diff --git a/doc/TechnicalReference/TechnicalReference.tex b/doc/TechnicalReference/TechnicalReference.tex
index bbbe5a54d12a26279299b07b7e3d53247d3f0d88..23564f82c2295ee84a60a909efe5060762e428ad 100644
--- a/doc/TechnicalReference/TechnicalReference.tex
+++ b/doc/TechnicalReference/TechnicalReference.tex
@@ -644,9 +644,72 @@ transcription start, transcription stop and CDS stop, a function
\newpage
\section{Programs} \label{sec:programs}
+In this section we discuss a number of possible interconnections between the
+modules.
\subsection{Mutalyzer} \label{subsec:mutalyzer}
+\subsubsection{Semantic checks}
+The main function of \texttt{Mutalyzer} program, is \emph{semantic name
+checking}. It uses the \texttt{Parser} module for syntactic checking and the
+generation of a parse tree, and applies the given description to a reference
+sequence. This reference sequence is provided by either the \texttt{LRGparser}
+of \texttt{GBparser} module. By combining the variant description and the
+interpreted reference sequence file, semantic checking can be done.
+
+Semantic checks focus on several aspects of a variant description:
+\begin{itemize}
+\item Correctness of an intronic position notation.
+\item Disambiguation of a deletion or insertion.
+\item Minimising a description.
+\item Verifying optional arguments.
+\end{itemize}
+
+As an example of an intronic position check, we look at the position $25+4$. In
+this case, position $25$ must be a splice donor site.
+
+When a nucleotide is deleted from a stretch of nucleotides, the HGVS prescribes
+that the last one should be deleted. This disambiguation also applies for more
+complex structures; deleting \verb#GACTATTCCCTG# from a sequence
+\verb#ATGGACTATTCCCTGGCT# for example, should be corrected to the deletion of
+\verb#ACTATTCCCTGG#. Only deletions, insertions and duplications are sensitive
+to this kind of ambiguity.
+
+Every description can be written as a deletion/insertion (\emph{delins})
+operation, but using this representation is not necessarily the shortest one. A
+delins of one nucleotide, for example should be written as a substitution.
+Several checks are implemented to reduce one representation to an other. In
+Table~\ref{tab:erosion} a list of possibly ``disguised'' variants is shown.
+
+\begin{table}[H]
+\begin{center}
+\begin{tabular}{l|l}
+Variant type & Could be \\
+\hline
+delins & del, ins, dup, subst, inv \\
+ins & dup \\
+inv & subst
+\end{tabular}
+\end{center}
+\caption{Disguised variants.} \label{tab:erosion}
+\end{table}
+
+Apart from this possible disguise, a variant can be described using too much
+nucleotides, or a range that is too large. A delins can include part of the
+flanking sequence of the real change. To prevent this, the \emph{longest common
+prefix} and \emph{longest common suffix} are pruned. Likewise, an inversion
+can be too large when the \emph{reverse complement} of a prefix is a suffix.
+This is pruned in a similar way. Finally, a delins, subst or inv can have no
+effect at all.
+
+Any optional arguments must also be checked. If a length of a deletion is given
+for example, it must match the range of the deletion. If a stretch of
+nucleotides is given, this stretch must match the reference sequence.
+
+\subsubsection{Visualisation}
+
+\subsubsection{Effect prediction}
+
\subsection{VarInfo} \label{subsec:varinfo}
\subsection{UCSC\_Update} \label{subsec:ucsc_update}
diff --git a/src/Modules/Parser.py b/src/Modules/Parser.py
index be18693c2cf7b2ef2e959ca2b57037e48941aea3..4035b1ef00ca7582751b11031c4a0225dca8b858 100644
--- a/src/Modules/Parser.py
+++ b/src/Modules/Parser.py
@@ -70,7 +70,8 @@ class Nomenclatureparser() :
ProtIso = Suppress("_i") + Number("ProtIso")
GeneSymbol = Suppress('(') + Group(Name("GeneSymbol") + \
Optional(TransVar ^ ProtIso))("Gene") + Suppress(')')
- GI = Suppress(Optional("GI") ^ Optional("GI:")) + Number("RefSeqAcc")
+ GI = Suppress(Optional("GI") ^ Optional("GI:") ^ Optional("gi") ^
+ Optional("gi:")) + Number("RefSeqAcc")
Version = Suppress('.') + Number("Version")
AccNo = NotAny("LRG_") + \
Combine(Word(alphas + '_') + Number)("RefSeqAcc") + \
diff --git a/src/Modules/Web.py b/src/Modules/Web.py
index 80c20f619516e2a44b8a9eaa24914fa404a47626..5ec7476ed1df405127fd6fde14750d2591861f02 100644
--- a/src/Modules/Web.py
+++ b/src/Modules/Web.py
@@ -42,8 +42,9 @@ class Web() :
version ; Here the displayed version is defined.
"""
- self.version = "2.0α-5"
+ self.version = "2.0β-1"
self.nomenclatureVersion = "2.0"
+ self.releaseDate = "9 Aug 2010"
C = Config.Config()
self.email = C.Retriever.email
@@ -134,6 +135,7 @@ class Web() :
context.addGlobal("version", self.version)
context.addGlobal("nomenclatureVersion", self.nomenclatureVersion)
+ context.addGlobal("releaseDate", self.releaseDate)
context.addGlobal("contactEmail", self.email)
for i in args :
context.addGlobal(i, args[i])
diff --git a/src/Mutalyzer.py b/src/Mutalyzer.py
index 65f1fe9df98038d9fead8a3edac508f96fd031e7..8e09f53cc0c5b11677c185835f7634f744ba1b2b 100644
--- a/src/Mutalyzer.py
+++ b/src/Mutalyzer.py
@@ -269,6 +269,16 @@ def __cdsLen(splice_sites) :
return l
#__cdsLen
+def __checkDNA(arg) :
+ """
+ """
+
+ for i in str(arg) :
+ if not i in IUPAC.unambiguous_dna.letters :
+ return False
+ return True
+#__checkDNA
+
def __checkOptArg(ref, p1, p2, arg, O) :
"""
"""
@@ -285,6 +295,10 @@ def __checkOptArg(ref, p1, p2, arg, O) :
#if
#if
else :
+ if not __checkDNA(arg) :
+ O.addMessage(__file__, 4, "ENODNA",
+ "Invalid letters in argument.")
+ return False
ref_slice = str(ref[p1 - 1:p2])
if ref_slice != str(arg) : # FIXME more informative.
O.addMessage(__file__, 3, "EREF",
@@ -537,11 +551,15 @@ def _createBatchOutput(O):
O.addOutput("batchDone", outputline)
+#_createBatchOutput
def checkSubstitution(start_g, Arg1, Arg2, MUU, GenRecordInstance, O) :
"""
"""
+ if not __checkDNA(Arg2) :
+ #O.addMessage(__file__, 4, "ENODNA", "Invalid letter in input")
+ return
if Arg1 == Arg2 :
O.addMessage(__file__, 3, "ENOVAR",
"No mutation given (%c>%c) at position %i." % (
@@ -640,6 +658,14 @@ def checkInsertion(start_g, end_g, Arg1, MUU, GenRecordInstance, O) :
if start_g + 1 != end_g :
O.addMessage(__file__, 3, "EINSRANGE",
"%i and %i are not consecutive positions." % (start_g, end_g))
+ return
+ #if
+ if not Arg1 or not __checkDNA(Arg1) :
+ O.addMessage(__file__, 3, "EUNKVAR", "Although the syntax of this " \
+ "variant is correct, the effect can not be analysed.")
+ return
+ #if
+
MUU.insM(start_g, Arg1)
insertionLength = len(Arg1)
newStart = MUU.shiftpos(start_g)
@@ -674,6 +700,13 @@ def checkInsertion(start_g, end_g, Arg1, MUU, GenRecordInstance, O) :
(roll[0] + shift - insertionLength, 0))
#if
else :
+ if shift :
+ O.addMessage(__file__, 2, "WROLL", "Insertion of %s at position " \
+ "%i_%i was given, however, the HGVS notation prescribes " \
+ "that it should be an insertion of %s at position %i_%i." % (
+ MUU.mutated[newStart:newStop], start_g, start_g + 1,
+ MUU.mutated[newStart + shift:newStop + shift],
+ newStart + shift, newStart + shift + 1))
GenRecordInstance.name(start_g, start_g + 1, "ins",
MUU.mutated[newStart + shift:newStop + shift] , "",
(roll[0], shift))
@@ -899,6 +932,9 @@ def __rv(MUU, RawVar, GenRecordInstance, parts, O, transcript) :
def __ppp(MUU, parts, GenRecordInstance, O) :
if parts.RawVar or parts.SingleAlleleVarSet :
+ if parts.RefType == 'r' :
+ O.addMessage(__file__, 4, "ERNA", "Descriptions on RNA level " \
+ "are not supported.")
if parts.RefType in ['c', 'n'] :
GS, W = None, None
goi, toi = O.getOutput("geneSymbol")[-1]
@@ -1194,6 +1230,7 @@ def process(cmd, C, O) :
fullDescr =\
"%st%s:%c.%s" % (reference, j.name, j.molType, descr)
O.addOutput("descriptions", fullDescr)
+ #if
else:
O.addOutput("descriptions", (i.name))
@@ -1203,12 +1240,14 @@ def process(cmd, C, O) :
fullpDescr = "%sp%s:%s" % (reference, j.name, pDescr)
O.addOutput("protDescriptions", fullpDescr)
cAcc, pAcc = j.transcriptID, j.proteinID
+ #if
O.addOutput("NewDescriptions", (
iName, jName, mType, cDescr, pDescr, gAcc,
cAcc, pAcc, fullDescr, fullpDescr))
-
- #if
+ #for
+ #for
+ #if
else :
for i in GenRecordInstance.record.geneList :
for j in sorted(i.transcriptList, key = attrgetter("name")) :
@@ -1232,11 +1271,13 @@ def process(cmd, C, O) :
reference, iName, jName, pDescr)
O.addOutput("protDescriptions", fullpDescr)
cAcc, pAcc = j.transcriptID, j.proteinID
+ #if
O.addOutput("NewDescriptions", (
iName, jName, mType, cDescr, pDescr, gAcc,
cAcc, pAcc, fullDescr, fullpDescr))
#for
+ #for
#else
diff --git a/src/index.py b/src/index.py
index e67584ccd6970cb8e8897597f6bd980213b4379a..60f123adc13e78f94f2c32c7af39d0e6303fd53f 100644
--- a/src/index.py
+++ b/src/index.py
@@ -44,6 +44,7 @@ def snp(req) :
R = Retriever.Retriever(C.Retriever, O, None)
R.snpConvert(rsId)
O.addMessage(__file__, -1, "INFO", "Finished processing rs%s" % rsId)
+ #if
args = {
"snp" : O.getOutput("snp"),
@@ -63,6 +64,16 @@ def index(req) :
return W.tal("HTML", "templates/index.html", {})
#index
+def help(req) :
+ W = Web.Web()
+ return W.tal("HTML", "templates/help.html", {})
+#about
+
+def about(req) :
+ W = Web.Web()
+ return W.tal("HTML", "templates/about.html", {})
+#about
+
def nameGenerator(req):
W = Web.Web()
return W.tal("HTML", "templates/generator.html", {})
@@ -113,11 +124,15 @@ def check(req) :
else :
reference += ".gb"
+ pe = O.getOutput("parseError")
+ if pe :
+ pe[0] = pe[0].replace('<', "<")
+
args = {
"lastpost" : name,
"messages" : O.getMessages(),
"summary" : summary,
- "parseError" : O.getOutput("parseError"),
+ "parseError" : pe,
"errors" : errors,
"genomicDescription" : W.urlEncode([O.getIndexedOutput(
"genomicDescription", 0)])[0],
@@ -188,10 +203,15 @@ def syntaxCheck(req) :
#else :
# args["messages"].append("The syntax of this variant is OK!")
#if
+
+ pe = O.getOutput("parseError")
+ if pe :
+ pe[0] = pe[0].replace('<', "<")
+
args = {
"variant" : variant,
"messages" : O.getMessages(),
- "parseError" : O.getOutput("parseError"),
+ "parseError" : pe,
"debug" : ""
}
ret = W.tal("HTML", "templates/parse.html", args)
diff --git a/templates/about.html b/templates/about.html
new file mode 100644
index 0000000000000000000000000000000000000000..aad12185a7a9348950f49997bb6761ad3331d58a
--- /dev/null
+++ b/templates/about.html
@@ -0,0 +1,49 @@
+<html>
+ <head>
+ <title></title>
+ </head>
+ <body>
+ <div metal:define-macro="content">
+ <center>
+ <h3>About</h3>
+ </center>
+ Mutalyzer <span tal:content = "structure string:${version}"></span>
+ is designed and developed by Jeroen F. J. Laros, with the
+ following exceptions:
+ <ul>
+ <li>The LRG parser, as well as the Batch interfaces are written
+ by Gerben R. Stouten.</li>
+ <li>The position converter interfaces (webservice and WWW) are
+ written by Gerard C. P. Schaafsma.</li>
+ </ul>
+ Specifications are given by Peter E. M. Taschner and Johan T. den
+ Dunnen.<br>
+ <br>
+ Since the publication is under development, please use the old
+ reference for now when referring to these pages:
+ <a href="http://www.ncbi.nlm.nih.gov/entrez/utils/fref.fcgi?PrId=3058&itool=AbstractPlus-def&uid=18000842&db=pubmed&url=http://dx.doi.org/10.1002/humu.20654">
+ "Wildeman M et al. (2008). Improving sequence variant
+ descriptions in mutation databases and literature using the
+ Mutalyzer sequence variation nomenclature checker. Hum Mutat 29,
+ 6-13"</a>.<br>
+ <br>
+ Project development is sponsored by
+ <a href="http://www.gen2phen.org" target="_blank">
+ <img src="base/images/gen_2_phen_logo_print.png"
+ width="110"
+ height="50"
+ align="middle"
+ border="0"
+ alt="Eurogentest"></a>
+ and has been supported by
+ <a href="http://www.eurogentest.org" target="_blank">
+ <img src="base/images/Eurogentest.png"
+ width="110"
+ height="50"
+ align="middle"
+ border="0"
+ alt="Eurogentest"></a>
+ <br>
+ </div>
+ </body>
+</html>
diff --git a/templates/help.html b/templates/help.html
new file mode 100644
index 0000000000000000000000000000000000000000..52ebab3ef0b98aea523fa1b7d755dfcbb1cb428c
--- /dev/null
+++ b/templates/help.html
@@ -0,0 +1,953 @@
+<html>
+ <head>
+ <title>Mutalyzer - Sequence variant nomenclature check - Help</title>
+ </head>
+ <body>
+ <div metal:define-macro="content">
+ <center><h3>Mutalyzer 2 Help</h3></center>
+
+ <h3>About Mutalyzer</h3>
+ <p>
+ Mutalyzer is a tool primarily designed to check descriptions of
+ sequence variants according to the standard human sequence variant
+ nomenclature of the Human Genome Sequence Variation Society
+ (<a href="http://www.hgvs.org/">HGVS</a>) (For an overview, visit
+ <a href="http://www.hgvs.org/mutnomen/"
+ >http://www.hgvs.org/mutnomen/</a>).
+ Mutalyzer aims to encourage the proper use of nomenclature in
+ publications and reduce redundancy in sequence variation databases. In
+ principle, Mutalyzer can check descriptions of sequence variants
+ detected in other organisms, provided that the standard HGVS
+ nomenclature is applied.
+ </p>
+
+ <h3>Mutalyzer 2 flow</h3>
+ <p>
+ The user specifies a reference sequence (file) and a variant using the
+ <a href="#NameGenerator">Name Generator</a> or the
+ <a href="#NameChecker">Name checker</a> interface. The Name Generator
+ builds the complete variant description for the Name Checker (e.g.,
+ Mutalyzer uses this input to perform the nomenclature check in the
+ following steps:
+ </p>
+ <p>
+ 1) Retriever: retrieves
+ <a href="#Ref">reference sequence records</a> from the
+ <a href="http://www.ncbi.nlm.nih.gov/">NCBI</a> or
+ <a href="http://www.lrg-sequence.org/">LRG</a> websites.
+ </p>
+ <p>
+ 2) Reference sequence parser: extracts sequence and annotation from
+ reference sequence records
+ </p>
+ <p>
+ 3) <a href="#SyntaxChecker">Syntax checker</a>: context-free parser
+ using the complete sequence variant description to check whether the
+ syntax is correct according to standard HGVS sequence variant
+ nomenclature
+ </p>
+ <p>
+ 4) <a href="#NameChecker">Name checker</a>: the core nomenclature
+ checker using the complete sequence variant description to check
+ whether it is correct according to standard HGVS sequence variant
+ nomenclature
+ </p>
+ <p> </p>
+ <p>
+ <b>Additional Mutalyzer 2 functionality:</b>
+ </p>
+ <p>
+ - <a href="#PositionConverter">Position Converter</a>: converts hg18
+ and hg19 chromosomal positions to transcript positions in HGVS n. or
+ c. notation and vice versa. The n. or c. notation should be checked
+ with the Name checker
+ </p>
+ <p>
+ - <a href="#GenBankUploader">GenBank Uploader</a>: allows you to
+ upload and use your own reference sequence.
+ </p>
+ <p>
+ - <a href="#SNPConverter">SNP converter</a>: allows you to convert a
+ <a href="http://www.ncbi.nlm.nih.gov/projects/SNP/">dbSNP</a> rsId to
+ HGVS notation.
+ </p>
+ <p>
+ - <a href="#BatchChecker">Batch Checkers</a>: interfaces for the
+ different checkers that accept a large list of descriptions as input.
+ </p>
+ <p>
+ - <a href="#Webservices">Webservices</a>: programmatic access to
+ Mutalyzer's functionality.
+ </p>
+ <p> </p>
+
+ <h2>Introduction</h2>
+
+ <h3>Reference sequences<a name="Ref"></a></h3>
+ <p>
+ <b>
+ We strongly recommend the use of genomic reference sequences
+ containing proper annotation for optimal use of Mutalyzer's
+ capabilities to generate descriptions for all transcripts and protein
+ isoforms of the gene(s) affected by the sequence variation.
+ </b>
+ </p>
+ <p>
+ Mutalyzer accepts the following reference sequences:
+ </p>
+ <p>
+ 1) GenBank files
+ </p>
+ <p>
+ GenBank records (e.g., NG_007400.1) are specified by a
+ <i>GenBank accession number</i> (NG_007400) and a version number (.1).
+ Omission of the version number automatically results in selection of
+ the most recent version of that record. In case of outdated versions,
+ Mutalyzer will issue a warning. Alternatively, the unique
+ <i>GenInfo identifier</i> (gi) of the reference sequence (e.g.,
+ 4506864) can be used with or without the letters “gi”.
+ Mutalyzer does not accept GenBank records containing no sequence (e.g.
+ chromosomal reference sequence identifiers referring to contig
+ accession numbers) or files larger than 10 MB. Mutalyzer also accepts
+ user-defined files in GenBank format, including slices of chromosomal
+ reference sequences. These files are specified by unique
+ <i><a href="#UD">UD identifiers</a></i>, which are returned by Mutalyzer
+ after upload (See the <a href="#GenBankUploader">GenBank Uploader</a>
+ section for more information).<br>
+ </p>
+ <p>
+ 2) LRG files
+ </p>
+ <p>
+ Locus Reference Genomic (LRG) files containing uniquely and stable
+ reference DNA sequences along with all relevant transcript and protein
+ sequences essential to the description of gene variants (see the
+ <a href="http://www.lrg-sequence.org/"> LRG website</a> for more
+ information). LRG files are based on
+ <a href="http://www.ncbi.nlm.nih.gov/">NCBI</a>'s
+ <a href="http://www.ncbi.nlm.nih.gov/RefSeq/RSG/">RefSeqGene project</a>
+ and created in collaboration with the community of research and
+ diagnostic labs, LSDB curators and mutation consortia. LRG files are
+ specified by the prefix "LRG_" followed by a number (e.g.,
+ LRG_1). The <a href="http://www.lrg-sequence.org/"> LRG website</a>
+ lists existing LRG sequences and has an
+ <a href="ftp://ftp.ebi.ac.uk/pub/databases/lrgex/">FTP site</a> for
+ downloading LRGs. To maintain LRG stability, Mutalyzer's uploader does
+ not accept user-defined LRG files.
+ </p>
+
+ <h3>Variant descriptions</h3>
+ <p>
+ The Mutalyzer nomenclature checker accepts variant descriptions in
+ standard human sequence variant nomenclature format. For users, who are
+ not familiar with the nomenclature syntax, Mutalyzer's
+ <a href="#NameGenerator">Name Generator</a> provides a form to acquire
+ the separate components necessary to construct variant descriptions.
+ </p>
+ <p>
+ These components, which are discussed in more detail below are:\
+ </p>
+ <p>
+ 1) <a href="#Position">Position numbering scheme (Sequence Type)</a>
+ </p>
+ <p>
+ 2) <a href="#GeneSymbol"
+ >Gene symbol, transcript variant and protein isoform</a>
+ </p>
+ <p>
+ 3) <a href="#Start">Variant start and end positions</a>
+ </p>
+ <p>
+ 4) <a href="#Mutation">Mutation type</a>
+ </p>
+ <p>
+ 5) <a href="#Deleted">Deleted and Inserted sequence</a>
+ </p>
+ <p>
+ <b><a name="Position"></a>Position numbering scheme (Sequence Type)</b>
+ </p>
+ <p>
+ The standard human sequence variant nomenclature uses different
+ position numbering schemes to describe variants relative to the
+ reference sequence. Mutalyzer checks if the specified reference
+ sequence is compatible with the selected position numbering scheme for
+ the sequence variation. Variant descriptions involving upstream or
+ downstream regulatory sequences and intron sequences can only be
+ checked using genomic sequence records. Therefore, genomic records with
+ correct annotation of all genes, transcripts and protein isoforms
+ support most position numbering schemes. Mutalyzer automatically
+ converts the given variant description to other position numbering
+ schemes supported by the reference sequence and its annotation.
+ Mutalyzer will not return results when the selected reference sequence
+ does not contain sufficient sequence or annotation to support the
+ nomenclature check of the variant.
+ </p>
+ <p>
+ There are six position numbering schemes (Sequence Types):
+ </p>
+ <p>
+ <i>Genomic</i>
+ </p>
+ <p>
+ The <i>Genomic</i> position numbering scheme is applied to raw genomic
+ records. The value 1 is assigned to the first base in the record and
+ all bases are counted from there. In the output, genomic numbering is
+ indicated by the g. prefix preceding the position number(s). LRG
+ records and all <i>GenBank</i> records with 'DNA' in the first line
+ will be accepted.
+ </p>
+ <p>
+ Please note that well-annotated genomic sequence records containing
+ annotated transcripts and corresponding coding sequences can be used in
+ combination with non-coding DNA, coding DNA and protein position
+ numbering schemes.
+ </p>
+ <p>
+ <i>Non-coding DNA (ncDNA)</i>
+ </p>
+ <p>
+ The <i>Non-coding DNA</i> or <i>ncDNA</i> position numbering scheme can
+ be used with:<br>
+ a) <i> GenBank</i> records containing genomic sequences with annotated
+ transcripts without a corresponding coding sequence.<br>
+ b) LRG records<br>
+ c) <i> Genbank </i>records containing transcript sequences without
+ annotated coding sequences, provided that no intronic bases are
+ involved in the variation. Mutalyzer needs a correctly annotated
+ genomic reference sequence to check HGVS Non-coding DNA numbering of
+ intron positions.
+ </p>
+ <p>
+ The value 1 is assigned to to the first base of the transcript in the
+ record and all the exonic bases are counted from there. Intronic bases
+ are numbered x+1, x+2, x+3 … y-3, y-2, y-1 where x is the value
+ of the last exonic base upstream of the intron, y is the value of the
+ first exonic base downstream of the intron and x and y are consecutive
+ numbers. Intronic position numbers are always counted from the closest
+ exonic base. In case of a tie, the upstream base is used. In the
+ output, ncDNA numbering is indicated by the n. prefix preceding the
+ position number(s).
+ </p>
+ <p>
+ <i>Coding DNA (cDNA)</i>
+ </p>
+ <p>
+ The <i>Coding DNA</i> or <i>cDNA</i> position numbering scheme can be
+ used with:<br>
+ a) <i> Genbank</i> records containing genomic sequences with annotated
+ transcripts and corresponding coding sequences. <br>
+ b) LRG records<br>
+ c) <i>Genbank </i>records containing transcript sequences with
+ annotated coding sequences, provided that no intronic bases are
+ involved in the variation. Mutalyzer needs a correctly annotated
+ genomic reference sequence to check HGVS Coding DNA numbering of intron
+ positions.
+ </p>
+ <p>
+ The value 1 is assigned to the A of the ATG start codon and all the
+ exonic bases between start and stop are counted normally.<br>
+ 5' untranslated region: Exonic bases upstream of (i.e. before) the ATG
+ are numbered -1, -2, -3 and so on.<br>
+ 3' untranslated region: Exonic bases downstream of (i.e. behind) the
+ stop codon are numbered *1, *2, *3 and so on.<br>
+ Intronic bases in the Coding sequence are numbered x+1, x+2, x+3
+ … y-3, y-2, y-1 where x is the value of the last exonic base
+ upstream of the intron, y is the value of the first exonic base
+ downstream of the intron and x and y are consecutive numbers. Intronic
+ position numbers are always counted from the closest exonic base. In
+ case of a tie, the upstream base is used.<br>
+ In case of: a 5' untranslated region split over two or more exons:
+ Intronic bases are numbered -x+1, -x+2, -x+3 … -y-3, -y-2, -y-1
+ where -x is the value of the last exonic base upstream of the intron,
+ -y is the value of the first exonic base downstream of the intron and x
+ and y are consecutive numbers.<br>
+ In case of: a 3' untranslated region split over two or more exons:
+ Intronic bases are numbered *x+1, *x+2, *x+3 … *y-3, *y-2, *y-1
+ where *x is the value of the last exonic base upstream of the intron,
+ *y is the value of the first exonic base downstream of the intron and y
+ are consecutive numbers.
+ <br>
+ In the output, cDNA numbering is indicated by the c. prefix preceding
+ the position number(s).
+ </p>
+ <p>
+ <i>RNA</i>
+ </p>
+ <p>
+ The <i>RNA</i> position numbering scheme has not yet been implemented
+ in Mutalyzer 2. The value 1 is assigned to the first base in the record
+ and from there all bases are counted normally. In the output, RNA
+ numbering is indicated by the r. notation preceding the position
+ number(s).
+ </p>
+ <p>
+ <i>Mitochondrial DNA (mtDNA)</i>
+ </p>
+ <p>
+ The <i>Mitochondrial DNA (mtDNA)</i> position numbering scheme uses raw
+ genomic records. The value 1 is assigned to the first base in the
+ record and from there all bases are counted normally.
+ </p>
+ <p>
+ <i>Protein</i>
+ </p>
+ <p>
+ The <i>Protein</i> position numbering scheme is used to generate
+ variant descriptions at protein level from genomic or Coding DNA
+ descriptions by translation of the Coding sequence. The current version
+ of Mutalyzer 2 does not yet support checks of protein variants using a
+ <i>GenBank</i> protein record. The value 1 is assigned to the first
+ amino acid of the translated Coding sequence and from there all amino
+ acids are counted normally. In the output, protein variants have the
+ prefix p. folllowed by the amino acid changes between parentheses to
+ indicate that they are predicted by translation of the modified Coding
+ sequence.
+ </p>
+ <p>
+ <i>EST</i>
+ </p>
+ <p>
+ The <i>EST</i> position numbering scheme can be used with
+ <i>GenBank</i> <i>EST</i> records. The value 1 is assigned to the first
+ base in the record and from there all bases are counted normally.
+ Sequence variation descriptions based on EST sequences lack the c.
+ prefix to indicate that only part of the coding sequence may be
+ present. All records with 'EST' in the first line will be accepted.
+ These records do not allow checks of intronic sequence variations.
+ </p>
+ <p>
+ <b><a name="GeneSymbol"></a>Gene Symbol and Variant</b>
+ </p>
+ <p>
+ In genomic records containing annotation of multiple genes, alternative
+ transcript variants and protein isoforms, only genomic positions are
+ unambiguous. Descriptions at <i>Non-coding DNA, coding DNA, </i>or
+ protein level may be ambiguous. Mutalyzer parses the annotation of the
+ reference sequence record and displays the detected genes, transcript
+ variants or protein isoforms in the legend at the bottom of the output
+ page. Mutalyzer uses the annotation to detect potential ambiguity in a
+ variant description. Further specification of genes, transcript
+ variants or protein isoforms may be required to solve it. Only Gene
+ Symbols matching the reference sequence annotation are allowed.
+ Usually, gene symbols have to be combined with the desired transcript
+ variant or protein isoform
+ </p>
+ <p>
+ Variant descriptions are accepted in two formats:
+ </p>
+ <p>
+ - A positive integer referring to the order of the transcripts in the
+ annotation, e.g. <b>1</b>, <b>2</b>, <b>3</b>, ...<br>
+ - The exact identifier following the underscore behind the Gene symbol
+ in the legend, e.g. v002 for a transcript variant or i002 for a
+ protein isoform
+ </p>
+ <p>
+ <b><a name="Start"></a>Start and End Position</b>
+ </p>
+ <p>
+ The Start position is the positional value of the most upstream base or
+ amino acid in the reference sequence affected by the mutation. The End
+ position is the positional value of the most downstream base or amino
+ acid in the reference sequence affected by the mutation. Mutalyzer only
+ accepts positions contained within the reference sequence. The values
+ should be a positive integer (whole number) for all position numbering
+ schemes, except <i>Non-coding DNA </i> and<i> Coding DNA </i> . For
+ <i>Non-coding </i> and<i> Coding DNA,</i> these positions may also
+ contain + and - signs to indicate intron positions. For
+ <i> Coding DNA,</i> positions can also have prefixes - and * to
+ indicate exonic positions in 5' or 3' untranslated regions.
+ Furthermore, in descriptions of deletions, exonic positions can be
+ followed by +? or -? to indicate unknown intronic positions.<br>
+ The Mutalyzer nomenclature checker has a strict implementation of Start
+ and End positions in <i>Non-coding DNA </i> and<i> Coding DNA</i>
+ position numbering schemes. To prevent discrepancies between
+ <i>Non-coding DNA </i> and<i> Coding DNA</i> descriptions based on
+ genomic RefSeqGene (NG_) records and the corresponding RefSeq
+ transcript (NR_ or NM_) records, exon positions may not exceed those of
+ the transcript annotated in the genomic reference sequence record.
+ Therefore, Mutalyzer cannot use - or * prefixes to indicate positions
+ in upstream or downstream intergenic regions.
+ </p>
+ <p>
+ For upstream intergenic positions, Mutalyzer combines the position of
+ the first nucleotide of the transcript with the suffix -u followed by
+ the position of the upstream nucleotide. Intergenic bases upstream of
+ <i>Non-coding DNA </i>are numbered n.1-uy, ..., n.1-u3, n.1-u2, n.1-u1
+ where y is the value of the most upstream base and n.1-u1 is the value
+ of the first intergenic base upstream of the first exon. Intergenic
+ bases upstream of <i>Coding DNA </i>are numbered c.x-uy, ..., c.x-u3,
+ c.x-u2, c.x-u1 where x is the value of the first nucleotide of the
+ first exon and y is the value of the most upstream base. The advantage
+ of this notation is that the -u position corresponds to the - position
+ used by to describe transcription factor binding sites.
+ </p>
+ <p>
+ For downstream intergenic positions, Mutalyzer combines the position of
+ the last nucleotide of the transcript with the suffix +d followed by
+ the position of the downstream nucleotide. Intergenic bases downstream
+ of <i>Non-coding DNA </i>are numbered n.x+d1, n.x+d2, n.x+d3 ... where
+ x is the value of the last nucleotide of the last exon. Intergenic
+ bases downstream of <i>Coding DNA </i>are numbered c.x+d1, c.x+d2,
+ c.x+d3, ... where x is the value of the last nucleotide of the last
+ exon.
+ </p>
+ <p>
+ <b><a name="Mutation"></a>Mutation Type</b>
+ </p>
+ <p>
+ The syntax of the standard human sequence variant nomenclature depends
+ on the type of mutation. Six mutation types are supported:
+ </p>
+ <p>
+ <i>Substitution</i>
+ </p>
+ <p>
+ A substitution is the replacement of a single nucleotide or amino acid
+ by another. A substitution involving multiple residues is classified as
+ an indel. The start and end position should be identical. The original
+ residue and the new residue have to be specified and must be
+ non-identical. In the Name Generator, the Deleted Sequence and Inserted
+ Sequence fields must be filled in.
+ </p>
+ <p>
+ <i>Deletion</i>
+ </p>
+ <p>
+ A deletion is the removal of one or more nucleotides or amino acids
+ without replacement. In the Name Generator, the Inserted Sequence field
+ must remain empty. The Deleted Sequence field can be filled in to check
+ the start and end positions and to match the deleted residues with the
+ reference sequence (Optional). Please note that the start and end
+ positions should be equal when only one nucleotide or amino acid is
+ deleted.
+ </p>
+ <p>
+ <i>Insertion</i>
+ </p>
+ <p>
+ An insertion is the addition of one or more nucleotides or amino acids
+ without removing any previously existing ones. The starting and end
+ positions should differ by exactly one. In the Name Generator, Inserted
+ Sequence must be filled in with the actual new sequence. If the
+ inserted sequence is already present in the reference sequence at the
+ location of the insertion, it should be represented as a
+ duplication.
+ </p>
+ <p>
+ <i>Duplication</i>
+ </p>
+ <p>
+ Duplication is the addition of one or more nucleotides or amino acids
+ identical to the sequence from the specified start position to the
+ specified end position, at the end position. In the Name
+ Generator, Deleted Sequence must remain empty. Inserted Sequence
+ can be filled in to check the start and end positions and to match the
+ duplicated residues with the reference sequence (Optional).
+ </p>
+ <p>
+ <i>Insertion/Deletion (indel)</i>
+ </p>
+ <p>
+ An indel is the removal of one or more bases or amino acids, combined
+ with the addition of one or more bases or amino acids. In case a single
+ residue is deleted and another residue is inserted, the mutation should
+ be described as a substitution, not an indel. If the inserted sequence
+ is the reverse complement of the original sequence, it should be
+ described as an inversion. Start and end position define the boundaries
+ of the deletion in the original sequence. In the Name Generator, the
+ deleted sequence should be entered in the Deleted Sequence field and
+ the Inserted sequence in the New Sequence field.
+ </p>
+ <p>
+ <i>Inversion (nucleotide sequences only)</i>
+ </p>
+ <p>
+ An inversion is a sequence of two or more bases inserted as its reverse
+ complement. Start and end position must be non-identical. In the Name
+ Generator, the Deleted Sequence and Inserted Sequence fields must
+ remain empty.
+ </p>
+ <p>
+ <b><a name="Deleted"></a>Deleted and Inserted Sequence</b>
+ </p>
+ <p>
+ The syntax of the standard human sequence variant nomenclature requires
+ specification of the inserted residue(s) for several mutation types.
+ Specification of the original residue(s) is optional for most types,
+ except for subsitutions. In the Name Generator, the presence or absence
+ of these fields depends on the selected Mutation Type. These fields
+ should be used:<br>
+ -to enter the original amino acid or nucleotide residue(s) present in
+ the reference sequence (Deleted Sequence).<br>
+ -to enter the amino acid(s) or nucleotide residue(s) introduced by the
+ change (Inserted Sequence).
+ </p>
+
+ <hr>
+
+ <h3>Mutalyzer Name Checker Help<a name="NameChecker"></a></h3>
+ <p>
+ Users can check the correctness of a variant description. The Name
+ Checker will try to regenerate the variant sequence and name it
+ according to the HGVS standard human sequence variant nomenclature.
+ </p>
+ <p>
+ Examples: <br>
+ AB026906.1:c.3_4insG<br>
+ AB026906.1:c.[1del;4G>T]<br>
+ AL449423.14(CDKN2A_v1):c.1_10del<br>
+ UD_127955523176(DMD_v002):c.136G>T<br>
+ LRG_1t1:c.266G>T
+ </p>
+
+ <hr>
+
+ <h3>Mutalyzer Syntax Checker Help<a name="SyntaxChecker"></a></h3>
+ <p>
+ Users can check the correctness of the standard nomenclature syntax.
+ The Syntax Checker uses a context-free parser to detect deviations from
+ the standard nomenclature syntax in the input. The position of
+ the deviation is indicated in the error message and by a caret (^)
+ below the description.
+ </p>
+ <p>
+ Examples: <br>
+ AB026906:c.3_4inG<br>
+ AB026906.1:c.35_36ins<br>
+ LRG_1t1:c.266G<T
+ </p>
+
+ <hr>
+
+ <h3>
+ Mutalyzer Position Converter Help<a name="PositionConverter"></a>
+ </h3>
+ <p>
+ The Position Converter will convert the positions of the variation
+ description from the chromosomal position for a specific human genome
+ build to a position relative to RefSeq transcript reference sequences.
+ The Position Converter uses a local database containing the mapping
+ information from the
+ <a href="http://genome.ucsc.edu/index.html?org=Human"
+ >UCSC genome browser</a> for human genome builds hg18 (NCBI 36) and
+ hg19 (GRCh37). The specified version of the RefSeq transcript Accession
+ number has to be present in the database. The sequence variation
+ description has <u>not</u> been checked by Mutalyzer's
+ <a href="#NameChecker">Name Checker</a>.
+ </p>
+ <p>
+ Examples:<br>
+ NM_003002.2:c.274G>T<br>
+ chr11:g.111959693G>T<br>
+ NC_000011.9:g.111959693G>T
+ </p>
+
+ <hr>
+
+ <h3>Mutalyzer SNP Converter Help<a name="SNPConverter"></a></h3>
+ <p>
+ The SNP Converter will submit a <a
+ href="http://www.ncbi.nlm.nih.gov/projects/SNP/">dbSNP</a> rsID to
+ dbSNP to retrieve the sequence variation description according to the
+ HGVS sequence variation description listed in dbSNP.<br>
+ The sequence variation description has <u>not</u> been checked by
+ Mutalyzer's <a href="#NameChecker">Name Checker</a>.
+ </p>
+ <p>
+ Example:<br>
+ SNP Accession number: rs9919552
+ </p>
+
+ <hr>
+
+ <h3>Mutalyzer Name Generator Help<a name="NameGenerator"></a></h3>
+ <p>
+ The Name Generator aims to assist users, who are not familiar with all
+ the details of the HGVS standard human sequence variant nomenclature,
+ to construct variant descriptions. The Name Generator presents a form
+ to collect the separate components of a variant description described
+ above. The variant description generated is subsequently used by the
+ Name Checker to construct the variant sequence and name it according to
+ the HGVS standard human sequence variant nomenclature.
+ </p>
+ <p>
+ Example: <br>
+ Reference: AL449423.14<br>
+ Sequence Type: Coding DNA<br>
+ Gene symbol: CDKN2A<br>
+ Transcript: v_1
+ </p>
+ <p>
+ Variant 1<br>
+ Mutation Type: Substitution<br>
+ Start Position: 112<br> End Position: 112<br>
+ Deleted Sequence: C<br>
+ Inserted Sequence: T
+ </p>
+
+ <hr>
+
+ <h3>Mutalyzer Batch Checker Help<a name="BatchChecker"></a></h3>
+ <p>
+ <br>
+ The Batch checkers support submission of files containing large
+ datasets to the <a href="#NameChecker">Name Checker</a>,
+ <a href="#SyntaxChecker">Syntax Checker</a>, and
+ <a href="#PositionConverter">Position Converter</a> tools.
+ </p>
+ <p>The Mutalyzer batch checker accepts the following file formats
+ <ul>
+ <li>Tab Delimited Text File</li>
+ <li>Microsoft Excel XML File</li>
+ <li>OpenOffice .odt File</li>
+ </ul>
+ </p>
+
+ <h5>
+ We accept two types of input files, you can download examples below
+ </h5>
+
+ <h5>
+ New Style <a href="downloads/batchtestnew.txt">Download Example File</a>
+ </h5>
+ <div style="padding-left:20px; width:400px">
+ <p>
+ This file format has no header-row and no columns. Instead each row
+ contains a single variant for the Batch check.
+ </p>
+ <table>
+ <tr>
+ <td>AB026906.1:c.274G>T</td>
+ </tr>
+ <tr>
+ <td>AL449423.14(CDKN2A_v002):c.5_400del<td>
+ </tr>
+ </table>
+ </div>
+
+ <h5>
+ Old Style:
+ <a href="downloads/batchtestold.txt">Download Example File</a>
+ </h5>
+ <div style="padding-left:20px; width:400px">
+ <p>
+ This file format has a header-row, which consists of three tab
+ delimited fields. In each following row, the corresponding data is
+ also tab delimited.The gene symbol field may be left empty, when it
+ is not nessary to select a particular gene or transcript.
+ </p>
+ <table>
+ <tr>
+ <td>AccNo</td><td>Genesymbol</td><td>Mutation</td>
+ </tr>
+ <tr>
+ <td>AB026906.1</td><td>SDHD</td><td>g.7872G>T</td>
+ </tr>
+ </table>
+ </div>
+
+ <h5>Output Format</h5>
+ <div style="padding-left:20px; width:400px">
+ <p>
+ The output of a Mutalyzer Batch run is a Tab Delimited Text file,
+ which has a header-row to clarify the results.
+ </p>
+ </div>
+ <p>
+ Users can upload a tab-delimited text file with the sequence
+ variations to be checked. Files for the Name Checker and the Syntax
+ Checker may contain any combination of reference sequences and sequence
+ types for different genes. Mutalyzer's
+ <i><a href="#UD">UD identifiers</a></i> can also be used, but we
+ strongly suggest to update any GenBank record following
+ <a href="http://www.ncbi.nlm.nih.gov/Genbank/update.html"
+ >these instructions</a>.<br>
+ </p>
+ <p>
+ A message containing a link to the results will be send to the e-mail
+ address specified, when the analysis is finished, but Mutalyzer's
+ progress can be followed in the browser window also. Performance
+ depends on the server load and the number of reference sequence records
+ to be downloaded. The program will process approximately 100 variations
+ per minute, when using a single reference sequence record.
+ </p>
+ <p>
+ The Batch checkers use JavaScript to update the progress report. In
+ Internet Explorer, progress may not be reported correctly. Adding
+ Mutalyzer to your trusted sites is one option to solve this.
+ </p>
+
+ <hr>
+
+ <h2>Mutalyzer Output</h2>
+ <p>
+ Mutalyzer has been designed to issue warnings, when correcting entries,
+ encountering inconsistencies, incomplete sequences or annotation, or
+ identifying variations with potential effects on splicing before
+ presenting the results of the analysis. Errors will be generated when
+ the entries can not be processed properly (see below for more
+ information). <br>
+ The sequence variation description will always be in the format:
+ </p>
+ <p>
+ <<i>Accession Number</i>>.<<i>version number></i>:<i><sequence type</i>>.<<i >mutation</i>><br>
+
+ (Examples: NM_003002.1:c.5delC or AL449423.14:g.61866_85191del)<br>
+ or<br>
+ <<i>Accession Number</i>>.<<i>version number><(Gene Symbol)></i>:<i ><sequence type</i>>.<<i >mutation</i>><br>
+ In the latter case, the gene symbol may be followed by transcript
+ variant or protein isoform numbers (e.g., _v001 or _i001,
+ respectively).<br>
+ Example: the fictitious sequence variation AL449423.14:g.61866_85191del
+ corresponds with the following changes in transcript variants and
+ protein isoforms:<br>
+ AL449423.14(CDKN2A_v001):c.-271_234del<br>
+ AL449423.14(CDKN2A_v002):c.5_400del<br>
+ AL449423.14(CDKN2A_v003):c.1_*3352del<br>
+ and<br>
+ CAH70600.1(CDKN2A_i001):p.Met1?<br>
+ CAH70601.1(CDKN2A_i002):p.Gly2AspfsX41<br>
+ CAH70599.1(CDKN2A_i003):p.Met1?
+ </p>
+ <p>
+ From the example “CAD55702.1:p.Pro2Arg (missense
+ mutation)”, you can conclude that the protein in version 1 of the
+ record CAD55702 has a mutation denoted as Pro2Arg (which signifies an
+ arginine substituted for a proline at position 2).
+ </p>
+ <p>
+ Please note the following:
+ </p>
+ <p>
+ - Sequence variation descriptions using genomic references in
+ combination with Sequence Type "Coding DNA" will result in
+ the use of nucleotides in reverse complement for genes transcribed in
+ the opposite orientation.
+ </p>
+ <p>
+ - Genbank Identifiers are always converted to Genbank Accession
+ Numbers, which are automatically retrieved from the annotation based
+ on the selected Sequence Type. Example: 4506864:c.5del will be
+ converted into NM_003002.1:c.5delC
+ </p>
+
+ <hr>
+
+ <h3>GenBank Uploader Help<a name="GenBankUploader"></a></h3>
+ <p>
+ Users can upload their own reference sequence file in
+ <a href="http://www.ncbi.nlm.nih.gov/Sitemap/samplerecord.html"
+ >GenBank Flat file format</a>, retrieve the genomic sequence of a
+ gene with its flanking regions, or specify a chromosomal range for use
+ as a reference sequence. Mutalyzer checks whether the file is in valid
+ GenBank Flat file format. If so, Mutalyzer stores the file locally and
+ returns a unique number the <i><a href="#UD">UD identifier</a></i> that
+ can be used with all different forms of the Mutalyzer Sequence
+ Variation Nomenclature Checker. This option allows users to use
+ reference files, which are not present in GenBank, or add information
+ about alternative transcripts or proteins or additional genes contained
+ within or derived from the reference sequence to an existing GenBank
+ file. Users are encouraged to limit their use of this option by
+ submitting annotation updates and corrections of existing GenBank files
+ following <a href="http://www.ncbi.nlm.nih.gov/Genbank/update.html"
+ >these instructions</a>.
+ </p>
+ <p>
+ Uploader options:
+ </p>
+ <p>
+ <b>The reference sequence file is a local file</b>
+ </p>
+ <p>
+ Browse to locate your Genbank Flat file with a .gb extension and press
+ the submit button.
+ </p>
+ <p> </p>
+ <p>
+ <b>The reference sequence file can be found at the following URL</b>
+ </p>
+ <p>
+ Enter the URL of the website, where the Genbank Flat file with a .gb
+ extension can be found and press the submit button.
+ </p>
+ <p> </p>
+ <p>
+ <b>
+ Retrieve part of the reference genome for a
+ (<a href="http://www.genenames.org">HGNC</a>) gene symbol
+ </b>
+ </p>
+ <p>
+ This option retrieves part of the chromosomal reference sequence, which
+ is annotated for this gene in the last genome build of the
+ organism.
+ </p>
+ <p>
+ The organism name should not contain any spaces (e.g., use
+ homo_sapiens, human or man)
+ </p>
+ <p>
+ Input:
+ </p>
+ <div style="padding-left:20px; width:400px">
+ <i>Please enter the Gene symbol and organism name without spaces and
+ specify the length of the flanking sequences</i>
+ <table>
+ <tr>
+ <td>Gene symbol</td>
+ <td><input type="text" name="genesymbol"></td>
+ </tr>
+ <tr>
+ <td>Organism name</td>
+ <td><input type="text" name="organism"></td>
+ </tr>
+ <tr>
+ <td>Number of 5' flanking nucleotides</td>
+ <td><input type="text" name="5utr" value="5000"></td>
+ </tr>
+ <tr>
+ <td>Number of 3' flanking nucleotides</td>
+ <td><input type="text" name="3utr" value="2000"></td>
+ </tr>
+ </table>
+ </div>
+ <p>
+ <b>Retrieve a range of a chromosome</b>
+ </p>
+ <p>
+ Use of NC_accession numbers without version number will result in
+ retrieval of the latest version.
+ </p>
+ <p>
+ Input:
+ </p>
+ <div style="padding-left:20px; width:400px">
+ <i>Please enter the accession number of the chromosome or contig and
+ specify the range</i><br>
+ <table>
+ <tr>
+ <td>Chromosome Accession Number</td>
+ <td><input type="text" name="chracc"></td>
+ </tr>
+ <tr>
+ <td>Start Position</td>
+ <td><input type="text" name="start"></td>
+ </tr>
+ <tr>
+ <td>Stop Position</td>
+ <td><input type="text" name="stop"></td>
+ </tr>
+ <tr>
+ <td>Orientation</td>
+ <td>
+ <select name="orientation">
+ <option value="1">Forward</option>
+ <option value="-1">Reverse</option>
+ </select>
+ </td>
+ </tr>
+ </table>
+ </div>
+ <p>
+ <b>Mutalyzer output for all options:</b>
+ </p>
+ <p>
+ Output:<a name="UD"></a>
+ </p>
+ <div style="padding-left:20px; width:400px">
+ <p>
+ Your reference sequence was uploaded successfully. You now can use
+ mutalyzer with the following accession number as reference:
+ UD_127955523176 <br>
+ Download this reference sequence.
+ </p>
+ </div>
+ <p>
+ The GenBank uploader uses JavaScript to change the form depending on
+ the selected option. In Internet Explorer, forms may not be displayed
+ correctly. Adding Mutalyzer to your trusted sites is one option to
+ solve this.
+ </p>
+
+ <hr>
+
+ <h3>Mutalyzer Webservices <a name="Webservices"></a></h3>
+ <p>
+ Mutalyzer's webservices provide programmatic access to different parts
+ of Mutalyzer's functionality. In the future, these will be used by
+ <a href="http://www.LOVD.nl">LOVD</a> to convert coding DNA positions
+ to chromosomal positions for mapping and display purposes. A full
+ description of available webservices can be found at the
+ <a href="documentation">Webservice documentation page</a>.
+ Example scripts and requirements can be found at the
+ <a href="webservices">Webservice page</a>.
+ </p>
+
+ <hr>
+
+ <h3>Using Mutalyzer with sequences from other organisms</h3>
+ <p>
+ Mutalyzer can process Genbank reference files from other organisms than
+ man and will apply the appropriate coding table to translate an open
+ reading frame into a protein sequence. Please note that all variants
+ will be described according to the HGVS
+ <a href="http://www.hgvs.org/mutnomen/"
+ >standard human sequence variation nomenclature</a>. When trying to
+ retrieve genomic reference sequences using gene symbols with the
+ Genbank uploader or when specifying a particular gene in a genomic
+ reference sequence, the gene symbol should be similar to that used in
+ the (genome) sequence annotation.
+ </p>
+
+ <h3>Errors and feature requests</h3>
+ <p>
+ Any error message gives an indication of the problem encountered and
+ replicates the input of the user. Most errors occurring after mistyping
+ should be easy to understand and can be corrected immediately by
+ altering the data in the field specified. In other cases, Mutalyzer
+ should advise you to contact
+ <a href="mailto:Mutalyzer@humgen.nl">us</a> when the error persists.
+ Please specify your input and which tool you used.
+ </p>
+ <p>
+ Occasionally, Mutalyzer will display an Internal Server Error message
+ due to unexpected behavior. You can use Mutalyzer's
+ <a href="https://www.mutalyzer.nl/projects/mutalyzer2/"
+ >bugtracking system</a> to report errors and send in feature requests.
+ </p>
+
+ <h3>Citing Mutalyzer </h3>
+ <p>
+ When you use Mutalyzer, please cite this paper: Wildeman M, van
+ Ophuizen E, den Dunnen JT, Taschner PE. Improving sequence variant
+ descriptions in mutation databases and literature using the MUTALYZER
+ sequence variation nomenclature checker.
+ <a href="http://www.ncbi.nlm.nih.gov/entrez/utils/fref.fcgi?PrId=3058&itool=AbstractPlus-def&uid=18000842&db=pubmed&url=http://dx.doi.org/10.1002/humu.20654">Hum Mutat 29:6-13 (2008)</a>
+ [<a href="http://www.ncbi.nlm.nih.gov/pubmed/18000842?"
+ >PMID: 18000842</a>].
+ </p>
+ <p>
+ Mutalyzer 2 has been completely redesigned by Jeroen F.J. Laros, with
+ help from Gerben R. Stouten and Gerard C. P. Schaafsma, according to
+ specifications provided by Peter E. M. Taschner and Johan T. den
+ Dunnen. The different parts of the nomenclature checker functionality
+ have been separated into modules, which can be used as independent
+ webservices and undergo further development and extension in the
+ future.
+ </p>
+
+ <hr>
+
+ <p>
+ If you have any comments or suggestions be sure to let us know!
+ </p>
+
+ <p>
+ Last modified: August 6, 2010
+ </p>
+ <a href="mailto:Mutalyzer@humgen.nl">
+ <address>mutalyzer@humgen.nl</address></a>
+ </div>
+ </body>
+</html>
diff --git a/templates/index.html b/templates/index.html
index 052a4275e1577814befef8a0215fae02ebf95d0e..329d53a3875ac2055cc7749102e6c4507921b830 100644
--- a/templates/index.html
+++ b/templates/index.html
@@ -50,28 +50,6 @@
</li>
</ul>
<br>
- Mutalyzer <span tal:content = "structure string:${version}"></span>
- is designed and developed by Dr. Jeroen F. J. Laros, with the
- following exceptions:
- <ul>
- <li>The LRG parser, as well as the Batch interfaces are written
- by Gerben R. Stouten.</li>
- <li>The position converter interfaces (webservice and WWW) are
- written by Ir. Gerard C. P. Schaafsma.</li>
- </ul>
- Specifications are given by Dr. Peter E. M. Taschner and Prof. Dr.
- Johan T. den Dunnen.<br>
- <br>
- Since the publication is under development, please use the old
- reference for now when referring to these pages:
- <a href="http://www.ncbi.nlm.nih.gov/entrez/utils/fref.fcgi?PrId=3058&itool=AbstractPlus-def&uid=18000842&db=pubmed&url=http://dx.doi.org/10.1002/humu.20654">
- "Wildeman M et al. (2008). Improving sequence variant
- descriptions in mutation databases and literature using the
- Mutalyzer sequence variation nomenclature checker. Hum Mutat 29,
- 6-13"
- </a>.<br>
- <br>
- <br>
<!--
Mutalyzer <span tal:content = "structure string:${version}"></span> is
written completely in <a href="http://www.python.org">Python</a>. The
@@ -86,22 +64,6 @@
<a href = "http://www.sun.com">SUN Microsystems</a> with server
hardware within the scope of the Academic Excellence Grant (AEG)
program (award EDUD-7832-080223-CNE).<br>
- Project development is sponsored by
- <a href="http://www.gen2phen.org" target="_blank">
- <img src="base/images/gen_2_phen_logo_print.png"
- width="110"
- height="50"
- align="middle"
- border="0"
- alt="Eurogentest"></a>
- and has been supported by
- <a href="http://www.eurogentest.org" target="_blank">
- <img src="base/images/Eurogentest.png"
- width="110"
- height="50"
- align="middle"
- border="0"
- alt="Eurogentest"></a>
</div>
</body>
</html>
diff --git a/templates/menu.html b/templates/menu.html
index a8abaa0a3bdb1417f7c0f44df3efa1d38da57065..0e1d4ddb4a21e5efad2eef1cec15aeae8a6398d6 100644
--- a/templates/menu.html
+++ b/templates/menu.html
@@ -40,7 +40,7 @@
preloadImages('base/images/bullitlicht1.gif',
'base/images/bullitlicht2.gif');">
<!-- Header -->
- <a id="top"></a>
+ <a id = "top" name = "top"></a>
<table width="98%"
border="0"
@@ -89,6 +89,8 @@
<td align="right">
<a href="index"
class="hornav">home</a>
+ <a href="about"
+ class="hornav">about</a>
<a tal:attributes = "href string:mailto:${contactEmail}"
class="hornav">contact</a>
<a href="#bottom" class="hornav">go to bottom</a>
@@ -120,81 +122,6 @@
<img src="base/images/1x1b.gif" height="19" border="0">
</td>
</tr>
-
- <!-- Home
- <tr>
- <td valign="top" width="20">
- <img src="base/images/bullitdonker.gif" id="b_">
- </td>
- <td colspan="3">
- <a id="page_"
- onClick="swapActive('');"
- href="/"
- onMouseover="navAct('base/images/bullitlicht1.gif',
- '');"
- onMouseout="navDeAct('base/images/bullitdonker.gif',
- '');"
- class="vertnavsub">Home</a>
- </td>
- </tr>
- -->
-
- <!-- Contact - ->
- <tr>
- <td valign="top" width="20">
- <img src="base/images/bullitdonker.gif" id="b_contact">
- </td>
- <td colspan="3">
- <a id="page_contact"
- onClick="swapActive('contact');"
- href="/#contact"
- onMouseover="navAct('base/images/bullitlicht1.gif',
- 'contact');"
- onMouseout="navDeAct('base/images/bullitdonker.gif',
- 'contact');"
- class="vertnavsub">Contact</a>
- </td>
- </tr>
- -->
-
- <!-- Current Projects -->
- <!--
- <tr>
- <td valign="top" width="20">
- <img src="base/images/bullitdonker.gif" id="b_projects">
- </td>
- <td colspan="3">
- <a id="page_projects"
- onClick="swapActive('projects');"
- href="/#projects"
- onMouseover="navAct('base/images/bullitlicht1.gif',
- 'projects');"
- onMouseout="navDeAct('base/images/bullitdonker.gif',
- 'projects');"
- class="vertnavsub">Current Projects</a>
- </td>
- </tr>
- <!- - Current Projects sub: SNP - ->
- <tr style="display:none" id="projects_0">
- <td></td>
- <td valign="baseline" width="10">
- <img src="base/images/bullitmiddel.gif" id="b_projects_snp">
- </td>
- <td colspan="2">
- <a id="page_projects_snp"
- onClick="swapActive('projects_snp');"
- href="/projects/snp/"
- onMouseover="navAct('base/images/bullitlicht2.gif',
- 'projects_snp');"
- onMouseout="navDeAct('base/images/bullitmiddel.gif',
- 'projects_snp');"
- class="vertnavsub">SNP</a>
- </td>
- </tr>
- -->
-
- <!-- Finished Projects -->
-
<tr>
<td valign="top" width="20">
@@ -260,38 +187,6 @@
</td>
</tr>
- <tr>
- <td valign="top" width="20">
- <img src="base/images/bullitdonker.gif" id="b_nameGenerator">
- </td>
- <td colspan="3">
- <a id="page_nameGenerator"
- onclick="swapActive('nameGenerator');"
- href="nameGenerator"
- onmouseover="navAct('base/images/bullitlicht1.gif',
- 'nameGenerator');"
- onmouseout="navDeAct('base/images/bullitdonker.gif',
- 'nameGenerator');"
- class="vertnavsub">Name Generator</a>
- </td>
- </tr>
-
- <tr>
- <td valign="top" width="20">
- <img src="base/images/bullitdonker.gif" id="b_upload">
- </td>
- <td colspan="3">
- <a id="page_upload"
- onclick="swapActive('upload');"
- href="upload"
- onmouseover="navAct('base/images/bullitlicht1.gif',
- 'upload');"
- onmouseout="navDeAct('base/images/bullitdonker.gif',
- 'upload');"
- class="vertnavsub">GenBank uploader</a>
- </td>
- </tr>
-
<tr>
<td valign="top" width="20">
<img src="base/images/bullitdonker.gif" id="b_snp">
@@ -310,17 +205,17 @@
<tr>
<td valign="top" width="20">
- <img src="base/images/bullitdonker.gif" id="b_webservices">
+ <img src="base/images/bullitdonker.gif" id="b_nameGenerator">
</td>
<td colspan="3">
- <a id="page_webservices"
- onclick="swapActive('webservices');"
- href="webservices"
- onmouseover="navAct('base/images/bullitlicht1.gif',
- 'webservices');"
- onmouseout="navDeAct('base/images/bullitdonker.gif',
- 'webservices');"
- class="vertnavsub">Webservices</a>
+ <a id="page_nameGenerator"
+ onclick="swapActive('nameGenerator');"
+ href="nameGenerator"
+ onmouseover="navAct('base/images/bullitlicht1.gif',
+ 'nameGenerator');"
+ onmouseout="navDeAct('base/images/bullitdonker.gif',
+ 'nameGenerator');"
+ class="vertnavsub">Name Generator</a>
</td>
</tr>
@@ -347,7 +242,6 @@
</td>
<td colspan="2">
<a id="page_batchNameChecker"
- onclick="swapActive('batchNameChecker');"
href="batchNameChecker"
class="vertnavsub">Name Checker</a>
</td>
@@ -360,7 +254,6 @@
</td>
<td colspan="2">
<a id="page_batchSyntaxChecker"
- onclick="swapActive('batchSyntaxChecker');"
href="batchSyntaxChecker"
class="vertnavsub">Syntax Checker</a>
</td>
@@ -373,12 +266,45 @@
</td>
<td colspan="2">
<a id="page_batchPositionConverter"
- onclick="swapActive('batchPositionConverter');"
href="batchPositionConverter"
class="vertnavsub">Position Converter</a>
</td>
</tr>
+ <tr>
+ <td valign="top" width="20">
+ <img src="base/images/bullitdonker.gif" id="b_upload">
+ </td>
+ <td colspan="3">
+ <a id="page_upload"
+ onclick="swapActive('upload');"
+ href="upload"
+ onmouseover="navAct('base/images/bullitlicht1.gif',
+ 'upload');"
+ onmouseout="navDeAct('base/images/bullitdonker.gif',
+ 'upload');"
+ class="vertnavsub">GenBank uploader</a>
+ </td>
+ </tr>
+
+ <tr>
+ <td valign="top" width="20">
+ <img src="base/images/bullitdonker.gif" id="b_webservices">
+ </td>
+ <td colspan="3">
+ <a id="page_webservices"
+ onclick="swapActive('webservices');"
+ href="webservices"
+ onmouseover="navAct('base/images/bullitlicht1.gif',
+ 'webservices');"
+ onmouseout="navDeAct('base/images/bullitdonker.gif',
+ 'webservices');"
+ class="vertnavsub">Webservices</a>
+ </td>
+ </tr>
+
+ <tr><td> </td></tr>
+
<tr>
<td valign="top" width="20">
<img src="base/images/bullitdonker.gif" id="b_help">
@@ -468,7 +394,6 @@
</td>
<td colspan="2">
<a id="page_external_hgb"
- onclick="swapActive('external_hgb');"
href="http://www.genenames.org/guidelines.html"
class="vertnavsub">Human Gene Nomenclature</a>
</td>
@@ -481,7 +406,6 @@
</td>
<td colspan="2">
<a id="page_external_hgvs"
- onclick="swapActive('external_hgvs');"
href="http://www.hgvs.org/mutnomen/"
class="vertnavsub">HGVS variation nomenclature</a>
</td>
@@ -494,7 +418,6 @@
</td>
<td colspan="2">
<a id="page_external_hgvsext"
- onclick="swapActive('external_hgvsext');"
href="downloads/HGVS_nomenclature_extension_proposal.pdf"
class="vertnavsub">HGVS nomenclature extension proposal</a>
</td>
@@ -559,7 +482,10 @@
<center>
- <h2 tal:content = "structure string:Mutalyzer ${version}"></h2>
+ <h2 tal:content = "structure string:Mutalyzer ${version}<br>
+ <small><small><small><small>
+ released on ${releaseDate}
+ </small></small></small></small>"></h2>
HGVS nomenclature version
<span tal:content = "nomenclatureVersion"></span>
</center>
@@ -590,7 +516,7 @@
</tr>
<tr>
<td align="left">
- <a href="javascript:history.back(-1);"
+ <a href="javascript:history.back(-1);"
class="hornav">previous page</a>
</td>
<td align="middle">
@@ -599,7 +525,9 @@
</td>
- <td align="right"><a href="#top" class="hornav">go to top</a></td>
+ <td align="right">
+ <a href="#top" class="hornav">go to top</a>
+ </td>
</tr>
<tr>
<!--
@@ -620,6 +548,6 @@
</td>
</tr>
</table>
- <a id="bottom"></a>
+ <a id = "bottom" name = "bottom"></a>
</body>
</html>