protected void SendBAMs(List <string> fNames)
{
AllBAMPairs.Clear();
MainData.LoadedSeqs = 0;
ProgramState.LoadedSamples = false;
ProgramState.BAMLoadLock = false;
foreach (string st in fNames)
{
MainData.UpdateLog("Reading " + MainData.MainWindow.MaxLenString(st, 20) + " to Sample ID -- \"" + ID + "\" -- ", true);
if (AppSettings.Loading.LOAD_SEQ_NAMES.Item)
{
LoadBAMNameFile(st);
}
else
{
LoadBAMFile(st);
}
}
if (AllBAMPairs.Count > 0)
{
HasBAM = true;
}
MainData.UpdateLog("Assigning -- \"" + ID + "\" -- sample reads to all annotated regions..", true);
MainData.Genome.SendReads(AllBAMPairs);
MainData.UpdateLog("Assignment of: " + MainData.LoadedSeqs.ToString() + " seqs complete", true);
ProgramState.LoadedSamples = true;
ProgramState.BAMLoadLock = true;
AllBAMPairs.Clear();
}
protected void OnSave(object sender, EventArgs e)
{
bool success = true;
double x, y;
model.Axes [0].Title = xAxisEntry.Text;
model.Axes [1].Title = yAxisEntry.Text;
model.Title = titleEntry.Text;
if (!double.TryParse(xScaleEntry.Text, out x))
{
success = false;
}
if (!double.TryParse(yScaleEntry.Text, out y))
{
success = false;
}
if (fileEntry.Text.Length < 2)
{
success = false;
}
if (!success)
{
MainData.ShowMessageWindow("Unable to verify field entries, x & y are numbers, and you need a file location!", false);
}
else
{
SaveToPdf(fileEntry.Text, x, y);
MainData.UpdateLog("Success!\nSaved Pdf to: " + fileEntry.Text, false);
this.Destroy();
}
}
protected void LoadBAMNameFile(string fileName)
{
int count = 0;
using (StreamReader st = new StreamReader(fileName)) {
string line = "";
while ((int)'@' == st.Peek())
{
st.ReadLine();
}
while ((line = st.ReadLine()) != null)
{
string[] spstrs = line.Split('\t');
if (spstrs [2].Length > 2 && spstrs.Length >= 10)
{
int start = int.Parse(spstrs [3]);
NameRead sq = new NameRead(this, start, spstrs [9].Length + start, spstrs[0]);
AllBAMPairs.Add(new SeqScaffPair(spstrs [2], sq));
count++;
if (count % 1000000 == 0)
{
int tot = count / 1000000;
MainData.UpdateLog("Read " + tot + "M seqs from " + MainData.MainWindow.MaxLenString(fileName, 20), true);
}
}
}
}
//Parallel.ForEach(lines, x =>
// {
// ProcessLines(x);
// });
}
public void LoadGenomeLongSeq(string _fileName)
{
bool lite = AppSettings.Loading.GEN_LITE_LOAD.Item;
FileName = _fileName;
Scaffolds.Clear();
long count = 0;
string line = "";
string sequence = "";
string id = "";
//long modulo = MainData.ScanFileForModulo (_fileName, 10);
long nextMark = 50000000;
long markIncrement = 50000000;
int markCnt = 0;
count = 0;
MainData.UpdateLog("Reading...", true);
using (StreamReader sr = new StreamReader(_fileName)) {
while (!sr.EndOfStream)
{
line = sr.ReadLine();
if (line.Length < 3)
{
continue;
}
else if (line.StartsWith(">"))
{
id = line.TrimStart('>');
GENApplyOptionsToID(ref id);
}
else
{
sequence = line;
Scaffolds.Add(id, (new Scaffold(id, ref sequence, lite)));
count += sequence.Length;
}
if (count > nextMark)
{
markCnt++;
nextMark += markIncrement;
MainData.UpdateLog("Read " + (markCnt * 50).ToString() + " mega-bases from genome..", true);
}
}
}
long finalCnt = count / 1000000;
MainData.UpdateLog("Read " + finalCnt.ToString() + " mega-bases in total.", true);
}
public static long ScanFileForModulo(string fileName, int division)
{
int count = 0;
MainData.UpdateLog("Scanning " + ShortFileName(fileName) + "...", true);
using (StreamReader sr = new StreamReader(fileName)) {
while ((sr.ReadLine()) != null)
{
count++;
}
}
return(count / division);
}
private static void RunAndWait <T>(List <Thread> lt, List <T> Content)
{
int tmax = AppSettings.Processing.MAX_THREADS.Item;
MainData.UpdateLog("Running func with " + tmax + " threads...", true);
int it = 0;
foreach (Thread t in lt)
{
t.Start((object)Content[it]);
it++;
}
foreach (var thread in lt)
{
thread.Join();
}
lt.Clear();
Content.Clear();
}
protected static void LoadAllVars()
{
AllVarPairs.Clear();
MainData.LoadedVars = 0;
ProgramState.LoadedVariants = false;
ProgramState.VariantLoadLock = false;
foreach (KeyValuePair <string, BioSample[]> kvp in LatestVarColIndexed)
{
LoadVarFile(kvp.Key, kvp.Value, IsGenotypedNames [kvp.Key]);
}
MainData.UpdateLog("Assigning Variants to annotation elements..", true);
MainData.Genome.SendVars(AllVarPairs);
MainData.UpdateLog("Assignment of: " + MainData.LoadedVars.ToString() + " variants complete", true);
ProgramState.LoadedVariants = true;
ProgramState.VariantLoadLock = true;
hasVarSomethingToLoad = false;
AllVarPairs.Clear();
}
protected static void LoadAllFKPMS()
{
AllFKPMS.Clear();
MainData.LoadedFKPM = 0;
ProgramState.LoadedFPKM = false;
ProgramState.FKPMLoadLock = false;
foreach (KeyValuePair <string, BioSample[]> kvp in LatestFKPMColIndexed)
{
LoadFKPMFile(kvp.Key, kvp.Value);
}
MainData.UpdateLog("Assigning FKPM scores to genes..", true);
MainData.Genome.SendFKPMS(AllFKPMS);
MainData.UpdateLog("Assignment of: " + MainData.LoadedFKPM.ToString() + " fkpm scores complete", true);
ProgramState.LoadedFPKM = true;
ProgramState.FKPMLoadLock = true;
hasFKPMSomethingToLoad = false;
AllFKPMS.Clear();
}
protected static void LoadVarFile(string fName, BioSample [] samps, bool genotyped)
{
char[] seps = { '/', '|' };
int count = 0;
using (StreamReader sr = new StreamReader(fName)) {
while ((int)'#' == sr.Peek())
{
sr.ReadLine();
}
string[] spstrs;
string line;
while ((line = sr.ReadLine()) != null)
{
spstrs = line.Split('\t');
if (spstrs [6] == "PASS")
{
Variant v;
string[] sps = spstrs [4].Split(',');
if (sps.Length == 1)
{
v = new Variant(int.Parse(spstrs [1]), spstrs [3], spstrs [4]);
}
else if (sps.Length == 2)
{
v = new Variant(int.Parse(spstrs [1]), spstrs [3], sps [0], sps [1]);
}
else
{
v = new Variant(int.Parse(spstrs [1]), spstrs [3], sps [0], sps [1], sps [2]);
}
if (genotyped)
{
int genLen = spstrs.Length;
int stInd = 9;
for (int i = stInd; i < genLen; i++)
{
bool parsed = true;
string[] sps2 = spstrs [i].Split(':');
string[] sps3 = sps2 [0].Split(seps);
int ma = 0;
int al = 0;
if (!int.TryParse(sps3 [0], out ma))
{
parsed = false;
}
if (sps3.Length > 1)
{
if (!int.TryParse(sps3 [1], out al))
{
parsed = false;
}
}
if (parsed)
{
SampleVariant s = new SampleVariant(ma, al, samps [i - stInd]);
v.AddSampleVars(s);
}
}
}
AllVarPairs.Add(new VarScaffPair(spstrs [0], v));
count++;
if (count % 100000 == 0)
{
int tot = count / 100000;
MainData.UpdateLog("Read " + tot + "00K variants from " + MainData.MainWindow.MaxLenString(fName, 20), true);
}
}
}
}
}
public static void WriteDataFile(string fileName, NumericalText nt)
{
if (((nt.Data != null) && (nt.Data.Count > 0)) || ((nt.Tags != null) && (nt.Tags.Count > 0)))
{
int useLen = Math.Min(nt.Titles.Count, (nt.Data.Count + nt.Tags.Count));
int dataLen = nt.Data [0].Count;
List <int> counts = new List <int> ();
List <int> currentIndexes = new List <int> ();
List <PrintOutNext> printTypes = new List <PrintOutNext> ();
if (nt.Tags != null)
{
int tagInd = 0;
foreach (List <string> sl in nt.Tags)
{
counts.Add(sl.Count - 1);
printTypes.Add(PrintOutNext.Tag);
dataLen = Math.Max(dataLen, sl.Count);
currentIndexes.Add(tagInd);
tagInd++;
}
}
if (nt.Data != null)
{
int datInd = 0;
foreach (List <Double> ld in nt.Data)
{
counts.Add(ld.Count - 1);
printTypes.Add(PrintOutNext.Data);
dataLen = Math.Max(dataLen, ld.Count);
currentIndexes.Add(datInd);
datInd++;
}
}
using (StreamWriter sw = new StreamWriter(fileName)) {
for (int i = 0; i < useLen; i++)
{
if (i > 0)
{
sw.Write("\t");
}
sw.Write(nt.Titles [i]);
}
sw.Write("\n");
for (int j = 0; j < dataLen; j++)
{
for (int i = 0; i < useLen; i++)
{
if (i > 0)
{
sw.Write("\t");
}
if (counts [i] >= j)
{
if (printTypes [i] == PrintOutNext.Data)
{
sw.Write(nt.Data [currentIndexes[i]] [j]);
}
else
{
sw.Write(nt.Tags [currentIndexes [i]] [j]);
}
}
else
{
sw.Write("x");
}
}
sw.Write("\n");
}
}
MainData.UpdateLog("Saved " + MainData.MainWindow.MaxLenString(fileName, 20), false);
}
else
{
MainData.ShowMessageWindow("There isn't any data there to save!", false);
}
}
public void LoadGFF3(string fileName)
{
string idTag = AppSettings.Loading.GFF3_ID_TAG.Item;
int tagSize = idTag.Length;
string line = "";
string parentTag = "arent=";
int pTagSize = parentTag.Length;
int count = 0;
long modulo = MainData.ScanFileForModulo(fileName, 5);
long lineCount = modulo * 5;
MainData.UpdateLog("Reading... ", true);
char[] spChar = { '\t' }; char[] spChar2 = { ';' };
using (StreamReader sr = new StreamReader(fileName)) {
while ((line = sr.ReadLine()) != null)
{
if (line.Length > 10)
{
string[] spstr = line.Split(spChar, 10);
string[] spstr2 = spstr [8].Split(spChar2, 20);
string ID = "";
string pID = "";
foreach (string st in spstr2)
{
if (st.Contains(idTag))
{
ID = st;
break;
}
}
foreach (string st in spstr2)
{
if (st.Contains(parentTag))
{
pID = st;
break;
}
}
ID = ID.Substring(tagSize);
GFF3ApplyOptionsToID(ref ID);
if (pID != "")
{
GFF3ApplyOptionsToID(ref pID);
}
Sense sn = Sense.Sense;
if (spstr [6].Equals("-"))
{
sn = Sense.AntiSense;
}
else if (spstr [6].Equals("."))
{
sn = Sense.None;
}
string nameOfType = ID + "#" + spstr [2] + "#" + pID;;
int sta, end;
bool A = int.TryParse(spstr [3], out sta);
bool B = int.TryParse(spstr [4], out end);
if (A && B)
{
if (Scaffolds.ContainsKey(spstr [0]))
{
Scaffolds [spstr [0]].SendComponent(nameOfType, sta, end, sn);
}
else
{
throw new Exception("Gff3 references scaffold not found in genome!");
}
}
}
count++;
if (count % modulo == 0)
{
long perc = (long)(((float)count / (float)lineCount) * 100);
MainData.UpdateLog("Read " + perc + "% of gff3..", true);
}
}
}
if (AppSettings.Genes.GENERATE_ANY_PROMO.Item || AppSettings.Genes.GENERATE_FLANK3.Item)
{
MainData.UpdateLog("Generating GFF3 additional elements as described in Settings -> Genes", true);
foreach (KeyValuePair <string, Scaffold> kvp in Scaffolds)
{
kvp.Value.RunGenePostLoad();
}
}
}