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;
+                         sh make.sh
+                         ./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 ########################### ##
+
+
+
+

Install.NJ.cn.md

@@ -0,0 +1,56 @@
+
+## 安装 PHYLIPNEW 记要
+
+要运行 PHYLIPNEW-3.69.650/bin/fconsense 须先安装<b> PHYLIPNEW-3.69.660 </b>，其步骤如下：
+
+### 第一步：下载
+	cd /public/software/
+        wget ftp://emboss.open-bio.org/pub/EMBOSS/EMBOSS-6.6.0.tar.gz   ./
+        wget ftp://emboss.open-bio.org/pub/EMBOSS/PHYLIPNEW-3.69.660.tar.gz ./
+	#在  ftp://emboss.open-bio.org/pub/EMBOSS/   里面下载好  EMBOSS-6.6.0.tar.gz  和 PHYLIPNEW-3.69.660.tar.gz
+
+
+### 第二步：安装EMBOSS ;
+	tar -xzvf EMBOSS-6.6.0.tar.gz   # 解压
+	cd  EMBOSS-6.6.0/    
+	./configure --prefix=/public/software/EMBOSS-6.6.0   # [prefix后面接的目录必须是你自己有权限的目录]
+	make 
+
+		##   其中这个软件依赖一些其他包，若系统没有就先安装之，在这打个比如，如报了少  缺libmysqlclient.so.*的库的错
+		##   那么请安装之，若有root:  运行： yum install mysql   ;  yum install mysql-devel即可以安装，若没有到自行安装
+		##   现别人已经安装好在这了： /gss1/App_dir/mariadb-10.1.26/bin/mysql  在 /gss1/App_dir/mariadb-10.1.26/lib/里面存在
+		##   libmysqlclient.*的，即可以直接加载环境变量就行   export LD_LIBRARY_PATH ;
+		##   在这运行：  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/gss1/App_dir/mariadb-10.1.26/lib/  [可写入： ~/.bashrc 里面，免得每次都要重新加载]
+
+	make install  
+
+### 第三步：安装好EMBOSS以后，安装PHYLIBNEW
+
+	tar -xzvf PHYLIPNEW-3.69.660.tar.gz   # 解压 
+	cp  -r /public/software/EMBOSS-6.6.0/lib/*        /public/software/PHYLIPNEW-3.69.650/lib/
+	cp  -r /public/software/EMBOSS-6.6.0/include/*    /public/software/PHYLIPNEW-3.69.650/include/
+	   # 在安装好EMBOSS后 即在 EMBOSS-6.6.0  里面有include 和lib 目录;
+	   # 将EMBOSS-6.60下include里的头文件和lib文件夹copy到 PHYLIBNEW下 [or 加载一些变量 export LD_LIBRARY_PATH ; CFLAGS="-I$prefix/include" ;  LDFLAGS="-L$prefix/ ]
+ 	./configure --prefix=/public/software/PHYLIPNEW-3.69.650  
+	make 
+
+		##  其中这个软件依赖一些其他包，若系统没有就先安装之，在这打个比例  报了少 LibXaw.soXX的库
+		##  在 https://www.x.org/archive/individual/lib/ 下载里面的 	libXaw-1.0.13.tar.gz ;
+		##  #解压 libXaw-1.0.13.tar.gz，./configure  --prefix=/public/software/PHYLIPNEW-3.69.650 (可以这个目录，免得又重新加载环境变量就行 
+		##  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/public/software/PHYLIPNEW-3.69.650/lib; 
+		##  make  ;make install;
+
+	make install
+
+### 第四步： 安装后好在 PHYLIPNEW-3.69.660/bin/fconsense 
+	 #但运行会报  少了在EMBOSS目录少了  fneighbor.acd 的文件
+  	 # 那么在 PHYLIPNEW-3.69.660 找之(find ./ -name fneighbor.acd),正常当在HYLIPNEW-3.69.650/emboss_acd下
+	mkdir  -p /public/software/EMBOSS-6.6.0/embassy/phylipnew/ ;
+	ln -s  /public/software/PHYLIPNEW-3.69.650/emboss_acd  /public/software/EMBOSS-6.6.0/embassy/phylipnew/emboss_acd
+	 # 创建目录 并链接  or 可以copy 
+
+### 其它信息
+ 若后面再运行报少了xxx.so\.*的话  把这个xxx.so.\*的路径找到并记录下来,直接在 \~/.bashrc加载之，export LD_LIBRARY_PATH=$export LD_LIBRARY_PATH:库所在路径
+ 如把 <b><i>export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/public/software/PHYLIPNEW-3.69.650/lib;  </i></b>写进  <b>\~/.bashrc</b>
+ 免得每次要用都重新加载之
+

Install.NJ.en.md

@@ -0,0 +1,57 @@
+# Install PHYLIPNEW
+
+ </br>To run <b>PHYLIPNEW-3.69.650/bin/fconsense</b> software, <b>PHYLIPNEW-3.69.660</b> must be installed first, and the steps are as follows:
+
+###  Step 1: Download
+	cd /public/software/
+	wget ftp://emboss.open-bio.org/pub/EMBOSS/EMBOSS-6.6.0.tar.gz   ./
+	wget ftp://emboss.open-bio.org/pub/EMBOSS/PHYLIPNEW-3.69.660.tar.gz ./
+	#Download EMBOSS-6.6.0.tar.gz and PHYLIPNEW-3.69.660.tar.gz at [ftp://emboss.open-bio.org/pub/EMBOSS/]
+
+
+###  Step 2: Install EMBOSS
+	tar -xzvf EMBOSS-6.6.0.tar.gz  # Unzip package
+	cd EMBOSS-6.6.0
+	./configure --prefix=/public/software/EMBOSS-6.6.0   #[You must have read and write permissions for this Dir]
+	make 
+
+		## This software depends on some other packages. If your system does not have one, install them first. For example, Error with a report missing [libmysqlclient.so.*] library
+		## then please install it, if you have root: Run:[ yum install mysql; yum install mysql-devel ] can be installed, if not, install it yourself.
+		## Now others have installed mysqlclient here: [/gss1/App_dir/mariadb-10.1.26/bin/mysql] and [libmysqlclient.*] exists in [/gss1/App_dir/mariadb-10.1.26/lib/]
+		## That is, you can load the environment variables directly [export LD_LIBRARY_PATH]
+		## Run here: [export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/gss1/App_dir/mariadb-10.1.26/lib/]  [Writable: ~/.bashrc inside, so as not to reload every time]
+
+	make install
+
+
+### Step 3: After installing EMBOSS, install PHYLIBNEW
+	tar -xzvf PHYLIPNEW-3.69.660.tar.gz   #Unzip package
+	cp  -r /public/software/EMBOSS-6.6.0/lib/*        /public/software/PHYLIPNEW-3.69.650/lib/
+	cp  -r /public/software/EMBOSS-6.6.0/include/*    /public/software/PHYLIPNEW-3.69.650/include/
+		# After successfully installing EMBOSS, there are [include] and [lib] directories in EMBOSS-6.6.0;
+		# Copy the header file and lib folder in include under EMBOSS-6.60 to PHYLIBNEW [or load some variables :export LD_LIBRARY_PATH; CFLAGS="-I$prefix/include"; LDFLAGS="-L$prefix/]
+	./configure --prefix=/public/software/PHYLIPNEW-3.69.650
+	make 
+
+		##  This software depends on some other library. If the system does not have it, install them first. Let’s make an analogy here. reporting less [LibXaw.so.*] library.
+		##  Then download [libXaw-1.0.13.tar.gz] in [https://www.x.org/archive/individual/lib/];
+		##  tar -zxvf libXaw-1.0.13.tar.gz; cd libXaw-1.0.13 ; ./configure  --prefix=/public/software/PHYLIPNEW-3.69.650 (This directory can be used to avoid reloading environment variables)
+		##  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/public/software/PHYLIPNEW-3.69.650/lib;
+		##  make ;make install;
+
+	make install
+
+
+### Step 4: Run PHYLIPNEW-3.69.660/bin/fconsense 
+	# After installation, the first run [PHYLIPNEW-3.69.660/bin/fconsense] will report that the [fneighbor.acd] file is missing in the EMBOSS directory.
+	# Then find it in PHYLIPNEW-3.69.660 Dir [find ./ -name fneighbor.acd], normally it will under Dir [HYLIPNEW-3.69.650/emboss_acd]
+	mkdir  -p /public/software/EMBOSS-6.6.0/embassy/phylipnew/ ;
+	ln -s  /public/software/PHYLIPNEW-3.69.650/emboss_acd  /public/software/EMBOSS-6.6.0/embassy/phylipnew/emboss_acd
+	# Create directory and link or copy
+
+
+### Other Info:
+  </br> If [xxx.so.\*] missing is report after running the software later, find and record the path of this [xxx.so.\*] and load it directly in \~/.bashrc, <i> export LD_LIBRARY_PATH=$export LD_LIBRARY_PATH:/Dir_Path_For_Thislibrary_located/;</i> 
+  </br> such  writing info <b><i>export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/public/software/PHYLIPNEW-3.69.650/lib;</i></b> to file <b>[\~/.bashrc]</b>; Avoid reloading every time you use it
+
+

README.md

@@ -1 +1,128 @@
 # VCF2Dis
+<b>VCF2Dis: A new simple and efficient software to calculate p-distance matrix based Variant Call Format</b>
+
+###  1) Install
+------------
+The <b>new version</b> will be updated and maintained in <b>[hewm2008/VCF2Dis](https://github.com/hewm2008/VCF2Dis)</b>, please click below Link to download the latest version
+</br><p align="center"><b>[hewm2008/VCF2Dis](https://github.com/hewm2008/VCF2Dis)</b></p>
+<b> [Download](https://github.com/hewm2008/VCF2Dis/archive/v1.50.tar.gz) </b>
+
+  </br> Just [make]  or [sh  make.sh ]  to compile this software.the final software can be found in the Dir <b>[bin/VCF2Dis]</b>
+  </br> For <b>linux /Unix </b> and <b>macOS</b>
+  <pre>
+        tar -zxvf  VCF2DisXXX.tar.gz            # if Link do not work ,Try <b>re-install</b> [zlib]library
+        cd VCF2DisXXX;                          # [zlib] and copy them to the library Dir
+        sh make.sh;                             # VCF2Dis-xx/src/include/zlib
+        ./bin/VCF2Dis
+  </pre>
+
+**Note:** If fail to link,try to <b>re-install</b> the libraries [**_zlib_**](https://zlib.net/)
+
+###  2) an Example of nj-tree with no boostrap
+------------
+* 1) Parameter description:
+```php
+	Usage: VCF2Dis -InPut  <in.vcf>  -OutPut  <p_dis.mat>
+
+		-InPut     <str>     Input one or muti GATK VCF genotype File
+		-OutPut    <str>     OutPut Sample p-Distance matrix
+
+		-InList    <str>     Input GATK muti-chr VCF Path List
+		-SubPop    <str>     SubGroup SampleList of VCFFile [ALLsample]
+		-Rand      <float>   Probability (0-1] for each site to join Calculation [1]
+		-KeepMF              Keep the Middle File diff & Use matrix
+
+		-help                Show more help [hewm2008 v1.50]
+
+```
+
+* 2) To Create the  p_distance matrix
+
+```
+# 2.1) To new all the sample p_distance matrix based VCF, run VCF2Dis directly
+      ./bin/VCF2Dis	-InPut	in.vcf.gz	-OutPut p_dis.mat
+      #  ./bin/VCF2Dis     -InPut  in.fa.gz	-OutPut p_dis.mat -InFormat  FA
+
+# 2.2) To new sub group sample p_distance matrix ; put their sample name into File sample.list
+      ./bin/VCF2Dis	-InPut	chr1.vcf.gz chr2.vcf.gz	-OutPut p_dis.mat  -SubPop  sample.list
+```
+
+* 3) construct nj-tree and present it (need deal with Other software)
+
+#### method 1
+   Choose one of **A/B**
+   </br> **A.** Upload the web [fneighbor(http://emboss.toulouse.inra.fr/cgi-bin/emboss/fneighbor?_pref_hide_optional=1)](http://emboss.toulouse.inra.fr/cgi-bin/emboss/fneighbor?_pref_hide_optional=1) ，the Click the **Run fneighbor** bottom . then you can get the output file **datafile.treefile**
+   </br> **B.**  Upload the <b>p_dis.mat</b> to the website [fastme (http://www.atgc-montpellier.fr/fastme/)](http://www.atgc-montpellier.fr/fastme/), select <b>Data Type</b> to the  <b>Distance matrix </b>,Click the bottom twist <b>execute & email results</b>. you will get the <b>p_dis_mat_fastme-tree.nwk</b> , and Email not mandatory;
+
+
+   Run  MEGA        #    The MEGA (http://www.megasoftware.net/) was used to present the phylogenetic tree based this file [p_dis_mat_fastme-tree.nwk]
+
+#### method 2
+   Use the PHYLIPNEW to construct nj-tree
+</br>How to Install PHYLIPNEW please Click on <b> [here](https://github.com/hewm2008/VCF2Dis/blob/main/Install.NJ.en.md)</b> or Click on <b>[here(Chinese)](https://github.com/hewm2008/VCF2Dis/blob/main/Install.NJ.cn.md)</b>
+```
+      #    3.1 Run  PHYLIP
+      #   After p_distance done , software PHYLIPNEW 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
+
+      #    3.2 Run  MEGA
+      #    The MEGA6 (http://www.megasoftware.net/) was used to present the phylogenetic tree based this file [tree.out2.tre]
+```
+* 4) you can see the neighbor-joining tree and save it as PDF format
+
+
+###  3) an Example of nj-tree with boostrap
+
+* 1) muti-run the nj-tree by using  put back sampling.
+To using the the part of the sites and new the nj-tree as above. Repeat For the <b>NN</b> times. X=(1,2....NN); 
+
+```
+    ./bin/VCF2Dis	-InPut	in.vcf.gz	-OutPut p_dis_X.mat    -Rand     0.25
+    PHYLIPNEW-3.69.650/bin/fneighbor  -datafile p_dis_X.matrix  -outfile tree.out1_X.txt -matrixtype s -treetype n -outtreefile tree.out2_X.tre 
+```
+
+* 2) merge the all the  put back sampling  NJ-tree and construct  boostrap nj-tree.
+
+```
+	cat   tree.out2_*.tre   >  ALLtree_merge.tre
+	PHYLIPNEW-3.69.650/bin/fconsense   -intreefile   ALLtree_merge.tre  -outfile out  -treeprint Y
+	perl  ./bin/percentageboostrapTree.pl    ALLtree_merge.treefile    NN    Final_boostrap.tre
+```
+* 3) construct nj-tree and present it (need deal with Other software)
+```
+      #    The MEGA6 (http://www.megasoftware.net/) was used to present the phylogenetic tree based this file Final_boostrap.tre] 
+```
+------------
+###  4) Introduction
+------------
+To new the p_distance matrix besed the VCF file. the more infomation about the p_distance matrix, see <b>[this website.](http://evolution.genetics.washington.edu/phylip/doc/distance.html)</b>
+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))]
+
+  </br> 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;
+```
+
+
+
+###  5) Results
+------------
+some NJ-tree images which I draw in the paper before.
+
+* [50 Rices NBT](http://www.nature.com/nbt/journal/v30/n1/images/nbt.2050-F1.jpg)
+* [31 soybeans  NG]( http://www.nature.com/ng/journal/v42/n12/images/ng.715-F1.jpg)
+
+###  6) Discussing
+------------
+- [:email:](https://github.com/hewm2008/VCF2Dis) hewm2008@gmail.com / hewm2008@qq.com
+- join the<b><i> QQ Group : 125293663</b></i>
+
+
+######################swimming in the sky and flying in the sea ########################### ##

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

exemple/sample.list

@@ -0,0 +1,6 @@
+S010
+S033
+S186
+S123
+S124
+S011