assembly.
\newblock {\em J. Comp. Biol.}, 2:275--90, 1995.

\bibitem{medvedev2007computability}
Paul Medvedev, Konstantinos Georgiou, Gene Myers, and Michael Brudno.
\newblock Computability of models for sequence assembly.
\newblock In {\em Algorithms in Bioinformatics}, pages 289--301. Springer,
  2007.

\bibitem{ABySS}
J.T. Simpson, K.~Wong, S.~D. Jackman, J.~E. Schein, S.~J.~M. Jones, and
  .I~Birol.
\newblock Abyss: a parallel assembler for short read sequence data.
\newblock {\em Genome Res.}, 19(6):1117--1123, 2009.

\bibitem{SOAPdenovo}
R~Li, H~Zhu, J~Ruan, W~Qian, X~Fang, Z~Shi, Y~Li, S~Li, G~Shan, and et~al.
  Kristiansen, K.
\newblock De novo assembly of human genomes with massively parallel short read
  sequencing.
\newblock {\em Bioinformatics}, 20(2):265--272, 2010.

\bibitem{Velvet}
D.~R. Zerbino and E.~Birney.
\newblock Velvet: algorithms for de novo short read assembly using de bruijn
  graphs.
\newblock {\em Genome Res.}, 18:821--829, 2008.

\bibitem{salzberg2005misassemblies}
S.~L. Salzberg and J.A. Yorke.
\newblock Beware of mis-assembled genomes.
\newblock {\em Bioinformatics}, 21(24):4320--4321, 2005.

\bibitem{nagarajan2010finishing}
N.~Nagarajan, C.~Cook, M.P. Di~Bonaventura, H.~Ge, A.~Richards,
  K.~Bishop-Lilly, R.~DeSalle, T.~Read, and M.~Pop.
\newblock Finishing genomes with limited resources: lessons from an ensemble of
  microbial genomes.
\newblock {\em BMC genomics}, 11(1):242, 2010.

\bibitem{chin2013nonhybrid}
Chen-Shan Chin, David~H Alexander, Patrick Marks, Aaron~A Klammer, James Drake,
  Cheryl Heiner, Alicia Clum, Alex Copeland, John Huddleston, Evan~E Eichler,
  et~al.
\newblock Nonhybrid, finished microbial genome assemblies from long-read smrt
  sequencing data.
\newblock {\em Nature methods}, 2013.

\bibitem{koren2013reducing}
Sergey Koren, Gregory~P Harhay, Timothy~PL Smith, James~L Bono, Dayna~M Harhay,
  D~Scott Mcvey, Diana Radune, Nicholas~H Bergman, and Adam~M Phillippy.
\newblock Reducing assembly complexity of microbial genomes with
  single-molecule sequencing.
\newblock {\em arXiv preprint arXiv:1304.3752}, 2013.

\bibitem{ribeiro2012finished}
Filipe~J Ribeiro, Dariusz Przybylski, Shuangye Yin, Ted Sharpe, Sante Gnerre,
  Amr Abouelleil, Aaron~M Berlin, Anna Montmayeur, Terrance~P Shea, Bruce~J
  Walker, et~al.
\newblock Finished bacterial genomes from shotgun sequence data.
\newblock {\em Genome research}, 22(11):2270--2277, 2012.

\bibitem{rusch2007sorcerer}
Douglas~B Rusch, Aaron~L Halpern, Granger Sutton, Karla~B Heidelberg, Shannon
  Williamson, Shibu Yooseph, Dongying Wu, Jonathan~A Eisen, Jeff~M Hoffman,
  Karin Remington, et~al.
\newblock The sorcerer ii global ocean sampling expedition: northwest atlantic
  through eastern tropical pacific.
\newblock {\em PLoS biology}, 5(3):e77, 2007.

\bibitem{wu2011stalking}
Dongying Wu, Martin Wu, Aaron Halpern, Douglas~B Rusch, Shibu Yooseph, Marvin
  Frazier, J~Craig Venter, and Jonathan~A Eisen.
\newblock Stalking the fourth domain in metagenomic data: searching for,
  discovering, and interpreting novel, deep branches in marker gene
  phylogenetic trees.
\newblock {\em PLoS One}, 6(3):e18011, 2011.

\bibitem{yooseph2007sorcerer}
Shibu Yooseph, Granger Sutton, Douglas~B Rusch, Aaron~L Halpern, Shannon~J
  Williamson, Karin Remington, Jonathan~A Eisen, Karla~B Heidelberg, Gerard
  Manning, Weizhong Li, et~al.
\newblock The sorcerer ii global ocean sampling expedition: expanding the
  universe of protein families.
\newblock {\em PLoS biology}, 5(3):e16, 2007.

\bibitem{varin2012metagenomic}
Thibault Varin, Connie Lovejoy, Anne~D Jungblut, Warwick~F Vincent, and Jacques
  Corbeil.
\newblock Metagenomic analysis of stress genes in microbial mat communities
  from antarctica and the high arctic.
\newblock {\em Applied and environmental microbiology}, 78(2):549--559, 2012.

\bibitem{he2013comparative}
Shaomei He, Natalia Ivanova, Edward Kirton, Martin Allgaier, Claudia Bergin,
  Rudolf~H Scheffrahn, Nikos~C Kyrpides, Falk Warnecke, Susannah~G Tringe, and
  Philip Hugenholtz.
\newblock Comparative metagenomic and metatranscriptomic analysis of hindgut
  paunch microbiota in wood-and dung-feeding higher termites.
\newblock {\em PloS one}, 8(4):e61126, 2013.

\bibitem{gill2006metagenomic}
Steven~R Gill, Mihai Pop, Robert~T DeBoy, Paul~B Eckburg, Peter~J Turnbaugh,
  Buck~S Samuel, Jeffrey~I Gordon, David~A Relman, Claire~M Fraser-Liggett, and
  Karen~E Nelson.
\newblock Metagenomic analysis of the human distal gut microbiome.
\newblock {\em science}, 312(5778):1355--1359, 2006.

\bibitem{peterson2009nih}
Jane Peterson, Susan Garges, Maria Giovanni, Pamela McInnes, Lu~Wang, Jeffery~A
  Schloss, Vivien Bonazzi, Jean~E McEwen, Kris~A Wetterstrand, Carolyn Deal,
  et~al.
\newblock The nih human microbiome project.
\newblock {\em Genome research}, 19(12):2317--2323, 2009.

\bibitem{peng2011meta}
Yu~Peng, Henry~CM Leung, Siu-Ming Yiu, and Francis~YL Chin.
\newblock Meta-idba: a de novo assembler for metagenomic data.
\newblock {\em Bioinformatics}, 27(13):i94--i101, 2011.

\bibitem{namiki2012metavelvet}
Toshiaki Namiki, Tsuyoshi Hachiya, Hideaki Tanaka, and Yasubumi Sakakibara.
\newblock Metavelvet: an extension of velvet assembler to de novo metagenome
  assembly from short sequence reads.
\newblock {\em Nucleic acids research}, 40(20):e155--e155, 2012.

\bibitem{boisvert2012ray}
S{\'e}bastien Boisvert, Fr{\'e}d{\'e}ric Raymond, {\'E}l{\'e}nie Godzaridis,
  Fran{\c{c}}ois Laviolette, Jacques Corbeil, et~al.
\newblock Ray meta: scalable de novo metagenome assembly and profiling.
\newblock {\em Genome biology}, 13(12):R122, 2012.

\bibitem{salzberg2011gage}
S.L. Salzberg, A.M. Phillippy, A.~Zimin, D.~Puiu, T.~Magoc, S.~Koren, T.J.
  Treangen, M.C. Schatz, A.L. Delcher, M.~Roberts, et~al.
\newblock Gage: A critical evaluation of genome assemblies and assembly
  algorithms.
\newblock {\em Genome Research}, 2011.

\bibitem{earl2011assemblathon}
D.~Earl, K.~Bradnam, J.S. John, A.~Darling, D.~Lin, J.~Fass, H.O.K. Yu,
  V.~Buffalo, D.R. Zerbino, M.~Diekhans, et~al.
\newblock Assemblathon 1: A competitive assessment of de novo short read
  assembly methods.
\newblock {\em Genome research}, 21(12):2224--2241, 2011.

\bibitem{bradnam2013assemblathon}
Keith~R Bradnam, Joseph~N Fass, Anton Alexandrov, Paul Baranay, Michael
  Bechner, {\.I}nan{\c{c}} Birol, S{\'e}bastien Boisvert10, Jarrod~A Chapman,
  Guillaume Chapuis, Rayan Chikhi, et~al.
\newblock Assemblathon 2: evaluating de novo methods of genome assembly in
  three vertebrate species.
\newblock {\em arXiv preprint arXiv:1301.5406}, 2013.

\bibitem{clark2013ale}
Scott Clark, Rob Egan, Peter~I Frazier, and Zhong Wang.
\newblock Ale: a generic assembly likelihood evaluation framework for assessing
  the accuracy of genome and metagenome assemblies.
\newblock {\em Bioinformatics}, 2013.

\bibitem{rahman2013cgal}
Atif Rahman and Lior Pachter.
\newblock Cgal: computing genome assembly likelihoods.
\newblock {\em Genome Biology}, 14(1):R8, 2013.

\bibitem{LAP}
M.~Ghodsi, Hill C.M., I.~Astrovskaya, H.~Lin, Sommer D., Koren S., and M.~Pop.
\newblock De novo genome assembly evaluation.
\newblock In press.

\bibitem{angly2006marine}
Florent~E Angly, Ben Felts, Mya Breitbart, Peter Salamon, Robert~A Edwards,
  Craig Carlson, Amy~M Chan, Matthew Haynes, Scott Kelley, Hong Liu, et~al.
\newblock The marine viromes of four oceanic regions.
\newblock {\em PLoS biology}, 4(11):e368, 2006.

\bibitem{dinsdale2008functional}
Elizabeth~A Dinsdale, Robert~A Edwards, Dana Hall, Florent Angly, Mya
  Breitbart, Jennifer~M Brulc, Mike Furlan, Christelle Desnues, Matthew Haynes,
  Linlin Li, et~al.
\newblock Functional metagenomic profiling of nine biomes.
\newblock {\em Nature}, 452(7187):629--632, 2008.

\bibitem{carrigg2007dna}
Cora Carrigg, Olivia Rice, Siobh{\'a}n Kavanagh, Gavin Collins, and Vincent
  O’Flaherty.
\newblock Dna extraction method affects microbial community profiles from soils
  and sediment.
\newblock {\em Applied microbiology and biotechnology}, 77(4):955--964, 2007.

\bibitem{krsek1999comparison}
M~Krsek and EMH Wellington.
\newblock Comparison of different methods for the isolation and purification of
  total community dna from soil.
\newblock {\em Journal of Microbiological Methods}, 39(1):1--16, 1999.

\bibitem{morgan2010metagenomic}
Jenna~L Morgan, Aaron~E Darling, and Jonathan~A Eisen.
\newblock Metagenomic sequencing of an in vitro-simulated microbial community.
\newblock {\em PLoS One}, 5(4):e10209, 2010.

\bibitem{temperton2009bias}
Ben Temperton, Dawn Field, Anna Oliver, Bela Tiwari, Martin M{\"u}hling, Ian
  Joint, and Jack~A Gilbert.
\newblock Bias in assessments of marine microbial biodiversity in fosmid
  libraries as evaluated by pyrosequencing.
\newblock {\em The ISME journal}, 3(7):792--796, 2009.

\bibitem{treangen2013metamos}
Todd~J Treangen, Sergey Koren, Daniel~D Sommer, Bo~Liu, Irina Astrovskaya,
  Brian Ondov, Aaron~E Darling, Adam~M Phillippy, and Mihai Pop.
\newblock Metamos: a modular and open source metagenomic assembly and analysis
  pipeline.
\newblock {\em Genome biology}, 14(1):R2, 2013.

\bibitem{langmead2012fast}
Ben Langmead and Steven~L Salzberg.
\newblock Fast gapped-read alignment with bowtie 2.
\newblock {\em Nature methods}, 9(4):357--359, 2012.

\bibitem{mitreva2012structure}
Makedonka Mitreva et~al.
\newblock Structure, function and diversity of the healthy human microbiome.
\newblock {\em Nature}, 486:207--214, 2012.

\bibitem{methe2012framework}
Barbara~A Meth{\'e}, Karen~E Nelson, Mihai Pop, Heather~H Creasy, Michelle~G
  Giglio, Curtis Huttenhower, Dirk Gevers, Joseph~F Petrosino, Sahar Abubucker,
  Jonathan~H Badger, et~al.
\newblock A framework for human microbiome research.
\newblock {\em Nature}, 486(7402):215--221, 2012.

\bibitem{phillippy2008genome}
A.M. Phillippy, M.C. Schatz, and M.~Pop.
\newblock Genome assembly forensics: finding the elusive mis-assembly.
\newblock {\em Genome Biology}, 9(3):R55, 2008.

\bibitem{delcher2003using}
Arthur~L Delcher, Steven~L Salzberg, and Adam~M Phillippy.
\newblock Using mummer to identify similar regions in large sequence sets.
\newblock {\em Current Protocols in Bioinformatics}, pages 10--3, 2003.

\bibitem{chikhi2013informed}
Rayan Chikhi and Paul Medvedev.
\newblock Informed and automated k-mer size selection for genome assembly.
\newblock {\em arXiv preprint arXiv:1304.5665}, 2013.

\bibitem{Cock:2010ve}
PJA Cock, CJ~Fields, N~Goto, ML~Heuer, and PM~Rice.
\newblock The {S}anger {FASTQ} file format for sequences with quality scores,
  and the {Solexa/Illumina FASTQ} variants.
\newblock {\em Nucleic Acids Res}, 38(6):1767--71, Apr 2010.

\bibitem{Ewing:1998ly}
B~Ewing and P~Green.
\newblock Base-calling of automated sequencer traces using {P}hred. {II}.
  {E}rror probabilities.
\newblock {\em Genome Res}, 8(3):186--94, Mar 1998.

\bibitem{Langmead:2012rw}
Ben Langmead and Steven~L Salzberg.
\newblock Fast gapped-read alignment with bowtie 2.
\newblock {\em Nat Methods}, 9(4):357--9, Apr 2012.

\bibitem{Minoche:2011km}
AE~Minoche, JC~Dohm, and H~Himmelbauer.
\newblock Evaluation of genomic high-throughput sequencing data generated on
  {Illumina HiSeq} and {Genome Analyzer} systems.
\newblock {\em Genome Biol}, 12(11):R112, 2011.

\bibitem{Canovas:2014fr}
Rodrigo C{\'a}novas, Alistair Moffat, and Andrew Turpin.
\newblock Lossy compression of quality scores in genomic data.
\newblock {\em Bioinformatics}, 30(15):2130--6, Aug 2014.

\bibitem{janin2013adaptive}
Lilian Janin, Giovanna Rosone, and Anthony~J Cox.
\newblock Adaptive reference-free compression of sequence quality scores.
\newblock {\em Bioinformatics}, page btt257, 2013.

\bibitem{mcgill1978variations}
Robert McGill, John~W Tukey, and Wayne~A Larsen.
\newblock Variations of box plots.
\newblock {\em The American Statistician}, 32(1):12--16, 1978.

\bibitem{Wan:2012kq}
Raymond Wan, Vo~Ngoc Anh, and Kiyoshi Asai.
\newblock Transformations for the compression of {FASTQ} quality scores of
  next-generation sequencing data.
\newblock {\em Bioinformatics}, 28(5):628--35, Mar 2012.

\bibitem{Ochoa:2013rt}
Idoia Ochoa, Himanshu Asnani, Dinesh Bharadia, Mainak Chowdhury, Tsachy
  Weissman, and Golan Yona.
\newblock {QualComp}: a new lossy compressor for quality scores based on rate
  distortion theory.
\newblock {\em BMC Bioinformatics}, 14:187, 2013.

\bibitem{macqueen1967some}
James MacQueen et~al.
\newblock Some methods for classification and analysis of multivariate
  observations.
\newblock In {\em Proceedings of the fifth Berkeley symposium on mathematical
  statistics and probability}, volume~1, pages 281--297. Oakland, CA, USA.,
  1967.

\bibitem{hartigan1979algorithm}
John~A Hartigan and Manchek~A Wong.
\newblock Algorithm as 136: A k-means clustering algorithm.
\newblock {\em Applied statistics}, pages 100--108, 1979.

\bibitem{Salzberg:2012rc}
SL~Salzberg, AM~Phillippy, A~Zimin, D~Puiu, T~Magoc, S~Koren, TJ~Treangen,
  MC~Schatz, AL~Delcher, M~Roberts, G~Mar{\c c}ais, M~Pop, and JA~Yorke.
\newblock {GAGE}: A critical evaluation of genome assemblies and assembly
  algorithms.
\newblock {\em Genome Res}, 22(3):557--67, Mar 2012.

\bibitem{sickle}
Joshi NA and Fass JN.
\newblock Sickle: A sliding-window, adaptive, quality-based trimming tool for
  {FastQ} files (version 1.33), 2013.

\bibitem{Ghodsi:2013hb}
M~Ghodsi, CM~Hill, I~Astrovskaya, H~Lin, DD~Sommer, S~Koren, and M~Pop.
\newblock De novo likelihood-based measures for comparing genome assemblies.
\newblock {\em BMC Res Notes}, 6:334, 2013.

\bibitem{Gnerre:2011kx}
S~Gnerre, I~MacCallum, D~Przybylski, FJ~Ribeiro, JN~Burton, BJ~Walker,
  T~Sharpe, G~Hall, TP~Shea, S~Sykes, AM~Berlin, D~Aird, M~Costello, R~Daza,
  L~Williams, R~Nicol, A~Gnirke, C~Nusbaum, ES~Lander, and DB~Jaffe.
\newblock High-quality draft assemblies of mammalian genomes from massively
  parallel sequence data.
\newblock {\em Proc Natl Acad Sci USA}, 108:1513--1518, 2011.

\bibitem{Kozanitis:2011kl}
Christos Kozanitis, Chris Saunders, Semyon Kruglyak, Vineet Bafna, and George
  Varghese.
\newblock Compressing genomic sequence fragments using {SlimGene}.
\newblock {\em J Comput Biol}, 18(3):401--13, Mar 2011.

\bibitem{Ferrarini:2013vf}
Marco Ferrarini, Marco Moretto, Judson~A Ward, Nada {\v S}urbanovski, Vladimir
  Stevanovi{\'c}, Lara Giongo, Roberto Viola, Duccio Cavalieri, Riccardo
  Velasco, Alessandro Cestaro, and Daniel~J Sargent.
\newblock An evaluation of the {PacBio RS} platform for sequencing and de novo
  assembly of a chloroplast genome.
\newblock {\em BMC Genomics}, 14:670, 2013.

\bibitem{Koren:2013ye}
Sergey Koren, Gregory~P Harhay, Timothy P~L Smith, James~L Bono, Dayna~M
  Harhay, Scott~D Mcvey, Diana Radune, Nicholas~H Bergman, and Adam~M
  Phillippy.
\newblock Reducing assembly complexity of microbial genomes with
  single-molecule sequencing.
\newblock {\em Genome Biol}, 14(9):R101, 2013.

\end{thebibliography}