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();
}
}
