public static Polymorphism getReferenceBase(int position)
{
string refBase = Convert.ToString(rCRS [position - 1]);
refBase = refBase.ToUpper();
return(new Polymorphism(position, MutationAssigner.getBase(refBase)));
}
//public static string TREE_XML_FILE { get { return addFileNameToEndOfDirectory ("phylotree15.xml"); } }
//public static string WEIGHT_FILE { get { return addFileNameToEndOfDirectory ("fluctRates15.txt"); } }
/// <summary>
/// Applies the current best practices filters to a list of polymorphisms, to
/// avoid erroneous calls. Currently removes indels and bad positions
/// </summary>
/// <param name="polys"></param>
/// <returns></returns>
internal static IEnumerable <Polymorphism> CommonPolymorphismFilter(IEnumerable <Polymorphism> polys)
{
return(polys.Where(x => !EXCLUDED_POSITIONS.Contains(x.position) && MutationAssigner.MutationIsBasePair(x.mutation)));
}
//TODO: VERIFY ALL OF THIS!!!
//Nucleotide position numbers are relative to the RSRS and rCRS. Mutations are given in forward evolutionary time direction. In case of a transversion the derived allele is shown in lowercase.
//Coding region mutations (np 577-16023) are shown in black; control region mutations (np 16024-576) in blue.
//Back mutations to an ancestral state are indicated with an exclamation mark (!), two exclamation marks for a double back mutation (!!), etc.
//Mutations between brackets () are recurrent/unstable within the respective clade, or are yet uncertain based on current data.
//Mutation motifs in italic are preliminary and are likely to be further refined as additional sequences become available.
//The mutations 309.1C(C), 315.1C, AC indels at 515-522, 16182C, 16183C, 16193.1C(C) and 16519 were not considered for phylogenetic reconstruction and are therefore excluded from the tree.
//Accession numbers provided at the tips of branches are representative examples of mtDNA sequences available at GenBank or from individuals included in HapMap/1000Genomes.
//The references are independent from the accession numbers and refer to publications that have described the corresponding branch and/or have proposed haplogroup nomenclature.
//It may be convenient to use the Find function (Ctrl+F) of your browser to search for a particular mutation or haplogroup.
private void parse(string phyloString)
{
phyloString = phyloString.Trim();
if (phyloString.StartsWith("("))
{
phyloString = phyloString.Substring(1, phyloString.Length - 1 - 1);
}
if (phyloString.Contains("!"))
{
phyloString = phyloString.Replace("!", "");
BackMutation = true;
}
//TODO: This needs a length
if ((phyloString.Contains("d")) || (phyloString.Contains("D")))
{
//8288d
phyloString = phyloString.Replace("del", "");
phyloString = phyloString.Replace("d", "");
phyloString = phyloString.Replace("DEL", "");
this.position = (int)Convert.ToInt32(phyloString);
this.mutation = Mutations.DEL;
}
else if (phyloString.Contains("."))
{
//315.1C
var match = System.Text.RegularExpressions.Regex.Match(phyloString, @"(?<Position>[\d]+)\.(?<Size>[\d+|X])(?<Sequence>[A|C|G|T]+)");
//Giant pain above because the possible "X" for size is ambiguous
try {
this.position = Convert.ToInt32(match.Groups ["Position"].Value);
} catch (FormatException e) {
throw new FormatException("Could not convert " + match.Groups ["Position"].Value.ToString() + " to value");
}
this.mutation = Mutations.INS;
this.numberOfIns = "." + match.Groups ["Size"].Value;
string mutationString = match.Groups ["Sequence"].Value;
if (numberOfIns == "X")
{
this.numberOfIns = mutationString.Length.ToString();
}
this.insertedPolys = match.Groups ["Sequence"].Value;
if (match.Groups ["Sequence"].Value.Length != match.Groups ["Sequence"].Value.Length)
{
throw new HaploGrepException("Could not align mutations");
}
//ORIGINAL CODE BELOW
//string[] split = phyloString.Split('.');
//string token = split[0];
//string token1 = split[1].Trim();
////TODO: Was going to translate this, but then it seemed that it was never used...
////Pattern p = Pattern.compile("\\d+");
////Matcher m = p.matcher(token1);
////m.find();
//this.position = Convert.ToInt32(token);
//this.mutation = Mutations.INS;
//string mutationString = "";
////TODO: This seems to only allow up to 3 basepairs
//for (int i = 0; i <= 2; i++)//why can this only be up to 2???
//{
// string number = Convert.ToString(i);
// if (token1.Contains(number))
// {
// mutationString = token1.Replace(number, "");//C
// this.numberOfIns = ("." + number);//1
// }
//}
//try
//{
// for (int i = 0; i < mutationString.Length; i++)
// {
// MutationAssigner.getBase(Convert.ToString(mutationString[i]));
// }
//}
//catch (Exception e)
//{
// throw new HaploGrepException("Could not parse mutation: "+phyloString, e);
//}
//this.insertedPolys = mutationString;
}
else
{
var match = System.Text.RegularExpressions.Regex.Match(phyloString, "[a-zA-Z]");
if (match.Success)
{
//should throw exception otherwise
this.mutation = MutationAssigner.getBase(match.Value);
this.position = Convert.ToInt32(phyloString.Replace(match.Value, ""));
}
else
{
match = System.Text.RegularExpressions.Regex.Match(phyloString, "\\d+");
int position = Convert.ToInt32(match.Value);
getTransitionPoly(position);
}
//152C
//var match=System.Text.RegularExpressions.Regex.Match(phyloString, @"(?<Position>[\d]+)(?<Sequence>[A|C|G|T]+)");
// //this.mutation = Mutations.getBase(phyloString.Substring(m.start(), m.end() - (m.start())));
// this.mutation=MutationAssigner.getBase(match.Groups["Sequence"].Value);
// // this.position = (int)Convert.ToInt32(phyloString.replaceFirst("[a-zA-Z]", ""));
// this.position=Convert.ToInt32(match.Groups["Position"].Value);
}
}