paper.bib

@ARTICLE{Hubley2016-ze,
  title    = "The Dfam database of repetitive {DNA} families",
  author   = "Hubley, Robert and Finn, Robert D and Clements, Jody and Eddy,
              Sean R and Jones, Thomas A and Bao, Weidong and Smit, Arian F A
              and Wheeler, Travis J",
  abstract = "Repetitive DNA, especially that due to transposable elements
              (TEs), makes up a large fraction of many genomes. Dfam is an open
              access database of families of repetitive DNA elements, in which
              each family is represented by a multiple sequence alignment and a
              profile hidden Markov model (HMM). The initial release of Dfam,
              featured in the 2013 NAR Database Issue, contained 1143 families
              of repetitive elements found in humans, and was used to produce
              more than 100 Mb of additional annotation of TE-derived regions
              in the human genome, with improved speed. Here, we describe
              recent advances, most notably expansion to 4150 total families
              including a comprehensive set of known repeat families from four
              new organisms (mouse, zebrafish, fly and nematode). We describe
              improvements to coverage, and to our methods for identifying and
              reducing false annotation. We also describe updates to the
              website interface. The Dfam website has moved to http://dfam.org.
              Seed alignments, profile HMMs, hit lists and other underlying
              data are available for download.",
  journal  = "Nucleic Acids Res.",
  volume   =  44,
  number   = "D1",
  pages    = "D81--9",
  month    =  jan,
  year     =  2016,
  doi      = {10.1093/nar/gkv1272},
  keywords = "LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Finn2011-fs,
  title    = "{HMMER} web server: interactive sequence similarity searching",
  author   = "Finn, Robert D and Clements, Jody and Eddy, Sean R",
  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.",
  journal  = "Nucleic Acids Res.",
  volume   =  39,
  number   = "",
  pages    = "W29--37",
  month    =  jul,
  year     =  2011,
  keywords = "LTRpred Manuscript",
  doi      = {10.1093/nar/gkr367},
  language = "en"
}

@ARTICLE{Rognes2016-sk,
  title    = "VSEARCH: a versatile open source tool for metagenomics",
  author   = "Rognes, Torbj{\o}rn and Flouri, Tom{\'a}{\v s} and Nichols, Ben
              and Quince, Christopher and Mah{\'e}, Fr{\'e}d{\'e}ric",
  abstract = "BACKGROUND: VSEARCH is an open source and free of charge
              multithreaded 64-bit tool for processing and preparing
              metagenomics, genomics and population genomics nucleotide
              sequence data. It is designed as an alternative to the widely
              used USEARCH tool (Edgar, 2010) for which the source code is not
              publicly available, algorithm details are only rudimentarily
              described, and only a memory-confined 32-bit version is freely
              available for academic use. METHODS: When searching nucleotide
              sequences, VSEARCH uses a fast heuristic based on words shared by
              the query and target sequences in order to quickly identify
              similar sequences, a similar strategy is probably used in
              USEARCH. VSEARCH then performs optimal global sequence alignment
              of the query against potential target sequences, using full
              dynamic programming instead of the seed-and-extend heuristic used
              by USEARCH. Pairwise alignments are computed in parallel using
              vectorisation and multiple threads. RESULTS: VSEARCH includes
              most commands for analysing nucleotide sequences available in
              USEARCH version 7 and several of those available in USEARCH
              version 8, including searching (exact or based on global
              alignment), clustering by similarity (using length pre-sorting,
              abundance pre-sorting or a user-defined order), chimera detection
              (reference-based or de novo), dereplication (full length or
              prefix), pairwise alignment, reverse complementation, sorting,
              and subsampling. VSEARCH also includes commands for FASTQ file
              processing, i.e., format detection, filtering, read quality
              statistics, and merging of paired reads. Furthermore, VSEARCH
              extends functionality with several new commands and improvements,
              including shuffling, rereplication, masking of low-complexity
              sequences with the well-known DUST algorithm, a choice among
              different similarity definitions, and FASTQ file format
              conversion. VSEARCH is here shown to be more accurate than
              USEARCH when performing searching, clustering, chimera detection
              and subsampling, while on a par with USEARCH for paired-ends read
              merging. VSEARCH is slower than USEARCH when performing
              clustering and chimera detection, but significantly faster when
              performing paired-end reads merging and dereplication. VSEARCH is
              available at https://github.com/torognes/vsearch under either the
              BSD 2-clause license or the GNU General Public License version
              3.0. DISCUSSION: VSEARCH has been shown to be a fast, accurate
              and full-fledged alternative to USEARCH. A free and open-source
              versatile tool for sequence analysis is now available to the
              metagenomics community.",
  journal  = "PeerJ",
  volume   =  4,
  pages    = "e2584",
  month    =  oct,
  year     =  2016,
  doi      = {10.7717/peerj.2584},
  keywords = "Alignment; Chimera detection; Clustering; Dereplication; Masking;
              Metagenomics; Parallellization; Searching; Sequences;
              Shuffling;LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Edgar2010-cb,
  title    = "Search and clustering orders of magnitude faster than {BLAST}",
  author   = "Edgar, Robert C",
  abstract = "MOTIVATION: Biological sequence data is accumulating rapidly,
              motivating the development of improved high-throughput methods
              for sequence classification. RESULTS: UBLAST and USEARCH are new
              algorithms enabling sensitive local and global search of large
              sequence databases at exceptionally high speeds. They are often
              orders of magnitude faster than BLAST in practical applications,
              though sensitivity to distant protein relationships is lower.
              UCLUST is a new clustering method that exploits USEARCH to assign
              sequences to clusters. UCLUST offers several advantages over the
              widely used program CD-HIT, including higher speed, lower memory
              use, improved sensitivity, clustering at lower identities and
              classification of much larger datasets. AVAILABILITY: Binaries
              are available at no charge for non-commercial use at
              http://www.drive5.com/usearch.",
  journal  = "Bioinformatics",
  volume   =  26,
  number   =  19,
  pages    = "2460--2461",
  month    =  oct,
  year     =  2010,
  doi      = {10.1093/bioinformatics/btq461},
  keywords = "LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Gremme2013-ba,
  title    = "{GenomeTools}: a comprehensive software library for efficient
              processing of structured genome annotations",
  author   = "Gremme, Gordon and Steinbiss, Sascha and Kurtz, Stefan",
  abstract = "Genome annotations are often published as plain text files
              describing genomic features and their subcomponents by an
              implicit annotation graph. In this paper, we present the
              GenomeTools, a convenient and efficient software library and
              associated software tools for developing bioinformatics software
              intended to create, process or convert annotation graphs. The
              GenomeTools strictly follow the annotation graph approach,
              offering a unified graph-based representation. This gives the
              developer intuitive and immediate access to genomic features and
              tools for their manipulation. To process large annotation sets
              with low memory overhead, we have designed and implemented an
              efficient pull-based approach for sequential processing of
              annotations. This allows to handle even the largest annotation
              sets, such as a complete catalogue of human variations. Our
              object-oriented C-based software library enables a developer to
              conveniently implement their own functionality on annotation
              graphs and to integrate it into larger workflows, simultaneously
              accessing compressed sequence data if required. The careful C
              implementation of the GenomeTools does not only ensure a
              light-weight memory footprint while allowing full sequential as
              well as random access to the annotation graph, but also
              facilitates the creation of bindings to a variety of script
              programming languages (like Python and Ruby) sharing the same
              interface.",
  journal  = "IEEE/ACM Trans. Comput. Biol. Bioinform.",
  volume   =  10,
  number   =  3,
  pages    = "645--656",
  month    =  may,
  year     =  2013,
  doi      = {10.1109/tcbb.2013.68},
  keywords = "LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Steinbiss2009-vg,
  title    = "Fine-grained annotation and classification of de novo predicted
              {LTR} retrotransposons",
  author   = "Steinbiss, Sascha and Willhoeft, Ute and Gremme, Gordon and
              Kurtz, Stefan",
  abstract = "Long terminal repeat (LTR) retrotransposons and endogenous
              retroviruses (ERVs) are transposable elements in eukaryotic
              genomes well suited for computational identification. De novo
              identification tools determine the position of potential LTR
              retrotransposon or ERV insertions in genomic sequences. For
              further analysis, it is desirable to obtain an annotation of the
              internal structure of such candidates. This article presents
              LTRdigest, a novel software tool for automated annotation of
              internal features of putative LTR retrotransposons. It uses local
              alignment and hidden Markov model-based algorithms to detect
              retrotransposon-associated protein domains as well as primer
              binding sites and polypurine tracts. As an example, we used
              LTRdigest results to identify 88 (near) full-length ERVs in the
              chromosome 4 sequence of Mus musculus, separating them from
              truncated insertions and other repeats. Furthermore, we propose a
              work flow for the use of LTRdigest in de novo LTR retrotransposon
              classification and perform an exemplary de novo analysis on the
              Drosophila melanogaster genome as a proof of concept. Using a new
              method solely based on the annotations generated by LTRdigest,
              518 potential LTR retrotransposons were automatically assigned to
              62 candidate groups. Representative sequences from 41 of these 62
              groups were matched to reference sequences with >80\% global
              sequence similarity.",
  journal  = "Nucleic Acids Res.",
  volume   =  37,
  number   =  21,
  pages    = "7002--7013",
  month    =  nov,
  year     =  2009,
  doi      = {10.1093/nar/gkp759},
  keywords = "LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Ellinghaus2008-hu,
  title    = "{LTRharvest}, an efficient and flexible software for de novo
              detection of {LTR} retrotransposons",
  author   = "Ellinghaus, David and Kurtz, Stefan and Willhoeft, Ute",
  abstract = "BACKGROUND: Transposable elements are abundant in eukaryotic
              genomes and it is believed that they have a significant impact on
              the evolution of gene and chromosome structure. While there are
              several completed eukaryotic genome projects, there are only few
              high quality genome wide annotations of transposable elements.
              Therefore, there is a considerable demand for computational
              identification of transposable elements. LTR retrotransposons, an
              important subclass of transposable elements, are well suited for
              computational identification, as they contain long terminal
              repeats (LTRs). RESULTS: We have developed a software tool
              LTRharvest for the de novo detection of full length LTR
              retrotransposons in large sequence sets. LTRharvest efficiently
              delivers high quality annotations based on known LTR transposon
              features like length, distance, and sequence motifs. A quality
              validation of LTRharvest against a gold standard annotation for
              Saccharomyces cerevisae and Drosophila melanogaster shows a
              sensitivity of up to 90\% and 97\% and specificity of 100\% and
              72\%, respectively. This is comparable or slightly better than
              annotations for previous software tools. The main advantage of
              LTRharvest over previous tools is (a) its ability to efficiently
              handle large datasets from finished or unfinished genome
              projects, (b) its flexibility in incorporating known sequence
              features into the prediction, and (c) its availability as an open
              source software. CONCLUSION: LTRharvest is an efficient software
              tool delivering high quality annotation of LTR retrotransposons.
              It can, for example, process the largest human chromosome in
              approx. 8 minutes on a Linux PC with 4 GB of memory. Its
              flexibility and small space and run-time requirements makes
              LTRharvest a very competitive candidate for future LTR
              retrotransposon annotation projects. Moreover, the structured
              design and implementation and the availability as open source
              provides an excellent base for incorporating novel concepts to
              further improve prediction of LTR retrotransposons.",
  journal  = "BMC Bioinformatics",
  volume   =  9,
  pages    = "18",
  month    =  jan,
  year     =  2008,
  doi      = {10.1186/1471-2105-9-18},
  keywords = "LTRpred Manuscript",
  language = "en"
}

@BOOK{Wickham2016-eq,
  title     = "ggplot2: Elegant Graphics for Data Analysis",
  author    = "Wickham, Hadley",
  abstract  = "This new edition to the classic book by ggplot2 creator Hadley
               Wickham highlights compatibility with knitr and RStudio. ggplot2
               is a data visualization package for R that helps users create
               data graphics, including those that are multi-layered, with
               ease. With ggplot2, it's easy to: produce handsome,
               publication-quality plots with automatic legends created from
               the plot specificationsuperimpose multiple layers (points,
               lines, maps, tiles, box plots) from different data sources with
               automatically adjusted common scalesadd customizable smoothers
               that use powerful modeling capabilities of R, such as loess,
               linear models, generalized additive models, and robust
               regressionsave any ggplot2 plot (or part thereof) for later
               modification or reusecreate custom themes that capture in-house
               or journal style requirements and that can easily be applied to
               multiple plotsapproach a graph from a visual perspective,
               thinking about how each component of the data is represented on
               the final plot This book will be useful to everyone who has
               struggled with displaying data in an informative and attractive
               way. Some basic knowledge of R is necessary (e.g., importing
               data into R). ggplot2 is a mini-language specifically tailored
               for producing graphics, and you'll learn everything you need in
               the book. After reading this book you'll be able to produce
               graphics customized precisely for your problems, and you'll find
               it easy to get graphics out of your head and on to the screen or
               page.",
  publisher = "Springer",
  month     =  jun,
  year      =  2016,
  doi       = {10.1007/978-3-319-24277-4},
  keywords  = "LTRpred Manuscript",
  language  = "en"
}

@ARTICLE{Lawrence2013-dv,
  title    = "Software for computing and annotating genomic ranges",
  author   = "Lawrence, Michael and Huber, Wolfgang and Pag{\`e}s, Herv{\'e}
              and Aboyoun, Patrick and Carlson, Marc and Gentleman, Robert and
              Morgan, Martin T and Carey, Vincent J",
  abstract = "We describe Bioconductor infrastructure for representing and
              computing on annotated genomic ranges and integrating genomic
              data with the statistical computing features of R and its
              extensions. At the core of the infrastructure are three packages:
              IRanges, GenomicRanges, and GenomicFeatures. These packages
              provide scalable data structures for representing annotated
              ranges on the genome, with special support for transcript
              structures, read alignments and coverage vectors. Computational
              facilities include efficient algorithms for overlap and nearest
              neighbor detection, coverage calculation and other range
              operations. This infrastructure directly supports more than 80
              other Bioconductor packages, including those for sequence
              analysis, differential expression analysis and visualization.",
  journal  = "PLoS Comput. Biol.",
  volume   =  9,
  number   =  8,
  pages    = "e1003118",
  month    =  aug,
  year     =  2013,
  doi      = {10.1371/journal.pcbi.1003118},
  keywords = "LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Wickham2019-kh,
  title    = "Welcome to the Tidyverse",
  author   = "Wickham, Hadley and Averick, Mara and Bryan, Jennifer and Chang,
              Winston and McGowan, Lucy and Fran{\c c}ois, Romain and
              Grolemund, Garrett and Hayes, Alex and Henry, Lionel and Hester,
              Jim and {Others}",
  journal  = "Journal of Open Source Software",
  volume   =  4,
  number   =  43,
  pages    = "1686",
  year     =  2019,
  doi      = {10.21105/joss.01686},
  keywords = "LTRpred Manuscript"
}

@ARTICLE{Chuong2017-cb,
  title    = "Regulatory activities of transposable elements: from conflicts to
              benefits",
  author   = "Chuong, Edward B and Elde, Nels C and Feschotte, C{\'e}dric",
  abstract = "Transposable elements (TEs) are a prolific source of tightly
              regulated, biochemically active non-coding elements, such as
              transcription factor-binding sites and non-coding RNAs. Many
              recent studies reinvigorate the idea that these elements are
              pervasively co-opted for the regulation of host genes. We argue
              that the inherent genetic properties of TEs and the conflicting
              relationships with their hosts facilitate their recruitment for
              regulatory functions in diverse genomes. We review recent
              findings supporting the long-standing hypothesis that the waves
              of TE invasions endured by organisms for eons have catalysed the
              evolution of gene-regulatory networks. We also discuss the
              challenges of dissecting and interpreting the phenotypic effect
              of regulatory activities encoded by TEs in health and disease.",
  journal  = "Nat. Rev. Genet.",
  volume   =  18,
  number   =  2,
  pages    = "71--86",
  month    =  feb,
  year     =  2017,
  doi      = {10.1038/nrg.2016.139},
  keywords = "LTRpred Manuscript",
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Sundaram2020-yw,
  title     = "Transposable elements as a potent source of diverse
               cis-regulatory sequences in mammalian genomes",
  author    = "Sundaram, Vasavi and Wysocka, Joanna",
  abstract  = "Eukaryotic gene regulation is mediated by cis-regulatory
               elements, which are embedded within the vast non-coding genomic
               space and recognized by the transcription factors in a
               sequence-and context-dependent manner. A large proportion of
               eukaryotic &hellip;",
  journal   = "Philos. Trans. R. Soc. Lond. B Biol. Sci.",
  publisher = "Royal Society",
  volume    =  375,
  number    =  1795,
  pages     = "20190347",
  month     =  mar,
  year      =  2020,
  keywords  = "LTRpred Manuscript"
}

@ARTICLE{Benoit2019-ux,
  title    = "Environmental and epigenetic regulation of Rider retrotransposons
              in tomato",
  author   = "Benoit, Matthias and Drost, Hajk-Georg and Catoni, Marco and
              Gouil, Quentin and Lopez-Gomollon, Sara and Baulcombe, David and
              Paszkowski, Jerzy",
  abstract = "Transposable elements in crop plants are the powerful drivers of
              phenotypic variation that has been selected during domestication
              and breeding programs. In tomato, transpositions of the LTR (long
              terminal repeat) retrotransposon family Rider have contributed to
              various phenotypes of agronomical interest, such as fruit shape
              and colour. However, the mechanisms regulating Rider activity are
              largely unknown. We have developed a bioinformatics pipeline for
              the functional annotation of retrotransposons containing LTRs and
              defined all full-length Rider elements in the tomato genome.
              Subsequently, we showed that accumulation of Rider transcripts
              and transposition intermediates in the form of extrachromosomal
              DNA is triggered by drought stress and relies on abscisic acid
              signalling. We provide evidence that residual activity of Rider
              is controlled by epigenetic mechanisms involving siRNAs and the
              RNA-dependent DNA methylation pathway. Finally, we demonstrate
              the broad distribution of Rider-like elements in other plant
              species, including crops. Our work identifies Rider as an
              environment-responsive element and a potential source of genetic
              and epigenetic variation in plants.",
  journal  = "PLoS Genet.",
  volume   =  15,
  number   =  9,
  pages    = "e1008370",
  month    =  sep,
  year     =  2019,
  doi      = {10.1371/journal.pgen.1008370},
  keywords = "DrostLab;LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Drost2019-rz,
  title    = "Becoming a Selfish Clan: Recombination Associated to
              {Reverse-Transcription} in {LTR} Retrotransposons",
  author   = "Drost, Hajk-Georg and Sanchez, Diego H",
  abstract = "Transposable elements (TEs) are parasitic DNA bits capable of
              mobilization and mutagenesis, typically suppressed by host's
              epigenetic silencing. Since the selfish DNA concept, it is
              appreciated that genomes are also molded by arms-races against
              natural TE inhabitants. However, our understanding of
              evolutionary processes shaping TEs adaptive populations is
              scarce. Here, we review the events of recombination associated to
              reverse-transcription in LTR retrotransposons, a process
              shuffling their genetic variants during replicative mobilization.
              Current evidence may suggest that recombinogenic retrotransposons
              could beneficially exploit host suppression, where clan behavior
              facilitates their speciation and diversification. Novel
              refinements to retrotransposons life-cycle and evolution models
              thus emerge.",
  journal  = "Genome Biol. Evol.",
  volume   =  11,
  number   =  12,
  pages    = "3382--3392",
  month    =  dec,
  year     =  2019,
  doi      = {10.1093/gbe/evz255},
  keywords = "LTR retrotransposons; epigenetics; recombination; retroelements;
              reverse-transcription; transcriptional gene silencing;
              transposable elements; transposons;DrostLab;LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Cho2019-zp,
  title    = "Sensitive detection of pre-integration intermediates of long
              terminal repeat retrotransposons in crop plants",
  author   = "Cho, Jungnam and Benoit, Matthias and Catoni, Marco and Drost,
              Hajk-Georg and Brestovitsky, Anna and Oosterbeek, Matthijs and
              Paszkowski, Jerzy",
  abstract = "Retrotransposons have played an important role in the evolution
              of host genomes1,2. Their impact is mainly deduced from the
              composition of DNA sequences that have been fixed over
              evolutionary time2. Such studies provide important 'snapshots'
              reflecting the historical activities of transposons but do not
              predict current transposition potential. We previously reported
              sequence-independent retrotransposon trapping (SIRT) as a method
              that, by identification of extrachromosomal linear DNA (eclDNA),
              revealed the presence of active long terminal repeat (LTR)
              retrotransposons in Arabidopsis3. However, SIRT cannot be applied
              to large and transposon-rich genomes, as found in crop plants. We
              have developed an alternative approach named ALE-seq
              (amplification of LTR of eclDNAs followed by sequencing) for such
              situations. ALE-seq reveals sequences of 5' LTRs of eclDNAs after
              two-step amplification: in vitro transcription and subsequent
              reverse transcription. Using ALE-seq in rice, we detected eclDNAs
              for a novel Copia family LTR retrotransposon, Go-on, which is
              activated by heat stress. Sequencing of rice accessions revealed
              that Go-on has preferentially accumulated in Oryza sativa ssp.
              indica rice grown at higher temperatures. Furthermore, ALE-seq
              applied to tomato fruits identified a developmentally regulated
              Gypsy family of retrotransposons. A bioinformatic pipeline
              adapted for ALE-seq data analyses is used for the direct and
              reference-free annotation of new, active retroelements. This
              pipeline allows assessment of LTR retrotransposon activities in
              organisms for which genomic sequences and/or reference genomes
              are either unavailable or of low quality.",
  journal  = "Nature Plants",
  volume   =  5,
  number   =  1,
  pages    = "26--33",
  month    =  jan,
  year     =  2019,
  doi      = {10.1038/s41477-018-0320-9},
  keywords = "DrostLab;LTRpred Manuscript",
  language = "en"
}

@ARTICLE{Drost2017-cw,
  title    = "Biomartr: genomic data retrieval with {R}",
  author   = "Drost, Hajk-Georg and Paszkowski, Jerzy",
  abstract = "Motivation: Retrieval and reproducible functional annotation of
              genomic data are crucial in biology. However, the current poor
              usability and transparency of retrieval methods hinders
              reproducibility. Here we present an open source R package,
              biomartr , which provides a comprehensive easy-to-use framework
              for automating data retrieval and functional annotation for
              meta-genomic approaches. The functions of biomartr achieve a high
              degree of clarity, transparency and reproducibility of analyses.
              Results: The biomartr package implements straightforward
              functions for bulk retrieval of all genomic data or data for
              selected genomes, proteomes, coding sequences and annotation
              files present in databases hosted by the National Center for
              Biotechnology Information (NCBI) and European Bioinformatics
              Institute (EMBL-EBI). In addition, biomartr communicates with the
              BioMart database for functional annotation of retrieved
              sequences. Comprehensive documentation of biomartr functions and
              five tutorial vignettes provide step-by-step instructions on how
              to use the package in a reproducible manner. Availability and
              Implementation: The open source biomartr package is available at
              https://github.com/HajkD/biomartr and
              https://cran.r-project.org/web/packages/biomartr/index.html .
              Contact: hgd23@cam.ac.uk. Supplementary information:
              Supplementary data are available at Bioinformatics online.",
  journal  = "Bioinformatics",
  volume   =  33,
  number   =  8,
  pages    = "1216--1217",
  month    =  apr,
  year     =  2017,
  doi      = {10.1093/bioinformatics/btw821},
  keywords = "DrostLab;LTRpred Manuscript",
  language = "en"
}


@ARTICLE{Wang2019,
  title    = "Transposon age and non-CG methylation",
  author   = "Wang, Zhengming and Baulcombe, David",
  abstract = "Silencing of transposable elements (TEs) is established by small RNA-directed DNA methylation (RdDM). Maintenance of silencing is then based on a combination of RdDM and RNA-independent mechanisms involving DNA methyltransferase MET1 and chromodomain DNA methyltransferases (CMTs). Involvement of RdDM, according to this model should decrease with TE age but here we show a different pattern in tomato and Arabidopsis. In these species the CMTs silence long terminal repeat (LTR) transposons in the distal chromatin that are younger than those affected by RdDM. To account for these findings we propose that, after establishment of primary RdDM as in the original model, there is an RNA-independent maintenance phase involving CMTs followed by secondary RdDM. This progression of epigenetic silencing in the gene-rich distal chromatin is likely to influence the transcriptome either in cis or in trans depending on whether the mechanisms are RNA-dependent or -independent.",
  journal  = "Nature Communications",
  volume   =  11,
  number   =  1221,
  year     =  2020,
  keywords = "",
  doi      = {10.1038/s41467-020-14995-6},
  language = "en"
}

@ARTICLE{Yin2012-ro,
   title    = "ggbio: an {R} package for extending the grammar of graphics for
               genomic data",
   author   = "Yin, Tengfei and Cook, Dianne and Lawrence, Michael",
   abstract = "We introduce ggbio, a new methodology to visualize and explore
               genomics annotations and high-throughput data. The plots provide
               detailed views of genomic regions, summary views of sequence
               alignments and splicing patterns, and genome-wide overviews with
               karyogram, circular and grand linear layouts. The methods
               leverage the statistical functionality available in R, the
               grammar of graphics and the data handling capabilities of the
               Bioconductor project. The plots are specified within a modular
               framework that enables users to construct plots in a systematic
               way, and are generated directly from Bioconductor data
               structures. The ggbio R package is available at
               http://www.bioconductor.org/packages/2.11/bioc/html/ggbio.html.",
   journal  = "Genome Biol.",
   volume   =  13,
   number   =  8,
   pages    = "R77",
   month    =  aug,
   year     =  2012,
   doi      = {10.1186/gb-2012-13-8-r77},
   language = "en"
 }
 
@ARTICLE{Sanchez2017-sy,
   title    = "High-frequency recombination between members of an {LTR}
               retrotransposon family during transposition bursts",
   author   = "Sanchez, Diego H and Gaubert, Herv{\'e} and Drost, Hajk-Georg and
               Zabet, Nicolae Radu and Paszkowski, Jerzy",
   abstract = "Retrotransposons containing long terminal repeats (LTRs) form a
               substantial fraction of eukaryotic genomes. The timing of past
               transposition can be estimated by quantifying the accumulation of
               mutations in initially identical LTRs. This way, retrotransposons
               are divided into young, potentially mobile elements, and old that
               moved thousands or even millions of years ago. Both types are
               found within a single retrotransposon family and it is assumed
               that the old members will remain immobile and degenerate further.
               Here, we provide evidence in Arabidopsis that old members enter
               into replication/transposition cycles through high rates of
               intra-family recombination. The recombination occurs pairwise,
               resembling the formation of recombinant retroviruses. Thus, each
               transposition burst generates a novel progeny population of
               chromosomally integrated LTR retrotransposons consisting of
               pairwise recombination products produced in a process comparable
               the sexual exchange of genetic information. Our observations
               provide an explanation for the reported high rates of sequence
               diversification in retrotransposons.",
   journal  = "Nature Communications",
   volume   =  8,
   number   =  1,
   pages    = "1283",
   month    =  nov,
   year     =  2017,
   doi      = {10.1038/s41467-017-01374-x},
   language = "en"
 }
 