diff --git a/src/doc/Publications/bmc_paper/bmc_article.bst b/src/doc/Publications/bmc_paper/bmc_article.bst
deleted file mode 100755
index e68e8943b6bb16bc58936656700ad04406165cff..0000000000000000000000000000000000000000
--- a/src/doc/Publications/bmc_paper/bmc_article.bst
+++ /dev/null
@@ -1,1880 +0,0 @@
-%% %
- % bmc_article.bst ver: 1.01 %
- % %
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
- %% %%
- %% BibTeX BST file for BioMed Central %%
- %% a style syntax for latex .bib %%
- %% bibliographies %%
- %% %%
- %% <1 September 2003> %%
- %% %%
- %% %%
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
- %
- %
- % The order in the reference list is that by which the
- % works were originally cited in the text, or that in
- % the database.
- %
- %
- % This file is based on the style 'unsrt.bst'
- % ------------------------------------------
- % BibTeX standard bibliography style `unsrt'
- % version 0.99a for BibTeX versions 0.99a
- % or later, LaTeX version 2.09.
- % Copyright (C) 1985, all rights reserved.
- % Copying of this file is authorized only if either
- % (1) you make absolutely no changes to your copy, including name, or
- % (2) if you do make changes, you name it something other than
- % btxbst.doc, plain.bst, unsrt.bst, alpha.bst, and abbrv.bst.
- % This restriction helps ensure that all standard styles are identical.
- % The file btxbst.doc has the documentation for this style.
- % ---------------------------------------------------------
-%%
-
-
-
-
-ENTRY
- { address
- archive
- author
- booktitle
- chapter
- edition
- editor
- eid
- howpublished
- institution
- journal
- key
- month
- note
- number
- organization
- pages
- publisher
- school
- series
- title
- type
- url
- volume
- year
- }
- {}
- { label }
-
-
-% Global variables - most initialised and used locally.
-STRINGS { longest.label }
-STRINGS { cur tag source bibinfo}
-STRINGS { p q r s t z name names }
-STRINGS { lr lp lt ls} % local copys fxns with these call no other fxns.
-INTEGERS { number.label longest.label.width }
-INTEGERS { multiresult nameptr namesleft numnames global.counter}
-INTEGERS { i j k l ll li}
-INTEGERS { output.state before.all mid.sentence after.sentence after.block }
-
-FUNCTION {init.state.consts}
-{ #0 'before.all :=
- #1 'mid.sentence :=
- #2 'after.sentence :=
- #3 'after.block :=
- #0 'global.counter :=
-}
-
-
-% Logical operators on integers
-FUNCTION {not}
-{ { #0 } { #1 } if$
-}
-FUNCTION {and}
-{ 'skip$ { pop$ #0 } if$
-}
-FUNCTION {or}
-{ { pop$ #1 } 'skip$ if$
-}
-FUNCTION {field.or.null}
-{ duplicate$ empty$ { pop$ "" } 'skip$ if$
-}
-
-FUNCTION {remove.dots}
-{ 'z :=
- ""
- { z empty$ not }
- { z #1 #1 substring$
- z #2 global.max$ substring$ 'z :=
- duplicate$ "." = 'pop$
- { * }
- if$
- }
- while$
-}
-
-%%
- % myreverse
- %
- % Takes 1 string
- % Returns the myreverse string
- %
- % not to be confused with REVERSE (opposite of ITERATE)
-%%
-FUNCTION {myreverse}
-{
- 'lt :=
- "" 'ls :=
- { lt empty$ not }
- {
- lt #1 #1 substring$ ls * 'ls :=
- lt #2 global.max$ substring$ 'lt :=
- }
- while$
- ls
-}
-
-%%
- % search
- %
- % Takes 2 strings (txt, pattern)
- % Retruns 1 if found 0 if not
-%%
-FUNCTION {search}
-{
- 'lp := % pattern
- 'lt := % text to search
- #0 'i := % result
- lp text.length$ 'll := % length of the search pattern
- { lt empty$ not }
- { lt #1 ll substring$ lp =
- { #1 'li :=
- "" 'lt := } % force exit
- { lt #2 global.max$ substring$ 'lt := } % pop 1 char
- if$
- }
- while$
- li
-}
-
-
-%%
- % general replace
- %
- % Takes 3 strings (txt, pattern, replace-str)
- % replaces all instances of pattern
- % Retruns a new string
-%%
-FUNCTION {replace}
-{
- 'lr := % replace string
- 'lp := % pattern
- 'lt := % text to search
- "" 'ls := % result string
- lp text.length$ 'll := % length of the search pattern
- { lt empty$ not }
- { lt #1 ll substring$ lp =
- { ls lr * 'ls :=
- lt ll #1 + global.max$ substring$ 'lt := }
- { ls lt #1 #1 substring$ * 'ls :=
- lt #2 global.max$ substring$ 'lt := }
- if$
- }
- while$
- ls
-}
-
-
-%%
- % strip.letters
- %
- % Takes 1 arg (string)
- % if string has letters get rid of them
- % - useful for 2nd -> 2
- % Returns string
-%%
-FUNCTION {strip.letters}
-{
- "" 's :=
- duplicate$ missing$
- 'pop$
- {
- 't :=
- { t "" = not }
- { % ascii '0' = 48, '9' = 57
- t #1 #1 substring$ chr.to.int$ 'i :=
- i #47 > i #58 < and
- { s t #1 #1 substring$ * 's := }
- 'skip$
- if$
- t #2 global.max$ substring$ 't :=
- }
- while$
- }
- if$
- s
-}
-
-FUNCTION {output.nonnull}
-{ 's :=
- output.state mid.sentence =
- { ", " * write$ }
- { output.state after.block =
- { add.period$ write$
- newline$
- "\newblock " write$
- }
- { output.state before.all =
- %{ "OS=(" * output.state int.to.str$ * ") " * write$ }
- 'write$
- { add.period$ " " * write$ } % after.sentence
- if$
- }
- if$
- mid.sentence 'output.state :=
- }
- if$
- s
-}
-
-FUNCTION {output}
-{ duplicate$ empty$
- 'pop$
- 'output.nonnull
- if$
-}
-
-% raises an error (warning message) if type not present.
-FUNCTION {output.check}
-{ 't :=
- duplicate$ empty$
- { pop$ "empty " t * " in " * cite$ * warning$ }
- 'output.nonnull
- if$
-}
-
-FUNCTION {fin.entry}
-{ add.period$
- write$
- newline$
-}
-
-FUNCTION {new.block}
-{ output.state before.all =
- 'skip$
- { after.block 'output.state := }
- if$
-}
-FUNCTION {new.sentence}
-{ output.state after.block =
- 'skip$
- { output.state before.all =
- 'skip$
- { after.sentence 'output.state := }
- if$
- }
- if$
-}
-FUNCTION {add.blank}
-{ " " * before.all 'output.state :=
-}
-
-FUNCTION {add.bold.colon}
-{ duplicate$ empty$
- 'skip$
- { "\textbf{:}" * add.blank }
- if$
-}
-
-FUNCTION {add.colon}
-{ duplicate$ empty$
- 'skip$
- { ":" * add.blank }
- if$
-}
-FUNCTION {bold}
-{ duplicate$ empty$
- { pop$ "" }
- { "\textbf{" swap$ * "}" * }
- if$
-}
-FUNCTION {emphasize}
-{ duplicate$ empty$
- { pop$ "" }
- { "\emph{" swap$ * "}" * }
- if$
-}
-FUNCTION {tie.or.space.prefix}
-{ duplicate$ text.length$ #3 <
- { "~" }
- { " " }
- if$
- swap$
-}
-
-FUNCTION {capitalize}
-{ "u" change.case$ "t" change.case$ }
-
-FUNCTION {space.word}
-{ " " swap$ * " " * }
-
-% if field not entered - push empty string ""
-FUNCTION {bibinfo.check}
-{ swap$
- duplicate$ missing$
- { pop$ pop$
- "" }
- { duplicate$ empty$
- { swap$ pop$ }
- { swap$ pop$ }
- if$
- }
- if$
-}
-FUNCTION {bibinfo.warn}
-{ swap$
- duplicate$ missing$
- {
- swap$ "missing " swap$ * " in " * cite$ * warning$ pop$
- ""
- }
- { duplicate$ empty$
- {
- swap$ "empty " swap$ * " in " * cite$ * warning$
- }
- { swap$
- pop$
- }
- if$
- }
- if$
-}
-
-FUNCTION {format.thesis.type}
-{ type duplicate$ empty$
- 'pop$
- { swap$ pop$
- "t" change.case$ "type" bibinfo.check
- }
- if$
-}
-
-
- % Here are the language-specific definitions for explicit words.
- % Each function has a name bbl.xxx where xxx is the English word.
- % The language selected here is ENGLISH
-FUNCTION {bbl.and}
-{ "and"}
-
-FUNCTION {bbl.etal}
-{ "et~al." }
-
-FUNCTION {bbl.editors}
-{ "(Eds)" }
-%{ "editors" }
-
-FUNCTION {bbl.editor}
-{ "(Ed)" }
-%{ "editor" }
-
-FUNCTION {bbl.edby}
-{ "Edited by" }
-
-FUNCTION {bbl.edition}
-{ "edition" }
-%{ "edn." }
-
-FUNCTION {bbl.volume}
-{ "Volume" }
-%{ "vol." }
-
-FUNCTION {bbl.of}
-{ "of" }
-
-FUNCTION {bbl.number}
-{ "no." }
-
-FUNCTION {bbl.nr}
-{ "no." }
-
-FUNCTION {bbl.in}
-{ "in" }
-
-FUNCTION {bbl.pages}
-{ "" }
-
-FUNCTION {bbl.page}
-{ "" }
-
-FUNCTION {bbl.chapter}
-{ "chap." }
-
-FUNCTION {bbl.techrep}
-{ "Tech. Rep." }
-
-FUNCTION {bbl.mthesis}
-{ "Master's thesis" }
-
-FUNCTION {bbl.phdthesis}
-{ "PhD thesis" }
-
-MACRO {jan} {"Jan."}
-
-MACRO {feb} {"Feb."}
-
-MACRO {mar} {"Mar."}
-
-MACRO {apr} {"Apr."}
-
-MACRO {may} {"May"}
-
-MACRO {jun} {"Jun."}
-
-MACRO {jul} {"Jul."}
-
-MACRO {aug} {"Aug."}
-
-MACRO {sep} {"Sep."}
-
-MACRO {oct} {"Oct."}
-
-MACRO {nov} {"Nov."}
-
-MACRO {dec} {"Dec."}
-
-MACRO {acmcs} {"ACM Computing Surveys"}
-
-MACRO {acta} {"Acta Informatica"}
-
-MACRO {cacm} {"Communications of the ACM"}
-
-MACRO {ibmjrd} {"IBM Journal of Research and Development"}
-
-MACRO {ibmsj} {"IBM Systems Journal"}
-
-MACRO {ieeese} {"IEEE Transactions on Software Engineering"}
-
-MACRO {ieeetc} {"IEEE Transactions on Computers"}
-
-MACRO {ieeetcad}
- {"IEEE Transactions on Computer-Aided Design of Integrated Circuits"}
-
-MACRO {ipl} {"Information Processing Letters"}
-
-MACRO {jacm} {"Journal of the ACM"}
-
-MACRO {jcss} {"Journal of Computer and System Sciences"}
-
-MACRO {scp} {"Science of Computer Programming"}
-
-MACRO {sicomp} {"SIAM Journal on Computing"}
-
-MACRO {tocs} {"ACM Transactions on Computer Systems"}
-
-MACRO {tods} {"ACM Transactions on Database Systems"}
-
-MACRO {tog} {"ACM Transactions on Graphics"}
-
-MACRO {toms} {"ACM Transactions on Mathematical Software"}
-
-MACRO {toois} {"ACM Transactions on Office Information Systems"}
-
-MACRO {toplas} {"ACM Transactions on Programming Languages and Systems"}
-
-MACRO {tcs} {"Theoretical Computer Science"}
-
-
-% Takes 2 args (author field) and string "author"
-FUNCTION {format.names}
-{ 'bibinfo :=
- duplicate$ empty$ 'skip$ {
- 's :=
- "" 't :=
- #1 'nameptr :=
- s num.names$ 'numnames :=
- numnames 'namesleft :=
- { namesleft #0 > }
- { s nameptr
- "{vv~}{ll}{ f{}}{ jj}"
- format.name$
- remove.dots
- bibinfo bibinfo.check
- 't :=
- nameptr #1 >
- {
- namesleft #1 >
- { ", " * t * }
- {
- "," *
- s nameptr "{ll}" format.name$ duplicate$ "others" =
- { 't := }
- { pop$ }
- if$
- t "others" =
- {
- " " * bbl.etal *
- }
- { " " * t * }
- if$
- }
- if$
- }
- 't
- if$
- nameptr #1 + 'nameptr :=
- namesleft #1 - 'namesleft :=
- }
- while$
- } if$
-}
-
-
-%"{f{~}~}{vv~}{ll}{ jj}"
-FUNCTION {format.names.ed}
-{
- 'bibinfo :=
- duplicate$ empty$ 'skip$ {
- 's :=
- "" 't :=
- #1 'nameptr :=
- s num.names$ 'numnames :=
- numnames 'namesleft :=
- { namesleft #0 > }
- { s nameptr
- "{vv~}{ll}{ f{}}{ jj}"
- format.name$
- remove.dots
- bibinfo bibinfo.check
- 't :=
- nameptr #1 >
- {
- namesleft #1 >
- { ", " * t * }
- {
- "," *
- s nameptr "{ll}" format.name$ duplicate$ "others" =
- { 't := }
- { pop$ }
- if$
- t "others" =
- {
-
- " " * bbl.etal *
- }
- { " " * t * }
- if$
- }
- if$
- }
- 't
- if$
- nameptr #1 + 'nameptr :=
- namesleft #1 - 'namesleft :=
- }
- while$
- } if$
-}
-FUNCTION {format.authors}
-{ author "author" format.names
-}
-FUNCTION {get.bbl.editor}
-{ editor num.names$ #1 > 'bbl.editors 'bbl.editor if$ }
-
-FUNCTION {format.editors}
-{ editor "editor" format.names duplicate$ empty$ 'skip$
- {
- " " * get.bbl.editor *
-%% "," * " " * get.bbl.editor *
- }
- if$
-}
-FUNCTION {format.note}
-{
- url empty$
- 'skip$
- {
- "\urlprefix\url{[" url * "]}" * output }
- if$
- note empty$
- { "" }
- {
- note "l" change.case$ "in press" =
- { after.sentence 'output.state :=
- " in press" }
- {
- after.sentence 'output.state :=
- note #1 #1 substring$
- duplicate$ "{" =
- 'skip$
- { output.state mid.sentence =
- { "l" }
- { "u" }
- if$
- change.case$ % leave note * As Is *
- }
- if$
- note #2 global.max$ substring$ * "note" bibinfo.check
- "[" swap$ * "]" *
- }
- if$
- }
- if$
-}
-
-FUNCTION {bold.format.title}
-{ title
- "title" bibinfo.check
- duplicate$ empty$ 'skip$
- {
- bold
- }
- if$
-}
-
-FUNCTION {emph.format.title}
-{ title
- "title" bibinfo.check
- duplicate$ empty$ 'skip$
- {
- emphasize
- }
- if$
-}
-
-% Returns ""
-FUNCTION {output.bibitem}
-{ newline$
- "\bibitem{" write$
- cite$ write$
- "}" write$
- newline$
- ""
- before.all 'output.state :=
-}
-
-FUNCTION {output.allinfo.comment}
-{ }
-
-FUNCTION {n.dashify}
-{
- 't :=
- ""
- { t empty$ not }
- { t #1 #1 substring$ "-" =
- { t #1 #2 substring$ "--" = not
- { "--" *
- t #2 global.max$ substring$ 't :=
- }
- { { t #1 #1 substring$ "-" = }
- { "-" *
- t #2 global.max$ substring$ 't :=
- }
- while$
- }
- if$
- }
- { t #1 #1 substring$ *
- t #2 global.max$ substring$ 't :=
- }
- if$
- }
- while$
-}
-
-FUNCTION {word.in}
-{ bbl.in capitalize
- " " * }
-
-FUNCTION {format.date}
-{
- before.all 'output.state :=
- ""
- duplicate$ empty$
- year "year" bibinfo.check duplicate$ empty$
- { swap$ 'skip$
- { "there's a month but no year in " cite$ * warning$ }
- if$
- *
- }
- { swap$ 'skip$
- {
- swap$
- " " * swap$
- }
- if$
- *
- remove.dots
- }
- if$
-
- duplicate$ "" =
- 'skip$
- { " " swap$ * }
- if$
-}
-
-% Source = book, conference, journal, manual
-% have the source avaliable on the stack
-FUNCTION {format.source}
-{ 'source :=
- source "source" bibinfo.check
- duplicate$ empty$ 'skip$
- {
- emphasize
- }
- if$
-}
-
-FUNCTION {format.title}
-{ title "title" bibinfo.check
- duplicate$ empty$ 'skip$
- {
- bold
- }
- if$
-}
-
-
-
-FUNCTION {either.or.check}
-{ empty$
- 'pop$
- { "can't use both " swap$ * " fields in " * cite$ * warning$ }
- if$
-}
-FUNCTION {format.bvolume}
-{ volume empty$
- { "" }
- { bbl.volume volume tie.or.space.prefix
- "volume" bibinfo.check * *
- series "series" bibinfo.check
- duplicate$ empty$ 'pop$
- { swap$ bbl.of space.word * swap$
- emphasize * }
- if$
- emphasize
- "volume and number" number either.or.check
- }
- if$
-}
-FUNCTION {format.number.series}
-{ volume empty$
- { number empty$
- { series field.or.null }
- { series empty$
- { number "number" bibinfo.check }
- { output.state mid.sentence =
- { bbl.number }
- { bbl.number capitalize }
- if$
- number tie.or.space.prefix "number" bibinfo.check * *
- bbl.in space.word *
- series "series" bibinfo.check *
- }
- if$
- }
- if$
- }
- { "" }
- if$
-}
-
-FUNCTION {format.edition}
-{ edition duplicate$ empty$ 'skip$
- {
- output.state mid.sentence =
- { "l" }
- { "t" }
- if$ change.case$
- "edition" bibinfo.check
- " " * bbl.edition *
- }
- if$
-}
-FUNCTION {multi.page.check}
-{ 't :=
- #0 'multiresult :=
- { multiresult not
- t empty$ not
- and
- }
- { t #1 #1 substring$
- duplicate$ "-" =
- swap$ duplicate$ "," =
- swap$ "+" =
- or or
- { #1 'multiresult := }
- { t #2 global.max$ substring$ 't := }
- if$
- }
- while$
- multiresult
-}
-
-FUNCTION {format.pages}
-{ pages duplicate$ empty$ 'skip$
- { duplicate$ multi.page.check
- {
- n.dashify
- }
- {
- }
- if$
- "pages" bibinfo.check
- ":" swap$ *
- }
- if$
-}
-
-FUNCTION {format.journal.pages}
-{ pages duplicate$ empty$ 'pop$
- { swap$ duplicate$ empty$
- { pop$ pop$ format.pages }
- {
- ":" *
- swap$
- n.dashify
- "pages" bibinfo.check
- *
- }
- if$
- }
- if$
-}
-FUNCTION {format.journal.eid}
-{ eid "eid" bibinfo.check
- duplicate$ empty$ 'pop$
- { swap$ duplicate$ empty$ 'skip$
- {
- ":" *
- }
- if$
- swap$ *
- }
- if$
-}
-
-% ignore issue (num) if == 1
-FUNCTION {format.vol.num.pages}
-{ volume field.or.null
- duplicate$ empty$ 'skip$
- {
- "volume" bibinfo.check bold
- }
- if$
- number "number" bibinfo.check duplicate$ empty$ 'skip$
- {
- duplicate$ "1" =
- {pop$ ""}
- { swap$ duplicate$ empty$
- { "there's a number but no volume in " cite$ * warning$ }
- 'skip$
- if$
- swap$
- "(" swap$ * ")" *
- }
- if$
- }
- if$ *
- eid empty$
- { format.journal.pages }
- { format.journal.eid }
- if$
-}
-
-FUNCTION {format.chapter.pages}
-{ chapter empty$
- 'format.pages
- { type empty$
- { bbl.chapter }
- { type "l" change.case$
- "type" bibinfo.check
- }
- if$
- chapter tie.or.space.prefix
- "chapter" bibinfo.check
- * *
- pages empty$
- 'skip$
- { ", " * format.pages * }
- if$
- }
- if$
-}
-
-
-
-%% FUNCTION {format.in.ed.booktitle}
-%% { booktitle format.source duplicate$ empty$ 'skip$
-%% {
-%% editor "editor" format.names.ed duplicate$ empty$ 'pop$
-%% {
-%% bbl.edby
-%% " " * swap$ *
-%% swap$
-%% "," *
-%% " " * swap$
-%% * }
-%% if$
-%% word.in swap$ *
-%% }
-%% if$
-%% }
-
-FUNCTION{format.edited.by}
-{ editor "editor" format.names.ed duplicate$ empty$
- 'pop$
- { bbl.edby
- " " * swap$ *
- swap$
- ". " *
- swap$
- * }
- if$
-}
-
-FUNCTION {format.in.booktitle}
-{ booktitle format.source duplicate$ empty$
- 'skip$
- { word.in swap$ * }
- if$
-}
-FUNCTION {format.in.journal}
-{ journal format.source duplicate$ empty$
- 'skip$
- { word.in swap$ * }
- if$
-}
-FUNCTION {empty.misc.check}
-{ author empty$ title empty$ howpublished empty$
- month empty$ year empty$ note empty$
- and and and and and
- { "all relevant fields are empty in " cite$ * warning$ }
- 'skip$
- if$
-}
-FUNCTION {format.tr.number}
-{ number "number" bibinfo.check
- type duplicate$ empty$
- { pop$ bbl.techrep }
- 'skip$
- if$
- "type" bibinfo.check
- swap$ duplicate$ empty$
- { pop$ "t" change.case$ }
- { tie.or.space.prefix * * }
- if$
-}
-FUNCTION {format.article.crossref}
-{
- key duplicate$ empty$
- { pop$
- journal duplicate$ empty$
- { "need key or journal for " cite$ * " to crossref " * crossref * warning$ }
- { "journal" bibinfo.check emphasize word.in swap$ * }
- if$
- }
- { word.in swap$ * " " *}
- if$
- " \cite{" * crossref * "}" *
-}
-FUNCTION {format.crossref.editor}
-{ editor #1 "{vv~}{ll}" format.name$
- "editor" bibinfo.check
- editor num.names$ duplicate$
- #2 >
- { pop$
- "editor" bibinfo.check
- " " * bbl.etal
- *
- }
- { #2 <
- 'skip$
- { editor #2 "{ff }{vv }{ll}{ jj}" format.name$ "others" =
- {
- "editor" bibinfo.check
- " " * bbl.etal
- *
- }
- {
- bbl.and space.word
- * editor #2 "{vv~}{ll}" format.name$
- "editor" bibinfo.check
- *
- }
- if$
- }
- if$
- }
- if$
-}
-FUNCTION {format.book.crossref}
-{ volume duplicate$ empty$
- { "empty volume in " cite$ * "'s crossref of " * crossref * warning$
- pop$ word.in
- }
- { bbl.volume
- capitalize
- swap$ tie.or.space.prefix "volume" bibinfo.check * * bbl.of space.word *
- }
- if$
- editor empty$
- editor field.or.null author field.or.null =
- or
- { key empty$
- { series empty$
- { "need editor, key, or series for " cite$ * " to crossref " *
- crossref * warning$
- "" *
- }
- { series emphasize * }
- if$
- }
- { key * }
- if$
- }
- { format.crossref.editor * }
- if$
- " \cite{" * crossref * "}" *
-}
-FUNCTION {format.incoll.inproc.crossref}
-{
- editor empty$
- editor field.or.null author field.or.null =
- or
- { key empty$
- { booktitle format.source duplicate$ empty$
- { "need editor, key, or booktitle for " cite$ * " to crossref " *
- crossref * warning$
- }
- { word.in swap$ * }
- if$
- }
- { word.in key * " " *}
- if$
- }
- { word.in format.crossref.editor * " " *}
- if$
- " \cite{" * crossref * "}" *
-}
-
-% Takes 1 arg (publisher or organisation}
-% if present appends address to the front. ie New York: Sachai Ltd
-% returns the formatted string.
-FUNCTION {format.org.or.pub}
-{ 't :=
- t empty$
- { address empty$
- 'skip$
- { address "address" bibinfo.check 't := }
- if$ }
- { address empty$
- 'skip$
- { address "address" bibinfo.check ": " * t * 't :=}
- if$
- }
- if$
- t
-}
-
-FUNCTION {format.publisher.address}
-{ publisher "publisher" bibinfo.warn format.org.or.pub
-}
-
-FUNCTION {format.organization.address}
-{ organization "organization" bibinfo.check format.org.or.pub
-}
-
-FUNCTION {article}
-{ output.bibitem
- author empty$
- { format.editors "author or editor" output.check
- add.colon
- }
- { format.authors output.nonnull
- add.colon
- crossref missing$
- { "author and editor" editor either.or.check }
- 'skip$
- if$
- }
- if$
- bold.format.title "title" output.check
- new.sentence
- crossref missing$
- {
- journal "journal" bibinfo.check
- format.source "journal" output.check
- format.date "year" output.check
- format.vol.num.pages output
- }
- { format.article.crossref output.nonnull
- format.pages output
- }
- if$
- format.note output
- fin.entry
-}
-FUNCTION {wholejournal}
-{ output.bibitem
- author empty$
- { format.editors "author or editor" output.check
- add.colon
- }
- { format.authors output.nonnull
- add.colon
- crossref missing$
- { "author and editor" editor either.or.check }
- 'skip$
- if$
- }
- if$
- bold.format.title "title" output.check
- new.sentence
- crossref missing$
- {
- journal emphasize word.in swap$ * "journal" output.check
- format.date "year" output.check
- format.vol.num.pages output
- }
- { format.article.crossref output.nonnull
- format.pages output
- }
- if$
- format.note output
- fin.entry
-}
-FUNCTION {book}
-{ output.bibitem
- author empty$
- { format.editors "author and editor" output.check
- add.colon
- }
- { format.authors output.nonnull
- add.colon
- crossref missing$
- { "author and editor" editor either.or.check }
- 'skip$
- if$
- }
- if$
- title format.source "source" output.check
- crossref missing$
- { format.bvolume output
- new.sentence
- format.number.series output
- format.publisher.address output
- }
- {
- new.sentence
- format.book.crossref output.nonnull
- }
- if$
- format.edition output
- format.date "year" output.check
- format.note output
- fin.entry
-}
-
-FUNCTION {inbook}
-{ output.bibitem
- author empty$
- { format.editors "author and editor" output.check
- add.colon
- }
- { format.authors output.nonnull
- add.colon
- crossref missing$
- { "author and editor" editor either.or.check }
- 'skip$
- if$
- }
- if$
- title format.source "title" output.check
- crossref missing$
- {
- format.publisher.address output
- format.bvolume output
- new.sentence
- format.number.series output
- }
- {
- new.sentence
- format.book.crossref output.nonnull
- }
- if$
- format.edition output
- format.date "year" output.check
- add.blank
- format.chapter.pages "chapter and/or pages" output.check
- format.note output
- fin.entry
-}
-
-% In <source> . Volume X. y edition. Edited by <ed>.
-% Add: Pub; date:pages.
-FUNCTION {incollection}
-{ output.bibitem
- format.authors "author" output.check
- add.colon
- bold.format.title "title" output.check
- new.sentence
- crossref missing$
- { format.in.booktitle "booktitle" output.check
- %format.in.ed.booktitle "booktitle" output.check
- format.bvolume output
- format.number.series output
- format.edition output
- booktitle empty$
- 'skip$
- {format.edited.by}
- if$
- format.publisher.address output
- }
- { format.incoll.inproc.crossref output.nonnull
- }
- if$
- format.date "year" output.check
- before.all 'output.state := %no space,comma,etc.. -> 1991:23
- format.pages output
- format.note output
- fin.entry
-}
-
-
-FUNCTION {inproceedings}
-{ output.bibitem
- format.authors "author" output.check
- add.colon
- bold.format.title "title" output.check
- new.sentence
- crossref missing$
- % In <source> . Volume X. x nd edition. Edited by <ed>.
- { format.in.booktitle "booktitle" output.check
- format.bvolume output
- format.edition output
- format.number.series output
- booktitle missing$
- 'skip$
- { booktitle missing$
- 'skip$
- {format.edited.by}
- if$
- }
- if$
- publisher missing$
- { format.organization.address output }
- { organization "organization" bibinfo.check output
- format.publisher.address output
- }
- if$
- }
- { format.incoll.inproc.crossref output.nonnull
- }
- if$
- format.date "year" output.check
- before.all 'output.state := %no space,comma,etc..
- format.pages output
- format.note output
- fin.entry
-}
-
-FUNCTION {conference} {inproceedings}
-
-
-FUNCTION {mastersthesis}
-{ output.bibitem
- format.authors "author" output.check
- add.colon
- bold.format.title
- "title" output.check
- new.sentence
- bbl.mthesis format.thesis.type format.source output.nonnull
- school "school" bibinfo.warn output
- address "address" bibinfo.check output
- format.date "year" output.check
- format.note output
- fin.entry
-}
-
-% old manual style syntax
-% all optional: (author, title, howpublished, month, year, note)
-% maybe missing: (organization, address, edition)
-FUNCTION {misc}
-{ output.bibitem
- author empty$
- { organization missing$ 'skip$
- { organization output }
- if$
- }
- { format.authors output }
- if$
- add.colon
- bold.format.title output
- new.sentence
- howpublished "howpublished" bibinfo.check format.source output
- new.sentence
- edition missing$ 'skip$
- {edition output}
- if$
- author empty$
- 'skip$
- { organization missing$
- 'skip$
- {organization output}
- if$
- }
- if$
- address missing$ 'skip$
- {address output}
- if$
- format.date output
- format.note output
- fin.entry
- empty.misc.check
-}
-
-FUNCTION {webpage}
-{ output.bibitem
- author empty$
- { organization missing$ 'skip$
- { organization output }
- if$
- }
- { format.authors output }
- if$
- add.colon
- bold.format.title " " * output
- new.sentence
- howpublished "howpublished" bibinfo.check format.source output
- new.sentence
- edition missing$ 'skip$
- {edition output}
- if$
- author empty$
- 'skip$
- { organization missing$
- 'skip$
- {organization output}
- if$
- }
- if$
- address missing$ 'skip$
- {address output}
- if$
- format.date output
- format.note output
- fin.entry
- empty.misc.check
-}
-
-
-FUNCTION {inpress}
-{ output.bibitem
- author empty$
- { organization missing$ 'skip$
- { organization output }
- if$
- }
- { format.authors output }
- if$
- add.colon
- bold.format.title output
- new.sentence
- journal emphasize output
- "in press" output
- fin.entry
- empty.misc.check
-}
-
-
-
-FUNCTION {manual}
-{ output.bibitem
- author empty$
- { organization missing$ 'skip$
- { organization output }
- if$
- }
- { format.authors output }
- if$
- add.colon
- title output
- emphasize
- new.sentence
- howpublished "howpublished" bibinfo.check format.source output
- new.sentence
- edition missing$ 'skip$
- {edition output}
- if$
- author empty$
- 'skip$
- { organization missing$
- 'skip$
- {organization output}
- if$
- }
- if$
- address missing$ 'skip$
- {address output}
- if$
- format.date output
- format.note output
- fin.entry
- empty.misc.check
-}
-
-FUNCTION {booklet}{misc}
-
-
-FUNCTION {phdthesis}
-{ output.bibitem
- format.authors "author" output.check
- add.colon
- bold.format.title
- "title" output.check
- new.sentence
- bbl.phdthesis format.thesis.type format.source output.nonnull
- school "school" bibinfo.warn output
- address "address" bibinfo.check output
- format.date "year" output.check
- format.note output
- fin.entry
-}
-
-FUNCTION {proceedings}
-{ output.bibitem
- editor empty$
- { organization "organization" bibinfo.check output
- }
- { format.editors output.nonnull }
- if$
- add.colon
- title format.source "source" output.check
- format.bvolume output
- format.number.series output
- editor empty$
- { publisher empty$
- 'skip$
- {
- format.publisher.address output
- }
- if$
- }
- { publisher empty$
- {
- format.organization.address output }
- {
- organization "organization" bibinfo.check output
- format.publisher.address output
- }
- if$
- }
- if$
- format.date "year" output.check
- format.note output
- fin.entry
-}
-
-FUNCTION {techreport}
-{ output.bibitem
- format.authors "author" output.check
- add.colon
- bold.format.title
- "title" output.check
- new.sentence
- format.tr.number output.nonnull
- institution "institution" bibinfo.warn output
- address "address" bibinfo.check output
- format.date "year" output.check
- format.note output
- fin.entry
-}
-
-FUNCTION {unpublished}
-{ output.bibitem
- format.authors "author" output.check
- add.colon
- bold.format.title "title" output.check
- format.date output
- format.note "note" output.check
- fin.entry
-}
-
-FUNCTION {default.type} { misc }
-
-
-
-%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %% %%%% %%% %%%%%%% %% %%%%%%%%%
-%% %%%% %% %%%% % %%%%% % %% %%%%%%%%%
-%% %%%%% %%%%% %% %%% %% %% %%%%%%%%%
-%% %%%%%% %%%%%% %%% % %%% %% %%%%%%%%%
-%% %%%%% %%%%% %%%% %%%% %% %%%%%%%%%
-%% %%%% %% %%%% %%%%%%%%%%% %% %%%%%%%%%
-%% %% %%%% %%% %%%%%%%%%%% %% %%
-%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
- %
- % Function for printing out all data in xml format.
- % { address archive author booktitle chapter edition editor
- % howpublished institution journal key month note number
- % organization pages publisher school series title
- % type url volume year
- % }
- %
-%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-%%
- % output.xml
- %
-%%
-FUNCTION {output.xml}
-{ duplicate$ "" =
- 'pop$
- { " " swap$ * write$ newline$ }
- if$
-}
-
-%%
- % markup.xml
- %
- % Takes 2 args text & tag {"the text " "tag"}
- % Returns 1 string {"<tag>the text <\tag>"}
-%%
-FUNCTION {markup.xml}
-{
- "" 'r := % result
- 't := % tag
- duplicate$ missing$
- 'pop$
- { 'r := }
- if$
- r "" =
- 'skip$
- { "<" t * ">" * r * "</" * t * ">" * 'r := }
- if$
- r
-}
-
-%% Takes 2 args - tag, string
-FUNCTION{markup.xml.title}
-{ pop$ % tag
- duplicate$ missing$
- 'pop$
- {
- 's := % string
- s "\&" "&" replace 's :=
- s "p" markup.xml 's :=
- s "title" markup.xml output.xml
- }
- if$
-}
-
-
-%%
- % markup.xml.pages
- %
- % Takes 1 arg (pages string)
- % seperates into <fpage> and <lpage> if
- % there is a - seperator. else no lpage.
- %
- % need to remove others
-%%
-FUNCTION{markup.xml.pages}
-{
- "" 'r := % fpage
- "" 's := % lpage
- duplicate$ missing$
- 'pop$
- {
- 't :=
- t " " "" replace 't := % remove all spaces. pgs must be - seperated
- { t empty$ not }
- {
- t #1 #1 substring$ "-" =
- {
- t #2 global.max$ substring$ 's :=
- "" 't := % break while loop
- }{
- r t #1 #1 substring$ * 'r :=
- t #2 global.max$ substring$ 't :=
- }
- if$
- }
- while$
- }
- if$
- r "fpage" markup.xml output.xml
- s "lpage" markup.xml output.xml
-}
-
-
-%%
- % markup.xml.names
- %
- % Takes 2 args
- % tag, namefield (eg. author "au")
- % splits fields into <fnm> and <snm>
- % writes info
- % returns nothing
-%%
-FUNCTION {markup.xml.names}
-{
- 't := % tag
- "" 'r :=
- "" 's :=
- duplicate$ empty$
- { pop$
- organization missing$
- { institution "cnm" markup.xml
- "au" markup.xml "aug" markup.xml output.xml }
- { organization "cnm" markup.xml
- "au" markup.xml "aug" markup.xml output.xml }
- if$ }
- {
- " <aug>" write$ newline$
- 'names := % names string
- names num.names$ 'j := % num of names
- #1 'i := % init counter
- { i #1 j + < } % while (i <= j)
- {
- " <au>" write$
-
- % Initial first names
- % if first name all in capitals
- % - assume is initial list of first names.
- names i "{ff{ }}" format.name$
- duplicate$ "u" change.case$ =
- { names i "{ff{ }}" format.name$ }
- { names i "{f{}}" format.name$ }
- if$
-
- % if last name but no first name use cnm; else snm
- duplicate$ "" =
- { names i "{ll{ }}" format.name$ % last names space seperated.
- "cnm" markup.xml write$ }
- { names i "{ll{ }}" format.name$ % last names space seperated.
- "snm" markup.xml write$ }
- if$
-
- "fnm" markup.xml write$
-
- "</au>" write$ newline$
- i #1 + 'i :=
- }
- while$
- " </aug>" write$ newline$
- }
- if$
-}
-
-
-%%
- % markup.xml.pub
- %
- % Takes 4 args (school address publisher tag)
- % prints concatenation
- % returns nothing
-%%
-FUNCTION {markup.xml.pub}
-{
- 't := % Tag
- "" 'p := % Publisher
- "" 'q := % Address
- "" 'r := % School
- "" 's := % Answer
- duplicate$ missing$ 'pop$ { 'p := } if$
- duplicate$ missing$ 'pop$ { 'q := } if$
- duplicate$ missing$ 'pop$ { 'r := } if$
- "" r = not % school not empty
- { r 's := } % return school as publisher
- { % else
- "" p = "" q = and % address and pub empty
- 'skip$
- {
- "" q =
- { p 's := } % return pub
- { "" p =
- { q 's := } % return add
- { q ": " * p * 's := } % return add : pub
- if$
- }
- if$
- }
- if$
- }
- if$
- s t markup.xml output.xml
-}
-
-%%
- % xml.phd
- %
- % Takes nothing
- % Returns type (phd/msc) of empty string
-%%
-FUNCTION {xml.phd}
-{
- "phdthesis" type$ =
- "mastersthesis" type$ = OR
- { "phdthesis" type$ =
- { bbl.phdthesis format.thesis.type }
- { bbl.mthesis format.thesis.type }
- if$
- }
- { type } % usually empty
- if$
-}
-
-% markup.xml.edition
-%
-% edition is a numeric value. ie "2"
-% if format 2nd 1st etc.. strip letters.
-%
-FUNCTION {markup.xml.edition}
-{ pop$ pop$ %clear stack
- edition strip.letters duplicate$ "" =
- { pop$ edition }
- 'skip$
- if$
- "edition" markup.xml output.xml
-}
-
-
-%% [bmc@xmlcomment]
- % this is an environment that returns nothing
- % so although it will be embedded in the bbl file it
- % will not display anything
-%%
-FUNCTION{begin.bmcxmlcomment}{
- newline$
- "\newcommand{\BMCxmlcomment}[1]{}" write$ newline$
- newline$
- "\BMCxmlcomment{" write$ newline$
- newline$ "<refgrp>" write$ newline$
-}
-
-FUNCTION{end.bmcxmlcomment}{
- newline$
- "</refgrp>" write$ newline$
- "} % end of \BMCxmlcomment" write$ newline$
-}
-
-%%
- % export.xml
- %
- % done for each entry referenced in the BibTeX database
-%%
-FUNCTION {export.xml}{
- newline$
- global.counter #1 + 'global.counter :=
- "<bibl id=" quote$ * "B" * global.counter int.to.str$ * quote$ * ">" *
- write$ newline$
-% title "\&" "&" replace "title" markup.xml.title
- title "title" markup.xml.title
- author "aug" markup.xml.names % org. and inst. here
- howpublished missing$
- { booktitle missing$
- { journal missing$
- { xml.phd } % <type> Phd/Msc
- {journal}
- if$
- } {booktitle}
- if$
- } { howpublished }
- if$ "source" markup.xml output.xml
- school
- address
- publisher "publisher" markup.xml.pub
- editor "editor" markup.xml output.xml
- edition "edition" markup.xml.edition
- series "p" markup.xml
- "title" markup.xml
- "series" markup.xml output.xml
- chapter "p" markup.xml
- "title" markup.xml
- "section" markup.xml output.xml
- % month % ignore
- year "pubdate" markup.xml output.xml
-
- note missing$
- { volume "volume" markup.xml output.xml
- number "issue" markup.xml output.xml
- pages markup.xml.pages
- url "url" markup.xml output.xml }
- { note "l" change.case$ "in press" =
- { " <inpress />" write$ newline$ }
- { volume "volume" markup.xml output.xml
- number "issue" markup.xml output.xml
- pages markup.xml.pages
- url "url" markup.xml output.xml
- note "note" markup.xml output.xml
- }
- if$
- }
- if$
- "</bibl>" write$ newline$
-}
-
-% xml fields not used
-% suppliment conference xrefbib issn issb archive key
-% BioMed_Central_Tex_Template_v1.01
-
-
-%%%%%%%%%%%%%%%%
-% %
-% Main %
-% %
-%%%%%%%%%%%%%%%%
-
-READ
-
-FUNCTION {initialize.longest.label}
-{ "" 'longest.label :=
- #1 'number.label :=
- #0 'longest.label.width :=
-}
-FUNCTION {longest.label.pass}
-{ number.label int.to.str$ 'label :=
- number.label #1 + 'number.label :=
- label width$ longest.label.width >
- { label 'longest.label :=
- label width$ 'longest.label.width :=
- }
- 'skip$
- if$
-}
-EXECUTE {initialize.longest.label}
-ITERATE {longest.label.pass}
-FUNCTION {begin.bib}
-{ "%% BioMed_Central_Bib_Style_v1.01" write$ newline$ newline$
- preamble$ empty$
- 'skip$
- { preamble$ write$ newline$ }
- if$
- "\begin{thebibliography}{" longest.label * "}" *
- write$ newline$
- "\providecommand{\url}[1]{[#1]}"
- write$ newline$
- "\providecommand{\urlprefix}{}"
- write$ newline$
-}
-
-EXECUTE {begin.bib}
-EXECUTE {init.state.consts}
-ITERATE {call.type$}
-FUNCTION {end.bib}
-{ newline$
- "\end{thebibliography}" write$ newline$
-}
-EXECUTE {end.bib}
-EXECUTE {begin.bmcxmlcomment}
-ITERATE {export.xml}
-EXECUTE {end.bmcxmlcomment}
-%% End of customized bst file
-%%
-%% End of file `basic.bst'.
diff --git a/src/doc/Publications/bmc_paper/bmc_article.cls b/src/doc/Publications/bmc_paper/bmc_article.cls
deleted file mode 100755
index 896154105b6dfa0769a4c8a5660bdc7d9945349b..0000000000000000000000000000000000000000
--- a/src/doc/Publications/bmc_paper/bmc_article.cls
+++ /dev/null
@@ -1,138 +0,0 @@
-%% %
- % bmc_article.cls ver: 1.03 %
- % %
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
- % %%
- % A Style Class based on article for %%
- % formating towards BioMed Central %%
- % guidelines %%
- % %%
- % <1 September 2003> %%
- % %%
- % %%
- % %%
- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
- %
- % See Readme.txt for ToDo list.
-%%
-%
-
-\NeedsTeXFormat{LaTeX2e}[1995/12/01]
-\ProvidesClass{bmc_article}[2003/09/01 v1.01 BioMed Central article class]
-\LoadClassWithOptions{article}
-
-\renewcommand\@biblabel[1]{#1.}
-\def\hi{}
-\def\pb{\\*[0.42cm]}
-
-
-\AtBeginDocument{}
-
-\def\@abstractline{\textwidth}
-
-\newcounter{bmc@correspondingauthor}
-\setcounter{bmc@correspondingauthor}{0} %never changes
-\newcounter{bmc@emailcounter} \setcounter{bmc@emailcounter}{0}
-
-
-% Corresponding Authors.
-% adds an asterisk * as a marker.
-\def\correspondingauthor{$^*$}
-\def\@corresponding{\footnotesize\correspondingauthor Corresponding author}
-
-
-% Email.
-% A variable to store names and emails.
-\gdef\bmc@email{Email: }
-\newcommand\bmc@curname{}
-\newcommand\email[1]{\relax
- \g@addto@macro\bmc@email{#1; }} % has trailing ;
-
-\def\@bmc@email{\relax\footnotesize{\bmc@email}}
-
-% Address
-\def\address#1{ \def\@address{\begin{hi}\footnotesize#1\end{hi}}}
-\def\iid(#1){\hi$^#1$}
-
-% Thanks
-\def\thempfootnote{\normalfont\@arabic\c@mpfootnote}
-\def\thanks#1{%
- \stepcounter{footnote}%
- \hbox{\@textsuperscript{\normalfont\thefootnote}}%
- \protected@xdef\@thanks{\@thanks%
- \protect\footnotetext[\the\c@footnote]{#1}}%
- }
-
-% Maketitle
-\let\old@maketitle\maketitle
-\renewcommand\maketitle{
- \begin{flushleft}\mbox{
- \global\let\@date\@empty % @date = null.
- {\sffamily\begin{minipage}{\textwidth}%
- \@maketitle
- {\raggedright%
- {\noindent\@address}\\ \hbox{}
- {\noindent\@bmc@email}\\ \hbox{}
- {\noindent\@corresponding}%
- }%end \raggedright
- \end{minipage}%
- }
- \renewcommand\thefootnote{\old@thefootnote} %
- } % \mbox
- \end{flushleft}
-}
-
-\def\and{, }
-
-\def\@maketitle{%
- \newpage
- \null
- \vskip 2em%
- {\noindent\LARGE \bfseries\@title \par}%
- \vskip 1.5em%
- {\large
- %\lineskip .5em%
- \noindent\@author
- \par}%
- \vskip 1em%
- \par
- \vskip 1.5em}
-
-
-% reformats abstract to BMC looks
-\let\old@abstract\abstract
-\renewenvironment{abstract}
- {
- \ifhmode\begingroup\parskip0pt\par\noindent\endgroup\fi%
- \begin{sffamily}
- \vspace{1cm} % use \topsep in list
- {\noindent\bfseries\large\abstractname\vspace{-0.5em}}
- {\par\vbox{\hrule width \@abstractline}}
- }{
- \ifhmode\begingroup\parskip0pt\par\noindent\endgroup\fi %
- \vbox{\hrule width \@abstractline} \vspace{1cm} %
- \end{sffamily}
- }
-
-
-
-%% \@startsection{sec-name}{level}{indent}{pre-skip}
-%% {post-skip}{style}*[srt title]{title}
-\renewcommand\section{\@startsection {section}{1}{\z@}%
- {-0.84cm \@plus -1ex \@minus -.2ex} {.2ex \@plus.2ex} %%
- {\normalfont\large\bfseries\sffamily}}
-\renewcommand\subsection{\@startsection{subsection}{2}{\z@}%
- {-0.84cm \@plus -1ex \@minus -.2ex} {.2ex \@plus.2ex} %%
- {\normalfont\normalsize\bfseries\sffamily}}
-\renewcommand\subsubsection{\@startsection{subsubsection}{3}{\z@}%
- {-0.84cm \@plus -1ex \@minus -.2ex} {.2ex \@plus.2ex} %%
- {\normalfont\normalsize\sffamily\itshape}}
-\renewcommand\paragraph{\@startsection{paragraph}{4}{\z@}%
- {-.2em \@plus1ex \@minus.2ex} {-0.5em} %%
- {\normalfont\small\bfseries\sffamily}}
-\renewcommand\subparagraph{\@startsection{subparagraph}{5}{\parindent}%
- {-.2em \@plus1ex \@minus.2ex} {-0.5em} %%
- {\normalfont\normalsize\sffamily}}
-
-\endinput
-%% end of bmc_article.cls
diff --git a/src/doc/Publications/bmc_paper/cover_letter.txt b/src/doc/Publications/bmc_paper/cover_letter.txt
deleted file mode 100644
index ebaaa17afa6c7e0d37299e42cd94da46476f8760..0000000000000000000000000000000000000000
--- a/src/doc/Publications/bmc_paper/cover_letter.txt
+++ /dev/null
@@ -1,4 +0,0 @@
-SeqTools: visual tools for manual analysis of sequence alignments
-
-This paper describes version 4 of the "SeqTools" suite of progrmas for visualising sequence alignments: Blixem, Dotter and Belvu. Previously, these programs were only available as part of the AceDB genome database system and as such had a limited audience. In version 4, they were re-written to become independent of AceDB, and have been vastly improved and updated to make them more generically useful. Significant enhancements have been added, particularly to Blixem, since the programs were first published (Sonnhammer, E. L. and Durbin, R. (1994); Sonnhammer, E. L. and Durbin, R. (1995); and Sonnhammer, E. and Hollich, V. (2005)). The aim of this paper is to promote awareness of these tools and the improvements which make them more widely useful.
-
diff --git a/src/doc/Publications/bmc_paper/fig1_blixem.png b/src/doc/Publications/bmc_paper/fig1_blixem.png
deleted file mode 100644
index 36543c91d94c7696a66a78ca257388a0ffd52d75..0000000000000000000000000000000000000000
Binary files a/src/doc/Publications/bmc_paper/fig1_blixem.png and /dev/null differ
diff --git a/src/doc/Publications/bmc_paper/fig2_dotter.png b/src/doc/Publications/bmc_paper/fig2_dotter.png
deleted file mode 100644
index a16c39ea79f417a5a8dc2d006386cdced839a2c2..0000000000000000000000000000000000000000
Binary files a/src/doc/Publications/bmc_paper/fig2_dotter.png and /dev/null differ
diff --git a/src/doc/Publications/bmc_paper/fig3_belvu_conservation.png b/src/doc/Publications/bmc_paper/fig3_belvu_conservation.png
deleted file mode 100644
index 92e2ac5276b7f39d8d2beec6bb1d06e0de8f6df1..0000000000000000000000000000000000000000
Binary files a/src/doc/Publications/bmc_paper/fig3_belvu_conservation.png and /dev/null differ
diff --git a/src/doc/Publications/bmc_paper/fig4_belvu_residues.png b/src/doc/Publications/bmc_paper/fig4_belvu_residues.png
deleted file mode 100644
index 25d11d407876c28923f10f80dfcbf8698858feea..0000000000000000000000000000000000000000
Binary files a/src/doc/Publications/bmc_paper/fig4_belvu_residues.png and /dev/null differ
diff --git a/src/doc/Publications/bmc_paper/fig5_belvu_plot.png b/src/doc/Publications/bmc_paper/fig5_belvu_plot.png
deleted file mode 100644
index 604464bb2372bb4ff6e914d6cf1bc56003f070b5..0000000000000000000000000000000000000000
Binary files a/src/doc/Publications/bmc_paper/fig5_belvu_plot.png and /dev/null differ
diff --git a/src/doc/Publications/bmc_paper/fig6_belvu_tree.png b/src/doc/Publications/bmc_paper/fig6_belvu_tree.png
deleted file mode 100644
index 78d1c4a56b9300f7a001c623b410a40d10bc50c3..0000000000000000000000000000000000000000
Binary files a/src/doc/Publications/bmc_paper/fig6_belvu_tree.png and /dev/null differ
diff --git a/src/doc/Publications/bmc_paper/seqtools.bib b/src/doc/Publications/bmc_paper/seqtools.bib
deleted file mode 100644
index c566fef2bc8a63bef23d0297824ca58eedc06e16..0000000000000000000000000000000000000000
--- a/src/doc/Publications/bmc_paper/seqtools.bib
+++ /dev/null
@@ -1,386 +0,0 @@
-@incollection{Du94,
-year={1994},
-isbn={978-1-4613-6042-1},
-booktitle={Computational Methods in Genome Research},
-editor={Suhai, Sándor},
-doi={10.1007/978-1-4615-2451-9_4},
-title={The ACEDB Genome Database},
-url={http://dx.doi.org/10.1007/978-1-4615-2451-9_4},
-publisher={Springer US},
-author={Durbin, Richard and Thierry-Mieg, Jean},
-pages={45-55},
-language={English}
-}
-
-@article{So94,
-author = {Sonnhammer, Erik L.L. and Durbin, Richard},
-title = {A Workbench for large-scale sequence homology analysis},
-volume = {10},
-number = {3},
-pages = {301-307},
-year = {1994},
-doi = {10.1093/bioinformatics/10.3.301},
-abstract ={When routinely analysing very long stretches of DNA sequences produced by genome sequencing projects, detailed analysis of database search results becomes exceedingly time consuming. To reduce the tedious browsing of large quantities of protein similarities, two programs, MSPcrunch and Blixem, were developed, which assist in processing the results from the database search programs in the BLAST suite. MSPcrunch removes biased composition and redundant matches while keeping weak matches that are consistent with a larger gapped alignment. This makes BLASTsearching in practice more sensitive and reduces the risk of overlooking distant similarities. Blixem is a multiple sequence alignment viewer for X-windows which makes it significantly easier to scan and evaluate the matches ratified by MSPcrunch. In Blixem, matches to the translated DNA query sequence are simultaneously aligned in three frames. Also, the distribution of matches over the whole DNA query is displayed. Examples of usage are drawn from 36 C.elegans cosmid clones totalling 1.2 megabases, to which these tools were applied.},
-URL = {http://bioinformatics.oxfordjournals.org/content/10/3/301.abstract},
-eprint = {http://bioinformatics.oxfordjournals.org/content/10/3/301.full.pdf+html},
-journal = {Computer applications in the biosciences : CABIOS}
-}
-
-@article{So95,
-author = {Sonnhammer, Erik L.L. and Durbin, Richard},
-title = {A dot-matrix program with dynamic threshold control suited for genomic DNA and protein sequence analysis},
-volume = {167},
-number = {1-2},
-pages = {GC1-10},
-year = {1995},
-doi = {10.1016/0378-1119(95)00714-8},
-abstract = {Graphical dot-matrix plots can provide the most complete and detailed comparison of two sequences. Presented here is DOTTER2, a dot-plot program for X-windows which can compare DNA or protein sequences, and also DNA versus protein. The main novel feature of DOTTER is that the user can vary the stringency cutoffs interactively, so that the dot-matrix only needs to be calculated once. This is possible thanks to a 'Greyramp tool' that was developed to change the displayed stringency of the matrix by dynamically changing the greyscale rendering of the dots. The Greyramp tool allows the user to interactively change the lower and upper score limit for the greyscale rendering. This allows exploration of the separation between signal and noise, and fine-grained visualisation of different score levels in the dot-matrix. Other useful features are dot-matrix compression, mouse-controlled zooming, sequence alignment display and saving/loading of dot-matrices. Since the matrix only has to be calculated once and since the algorithm is fast and linear in space, DOTTER is practical to use even for sequences as long as cosmids. DOTTER was integrated in the gene-modelling module of the genomic database system ACEDB3. This was done via the homology viewer BLIXEM in a way that also allows segments from the BLAST suite of searching programs to be superimposed on top of the full dot-matrix. This feature can also be used for very quick finding of the strongest matches. As examples, we analyse a Caenorhabditis elegans cosmid with several tandem repeat families, and illustrate how DOTTER can improve gene modelling.},
-URL = {http://ukpmc.ac.uk/abstract/MED/8566757},
-eprint = {http://bioinformatics.oxfordjournals.org/content/10/3/301.full.pdf+html},
-journal = {Computer applications in the biosciences : CABIOS}
-}
-
-@Article{Ha06,
-AUTHOR = {Harrow, Jennifer and Denoeud, France and Frankish, Adam and Reymond, Alexandre and Chen, Chao-Kung and Chrast, Jacqueline and Lagarde, Julien and Gilbert, James and Storey, Roy and Swarbreck, David and Rossier, Colette and Ucla, Catherine and Hubbard, Tim and Antonarakis, Stylianos and Guigo, Roderic},
-TITLE = {GENCODE: producing a reference annotation for ENCODE},
-JOURNAL = {Genome Biology},
-VOLUME = {7},
-YEAR = {2006},
-NUMBER = {Suppl 1},
-PAGES = {S4},
-URL = {http://genomebiology.com/2006/7/S1/S4},
-DOI = {10.1186/gb-2006-7-s1-s4},
-PubMedID = {16925838},
-ISSN = {1465-6906},
-ABSTRACT = {BACKGROUND:The GENCODE consortium was formed to identify and map all protein-coding genes within the ENCODE regions. This was achieved by a combination of initial manual annotation by the HAVANA team, experimental validation by the GENCODE consortium and a refinement of the annotation based on these experimental results.RESULTS:The GENCODE gene features are divided into eight different categories of which only the first two (known and novel coding sequence) are confidently predicted to be protein-coding genes. 5' rapid amplification of cDNA ends (RACE) and RT-PCR were used to experimentally verify the initial annotation. Of the 420 coding loci tested, 229 RACE products have been sequenced. They supported 5' extensions of 30 loci and new splice variants in 50 loci. In addition, 46 loci without evidence for a coding sequence were validated, consisting of 31 novel and 15 putative transcripts. We assessed the comprehensiveness of the GENCODE annotation by attempting to validate all the predicted exon boundaries outside the GENCODE annotation. Out of 1,215 tested in a subset of the ENCODE regions, 14 novel exon pairs were validated, only two of them in intergenic regions.CONCLUSION:In total, 487 loci, of which 434 are coding, have been annotated as part of the GENCODE reference set available from the UCSC browser. Comparison of GENCODE annotation with RefSeq and ENSEMBL show only 40% of GENCODE exons are contained within the two sets, which is a reflection of the high number of alternative splice forms with unique exons annotated. Over 50% of coding loci have been experimentally verified by 5' RACE for EGASP and the GENCODE collaboration is continuing to refine its annotation of 1% human genome with the aid of experimental validation.},
-}
-
-@article{Ma10,
-author = {Madupu, Ramana and Brinkac, Lauren M. and Harrow, Jennifer and Wilming, Laurens G. and Böhme, Ulrike and Lamesch, Philippe and Hannick, Linda I.},
-title = {Meeting report: a workshop on Best Practices in Genome Annotation},
-volume = {2010},
-year = {2010},
-doi = {10.1093/database/baq001},
-abstract ={Efforts to annotate the genomes of a wide variety of model organisms are currently carried out by sequencing centers, model organism databases and academic/institutional laboratories around the world. Different annotation methods and tools have been developed over time to meet the needs of biologists faced with the task of annotating biological data. While standardized methods are essential for consistent curation within each annotation group, methods and tools can differ between groups, especially when the groups are curating different organisms. Biocurators from several institutes met at the Third International Biocuration Conference in Berlin, Germany, April 2009 and hosted the ‘Best Practices in Genome Annotation: Inference from Evidence’ workshop to share their strategies, pipelines, standards and tools. This article documents the material presented in the workshop.},
-URL = {http://database.oxfordjournals.org/content/2010/baq001.abstract},
-eprint = {http://database.oxfordjournals.org/content/2010/baq001.full.pdf+html},
-journal = {Database}
-}
-
-
-@Article{20003482,
-AUTHOR = {Amid, Clara and Rehaume, Linda and Brown, Kelly and Gilbert, James and Dougan, Gordon and Hancock, Robert and Harrow, Jennifer},
-TITLE = {Manual annotation and analysis of the defensin gene cluster in the C57BL/6J mouse reference genome},
-JOURNAL = {BMC Genomics},
-VOLUME = {10},
-YEAR = {2009},
-NUMBER = {1},
-PAGES = {606},
-URL = {http://www.biomedcentral.com/1471-2164/10/606},
-DOI = {10.1186/1471-2164-10-606},
-PubMedID = {20003482},
-ISSN = {1471-2164},
-ABSTRACT = {BACKGROUND:Host defense peptides are a critical component of the innate immune system. Human alpha- and beta-defensin genes are subject to copy number variation (CNV) and historically the organization of mouse alpha-defensin genes has been poorly defined. Here we present the first full manual genomic annotation of the mouse defensin region on Chromosome 8 of the reference strain C57BL/6J, and the analysis of the orthologous regions of the human and rat genomes. Problems were identified with the reference assemblies of all three genomes. Defensins have been studied for over two decades and their naming has become a critical issue due to incorrect identification of defensin genes derived from different mouse strains and the duplicated nature of this region.RESULTS:The defensin gene cluster region on mouse Chromosome 8 A2 contains 98 gene loci: 53 are likely active defensin genes and 22 defensin pseudogenes. Several TATA box motifs were found for human and mouse defensin genes that likely impact gene expression. Three novel defensin genes belonging to the Cryptdin Related Sequences (CRS) family were identified. All additional mouse defensin loci on Chromosomes 1, 2 and 14 were annotated and unusual splice variants identified. Comparison of the mouse alpha-defensins in the three main mouse reference gene sets Ensembl, Mouse Genome Informatics (MGI), and NCBI RefSeq reveals significant inconsistencies in annotation and nomenclature. We are collaborating with the Mouse Genome Nomenclature Committee (MGNC) to establish a standardized naming scheme for alpha-defensins.CONCLUSIONS:Prior to this analysis, there was no reliable reference gene set available for the mouse strain C57BL/6J defensin genes, demonstrating that manual intervention is still critical for the annotation of complex gene families and heavily duplicated regions. Accurate gene annotation is facilitated by the annotation of pseudogenes and regulatory elements. Manually curated gene models will be incorporated into the Ensembl and Consensus Coding Sequence (CCDS) reference sets. Elucidation of the genomic structure of this complex gene cluster on the mouse reference sequence, and adoption of a clear and unambiguous naming scheme, will provide a valuable tool to support studies on the evolution, regulatory mechanisms and biological functions of defensins in vivo.},
-}
-
-@Article{16925837,
-AUTHOR = {Bajic, Vladimir and Brent, Michael and Brown, Randall and Frankish, Adam and Harrow, Jennifer and Ohler, Uwe and Solovyev, Victor and Tan, Sin},
-TITLE = {Performance assessment of promoter predictions on ENCODE regions in the EGASP experiment},
-JOURNAL = {Genome Biology},
-VOLUME = {7},
-YEAR = {2006},
-NUMBER = {Suppl 1},
-PAGES = {S3},
-URL = {http://genomebiology.com/2006/7/S1/S3},
-DOI = {10.1186/gb-2006-7-s1-s3},
-PubMedID = {16925837},
-ISSN = {1465-6906},
-ABSTRACT = {BACKGROUND:This study analyzes the predictions of a number of promoter predictors on the ENCODE regions of the human genome as part of the ENCODE Genome Annotation Assessment Project (EGASP). The systems analyzed operate on various principles and we assessed the effectiveness of different conceptual strategies used to correlate produced promoter predictions with the manually annotated 5' gene ends.RESULTS:The predictions were assessed relative to the manual HAVANA annotation of the 5' gene ends. These 5' gene ends were used as the estimated reference transcription start sites. With the maximum allowed distance for predictions of 1,000 nucleotides from the reference transcription start sites, the sensitivity of predictors was in the range 32% to 56%, while the positive predictive value was in the range 79% to 93%. The average distance mismatch of predictions from the reference transcription start sites was in the range 259 to 305 nucleotides. At the same time, using transcription start site estimates from DBTSS and H-Invitational databases as promoter predictions, we obtained a sensitivity of 58%, a positive predictive value of 92%, and an average distance from the annotated transcription start sites of 117 nucleotides. In this experiment, the best performing promoter predictors were those that combined promoter prediction with gene prediction. The main reason for this is the reduced promoter search space that resulted in smaller numbers of false positive predictions.CONCLUSION:The main finding, now supported by comprehensive data, is that the accuracy of human promoter predictors for high-throughput annotation purposes can be significantly improved if promoter prediction is combined with gene prediction. Based on the lessons learned in this experiment, we propose a framework for the preparation of the next similar promoter prediction assessment.},
-}
-
-
-@article{Mudge06052011,
-author = {Mudge, Jonathan M. and Frankish, Adam and Fernandez-Banet, Julio and Alioto, Tyler and Derrien, Thomas and Howald, Cédric and Reymond, Alexandre and Guigo, Roderic and Hubbard, Tim and Harrow, Jennifer},
-title = {The origins, evolution and functional potential of alternative splicing in vertebrates},
-year = {2011},
-doi = {10.1093/molbev/msr127},
-abstract ={Alternative splicing (AS) has the potential to greatly expand the functional repertoire of mammalian transcriptomes. However, few variant transcripts have been characterized functionally, making it difficult to assess the contribution of AS to the generation of phenotypic complexity and to study the evolution of splicing patterns. We have compared the AS of 309 protein-coding genes in the human ENCODE pilot regions against their mouse orthologs in unprecedented detail, utilizing traditional transcriptomic and RNAseq data. The conservation status of every transcript has been investigated, and each functionally categorized as coding (separated into CDS or nonsense-mediated decay (NMD)-linked) or non-coding. 36.7% of human and 19.3% of mouse coding transcripts are species specific, and we observe a 3.6 times excess of human NMD transcripts compared with mouse; in contrast to previous studies, the majority of species specific AS is unlinked to transposable elements. We observe one conserved CDS variant and one conserved NMD variant per 2.3 and 11.4 genes respectively. Subsequently, we identify and characterize equivalent AS patterns for 22.9% of these CDS or NMD-linked events in non-mammalian vertebrate genomes, and our data indicate that functional NMD-linked AS is more widespread and ancient than previously thought. Furthermore, whilst we observe an association between conserved AS and elevated sequence conservation, as previously reported, we emphasize that 30% of conserved AS exons display sequence conservation below the average score for constitutive exons. In conclusion, we demonstrate the value of detailed comparative annotation in generating a comprehensive set of AS transcripts, increasing our understanding of AS evolution in vertebrates. Our data support a model whereby the acquisition of functional AS has occurred throughout vertebrate evolution, and is considered alongside amino acid change as a key mechanism in gene evolution.},
-URL = {http://mbe.oxfordjournals.org/content/early/2011/05/06/molbev.msr127.abstract},
-eprint = {http://mbe.oxfordjournals.org/content/early/2011/05/06/molbev.msr127.full.pdf+html},
-journal = {Molecular Biology and Evolution}
-}
-
-@Article{18507838,
-AUTHOR = {Mudge, Jonathan and Armstrong, Stuart and McLaren, Karen and Beynon, Robert and Hurst, Jane and Nicholson, Christine and Robertson, Duncan and Wilming, Laurens and Harrow, Jennifer},
-TITLE = {Dynamic instability of the major urinary protein gene family revealed by genomic and phenotypic comparisons between C57 and 129 strain mice},
-JOURNAL = {Genome Biology},
-VOLUME = {9},
-YEAR = {2008},
-NUMBER = {5},
-PAGES = {R91},
-URL = {http://genomebiology.com/2008/9/5/R91},
-DOI = {10.1186/gb-2008-9-5-r91},
-PubMedID = {18507838},
-ISSN = {1465-6906},
-ABSTRACT = {BACKGROUND:The major urinary proteins (MUPs) of Mus musculus domesticus are deposited in urine in large quantities, where they bind and release pheromones and also provide an individual 'recognition signal' via their phenotypic polymorphism. Whilst important information about MUP functionality has been gained in recent years, the gene cluster is poorly studied in terms of structure, genic polymorphism and evolution.RESULTS:We combine targeted sequencing, manual genome annotation and phylogenetic analysis to compare the Mup clusters of C57BL/6J and 129 strains of mice. We describe organizational heterogeneity within both clusters: a central array of cassettes containing Mup genes highly similar at the protein level, flanked by regions containing Mup genes displaying significantly elevated divergence. Observed genomic rearrangements in all regions have likely been mediated by endogenous retroviral elements. Mup loci with coding sequences that differ between the strains are identified - including a gene/pseudogene pair - suggesting that these inbred lineages exhibit variation that exists in wild populations. We have characterized the distinct MUP profiles in the urine of both strains by mass spectrometry. The total MUP phenotype data is reconciled with our genomic sequence data, matching all proteins identified in urine to annotated genes.CONCLUSION:Our observations indicate that the MUP phenotypic polymorphism observed in wild populations results from a combination of Mup gene turnover coupled with currently unidentified mechanisms regulating gene expression patterns. We propose that the structural heterogeneity described within the cluster reflects functional divergence within the Mup gene family.},
-}
-
-% This file was created with JabRef 2.3b2.
-% Encoding: Cp1252
-
-@article{Fi10,
-author = {Finn, Robert D. and Mistry, Jaina and Tate, John and Coggill, Penny and Heger, Andreas and Pollington, Joanne E. and Gavin, O. Luke and Gunasekaran, Prasad and Ceric, Goran and Forslund, Kristoffer and Holm, Liisa and Sonnhammer, Erik L. L. and Eddy, Sean R. and Bateman, Alex},
-title = {The Pfam protein families database},
-volume = {38},
-number = {suppl 1},
-pages = {D211-D222},
-year = {2010},
-doi = {10.1093/nar/gkp985},
-abstract ={Pfam is a widely used database of protein families and domains. This article describes a set of major updates that we have implemented in the latest release (version 24.0). The most important change is that we now use HMMER3, the latest version of the popular profile hidden Markov model package. This software is ∼100 times faster than HMMER2 and is more sensitive due to the routine use of the forward algorithm. The move to HMMER3 has necessitated numerous changes to Pfam that are described in detail. Pfam release 24.0 contains 11 912 families, of which a large number have been significantly updated during the past two years. Pfam is available via servers in the UK (http://pfam.sanger.ac.uk/), the USA (http://pfam.janelia.org/) and Sweden (http://pfam.sbc.su.se/).},
-URL = {http://nar.oxfordjournals.org/content/38/suppl_1/D211.abstract},
-eprint = {http://nar.oxfordjournals.org/content/38/suppl_1/D211.full.pdf+html},
-journal = {Nucleic Acids Research}
-}
-
-@article{Wa09,
-author = {Waterhouse, Andrew M. and Procter, James B. and Martin, David M. A. and Clamp, Michèle and Barton, Geoffrey J.},
-title = {Jalview Version 2—a multiple sequence alignment editor and analysis workbench},
-volume = {25},
-number = {9},
-pages = {1189-1191},
-year = {2009},
-doi = {10.1093/bioinformatics/btp033},
-abstract ={Summary: Jalview Version 2 is a system for interactive WYSIWYG editing, analysis and annotation of multiple sequence alignments. Core features include keyboard and mouse-based editing, multiple views and alignment overviews, and linked structure display with Jmol. Jalview 2 is available in two forms: a lightweight Java applet for use in web applications, and a powerful desktop application that employs web services for sequence alignment, secondary structure prediction and the retrieval of alignments, sequences, annotation and structures from public databases and any DAS 1.53 compliant sequence or annotation server.Availability: The Jalview 2 Desktop application and JalviewLite applet are made freely available under the GPL, and can be downloaded from www.jalview.orgContact: g.j.barton@dundee.ac.uk},
-URL = {http://bioinformatics.oxfordjournals.org/content/25/9/1189.abstract},
-eprint = {http://bioinformatics.oxfordjournals.org/content/25/9/1189.full.pdf+html},
-journal = {Bioinformatics}
-}
-
-@article{Th97,
-author = {Thompson, Julie D. and Gibson, Toby J. and Plewniak, Frédéric and Jeanmougin, François and Higgins, Desmond G.},
-title = {The CLUSTAL\_X Windows Interface: Flexible Strategies for Multiple Sequence Alignment Aided by Quality Analysis Tools},
-volume = {25},
-number = {24},
-pages = {4876-4882},
-year = {1997},
-doi = {10.1093/nar/25.24.4876},
-abstract ={CLUSTAL X is a new windows interface for the widely-used progressive multiple sequence alignment program CLUSTAL W. The new system is easy to use, providing an integrated system for performing multiple sequence and profile alignments and analysing the results. CLUSTAL X displays the sequence alignment in a window on the screen. A versatile sequence colouring scheme allows the user to highlight conserved features in the alignment. Pull-down menus provide all the options required for traditional multiple sequence and profile alignment. New features include: the ability to cut-and-paste sequences to change the order of the alignment, selection of a subset of the sequences to be realigned, and selection of a sub-range of the alignment to be realigned and inserted back into the original alignment. Alignment quality analysis can be performed and low-scoring segments or exceptional residues can be highlighted. Quality analysis and realignment of selected residue ranges provide the user with a powerful tool to improve and refine difficult alignments and to trap errors in input sequences. CLUSTAL X has been compiled on SUN Solaris, IRIX5.3 on Silicon Graphics, Digital UNIX on DECstations, Microsoft Windows (32 bit) for PCs, Linux ELF for x86 PCs, and Macintosh PowerMac.},
-URL = {http://nar.oxfordjournals.org/content/25/24/4876.abstract},
-eprint = {http://nar.oxfordjournals.org/content/25/24/4876.full.pdf+html},
-journal = {Nucleic Acids Research}
-}
-
-@Article{So05,
-AUTHOR = {Sonnhammer, Erik and Hollich, Volker},
-TITLE = {Scoredist: A simple and robust protein sequence distance estimator},
-JOURNAL = {BMC Bioinformatics},
-VOLUME = {6},
-YEAR = {2005},
-NUMBER = {1},
-PAGES = {108},
-URL = {http://www.biomedcentral.com/1471-2105/6/108},
-DOI = {10.1186/1471-2105-6-108},
-PubMedID = {15857510},
-ISSN = {1471-2105},
-ABSTRACT = {BACKGROUND:Distance-based methods are popular for reconstructing evolutionary trees thanks to their speed and generality. A number of methods exist for estimating distances from sequence alignments, which often involves some sort of correction for multiple substitutions. The problem is to accurately estimate the number of true substitutions given an observed alignment. So far, the most accurate protein distance estimators have looked for the optimal matrix in a series of transition probability matrices, e.g. the Dayhoff series. The evolutionary distance between two aligned sequences is here estimated as the evolutionary distance of the optimal matrix. The optimal matrix can be found either by an iterative search for the Maximum Likelihood matrix, or by integration to find the Expected Distance. As a consequence, these methods are more complex to implement and computationally heavier than correction-based methods. Another problem is that the result may vary substantially depending on the evolutionary model used for the matrices. An ideal distance estimator should produce consistent and accurate distances independent of the evolutionary model used.RESULTS:We propose a correction-based protein sequence estimator called Scoredist. It uses a logarithmic correction of observed divergence based on the alignment score according to the BLOSUM62 score matrix. We evaluated Scoredist and a number of optimal matrix methods using three evolutionary models for both training and testing Dayhoff, Jones-Taylor-Thornton, and Muller-Vingron, as well as Whelan and Goldman solely for testing. Test alignments with known distances between 0.01 and 2 substitutions per position (1-200 PAM) were simulated using ROSE. Scoredist proved as accurate as the optimal matrix methods, yet substantially more robust. When trained on one model but tested on another one, Scoredist was nearly always more accurate. The Jukes-Cantor and Kimura correction methods were also tested, but were substantially less accurate.CONCLUSION:The Scoredist distance estimator is fast to implement and run, and combines robustness with accuracy. Scoredist has been incorporated into the Belvu alignment viewer, which is available at ftp://ftp.cgb.ki.se/pub/prog/belvu/.},
-}
-
-
-
-@Article{10666718,
-AUTHOR = {Bruno, WJ and Socci, ND and Halpern, AL},
-TITLE = {Weighted Neighbor Joining: A Likelihood-Based Approach to Distance-Based Phylogeny Reconstruction},
-JOURNAL = {Mol Biol Evol},
-VOLUME = {17},
-YEAR = {2000},
-PAGES = {189-197},
-PubMedID = {10666718},
-}
-
-@Article{9254330,
-AUTHOR = {Gascuel, O},
-TITLE = {BIONJ: An Improved Version on the NJ Algorithm Based on a Simple Model of Sequence Data},
-JOURNAL = {Mol Biol Evol},
-VOLUME = {14},
-YEAR = {1997},
-PAGES = {685-695},
-PubMedID = {9254330},
-}
-
-@Article{3447015,
-AUTHOR = {Saitou, N and Nei, M},
-TITLE = {The Neighbor-joining Method: A New Method for Reconstructing Phylogenetic Trees},
-JOURNAL = {Mol Biol Evol},
-VOLUME = {4},
-YEAR = {1987},
-PAGES = {406-425},
-PubMedID = {3447015},
-}
-
-@Article{12028595,
-AUTHOR = {Zmasek, C and Eddy, S},
-TITLE = {RIO: analyzing proteomes by automated phylogenenomics using resampled inference of orthologs},
-JOURNAL = {BMC Bioinformatics},
-VOLUME = {3},
-YEAR = {2002},
-PAGES = {14},
-DOI = {10.1186/1471-2105-3-14},
-PubMedID = {12028595},
-}
-
-@Article{12217923,
-AUTHOR = {Hollich, V and Storm, CE and Sonnhammer, ELL},
-TITLE = {OrthoGUI: graphical presentation of Orthostrapper results},
-JOURNAL = {Bioinformatics},
-VOLUME = {18},
-YEAR = {2002},
-NUMBER = {9},
-PAGES = {1272-1273},
-DOI = {10.1093/bioinformatics/18.9.1272},
-PubMedID = {12217923},
-}
-
-@Article{11836216,
-AUTHOR = {Storm, CE and Sonnhammer, ELL},
-TITLE = {Automated ortholog inference from phylogenetic trees and calculation of orthology reliability},
-JOURNAL = {Bioinformatics},
-VOLUME = {18},
-YEAR = {2002},
-NUMBER = {1},
-PAGES = {92-99},
-DOI = {10.1093/bioinformatics/18.1.92},
-PubMedID = {11836216},
-}
-
-@Article{1471-2105-6-108,
-AUTHOR = {Jukes, TH and Cantor, CR},
-TITLE = {Evolution of protein molecules},
-JOURNAL = {Mammalian Protein Metabolism},
-YEAR = {1969},
-PUBLISHER = {Academic Press},
-PAGES = {21-132},
-}
-
-@Article{1471-2105-6-108,
-AUTHOR = {Nei, M and Kumar, S},
-JOURNAL = {Molecular Evolution and Phylogenetics},
-YEAR = {2000},
-PUBLISHER = {New York: Oxford University Press},
-}
-
-@Article{1471-2105-6-108,
-AUTHOR = {Kimura, M},
-JOURNAL = {The Neutral Theory of Molecular Evolution},
-YEAR = {1983},
-PUBLISHER = {Cambridge: Cambridge University Press},
-}
-
-@Article{1471-2105-6-108,
-AUTHOR = {Dayhoff, MO and Schwartz, RM and Orcutt, BC},
-TITLE = {A model of Evolutionary Change in Proteins},
-JOURNAL = {Atlas of Protein Sequence and Structure vol 5 supplement 3},
-YEAR = {1978},
-PUBLISHER = {National Biomedical Research Foundation, Washington},
-PAGES = {353-352},
-}
-
-@Article{1633570,
-AUTHOR = {Jones, DT and Taylor, WR and Thornton, JM},
-TITLE = {The rapid generation of mutation data matrices from protein sequences},
-JOURNAL = {Comput Appl Biosci},
-VOLUME = {8},
-YEAR = {1992},
-NUMBER = {3},
-PAGES = {275-282},
-PubMedID = {1633570},
-}
-
-@Article{11382360,
-AUTHOR = {Muller, T and Vingron, M},
-TITLE = {Modeling amino acid replacement},
-JOURNAL = {J Comput Biol},
-VOLUME = {7},
-YEAR = {2000},
-NUMBER = {6},
-PAGES = {761-776},
-DOI = {10.1089/10665270050514918},
-PubMedID = {11382360},
-}
-
-@Article{11319253,
-AUTHOR = {Whelan, S and Goldman, N},
-TITLE = {A general empirical model of protein evolution derived from multiple protein families using a maximum-likelihood approach},
-JOURNAL = {Mol Biol Evol},
-VOLUME = {18},
-YEAR = {2001},
-NUMBER = {5},
-PAGES = {691-699},
-PubMedID = {11319253},
-}
-
-@Article{1438297,
-AUTHOR = {Henikoff, S and Henikoff, JG},
-TITLE = {Amino acid substitution matrices from protein blocks},
-JOURNAL = {Proc Natl Acad Sci USA},
-VOLUME = {89},
-YEAR = {1992},
-NUMBER = {22},
-PAGES = {10915-10919},
-PubMedID = {1438297},
-}
-
-@Article{8697232,
-AUTHOR = {Agarwal, P and States, JS},
-TITLE = {A Bayesian Evolutionary Distance for Parametrically Aligned Sequences},
-JOURNAL = {J Comput Biol},
-VOLUME = {3},
-YEAR = {1996},
-NUMBER = {1},
-PAGES = {1-17},
-PubMedID = {8697232},
-}
-
-@Article{9545448,
-AUTHOR = {Stoye, J and Evers, D and Meyer, F},
-TITLE = {Rose: generating sequence families},
-JOURNAL = {Bioinformatics},
-VOLUME = {14},
-YEAR = {1998},
-NUMBER = {2},
-PAGES = {157-163},
-DOI = {10.1093/bioinformatics/14.2.157},
-PubMedID = {9545448},
-}
-
-@Article{1471-2105-6-108,
-TITLE = {Belvu website},
-URL = {http://www.cgb.ki.se/cgb/groups/sonnhammer/Belvu.html},
-}
-
-@Article{1471-2105-6-108,
-TITLE = {Stockholm data format},
-URL = {http://www.cgb.ki.se/cgb/groups/sonnhammer/Stockholm.html},
-}
-
-@Article{1471-2105-6-108,
-AUTHOR = {Felsenstein, J},
-TITLE = {PHYLIP - Phylogeny Inference Package (Version 3.2)},
-JOURNAL = {Cladistics},
-VOLUME = {5},
-YEAR = {1989},
-PAGES = {164-166},
-}
-
-@Article{1471-2105-6-108,
-TITLE = {Belvu download site},
-URL = {ftp://ftp.cgb.ki.se/pub/prog/belvu/},
-}
-
-
-@comment{jabref-meta: selector_publisher:}
-
-@comment{jabref-meta: selector_author:}
-
-@comment{jabref-meta: selector_journal:}
-
-@comment{jabref-meta: selector_keywords:}
diff --git a/src/doc/Publications/bmc_paper/seqtools.tex b/src/doc/Publications/bmc_paper/seqtools.tex
deleted file mode 100644
index 0aae4d0e77dc5d5773d25ccda8fa8427bb1adac5..0000000000000000000000000000000000000000
--- a/src/doc/Publications/bmc_paper/seqtools.tex
+++ /dev/null
@@ -1,441 +0,0 @@
-%% BioMed_Central_Tex_Template_v1.05
-%% %
-% bmc_article.tex ver: 1.05 %
-% %
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% LaTeX template for BioMed Central %%
-%% journal article submissions %%
-%% %%
-%% <27 January 2006> %%
-%% %%
-%% %%
-%% Uses: %%
-%% cite.sty, url.sty, bmc_article.cls %%
-%% ifthen.sty. multicol.sty %%
-%% %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% For instructions on how to fill out this Tex template %%
-%% document please refer to Readme.pdf and the instructions for %%
-%% authors page on the biomed central website %%
-%% http://www.biomedcentral.com/info/authors/ %%
-%% %%
-%% Please do not use \input{...} to include other tex files. %%
-%% Submit your LaTeX manuscript as one .tex document. %%
-%% %%
-%% All additional figures and files should be attached %%
-%% separately and not embedded in the \TeX\ document itself. %%
-%% %%
-%% BioMed Central currently use the MikTex distribution of %%
-%% TeX for Windows) of TeX and LaTeX. This is available from %%
-%% http://www.miktex.org %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\NeedsTeXFormat{LaTeX2e}[1995/12/01]
-\documentclass[10pt]{bmc_article}
-
-
-
-% Load packages
-\usepackage{cite} % Make references as [1-4], not [1,2,3,4]
-\usepackage{url} % Formatting web addresses
-\usepackage{ifthen} % Conditional
-\usepackage{multicol} %Columns
-\usepackage[utf8]{inputenc} %unicode support
-%\usepackage[applemac]{inputenc} %applemac support if unicode package fails
-%\usepackage[latin1]{inputenc} %UNIX support if unicode package fails
-\urlstyle{rm}
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% If you wish to display your graphics for %%
-%% your own use using includegraphic or %%
-%% includegraphics, then comment out the %%
-%% following two lines of code. %%
-%% NB: These line *must* be included when %%
-%% submitting to BMC. %%
-%% All figure files must be submitted as %%
-%% separate graphics through the BMC %%
-%% submission process, not included in the %%
-%% submitted article. %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\def\includegraphic{}
-\def\includegraphics{}
-
-
-
-\setlength{\topmargin}{0.0cm}
-\setlength{\textheight}{21.5cm}
-\setlength{\oddsidemargin}{0cm}
-\setlength{\textwidth}{16.5cm}
-\setlength{\columnsep}{0.6cm}
-
-\newboolean{publ}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% You may change the following style settings %%
-%% Should you wish to format your article %%
-%% in a publication style for printing out and %%
-%% sharing with colleagues, but ensure that %%
-%% before submitting to BMC that the style is %%
-%% returned to the Review style setting. %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-%Review style settings
-\newenvironment{bmcformat}{\begin{raggedright}\baselineskip20pt\sloppy\setboolean{publ}{false}}{\end{raggedright}\baselineskip20pt\sloppy}
-
-%Publication style settings
-%\newenvironment{bmcformat}{\fussy\setboolean{publ}{true}}{\fussy}
-
-
-
-% Begin ...
-\begin{document}
-\begin{bmcformat}
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% Enter the title of your article here %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\title{SeqTools: visual tools for manual analysis of sequence alignments}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% Enter the authors here %%
-%% %%
-%% Ensure \and is entered between all but %%
-%% the last two authors. This will be %%
-%% replaced by a comma in the final article %%
-%% %%
-%% Ensure there are no trailing spaces at %%
-%% the ends of the lines %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\author{Gemma Barson\correspondingauthor$^{1}$%
- \email{Gemma Barson\correspondingauthor - gemma.barson@sanger.ac.uk}%
- \and
- Ed Griffiths$^1$%
- \email{Ed Griffiths - edgrif@sanger.co.uk}
- }
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% Enter the authors' addresses here %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\address{%
- \iid(1)Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus,%
- Hinxton, Cambridge, UK
-}%
-
-\maketitle
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% The Abstract begins here %%
-%% %%
-%% The Section headings here are those for %%
-%% a Research article submitted to a %%
-%% BMC-Series journal. %%
-%% %%
-%% If your article is not of this type, %%
-%% then refer to the Instructions for %%
-%% authors on http://www.biomedcentral.com %%
-%% and change the section headings %%
-%% accordingly. %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-\begin{abstract}
- % Do not use inserted blank lines (ie \\) until main body of text.
- \paragraph*{Background:} Manual annotation is essential to create high-quality reference alignments and annotation. Annotators need to be able to view sequence alignments in detail. The SeqTools package provides three tools for viewing different types of sequence alignment: Blixem is a many-to-one browser of pairwise alignments, displaying multiple match sequences aligned against a single reference sequence; Dotter provides a graphical dot-plot view of a single pairwise alignment; and Belvu is a Multiple Sequence Alignment viewer, editor, and phylogenetic tool. These tools were originally part of the AceDB genome database system but have been updated and repackaged as separate applications to make them more widely useful.
-
- \paragraph*{Results:} Blixem is used by annotators to give a detailed view of the evidence for particular gene models. Blixem displays the gene model positions and the match sequences aligned against the genomic reference sequence. Annotators use this for many reasons, including to check the quality of an alignment, to find missing/misaligned sequence and to identify splice sites and polyA sites and signals. Dotter is used to give a dot-plot representation of a particular pairwise alignment. This is used to identify sequence that is not represented (or is misrepresented) and to quickly compare annotated gene models with transcriptional and protein evidence that putatively supports them. Belvu is used to analyse conservation patterns in Multiple Sequence Alignments and to perform a combination of manual and automatic processing of the alignment. High-quality reference alignments are essential if they are to be used as a starting point for further automatic alignment generation.
-
- \paragraph*{Conclusions:} Many annotators have found Blixem, Dotter and Belvu to be essential for analysing sequence alignments as part of the manual annotation process. The SeqTools package provides vastly improved and updated versions of these tools, with support for modern file formats and feature types.
-\end{abstract}
-
-
-
-\ifthenelse{\boolean{publ}}{\begin{multicols}{2}}{}
-
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% The Main Body begins here %%
-%% %%
-%% The Section headings here are those for %%
-%% a Research article submitted to a %%
-%% BMC-Series journal. %%
-%% %%
-%% If your article is not of this type, %%
-%% then refer to the instructions for %%
-%% authors on: %%
-%% http://www.biomedcentral.com/info/authors%%
-%% and change the section headings %%
-%% accordingly. %%
-%% %%
-%% See the Results and Discussion section %%
-%% for details on how to create sub-sections%%
-%% %%
-%% use \cite{...} to cite references %%
-%% \cite{koon} and %%
-%% \cite{oreg,khar,zvai,xjon,schn,pond} %%
-%% \nocite{smith,marg,hunn,advi,koha,mouse}%%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-
-
-%%%%%%%%%%%%%%%%
-%% Background %%
-%%
-\section*{Background}
-Manual annotation is essential to create high-quality reference alignments and annotation. Annotators need to be able to view sequence alignments in detail in order to verify them and to correct any errors. The SeqTools package provides three interactive tools for viewing different types of sequence alignment: Blixem, Dotter and Belvu.
-
-The SeqTools programs were originally part of the AceDB\cite{Du94} genome database system and as such were used mostly by annotation groups at the Sanger Institute. In version 4, the programs were re-written as the SeqTools package to make them available independently of AceDB. They have been updated to support new feature types and file formats, making them more widely useful and compatible with other tools. Significant enhancements have also been added, particularly to Blixem, since the programs were first published\cite{So94,So95,So05}.
-
-
-\section*{Implementation}
-The SeqTools programs are desktop applications written in C using GTK+.
-
-\subsection*{Blixem}
-Blixem is a many-to-one browser of pairwise alignments. It takes two files as input: a FASTA file containing the reference sequence, and a GFF version 3 file containing alignments as well as any gene models or other features of interest. Input files can be passed on the command line or piped in and additional feature files can be loaded from within the program. The move to GFF from legacy AceDB file formats is a major improvement in version 4 of Blixem.
-
-The display consists of two sections: a zoomable overview section showing the feature positions along the reference sequence; and a detail section showing the actual alignment of protein or nucleotide sequences to the reference DNA sequence. Multiple match sequences are stacked below the reference sequence and individual bases are colour-coded to indicated how well they match. Markers indicate where deletions and insertions occur.
-
-Blixem works in nucleotide or protein mode depending on the type of the sequences. In nucleotide mode, both strands of the reference sequence are calculated and can be displayed simultaneously in the detail section. In protein mode, the three-frame translation of the reference sequence is calculated and all three frames for the current strand can be shown (Figure 1). In both modes, the user can easily toggle the display between the forward and reverse strand orientation.
-
-Blixem can display gene models and other feature types. Gene models are shown in the overview section as well as the detail section, and CDS and UTR sections can be highlighted in different colours. The colour scheme can be specified in an optional ``.ini''-like styles file. In version 4, support for new feature types has been added. These include: short-reads, which are displayed aligned against the reference sequence; SNPs, insertions and deletions, which are highlighted in the reference sequence; annotated polyA sites and signals, which again are highlighted in the reference sequence; and polyA tails, which are shown in the detail-view.
-
-An improved user-interface makes it easy to quickly find and navigate around alignments. There are flexible methods to filter, highlight and sort sequences. Other new features allow users to display a coverage plot, to display colinearity lines between alignment blocks, to show unaligned portions of match sequences, and to highlight splice-sites for particular features in the reference sequence.
-
-Dotter can be called from within Blixem to give a graphical representation of a particular alignment which often allows annotators to see matches they would otherwise have missed.
-
-\subsection*{Dotter}
-Dotter is a graphical dot-matrix program for detailed comparison of two sequences. Dotter can be called from the command-line or from other tools such as Blixem. It takes two sequences as input, in FASTA file format. Every residue in one sequence is compared to every residue in the other and a score is calculated. The scores are plotted on a grid with one sequence on the x-axis and the other on the y-axis. Dots are drawn in grey-scale, with darker shades indicating a higher score.
-
-Dotter can operate in nucleotide-nucleotide, nucleotide-protein or protein-protein mode. In nucleotide-nucleotide mode, comparisons are made against both strands of the horizontal sequence; alignments appear as diagonal lines, with alignments on the reverse strand sloping in the opposite direction to those on the forward strand (Figure 2). In nucleotide-protein mode, the three-frame translation of the horizontal sequence is computed and alignments against all three frames are shown. In protein-protein mode Dotter just performs a direct comparison between the two sequences.
-
-To improve visualisation, scores are averaged over a sliding window. Scores below a minimum cutoff are ignored and scores above a maximum cutoff are saturated. The stringency cutoffs can be adjusted interactively using the grey-ramp tool, without having to recalculate the dot-matrix. This is a major advantage because large matrices can take a long time to compute. It is not easy to predict the correct thresholds programatically, so manual adjustment is often necessary.
-
-The dot-plot can be navigated with keyboard shortcuts or the mouse. The sequence data at a particular position can be inspected using the alignment tool, which scrolls in unison with the dot-plot.
-
-Features such as gene-models and high-scoring pairs (HSPs) can optionally be loaded from a GFF file. HSPs can be superimposed onto the dot-plot, and gene models are displayed along the axis of the relevant sequence, so they can be easily compared with the alignment. Internal repeats can be analysed by running Dotter on a sequence versus itself. To find overlaps between several sequences, they can be concatenated and then Dotter run on the concatenated sequence versus itself.
-
-Dotter offers the option to save the plot to file, which is useful for large plots that take a long time to compute. Dotter can also be run in batch mode, where the matrix is computed in the background and saved for viewing later. Recreating a plot from a saved matrix is very fast, and has the advantage that it can still be dynamically adjusted and interacted with.
-
-\subsection*{Belvu}
-Belvu is a Multiple Sequence Alignment (MSA) viewer and editor used to create high-quality reference alignments. Belvu can load and save alignments in Stockholm, MSF, Selex and Fasta file formats.
-
-Opening an alignment brings up Belvu's graphical alignment window. By default, residues are coloured by conservation (Figure 3). Conservation can be calculated by average similarity by BLOSUM62, by percent identity (either including or ignoring gaps), or by a combination of percent identity and BLOSUM62. Residues are then coloured according to user-configurable conservation thresholds.
-
-Residues can also be coloured by residue type (Figure 4). There are several built-in modes for colouring residues by type, and colours can be edited to create custom colour schemes that can be saved to and loaded from file. Colouring can be applied to all residues, or to only those residues with a percent identity above a specified threshold. Again, gaps can be included or ignored in the identity calculation.
-
-Belvu can display a conservation profile for the alignment (Figure 5), which shows the maximum conservation for each column. The plot can be smoothed by applying a sliding window of user-configurable size.
-
-Belvu has basic alignment editing capabilities, whereby sequences or columns can be removed. Sequences can be removed by manual selection, or by automatically removing those that match certain criteria such as the percentage of gaps they contain, their score, or whether they are a redundant or partial sequence. Similarly, columns can be removed by criteria such as the percentage of gaps or the maximum conservation in the column.
-
-Editing operations can be performed within the graphical viewer or on the command line. Command-line operation allows the combination of several operations in conjunction with one another. This means that complete processes can be performed in a single call, such as automatically removing sequences and converting to another file format. This makes Belvu ideal for use in software pipelines. Table 1 shows some examples of the type of operation that can be performed; many other combinations are also possible.
-
-Belvu can construct a distance-based phylogenetic tree from a multiple alignment, using either neighbour-joining or UPGMA tree construction methods (Figure 6). Distance correction can be applied using Scoredist\cite{So05}, Storm \& Sonnhammer, Kimura or Jukes-Cantor methods. Tree nodes can be swapped, and the tree can be re-rooted around a particular node. Trees can be saved in New Hampshire format. The distance matrix can also be exported, and the tree can be reconstructed from a saved distance matrix. Belvu can also perform bootstrap analysis.
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% Results and Discussion %%
-%%
-\section*{Results and Discussion}
-Blixem and Dotter are used extensively by the HAVANA group at the Wellcome Trust Sanger Institute and are essential to the manual annotation process. Examples of work published by the HAVANA group that has involved the use of Blixem and Dotter includes\cite{Ha06,Ma10,20003482,16925837,Mudge06052011,18507838}. Belvu is used in the curation of high-quality ``seed'' alignments for the Pfam database\cite{Fi10}.
-
-\subsection*{Blixem}
-Blixem is the ``workhorse'' for manual gene annotation in the HAVANA group and is in continuous use. It represents the annotator's first point of contact at nucleotide-level for all sequence alignment data, including ESTs, mRNAs and proteins. Annotators use Blixem to check the quality of an alignment (including finding missing or misaligned sequence), to identify splice sites (using this information to construct gene models and confirm alternative splicing events), to identify polyA sites and signals, to investigate the functional effects of polymorphisms (including reference sequence disabling variants in polymorphic pseudogenes), to investigate potential genome sequence errors, to identify deleterious mutations in pseudogenes, and in rarer cases to identify selenocysteine residues and RNA editing events.
-
-\subsection*{Dotter}
-Dotter is essential to the HAVANA manual annotation process and is used for two main purposes:
-
-Firstly, to identify sequence that is not represented (or is misrepresented) in the EST2genome or BLAST alignments produced by the analysis pipeline and displayed in Blixem. Identification of missing sequences using Dotter frequently allows annotation of models with alternative 5' UTR and internal exons that are short in length, repeatmasked in the reference genome sequence, or contain transcript sequence errors/polymorphism that hinders their automated alignment. As the HAVANA group only annotate gene models to the extent they are supported by aligned evidence (i.e. they do not extend models by creating a tiling path of evidence or ``borrowing'' exons from other full-length models at the same locus), Dotter is useful to support the extension of gene models supported by evidence from paralogous and orthologous loci and locus-specific ESTs of inconsistent sequence quality.
-
-Secondly, to facilitate the rapid comparison of annotated gene models with transcriptional and protein evidence that putatively support them as breaks in alignment are more clearly identifiable than in a pairwise sequence alignment e.g. Clustal.
-
-
-\subsection*{Belvu}
-Belvu is used in the manual curation of high-quality ``seed'' alignments for the Pfam database\cite{Fi10}. Annotators might start with an alignment from MUSCLE or MAFFT, for example, and use Belvu to trim the ends of the alignment to the best conservation, and remove gappy and partial sequences. They use Belvu to analyse conservation patterns, sorting alphabetically to see readily repeated domains on a sequence, or sorting by tree order to see simple evolutionary relationships. They can also sort by similarity to a specific sequence, which is useful when trying to spot false positives. Redundant sequences are removed in order to see the variation across the whole. Once of a high enough quality, the seed alignment is then used to automatically generate a ``full'' alignment, which contains all detectable protein sequences belonging to the family.
-
-
-%%%%%%%%%%%%%%%%%%%%%%
-\section*{Conclusions}
-Blixem is a unique tool that displays multiple match sequences aligned against a single reference sequence. This allows annotators to compare evidence from a variety of sources in a very detailed nucleotide-level view. Support for new data types such as short-reads means that the annotator can see all relevant information in one place, and the move to GFF version 3 makes Blixem and Dotter more widely compatible with other tools.
-
-Dotter gives a graphical view of a particular pairwise alignment. Its dynamically-adjustable contrast allows annotators to quickly tweak the display to get the best view of the results, and the alignment can easily be compared to annotated gene models and HSPs. Dotter is extremely useful for identifying alignments that cannot be found using automated methods, and for validating putative evidence.
-
-Belvu is one of several programs available for viewing and editing multiple alignments and generating phylogenetic trees. Belvu's advantages are its ability to calculate conservation on a per-residue basis, to colour residues by user-configurable thresholds, and to automate complete processes. Belvu is also the only tool to implement the Scoredist algorithm\cite{So05}.
-
-
-%%%%%%%%%%%%%%%%%%
-\section*{Availability and requirements}
-\paragraph{Project name:} SeqTools
-\paragraph{Project home page:} \url{http://www.sanger.ac.uk/resources/software/seqtools/}
-\paragraph{Operating system(s):} Linux, Mac OS X, FreeBSD, Cygwin
-\paragraph{Programming language:} C
-\paragraph{Other requirements:} GTK+ 2.12 or higher
-\paragraph{Licence:} GNU GPL version 3
-\paragraph{Any restrictions to use by non-academics:} none
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\section*{List of abbreviations}
-\paragraph{MSA:} Multiple Sequence Alignment
-\paragraph{SNP:} Single Nucleotide Polymorphism
-\paragraph{GFF:} General Feature Format
-\paragraph{HSP}: High-Scoring Pair
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\section*{Competing interests}
-The authors declare that they have no competing interests.
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\section*{Authors' contributions}
-GB carried out the requirements gathering, redesign and implementation for the new versions of the programs, packaged them into the SeqTools package and drafted the manuscript. EG maintained the original programs as part of AceDB, conceived the idea of the SeqTools package, offered guidance in the programs' redesign and helped to draft the manuscript. All authors read and approved the final manuscript.
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%
-\section*{Acknowledgements}
- \ifthenelse{\boolean{publ}}{\small}{}
-The authors would like to thank everyone who has contributed to Blixem, Dotter and Belvu, in particular their original author, Erik Sonnhammer, and the authors of AceDB, Richard Durbin, Jean Thierry-Mieg and Ed Griffiths. We would also like to thank our users in the HAVANA and Pfam groups, especially Adam Frankish and Penny Coggill, who have offered a lot of guidance in the development of these tools. Adam and Penny also contributed to the descriptions of HAVANA and Pfam's annotation processes in the Results and Discussion section of this manuscript.
-
-This work was supported by the Wellcome Trust grant [098051]; and the National Human Genome Research Institute grant [5U54HG00455-04].
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% The Bibliography %%
-%% %%
-%% Bmc_article.bst will be used to %%
-%% create a .BBL file for submission, which includes %%
-%% XML structured for BMC. %%
-%% %%
-%% %%
-%% Note that the displayed Bibliography will not %%
-%% necessarily be rendered by Latex exactly as specified %%
-%% in the online Instructions for Authors. %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-
-{\ifthenelse{\boolean{publ}}{\footnotesize}{\small}
- \bibliographystyle{bmc_article} % Style BST file
- \bibliography{seqtools} } % Bibliography file (usually '*.bib' )
-
-%%%%%%%%%%%
-
-\ifthenelse{\boolean{publ}}{\end{multicols}}{}
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% Figures %%
-%% %%
-%% NB: this is for captions and %%
-%% Titles. All graphics must be %%
-%% submitted separately and NOT %%
-%% included in the Tex document %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%%
-%% Do not use \listoffigures as most will included as separate files
-
-\section*{Figures}
-\subsection*{Figure 1 - Blixem in protein mode}
-Blixem in protein mode, showing SwissProt alignments for human chromosome 4. The three-frame translation of the reference sequence is shown in yellow. The match sequence residues are highlighted in cyan for an exact match, blue for a conserved match and grey for a mismatch. Insertions are indicated by a vertical purple bar and deletions by a dot.
-
-\subsection*{Figure 2 - Dotter in nucleotide-nucleotide mode}
-Dotter in nucleotide-nucleotide mode. Top left: the dot-plot. Top-right: the grey-ramp tool, used for dynamically adjusting the stringency cut-offs. Bottom: the alignment tool, showing the sequence data at the current cross-hair position; both strands of the horizontal sequence are displayed, and residues are coloured according to how well they match.
-
-\subsection*{Figure 3 - Belvu colour-by-conservation mode}
-Multiple sequence alignment in Belvu with residues coloured by average similarity by BLOSUM62. Cyan indicates conservation of 3.0 or greater; blue 1.5; and grey 0.5. Colours and thresholds are user-configurable.
-
-\subsection*{Figure 4 - Belvu in colour-by-residue mode}
-Multiple sequence alignment in Belvu with residues coloured by residue type. Colours are user-configureable and thresholds can be specified to only colour residues with a given percent identity or higher.
-
-\subsection*{Figure 5 - Belvu conservation profile}
-The maximum conservation for each column is plotted against the column number. The red line shows the average conservation, and a sliding-window of 5 has been applied for smoothing.
-
-\subsection*{Figure 6: Belvu phylogenetic tree}
-Neighbour-joining tree using Scoredist correction.
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% Tables %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%% Use of \listoftables is discouraged.
-%%
-\section*{Tables}
-\subsection*{Table 1 - Belvu command-line examples}
- Examples of the type of processing that can be performed in a single command-line call to Belvu. \par \mbox{}
- \par
- \mbox{
- \begin{tabular}{|l|p{0.5\textwidth}|l|}
- \hline
- {\bf Input} & {\bf Processing} & {\bf Output}\\ \hline
- Alignment & Export to a different format & Alignment \\ \hline
- Alignment & Remove sequences more than 80\% identical and columns with conservation less than 0.9 & Alignment \\ \hline
- Alignment & Construct neighbour-joining tree using Kimura distance correction & Distance matrix\\ \hline
- Distance matrix & Reconstruct tree & Tree\\ \hline
- Alignment & Apply bootstrap analysis & Bootstrap trees\\ \hline
- \end{tabular}
- }
-
-
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%% %%
-%% Additional Files %%
-%% %%
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-\section*{Additional Files}
- \subsection*{Additional file 1 --- seqtools-4.26.tar.gz}
- A tarball of the current production release of the SeqTools source code at the time of publication.
-
-\end{bmcformat}
-\end{document}
-
-
-
-
-
-
-