/// <summary>
/// This is the method that gets hit first when this application is run.
/// In this method we read data from Chr1.fa for database and from Prog2-input-NM_032291-10exon-seqs.fa for
/// query sequence for matching. Get all the query sequences into Keyvalue pair list.
/// Loop the list so that optimum score is calucluated for each exon by calling SmithWatermanScore(string,string)
/// </summary>
/// <param name="args"></param>
static void Main(string[] args)
{
string bases = string.Empty;
//Read bases from file and make it as string from array
string[] lines = File.ReadAllLines(@"D:\BioInfo Activity\chr1.fa");
List <string> list = new List <string>(lines);
list.RemoveAt(0);
bases = string.Join("", list.ToArray());
string RefSeq = bases;
//Variables used to store query sequence label, bases and final text format to be displayed.
string PatternID = string.Empty;
string Pattern_Seq = string.Empty;
string FinalText = string.Empty;
//Initialize KeyValuePair List for storing query sequences.
List <KeyValuePair <string, string> > PatternData = new List <KeyValuePair <string, string> >();
//Loop through Prog2-input-NM_032291-10exon-seqs.fa file to store all query sequences into list.
foreach (string ExonData in File.ReadLines(@"E:\Bio Informatics\Assignment 2\Prog2-input-NM_032291-10exon-seqs.fa"))
{
if (ExonData.Contains(">"))
{
if (Pattern_Seq != string.Empty)
{
PatternData.Add(new KeyValuePair <string, string>(PatternID, Pattern_Seq));
Pattern_Seq = string.Empty;
}
PatternID = ExonData;
}
else
{
Pattern_Seq = ExonData;
}
}
PatternData.Add(new KeyValuePair <string, string>(PatternID, Pattern_Seq));
//Loop through List of query sequences and get Optimum Score and ending positions of optimum local alignment.
//For the string the required format mentioned below.
//>chr1.66999824.67000051.NM_032291_exon_0_0_chr1_66999825_f.+ len=227
//ref(1-10) = NNNNNNNNNN ; patern(1-10) = TTTCTCTCAG
//--- Optimum Smith-Waterman score = 454 (i=227, j=67000051)
foreach (KeyValuePair <string, string> PatternValue in PatternData)
{
//Forming string to show the output in required format.
string Header = PatternValue.Key + "\t len=" + PatternValue.Value.Length.ToString() + "\n";
string MiddleText = "ref(1-10) = " + RefSeq.Substring(0, 10) + " ; patern(1-10) = " + PatternValue.Value.Substring(0, 10) + "\n";
string score_indexText = SmithWatermanScore(RefSeq, PatternValue.Value);//calling SmithWatermanScore method
FinalText += Header + MiddleText + score_indexText;
}
//Store the output/complete result for all 10 exon sequences into Result.txt file.
File.WriteAllText(@"E:\Bio Informatics\Assignment 2\Result.txt", FinalText);
}
static void Main(string[] args)
{
string CHR1Data = string.Empty;
//Read bases from file and make it as string from array which will be used for masking non-exon region.
string[] lines = File.ReadAllLines(@"E:\Bio Informatics\Assignment 8\chr1.fa");
List <string> list = new List <string>(lines);
list.RemoveAt(0);
CHR1Data = string.Join("", list.ToArray());
////Program - 1\\\\
//Code below will collapse the exon regions
List <string> FinalData = new List <string>();
string Data = string.Empty;
int Start = 0;
int End = 0;
//Loop thru exon annotation file.
foreach (string ExonData in File.ReadAllLines(@"E:\Bio Informatics\Assignment 8\hg19-refseq-exon-annot-chr1_sorted"))
{
//Split each line to get details of each exon in exon annotation.
string[] ExonArray = ExonData.Split('\t');
//Check if current start value is same as previous start value then check current end is greater than
//previous end, if so then add entry into list with new end value.
if (ExonArray[1] == Start.ToString())
{
if (Convert.ToInt64(ExonArray[2]) >= End)
{
End = Convert.ToInt32(ExonArray[2]);
}
FinalData.RemoveAt(FinalData.Count - 1);
Data = "chr1\t" + Start.ToString() + "\t" + End.ToString() + "\t" + "X\t" + "0\t+";
FinalData.Add(Data);
}
else if (Convert.ToInt64(ExonArray[1]) <= End)
{
FinalData.RemoveAt(FinalData.Count - 1);
Data = "chr1\t" + Start.ToString() + "\t" + ExonArray[2] + "\t" + "X\t" + "0\t+";//End.ToString()
FinalData.Add(Data);
End = Convert.ToInt32(ExonArray[2]);
}
else
{
if (Convert.ToInt64(ExonArray[1]) >= Start && Convert.ToInt64(ExonArray[1]) <= End)
{
FinalData.RemoveAt(FinalData.Count - 1);
Data = "chr1\t" + Start.ToString() + "\t" + ExonArray[2] + "\t" + "X\t" + "0\t+";//End.ToString()
}
else
{
Data = ExonArray[0] + "\t" + ExonArray[1] + "\t" + ExonArray[2] + "\t" + "X" + "\t" + ExonArray[4] + "\t" + "+";
}
//Store start and end values for further use.
Start = Convert.ToInt32(ExonArray[1]);
End = Convert.ToInt32(ExonArray[2]);
FinalData.Add(Data);
}
}
//Convert list into string and place it into a file.
string CollapsedData = String.Join("\n", FinalData.ToList().ToArray());
File.WriteAllText(@"E:\Bio Informatics\Assignment 8\ExonCollapsedFile.txt", CollapsedData);
////Program - 2\\\\
//File will be created or used for writing new chr1 which contains masked non-exon region.
TextWriter tsw = new StreamWriter(@"E:\Bio Informatics\Assignment 8\Masked_chr1.fa");
tsw.Write(">chr1");
int indexValue = 0;
//Loop through the masked exon region data.
for (int j = 0; j < FinalData.Count; j++)
{
string data = string.Empty;
string[] ChangeData = FinalData[j].Split('\t');
int startIndex = Convert.ToInt32(ChangeData[1]);
//If index value less than start of exon then get substring from already saved chr1 and
//complement with N's. otherwise normal exon data will be picked and placed into a file.
if (indexValue < startIndex)
{
int length1 = startIndex - indexValue;
tsw.Write(ComplementBasesH(CHR1Data.Substring(indexValue, length1)));
}
//Write exon region data.
int endIndex = Convert.ToInt32(ChangeData[2]);
int length2 = endIndex - startIndex;
tsw.Write(CHR1Data.Substring(startIndex, length2));
//Populate end value in index value.
indexValue = endIndex;
}
//Close the text writer.
tsw.Close();
////Program - 3\\\\
//Initialize dictionary to store each Exon and its corresponding read count.
Dictionary <string, int> ExonReadData = new Dictionary <string, int>();
//Loop thru originial exon refseq file to find read count for each exon.
foreach (string ExonRefData in File.ReadAllLines(@"E:\Bio Informatics\Assignment 8\hg19-refseq-exon-annot-chr1_sorted"))
{
string[] ExonRefData_Array = ExonRefData.Split('\t');
string ExonName = ExonRefData_Array[3];
//Loop through the bowtie BED file fetched by mapping "ERR030893-1.fq" reads file onto Masked CHR1.
foreach (string BToutData in File.ReadAllLines(@"E:\Bio Informatics\Assignment 8\bowtie-0.12.7\BTout-BED-75_Modified_Sorted"))
{
string[] BToutData_Array = BToutData.Split('\t');
//Check if there exists Exon Name in dictionary and add 1 to the value.
if (ExonReadData.ContainsKey(ExonName))
{
//Add 1 to existing value for particular ExonID. If Map start and end are in range of Exon ID.
if ((Convert.ToInt32(BToutData_Array[1]) >= Convert.ToInt32(ExonRefData_Array[1])) &&
(Convert.ToInt32(BToutData_Array[2]) < Convert.ToInt32(ExonRefData_Array[2])))
{
ExonReadData[ExonName] = ExonReadData[ExonName] + 1;
}
}
else
{
//Add Exon ID and 1 as initial value. If Map start and end are in range of Exon ID.
if ((Convert.ToInt32(BToutData_Array[1]) >= Convert.ToInt32(ExonRefData_Array[1])) &&
(Convert.ToInt32(BToutData_Array[2]) < Convert.ToInt32(ExonRefData_Array[2])))
{
ExonReadData.Add(ExonName, 1);
}
}
}
}
//Initialize dictionary for gene level expression by having Gene ID and reads count.
Dictionary <string, int> GeneRead = new Dictionary <string, int>();
//Loop thru list of Exon data.
foreach (KeyValuePair <string, int> ExonRefValue in ExonReadData)
{
string GeneName = ExonRefValue.Key.Substring(0, ExonRefValue.Key.IndexOf("_e"));
//Check if there exists Gene Name in dictionary and add new value to the existing value.
if (GeneRead.ContainsKey(GeneName))
{
GeneRead[GeneName] = GeneRead[GeneName] + ExonRefValue.Value;
}
else
{
GeneRead.Add(GeneName, ExonRefValue.Value);
}
}
//Convert list into a string and write into a file.
String GeneD = String.Join("\n", GeneRead.ToArray());
GeneD = GeneD.Replace("[", "").Replace("]", "").Replace(',', '\t');
File.WriteAllText(@"E:\Bio Informatics\Assignment 8\GeneID_read.txt", GeneD);
}
