User:Lindenb/Notebook/UMR915/20101130

20101129        Top        20101201       

Thesis Stéphanie Chatel

Belgium

Working on belgium data.

script jrunscript sift

more jeter20101011a.js

importPackage(java.io);
importPackage(java.util.zip);
var f=new File("/GENOTYPAGE/data/project/belgium/20101007/XXXXXXXXXXXXXXXXXXXXXXX.csv.gz");
var input=new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(f))));
var line;
while((line=input.readLine())!=null)
  {
  if(!(line.startsWith("\"chr"))) continue;
  
  line=line.replaceAll("\"","").replace(" mapping","").replace(".","");
  var tokens=line.split("[;]");
  if(tokens[3].indexOf("SNP")==-1) continue;
  var bases=tokens[7].split("/");
  for(var i=0;i< bases.length;++i)
    {
    if(bases[i].equals(tokens[5])) continue;
    println(tokens[0].replace("chr","")+","+tokens[1]+",1,"+tokens[5]+"/"+bases[i]);
    }
  }

input.close();


f= new File("/GENOTYPAGE/data/project/belgium/XXXXXXXXXXXXXXXX/454AllDiffs.txt.gz");
input=new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(f))));
while((line=input.readLine())!=null)
  {
  if(!(line.startsWith(">chr"))) continue;

  var tokens=line.split("[\t]");
  if(!tokens[1].equals(tokens[2])) continue;
  if(tokens[3].equals("-") || tokens[4].length!=1) continue;
  println(tokens[0].replace(">chr","")+","+tokens[1]+",1,"+tokens[3]+"/"+tokens[4]);
  }

input.close();

polyphen

importPackage(java.io);
importPackage(java.util.zip);
var f=new File("/GENOTYPAGE/data/project/belgium/20101007/XXXXXXXXXXXXXXXXXXXXXX.csv.gz");
var input=new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(f))));
var line;
while((line=input.readLine())!=null)
  {
if(!(line.startsWith("\"chr"))) continue;
  
  line=line.replaceAll("\"","").replace(" mapping","").replace(".","");
  var tokens=line.split("[;]");
  if(tokens[3].indexOf("SNP")==-1) continue;
  var bases=tokens[7].split("/");
   for(var i=0;i< bases.length;++i)
    {
    if(bases[i].equals(tokens[5])) continue;
    println(tokens[0]+":"+tokens[1]+"\t"+tokens[5]+"/"+bases[i]);
    }
  }

input.close();


f= new File("/GENOTYPAGE/data/project/belgium/XXXXXX/454AllDiffs.txt.gz");
input=new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(f))));
while((line=input.readLine())!=null)
  {
  if(!(line.startsWith(">chr"))) continue;

  var tokens=line.split("[\t]");
  if(!tokens[1].equals(tokens[2])) continue;
  if(tokens[3].equals("-") || tokens[4].length!=1) continue;
  println(tokens[0].replace(">","")+":"+tokens[1]+"\t"+tokens[3]+"/"+tokens[4]);
  }

input.close();