V1.0.7 is ready

mjoppich · Sep 8, 2012 · 202e87a · 202e87a
1 parent 0f2191f
commit 202e87a
Show file tree

Hide file tree

Showing 7 changed files with 25 additions and 20 deletions.
diff --git a/DataProcessor.hpp b/DataProcessor.hpp
@@ -426,7 +426,8 @@ void loadGeneReadCounts(string from_file, vector<string>& gene_sym, vector<int>&
 
         gene_sym.push_back(fields[0]);
         read_counts.push_back(atoi(fields[1].data()));
-	gene_length.push_back(atoi(fields[2].data()));
+        if (fields.size() > 2)
+            gene_length.push_back(atoi(fields[2].data()));
     }
 
     if (verbos_level > 0)

diff --git a/GFOLD.hpp b/GFOLD.hpp
@@ -92,7 +92,7 @@ class GFOLD
     {
         mFirstGroupCnt = first_group_samples.size();
 
-	vector<int> gene_length;
+        vector<int> gene_length;
         vector<vector<int> > first_group_gene_read_counts;
         vector<vector<int> > second_group_gene_read_counts;
 

diff --git a/Makefile b/Makefile
@@ -1,4 +1,4 @@
-VERSION = V1.0.6
+VERSION = V1.0.7
 package=gfold.$(VERSION)
 packagename=gfold.$(VERSION).tar.gz 
 

diff --git a/README b/README
@@ -1,6 +1,10 @@
 Note that https://bitbucket.org/feeldead/gfold/ may have updated README file
 
 VERSIONS:
+V1.0.7. More explanation about input/output is added in the documentation. A
+tiny change is made in the source code such that GFOLD can safely accept
+read counts not generated by job 'count'.
+
 V1.0.6. A more comprehensive installation instruction is added. GTF format is
 set to default. RPKM is added in the 'count' output.
 

diff --git a/doc/gfold.html b/doc/gfold.html
@@ -2,7 +2,7 @@
 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
-<title>GFOLD V1.0.6</title>
+<title>GFOLD V1.0.7</title>
 <link rel="stylesheet" href="gfold.css" type="text/css" />
 <meta http-equiv="content-type" content="text/html; charset=utf-8" />
 <link rev="made" href="mailto:assp@beta.macosforge.org" />
@@ -12,7 +12,7 @@
 <table border="0" width="100%" cellspacing="0" cellpadding="3">
 <tr><td width="10%" class="block" align="left"> <img align=center src="gfold.png"></img> </td>
 <td class="block" valign="middle">
-<big><strong><span class="block">&nbsp;GFOLD V1.0.6</span></strong></big>
+<big><strong><span class="block">&nbsp;GFOLD V1.0.7</span></strong></big>
 </td></tr>
 </table>
 
@@ -154,10 +154,10 @@ <h1><a name="jobs">JOBS</a></h1>
 <strong>count</strong> as the input. Please refer to the output format of <strong>count</strong> for more
 information about the input format. If you are not satisfied with the strategy
 adopted by <strong>count</strong>, you can generate gene read counts by yourself. The input for <strong>diff</strong>
-should at least contain the first two columns of the output of <strong>count</strong> and the orders
-of gene names are the same for different samples. If the third column of the output of <strong>count</strong> 
-(gene length) is missed, RPKM in the output of <strong>diff</strong> will not be generated. <strong>diff</strong>
-does not use the forth column of the output of <strong>count</strong>, the RPKM.</p>
+should contain at least the first two columns of the output of <strong>count</strong> and the orders
+of gene names are the same for different samples. The third column of the output of <strong>count</strong> 
+(gene length) only influences the RPKM in the output of <strong>diff</strong>. If it is missing, RPKM 
+will not be generated by <strong>diff</strong>. <strong>diff</strong> does not use the forth column of the output of <strong>count</strong>.</p>
 </dd>
 </dl>
 <p>
@@ -213,8 +213,8 @@ <h1><a name="options">OPTIONS</a></h1>
 <dt><strong><a name="acc_t_f" class="item"><strong>-acc</strong> &lt;T/F&gt;</a></strong></dt>
 
 <dd>
-<p>When no replicate is available, whether to use accurate method to calculate GFOLD value. T stands for accurate, F stands for MCMC.
-Default T. For job <strong>diff</strong> only.</p>
+<p>When no replicate is available, whether to use accurate method to calculate GFOLD value. T stands for accurate which depends on
+sequencing depth and slower, F stands for MCMC.  Default T. For job <strong>diff</strong> only.</p>
 </dd>
 <dt><strong><a name="o_file" class="item"><strong>-o</strong> &lt;file&gt;</a></strong></dt>
 
@@ -364,7 +364,7 @@ <h1><a name="author">AUTHOR</a></h1>
 <p>Jianxing Feng (<a href="mailto:jianxing.tongji@gmail.com">jianxing.tongji@gmail.com</a>)</p>
 <table border="0" width="100%" cellspacing="0" cellpadding="3">
 <tr><td class="block" valign="middle">
-<big><strong><span class="block">&nbsp;GFOLD V1.0.6</span></strong></big>
+<big><strong><span class="block">&nbsp;GFOLD V1.0.7</span></strong></big>
 </td></tr>
 </table>
 

diff --git a/doc/gfold.pod b/doc/gfold.pod
@@ -113,10 +113,10 @@ For each gene, calculate GFOLD value and other statistics. B<diff> accepts the o
 B<count> as the input. Please refer to the output format of B<count> for more
 information about the input format. If you are not satisfied with the strategy
 adopted by B<count>, you can generate gene read counts by yourself. The input for B<diff>
-should at least contain the first two columns of the output of B<count> and the orders
-of gene names are the same for different samples. If the third column of the output of B<count> 
-(gene length) is missed, RPKM in the output of B<diff> will not be generated. B<diff>
-does not use the forth column of the output of B<count>, the RPKM.
+should contain at least the first two columns of the output of B<count> and the orders
+of gene names are the same for different samples. The third column of the output of B<count> 
+(gene length) only influences the RPKM in the output of B<diff>. If it is missing, RPKM 
+will not be generated by B<diff>. B<diff> does not use the forth column of the output of B<count>.
 
 =back
 
@@ -172,8 +172,8 @@ OK even for the strand specific case. For job B<count> only.
 
 =item B<-acc> <T/F>
 
-When no replicate is available, whether to use accurate method to calculate GFOLD value. T stands for accurate, F stands for MCMC.
-Default T. For job B<diff> only.
+When no replicate is available, whether to use accurate method to calculate GFOLD value. T stands for accurate which depends on
+sequencing depth and slower, F stands for MCMC.  Default T. For job B<diff> only.
 
 =item B<-o> <file>
 

diff --git a/main.cc b/main.cc
@@ -25,8 +25,8 @@
 #include "GFOLD.hpp"
 #include "Utility.hpp"
 
-#define VERSION "V1.0.6"
-#define DATE "Sat Sep  1 06:46:02 CST 2012"
+#define VERSION "V1.0.7"
+#define DATE "Sat Sep  8 20:57:01 CST 2012"
 
 
 using namespace std;