public void AddCodingSequence(CodingSequence cds)
{
collection.Add(cds);
}
public CodingSequence CreateCodingSequenceEntry(string currentEntryData)
{
string locusTag = "";
string geneId = "";
string translatedSequence = "";
string geneProduct = "";
string proteinId = "";
bool isReverse = true;
bool foundTranslatedSequence = false;
int start = 0;
int end = 0;
currentEntryData.Split('\n');
string[] entryLines = currentEntryData.Split('\n');
foreach (string item in entryLines)
{
//string[] geneData = entryLines.Where(line => !string.IsNullOrEmpty(line)).ToArray();
string[] splitItem = item.Split(' ');
string cdsData = splitItem[splitItem.Length - 1];
if (Regex.IsMatch(cdsData, "complement\\(\\d*\\.\\.\\d*\\)"))
{
String substring = cdsData.Substring(11);
string replaceData = substring.Replace(")", "");
string[] coordinates = Regex.Split(replaceData, @"\.\.");
start = Int32.Parse(coordinates[0]);
end = Int32.Parse(coordinates[1]);
isReverse = true;
}
else if (Regex.IsMatch(cdsData, "\\d*\\.\\.\\d*"))
{
//string[] coordinateSplit = data.Split(new[] { ".." }, StringSplitOptions.None);
string[] coordinates = Regex.Split(cdsData, @"\.\.");
start = Int32.Parse(coordinates[0]);
end = Int32.Parse(coordinates[1]);
isReverse = false;
}
else if (item.Contains("/gene"))
{
string split = item.Split('=')[1];
geneId = split.Replace("\"", "");
}
else if (item.Contains("/locus_tag"))
{
string split = item.Split('=')[1];
locusTag = split.Replace("\"", "");
}
else if (item.Contains("/product"))
{
string split = item.Split('=')[1];
geneProduct = split.Replace("\"", "");
}
else if (item.Contains("/protein_id"))
{
string split = item.Split('=')[1];
proteinId = split.Replace("\"", "");
}
else if (item.Contains("/translation") && !foundTranslatedSequence)
{
String sequence = splitItem[splitItem.Length - 2];
translatedSequence += sequence.Substring(0, sequence.Length);
foundTranslatedSequence = true;
}
else if (foundTranslatedSequence && !item.Contains("ORIGIN") && item != "")
{
String sequence = item.Replace(" ", "");
translatedSequence += sequence.Substring(0, sequence.Length - 1);
}
}
CodingSequence codingSequence = new CodingSequence(locusTag, geneId, translatedSequence, geneProduct, isReverse, start, end, proteinId);
return(codingSequence);
}
/**
* Fetches data from GeneCollection and CodingSequenceCollection.
* @returns siteFeatureCollection containing SiteFeature objects.
*/
public SiteFeatureCollection FetchSiteFeatures(GeneCollection geneCollection, CodingSequenceCollection cdsCollection, string[] featureCoordinateArray)
{
SiteFeatureCollection siteFeatureCollection = new SiteFeatureCollection();
List <string> nonMatchedFeatures = new List <string>();
foreach (string coordinate in featureCoordinateArray)
{
bool isMatch = false;
if (Regex.IsMatch(coordinate, "\\d*\\.\\.\\d*"))
{
string[] split = Regex.Split(coordinate, "\\.\\.");
int startCoordinate = Int32.Parse(split[0]);
int endCoordinate = Int32.Parse(split[1]);
for (int i = 0; i < geneCollection.collection.Count; i++)
{
string geneId = "";
string type = "";
string orientation = "";
Gene gene = geneCollection.collection[i];
CodingSequence cds = cdsCollection.collection[i];
if (gene.StartCoordinate >= startCoordinate && gene.EndCoordinate <= endCoordinate)
{
if (gene.ID != "")
{
geneId = gene.ID;
}
else
{
geneId = gene.LocusTag;
}
type = "gene";
int geneStartCoordinate = gene.StartCoordinate;
int geneStopCoordinate = gene.EndCoordinate;
if (gene.IsReverse)
{
orientation = "R";
}
else
{
orientation = "F";
}
SiteFeature feature = new SiteFeature(geneId, type, geneStartCoordinate, geneStopCoordinate, orientation);
siteFeatureCollection.AddSiteFeature(feature);
//Change type and change geneId to geneProduct for a CDS entry. Other values are similar to Gene values.
string product = cds.GeneProduct;
type = "CDS";
feature = new SiteFeature(product, type, geneStartCoordinate, geneStopCoordinate, orientation);
siteFeatureCollection.AddSiteFeature(feature);
isMatch = true;
}
}
if (!isMatch)
{
nonMatchedFeatures.Add(coordinate);
}
}
}
if (!siteFeatureCollection.collection.Any() || !nonMatchedFeatures.Any())
{
//Display list of site entries that did not match.
String message = "";
foreach (String feature in nonMatchedFeatures)
{
if (message != "")
{
message += "Some of the provided enrties could not be found. Here is the list of sites; ";
message += feature;
}
else
{
message += ", " + feature;
}
}
Console.WriteLine("\n" + message);
}
siteFeatureCollection.Sort();
return(siteFeatureCollection);
}
public CollectedGeneBankData ReadGenebankFile(string inputFile)
{
//Split path to get file name.
GeneCollection geneCollection = new GeneCollection();
CodingSequenceCollection codingSequenceCollection = new CodingSequenceCollection();
string fileName = Path.GetFileName(inputFile);
string organism = "";
string accession = "";
string length = "";
string originSequence = "";
//Booleans for if/else statements.
bool isFirst = true;
bool isOrigin = false;
bool currentEntryIsCDS = false;
bool currentEntryIsGene = false;
//Both patterns check if both complement and non-complement entries are present.
string genePattern = " *gene *(complement)?\\(?\\d*\\.\\.\\d*\\)?";
string cdsPattern = " *CDS *(complement)?\\(?\\d*\\.\\.\\d*\\)?";
string currentEntry = "";
StreamReader reader = new StreamReader(inputFile);
string gbkLine;
while ((gbkLine = reader.ReadLine()) != null)
{
//All comming lines contain nucleotide data which can be added to the origin sequence.
if (isOrigin)
{
originSequence += Regex.Replace(gbkLine, "(\\d| )", "");
}
//Only occurs untill first entry is false.
if (isFirst)
{
if (gbkLine.StartsWith("LOCUS"))
{
length = GetSequenceLength(gbkLine);
}
if (gbkLine.Contains(" ORGANISM"))
{
organism = GetOrganism(gbkLine);
}
if (gbkLine.Contains("ACCESSION"))
{
accession = GetAccessionId(gbkLine);
}
}
//Check if
if (currentEntryIsCDS && !Regex.IsMatch(gbkLine, genePattern))
{
currentEntry += gbkLine + "\n";
}
else if (currentEntryIsCDS && Regex.IsMatch(gbkLine, genePattern))
{
currentEntryIsGene = true;
currentEntryIsCDS = false;
CodingSequence codingSequence = CreateCodingSequenceEntry(currentEntry);
codingSequenceCollection.AddCodingSequence(codingSequence);
currentEntry = gbkLine + "\n";
}
else if (currentEntryIsGene && !Regex.IsMatch(gbkLine, cdsPattern))
{
currentEntry += gbkLine + "\n";
}
else if (currentEntryIsGene && Regex.IsMatch(gbkLine, cdsPattern))
{
currentEntryIsGene = false;
currentEntryIsCDS = true;
Gene gene = CreateGeneEntry(currentEntry);
geneCollection.AddGene(gene);
currentEntry = gbkLine + "\n";
}
else if (isFirst && Regex.IsMatch(gbkLine, genePattern))
{
currentEntryIsGene = true;
isFirst = false;
currentEntry += gbkLine + "\n";
}
else if (isFirst && Regex.IsMatch(gbkLine, cdsPattern))
{
currentEntryIsCDS = true;
isFirst = false;
currentEntry += gbkLine + "\n";
}
if (gbkLine.StartsWith("ORIGIN"))
{
//Set isOrigin to true: first if statement will be handled.
isOrigin = true;
string line = gbkLine.Replace("ORIGIN", "");
originSequence += Regex.Replace(line, "(\\d| )", "");
if (currentEntryIsCDS)
{
currentEntryIsCDS = false;
CodingSequence codingSequence = CreateCodingSequenceEntry(currentEntry);
codingSequenceCollection.AddCodingSequence(codingSequence);
}
else if (currentEntryIsGene)
{
currentEntryIsGene = false;
Gene gene = CreateGeneEntry(currentEntry);
geneCollection.AddGene(gene);
}
}
}
int geneCount = geneCollection.collection.Count; //Size of gene collection
int cdsCount = codingSequenceCollection.collection.Count; //Size of coding sequence collection
double totalGeneCounter = 0.0;
double forwardGeneCounter = 0.0;
foreach (Gene geneEntry in geneCollection.collection)
{
if (!geneEntry.IsReverse)
{
totalGeneCounter++;
forwardGeneCounter++;
}
else
{
totalGeneCounter++;
}
}
//Forward/Reverse (FR) ratio calculation.
double value = (forwardGeneCounter / totalGeneCounter);
double forwardReverseBalance = Math.Round(value, 1);
//For each gene: if gene isForward or !isReverse > +1 to total and foward
//else +1 to total
Summary summary = new Summary(fileName, organism, accession, length, geneCount, forwardReverseBalance, cdsCount, originSequence);
CollectedGeneBankData geneBankeData = new CollectedGeneBankData(geneCollection, codingSequenceCollection, summary);
return(geneBankeData);
}