code

INSTALL.txt

@@ -0,0 +1,44 @@
+
+VCF2Dis: A new simple and efficient software to calculate p-distance matrix based Variant Call Format
+
+
+1)  Introduction
+------------
+
+This software relies on two other library packages [zlib]
+
+----------------------  zlib   infomation ----------------------------
+If  Lib [zlib] do not work
+you can download form this website and install it
+http://www.zlib.net/
+
+
+2) linux/Unix/MacOS INSTALL
+--------------------------------------
+
+Just execute as follows :
+                         tar -zxvf  VCF2DisXXX.tar.gz
+                         cd VCF2DisXXX.tar.gz;
+                         make ; make clean
+                         ./bin/VCF2Dis
+
+#Note: If fail to link,try to re-install the libraries zlib
+#if Link do not work ,try Re-install the zlib librarys and copy them to the library Dir
+
+                     VCF2Dis-xx/src/include/zlib 
+
+
+#step3  : 
+sh make.sh # or [make && make clean]
+
+4) Contact
+email: hewm2008@gmail.com / hewm2008@qq.com
+join the QQ Group : 125293663
+
+
+
+######################swimming in the sky and flying in the sea ########################### ##
+
+
+
+

Makefile

@@ -0,0 +1,15 @@
+CXX=g++
+CXXFLAGS= -g  -O2
+BIN := ./bin
+LDFLAGS=-lz 
+INCLUDE=-L./src/zlib/
+all: $(BIN)/VCF2Dis
+
+$(BIN)/VCF2Dis: $(BIN)/../src/VCF2Dis.o 
+	$(CXX)   $^ -o $@   $(LDFLAGS)  $(INCLUDE) 
+
+$(BIN)/%.o: %.cpp
+	$(CXX)  -c $(CXXFLAGS) $< -o $@    $(INCLUDE) 
+
+clean:
+	$(RM) $(BIN)/*.o  $(BIN)/../src/*.o

Readme

@@ -0,0 +1,56 @@
+
+1 Introduction   (  VCF2Dis version   <1.20)
+
+	To new the p_distance matrix besed the VCF file. the more infomation
+  about the  p_distance matrix ,see this website:
+  http://evolution.genetics.washington.edu/phylip/doc/distance.html
+
+  The VCF SNPs datasets were used to calculate p-distance between individuals, according to the follow formula to operate the sample i and sample j genetic distance:
+
+                D_ij=(1/L) * [(sum(d(l)_ij))]
+
+   Where L is the length of regions where SNPs can be identified, and given the alleles at position l are A/C:
+        d(l)_ij=0.0     if the genotypes of the two individuals were AA and AA;
+        d(l)_ij=0.5     if the genotypes of the two individuals were AA and AC;
+        d(l)_ij=0.0     if the genotypes of the two individuals were AC and AC;
+        d(l)_ij=1.0     if the genotypes of the two individuals were AA and CC;
+        d(l)_ij=0.0     if the genotypes of the two individuals were CC and CC;
+
+  After p_distance done , software PHYLIP 3.69 (http://evolution.genetics.washington.edu/phylip.html) ,with neighbor-joining method can was used to construct the phylogenetic tree on the basis of this  p_distance matrix;
+       PHYLIPNEW-3.69.650/bin/fneighbor  -datafile p_dis.matrix  -outfile tree.out1.txt -matrixtype s -treetype n -outtreefile tree.out2.tre
+ The MEGA6 (http://www.megasoftware.net/) was used to present the phylogenetic tree based this file [tree.out2.tre].
+
+
+2 Install
+
+  Just  [make]  or [sh  make.sh ]  to compile this software.
+  the final software can be found in the Dir [bin/VCF2Dis]
+
+
+3
+
+  3.1 Parameter description:
+		Usage: VCF2Dis -InPut  <in.vcf>  -OutPut  <p_dis.mat>
+
+		-InPut     <str>     Input GATK VCF genotype File
+		-OutPut    <str>     OutPut Sample p-Distance matrix
+
+		-SubPop    <str>     SubGroup SampleList of VCFFile [ALLsample]
+		-KeepMF              Keep the Middle File diff & Use matrix
+
+		-help                Show more help [hewm2008 v1.10]
+
+ 3.2 To new all the sample p_distance matrix based VCF, run VCF2Dis directly
+
+       ./bin/VCF2Dis	-InPut	in.vcf.gz	-OutPut p_dis.mat
+
+ 3.3 To new sub group sample p_distance matrix ; Pput their sample name into File sample.list
+
+      ./bin/VCF2Dis	-InPut	in.vcf.gz	-OutPut p_dis.mat  -SubPop  sample.list
+
+
+
+4 Discussing
+  email: hewm2008@gmail.com / hewm2008@qq.com
+  join the QQ Group : 125293663
+

bin/percentageboostrapTree.pl

@@ -0,0 +1,79 @@
+#!/usr/bin/perl -w
+use strict;
+#explanation:this program is edited to 
+#edit by hewm;   Wed Feb 20 11:02:07 HKT 2019
+#Version 1.0    hewm@genomics.org.cn 
+
+die  "Version 1.0\t2019-02-20;\nUsage: $0 <merge.tre><RepeatTime><boostrap.tre>\n" unless (@ARGV ==3);
+
+#############Befor  Start  , open the files ####################
+
+open (IA,"$ARGV[0]") || die "input file can't open $!";
+my $TotalRepeat=$ARGV[1];
+open (OA,">$ARGV[2]") || die "output file can't open $!" ;
+
+################ Do what you want to do #######################
+$/=";";
+
+	while(<IA>) 
+	{
+		$_=~s/\n//g;
+		next if ($_ eq "");
+		my $Start=0;
+		my $Now=$Start;
+		my $Ttue=1;
+		my $Str=$_ ;
+
+		while($Ttue==1)
+		{
+			$Now=index($Str,":",$Start);
+			if  ($Now==-1)
+			{
+				$Ttue=0;
+			}
+			else
+			{
+				my $Length=$Now-$Start;
+				my $AAA=substr($Str,$Start,$Length);
+					$Start=$Now+1;
+				my $NowA=index($Str,",",$Start);
+				my $NowB=index($Str,")",$Start);
+				if  ($NowA!=-1  &&  $NowB!=-1)
+				{
+					if  ($NowA>$NowB)
+					{
+						$Now=$NowB;
+					}
+					else
+					{
+						$Now=$NowA;
+					}
+				}
+				elsif  ($NowA==-1  &&  $NowB==-1)
+				{
+					print "bad Format,some thing wrong!!!\n";
+				}
+				elsif  ($NowA==-1  &&  $NowB!=-1)
+				{
+					$Now=$NowB;
+				}
+				elsif   ($NowA!=-1  &&  $NowB==-1)
+				{
+					$Now=$NowA;					
+				}
+					$Length=$Now-$Start;
+				my $BBB=substr($Str,$Start,$Length);
+				   $BBB=sprintf ("%.1f",$BBB*100.0/$TotalRepeat);
+				   $Start=$Now;
+				 print OA "$AAA:$BBB"
+			}
+		}
+		my $Length=length($Str);
+		my $BBB=substr($Str,$Start,$Length);
+		 print OA  "$BBB\n";
+	}
+$/="\n";
+close IA;
+close OA ;
+
+######################swimming in the sky and flying in the sea ###########################

exemple/Run.sh

@@ -0,0 +1,9 @@
+#!/bin/sh
+#$ -S /bin/sh
+#Version1.0	hewm@genomics.org.cn	2017-06-13
+echo Start Time : 
+date
+../bin/VCF2Dis	-InPut	in.vcf.gz	-OutPut p_dis.mat
+#../bin/VCF2Dis	-InPut	in.vcf.gz	-OutPut p_dis.mat  -SubPop  sample.list
+echo End Time : 
+date