internal void FetchGeneDisplay(GeneCollection geneCollection, string[] geneArray, string originSequence)
{
GbkFeatureFetcher fetcher = new GbkFeatureFetcher();
GeneCollection updatedGeneCollection = fetcher.FetchGeneData(geneCollection, geneArray, originSequence);
foreach (Gene gene in updatedGeneCollection.collection)
{
String geneMessage = "";
if (gene.ID != "")
{
geneMessage += ">" + gene.ID + newLine;
}
else
{
geneMessage += ">" + gene.LocusTag + newLine;
} //Print sequence in substrings of 80.
String sequence = gene.Sequence;
int length = sequence.Length;
for (int start = 0; start < length;)
{
int end = start + 80;
if (end < length)
{
geneMessage += sequence.Substring(start, 80) + newLine;
}
else
{
geneMessage += sequence.Substring(start, (length - start));
}
start += 80;
}
Console.WriteLine(geneMessage);
}
Console.WriteLine(newLine);
}
public void FetchFeatures(GeneCollection geneCollection, CodingSequenceCollection cdsCollection, string[] featureArray)
{
Console.Write("FEATURE;TYPE;START;STOP;ORIENTATION");
GbkFeatureFetcher fetcher = new GbkFeatureFetcher();
SiteFeatureCollection siteFeatureCollection = fetcher.FetchSiteFeatures(geneCollection, cdsCollection, featureArray);
foreach (SiteFeature siteFeature in siteFeatureCollection.collection)
{
Console.WriteLine(siteFeature.GeneID + ";" + siteFeature.Type + ";" + siteFeature.StartCoordinate + ";" + siteFeature.EndCoordinate + ";" + siteFeature.Orientation);
}
Console.WriteLine(newLine);
}
public GeneCollection FetchGeneData(GeneCollection geneCollection, string[] geneArray, string originSequence)
{
List <string> nonMatchedGenes = new List <string>();
GeneCollection updatedGeneCollection = new GeneCollection();
foreach (String givenGene in geneArray)
{
Boolean isMatch = false;
foreach (Gene gene in geneCollection.collection)
{
if (gene.ID.Contains(givenGene) || gene.LocusTag.Contains(givenGene))
{
int start = gene.StartCoordinate;
int distance = gene.EndCoordinate - gene.StartCoordinate;
string nucleotideSequence = originSequence.Substring(start, distance);
gene.Sequence = nucleotideSequence;
updatedGeneCollection.AddGene(gene);
isMatch = true;
break;
}
}
//If no match was found: add to nonMatchedGenes list.
if (!isMatch)
{
nonMatchedGenes.Add(givenGene);
}
}
//If all or some geneId entries did not match:\
if (nonMatchedGenes.Any())
{
//Display list of gene entries that did not match.
String message = "";
foreach (String gene in nonMatchedGenes)
{
if (message.Length == 0)
{
message += "Some of the provided enrties could not be found. Here is the list of genes; ";
message += gene;
}
else
{
message += ", " + gene;
}
}
Console.WriteLine("\n" + message);
}
updatedGeneCollection.SortOnID();
return(updatedGeneCollection);
}
public void FetchSites(GeneCollection geneCollection, string originSequence, string[] siteArray)
{
Console.Write("POSITION;SEQUENCE;GENE");
GbkFeatureFetcher fetcher = new GbkFeatureFetcher();
List <SearchSiteCollection> list = fetcher.FetchSearchSiteData(geneCollection, originSequence, siteArray);
foreach (SearchSiteCollection searchSiteCollection in list)
{
foreach (SearchSite searchSite in searchSiteCollection.collection)
{
Console.WriteLine(searchSite.StartPosition + ";" + searchSite.Site + ";" + searchSite.GeneName);
}
}
Console.WriteLine(newLine);
}
public List <SearchSiteCollection> FetchSearchSiteData(GeneCollection geneCollection, string originSequence, string[] siteArray)
{
Dictionary <string, string> iupacTable = CreateIupacTable();
List <SearchSiteCollection> finalSiteList = new List <SearchSiteCollection>();
List <string> nonMatchedSites = new List <string>();
string upperOriginSequence = originSequence.ToUpper();
foreach (string site in siteArray)
{
SearchSiteCollection searchSiteCollection = new SearchSiteCollection();
string[] nucleotideSites = site.Split();
List <string> targetSequences = new List <string>();
bool isMatch = false;
foreach (char nucleotideSite in site)
{
string nucSite = nucleotideSite.ToString();
if (iupacTable.ContainsKey(nucSite))
{
String newNucleotides = iupacTable[nucSite];
String regex = "[" + newNucleotides + "]";
foreach (char newNuc in newNucleotides)
{
string nuc = newNuc.ToString();
string targetSequence = site.Replace(nucSite, nuc);
targetSequences.Add(targetSequence);
}
searchSiteCollection.searchSiteRegexMessage = "site search: " + nucSite + " (regex: " + nucSite.Replace(nucSite, regex) + ")";
}
}
foreach (String targetSequence in targetSequences)
{
int index = 0;
while (index >= 0 && index != upperOriginSequence.Length)
{
index++;
index = upperOriginSequence.IndexOf(targetSequence, index);
String strIndex = "" + (index + 1);
if (index != -1)
{
String geneName = "INTERGENIC";
foreach (Gene gene in geneCollection.collection)
{
if (index >= gene.StartCoordinate && index <= gene.EndCoordinate)
{
//Index + 1 because coding index starts at zero and sequence index starts at 1.
if (gene.ID != "")
{
geneName = gene.ID;
}
else
{
geneName = gene.LocusTag;
}
isMatch = true;
}
}
SearchSite searchSite = new SearchSite(strIndex, targetSequence, geneName);
if (searchSiteCollection.collection.Any())
{
bool newEntry = true;
foreach (SearchSite siteEntry in searchSiteCollection.collection)
{
if (siteEntry.StartPosition.Equals(strIndex))
{
if (siteEntry.Site.Equals("INTERGENIC") && !geneName.Equals("INTERGENIC"))
{
siteEntry.GeneName = geneName;
newEntry = false;
break;
}
}
}
if (newEntry)
{
searchSiteCollection.AddSearchSite(searchSite);
}
}
else
{
searchSiteCollection.AddSearchSite(searchSite);
}
}
}
}
finalSiteList.Add(searchSiteCollection);
if (!isMatch)
{
nonMatchedSites.Add(site);
}
}
//If all site entries did not match:
if (nonMatchedSites.Any())
{
//Display list of nucleotide site entries that did not match.
String message = "";
foreach (String site in nonMatchedSites)
{
if (message == "")
{
message += "Some of the provided entries could not be found. Here is the list of nucleotide sites; ";
message += site;
}
else
{
message += ", " + site;
}
}
Console.WriteLine("\n" + message);
}
return(finalSiteList);
}
/**
* 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(GeneCollection collectedGenes, CodingSequenceCollection cdsCollection, Summary sum)
{
geneCollection = collectedGenes;
codingSequenceCollection = cdsCollection;
summary = sum;
}
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);
}
static void Main(string[] args)
{
var options = new Options();
if (args.Length != 0)
{
Parser parser = new Parser();
FileReader reader = new FileReader();
GeneBankDisplayFetcher displayFetcher = new GeneBankDisplayFetcher();
try
{
if (parser.ParseArguments(args, options))
{
//Match to regex. Checks if file ends with .gbk
string gbkFile = options.InputFile;
if (File.Exists(gbkFile) && gbkFile.EndsWith(".gb") || gbkFile.EndsWith(".gbk"))
{
CollectedGeneBankData geneBankData = reader.ReadGenebankFile(gbkFile);
GeneCollection geneCollection = geneBankData.geneCollection;
Summary summary = geneBankData.summary;
CodingSequenceCollection cdsCollection = geneBankData.codingSequenceCollection;
if (options.Summary)
{
// get summary from data fetcher
displayFetcher.FetchSummary(geneBankData.summary);
}
string[] geneArray = options.FetchGenes;
if (geneArray != null && geneArray.Length != 0)
{
Console.WriteLine("Fetching gene sequences...");
displayFetcher.FetchGeneDisplay(geneCollection, geneArray, summary.OriginSequence);
//give options.GenesToFetch to dataFetcher and return the required data.
}
if (options.FetchCDS != null && options.FetchCDS.Length != 0)
{
Console.WriteLine("Fetching cds product sequences...");
string[] cdsArray = options.FetchCDS;
displayFetcher.FetchCDSs(cdsCollection, cdsArray);
//give options.CDSsToFetch to dataFetcher and return the required data.
}
if (options.FetchFeatures != null && options.FetchFeatures.Length != 0)
{
Console.WriteLine("Fetching gene location features...");
string[] featureArray = options.FetchFeatures;
displayFetcher.FetchFeatures(geneCollection, cdsCollection, featureArray);
//give options.FeaturesToFetch to dataFetcher and return the required data.
}
if (options.FetchSites != null && options.FetchSites.Length != 0)
{
Console.WriteLine("Fetching given nucleotide sites...");
string[] siteArray = options.FetchSites;
displayFetcher.FetchSites(geneCollection, geneBankData.summary.OriginSequence, siteArray);
//give options.SitesToFetch to dataFetcher and return the required data.
}
Console.ReadKey();
}
else
{
Console.WriteLine("Given file " + gbkFile + " seems to not exist on your computer. Please check your input.");
Console.WriteLine("Press any key to close the console.");
Console.ReadKey();
}
}
else
{
Console.WriteLine("The commandline parser could not find any arguments. Please use the --help function for options.");
Console.WriteLine("Press any key to close the console.");
Console.WriteLine(parser.ParseArguments(args, options));
Console.WriteLine(options.InputFile);
Console.WriteLine(args[0] + " " + args[1]);
Console.ReadKey();
}
}
catch (Exception e)
{
Console.WriteLine("Encounted an exception while parsing." + e + "\nPlease check your cmd arguments and try again, or use the --help function.");
Console.WriteLine("Press any key to close the console.");
Console.ReadKey();
}
}
else
{
Console.WriteLine("No arguments we're provided.");
options.GetHelp();
Console.WriteLine("Press any key to close the console.");
Console.ReadKey();
}
}
