RELEASE_NOTES.txt

+RELEASE NOTES FOR FastQC v0.11.8
+--------------------------------
+
+This release works around some edge cases in unusual sequence libraries
+and changes the behaviour of the read length module when run with the
+--nogroup option. Other minor fixes are also present.
+
+
 RELEASE NOTES FOR FastQC v0.11.7
 --------------------------------
 

debian/changelog

+fastqc (0.11.8+dfsg-1) unstable; urgency=medium
+
+  * New upstream release.
+
+  * Standards-Version: 4.2.1
+
+ -- Steffen Moeller <moeller@debian.org>  Wed, 17 Oct 2018 19:25:09 +0200
+
 fastqc (0.11.7+dfsg-1) unstable; urgency=medium
 
   [ Steffen Moeller ]

debian/control

@@ -12,7 +12,7 @@ Build-Depends: debhelper (>= 11~),
                libhtsjdk-java,
                libjbzip2-java,
                libcommons-math3-java
-Standards-Version: 4.1.4
+Standards-Version: 4.2.1
 Vcs-Browser: https://salsa.debian.org/med-team/fastqc
 Vcs-Git: https://salsa.debian.org/med-team/fastqc.git
 Homepage: http://www.bioinformatics.babraham.ac.uk/projects/fastqc/

debian/patches/drop-fast5.patch

@@ -13,8 +13,10 @@ Description: HDF5 1.10 is about to transition into unstable, and unfortunately
  poretools, I propose to temporarily drop fast5 support from FastQC
  to avoid a removal from testing.
 
---- a/fastqc
-+++ b/fastqc
+Index: fastqc/fastqc
+===================================================================
+--- fastqc.orig/fastqc
++++ fastqc/fastqc
 @@ -74,7 +74,6 @@ my $quiet;
  my $nogroup;
  my $expgroup;
@@ -46,7 +48,7 @@ Description: HDF5 1.10 is about to transition into unstable, and unfortunately
                      (including being gzipped and ending with .gz) otherwise they
                      won't be grouped together correctly.
                      
--    --nano          Files come from naopore sequences and are in fast5 format. In
+-    --nano          Files come from nanopore sequences and are in fast5 format. In
 -                    this mode you can pass in directories to process and the program
 -                    will take in all fast5 files within those directories and produce
 -                    a single output file from the sequences found in all files.                    
@@ -54,7 +56,9 @@ Description: HDF5 1.10 is about to transition into unstable, and unfortunately
      --nofilter      If running with --casava then don't remove read flagged by
                      casava as poor quality when performing the QC analysis.
                     
---- a/uk/ac/babraham/FastQC/Sequence/Fast5File.java
+Index: fastqc/uk/ac/babraham/FastQC/Sequence/Fast5File.java
+===================================================================
+--- fastqc.orig/uk/ac/babraham/FastQC/Sequence/Fast5File.java
 +++ /dev/null
 @@ -1,107 +0,0 @@
 -/**
@@ -164,8 +168,10 @@ Description: HDF5 1.10 is about to transition into unstable, and unfortunately
 -	}
 -
 -}
---- a/uk/ac/babraham/FastQC/Sequence/SequenceFactory.java
-+++ b/uk/ac/babraham/FastQC/Sequence/SequenceFactory.java
+Index: fastqc/uk/ac/babraham/FastQC/Sequence/SequenceFactory.java
+===================================================================
+--- fastqc.orig/uk/ac/babraham/FastQC/Sequence/SequenceFactory.java
++++ fastqc/uk/ac/babraham/FastQC/Sequence/SequenceFactory.java
 @@ -99,9 +99,9 @@ public class SequenceFactory {
  			// We default to using all reads
  			return new BAMFile(file,false);

debian/patches/fastqc.patch

 From: Steffen Moeller <moeller@debian.org>
 Subject: Ensure proper CLASSPATH according to location of Debian JARs
 
---- a/fastqc
-+++ b/fastqc
+Index: fastqc/fastqc
+===================================================================
+--- fastqc.orig/fastqc
++++ fastqc/fastqc
 @@ -33,16 +33,15 @@ if (-e "$RealBin/uk/ac/babraham/FastQC/F
  }
  
@@ -36,9 +38,3 @@ Subject: Ensure proper CLASSPATH according to location of Debian JARs
  }
  
  __DATA__
-@@ -405,4 +404,3 @@ BUGS
-     Any bugs in fastqc should be reported either to simon.andrews@babraham.ac.uk
-     or in www.bioinformatics.babraham.ac.uk/bugzilla/
-                    
--    
-\ No newline at end of file

fastqc

@@ -327,7 +327,7 @@ DESCRIPTION
                     (including being gzipped and ending with .gz) otherwise they
                     won't be grouped together correctly.
                     
-    --nano          Files come from naopore sequences and are in fast5 format. In
+    --nano          Files come from nanopore sequences and are in fast5 format. In
                     this mode you can pass in directories to process and the program
                     will take in all fast5 files within those directories and produce
                     a single output file from the sequences found in all files.                    

run_fastqc.bat

-java -Xmx250m -classpath .;./sam-1.103.jar;./jbzip2-0.9.jar uk.ac.babraham.FastQC.FastQCApplication
+java -Xmx250m -classpath .;./sam-1.103.jar;./jbzip2-0.9.jar uk.ac.babraham.FastQC.FastQCApplication %*

uk/ac/babraham/FastQC/FastQCApplication.java

@@ -54,7 +54,7 @@ import uk.ac.babraham.FastQC.Utilities.NanoporeBasename;
 
 public class FastQCApplication extends JFrame {	
 	
-	public static final String VERSION = "0.11.7";
+	public static final String VERSION = "0.11.8";
 	
 	private JTabbedPane fileTabs;
 	private WelcomePanel welcomePanel;

uk/ac/babraham/FastQC/Modules/DuplicationLevel.java

@@ -97,8 +97,6 @@ public class DuplicationLevel extends AbstractQCModule {
 			
 			correctedCounts.put(dupLevel,getCorrectedCount(overrepresentedModule.countAtUniqueLimit, overrepresentedModule.count, dupLevel, count));
 
-//			System.err.println("For dup level "+dupLevel+" raw count was "+count+" corrected count was "+correctedCounts.get(dupLevel));
-			
 		}
 		
 		// From the corrected counts we can now work out the raw and deduplicated proportions
@@ -133,7 +131,6 @@ public class DuplicationLevel extends AbstractQCModule {
 		
 //		System.err.println("True total = "+overrepresentedModule.count+" inferred total is "+rawTotal+" dedup total is "+dedupTotal);
 		
-		
 		labels = new String [16];
 		for (int i=0;i<deduplicatedPercentages.length;i++) {
 			if (i<9) labels[i] = ""+(i+1);
@@ -177,9 +174,22 @@ public class DuplicationLevel extends AbstractQCModule {
 		
 		double pNotSeeingAtLimit = 1;
 		
+		
+		// To save doing long calculations which are never going to produce anything meaningful
+		// we'll set a limit to our p-value calculation.  This is the probability below which we
+		// won't increase our count by 0.01 of an observation.  Once we're below this we stop caring
+		// about the corrected value since it's going to be so close to the observed value that
+		// we can just return that instead.
+		double limitOfCaring = 1d - (numberOfObservations/(numberOfObservations+0.01d));
+				
 		for (int i=0;i<countAtLimit;i++) {
 			pNotSeeingAtLimit *= ((totalCount-i)-duplicationLevel)/(double)(totalCount-i);
-//			System.err.println("At i="+i+" p is "+pNotSeeingAtLimit);
+			
+			if (pNotSeeingAtLimit < limitOfCaring) {
+				pNotSeeingAtLimit = 0;
+				break;
+			}
+			
 		}
 				
 		// Now we can invert this to get the chance of seeing a sequence with this count

uk/ac/babraham/FastQC/Modules/SequenceLengthDistribution.java

@@ -24,6 +24,7 @@ import java.io.IOException;
 import javax.swing.JPanel;
 import javax.xml.stream.XMLStreamException;
 
+import uk.ac.babraham.FastQC.FastQCConfig;
 import uk.ac.babraham.FastQC.Graphs.LineGraph;
 import uk.ac.babraham.FastQC.Report.HTMLReportArchive;
 import uk.ac.babraham.FastQC.Sequence.Sequence;
@@ -130,6 +131,11 @@ public class SequenceLengthDistribution extends AbstractQCModule {
 	
 	private int [] getSizeDistribution (int min, int max) {
 		
+		// We won't group if they've asked us not to
+		if (FastQCConfig.getInstance().nogroup) {
+			return(new int [] {min,1});
+		}
+		
 		int base = 1;
 		
 		while (base > (max-min)) {
@@ -221,7 +227,7 @@ public class SequenceLengthDistribution extends AbstractQCModule {
 	public void makeReport(HTMLReportArchive report) throws IOException,XMLStreamException {
 		if (!calculated) calculateDistribution();
 
-		writeDefaultImage(report, "sequence_length_distribution.png", "Sequence length distribution", 800, 600);
+		writeDefaultImage(report, "sequence_length_distribution.png", "Sequence length distribution",  Math.max(800, graphCounts.length*15), 600);
 		
 		StringBuffer sb = report.dataDocument();
 		sb.append("#Length\tCount\n");

uk/ac/babraham/FastQC/Results/ResultsPanel.java

@@ -124,6 +124,7 @@ public class ResultsPanel extends JPanel implements ListSelectionListener, Analy
 		panels = new JPanel[modules.length];
 		
 		for (int m=0;m<modules.length;m++) {
+			System.err.println("Getting panel for "+modules[m].name()+" with "+modules[m].description());
 			panels[m] = modules[m].getResultsPanel();
 		}