fixed FASTQ file handling of NCBI type data

deactivated FASTQ QC and fastq processing by default

Author: Jan Winter

README.md

@@ -147,7 +147,11 @@ __It is your responsibility to obtain all required licenses in case of commercia
 
 
 ```
-Version 1.50 (latest)
+Version 1.51 (latest)
+- fixes regarding FASTQ handling, now supports NCBI type of FASTQ
+- deactivated fast FASTQ handling due to incopatibility
+
+Version 1.50
 - many fixes with mouse libraries
 - improoved speed
 - added new sample data for cell fittnes screen

source/app/data_ui.r

@@ -365,14 +365,14 @@ GGGGGGGEGGGGGGGGGDGGFGGGEEGGFFGGFFCFFF=AFF<CEFFF@EFE
            shiny::tags$h4("Create a FASTQ data quality report"),
            shiny::helpText("By default, CRISPRAnalyzeR generates a FASTQ data quality report, which can take some time.
                            However, you can turn it off in case you are in a hurry."),
-           shinyWidgets::switchInput(inputId = "generateRQC",value = TRUE, onStatus = "success"),
+           shinyWidgets::switchInput(inputId = "generateRQC",value = FALSE, onStatus = "success"),
 
            # Make a fallback switch for FASTQ extraction using PERL
            shiny::tags$br(),
            shiny::tags$hr(width="50%"),
            shiny::tags$h4("Perform FASTQ extraction in fast mode"),
            shiny::helpText("By default, CRISPRAnalyzeR processes FASTQ files using a specialized tool for faster processing. In case you have issues with FASTQ extraction (e.g. all read counts are 0), you can try to disable the fast processing of FASTQ files and revert back to the old method."),
-           shinyWidgets::switchInput(inputId = "RUSTtools",value = TRUE, onStatus = "success")
+           shinyWidgets::switchInput(inputId = "RUSTtools",value = FALSE, onStatus = "success")
            )
 
     )

source/scripts/CRISPR-extract.pl

@@ -116,6 +116,7 @@ sub reverse_complement_IUPAC {
 		# found a read, increase counting
 		$counttotal++;
 
+		#print "Found a read"."\n";
 
 		# create read file, as we reached a line with a new readID
 		$fastq{'readID'}=$1;
@@ -130,12 +131,15 @@ sub reverse_complement_IUPAC {
       	if($inputline2=~m/$pattern/ )	
 		{ 	
 
+		#print "found pattern\n";
 			# found the required pattern, count this
 			$countextracted++;
 
 			$sequenceline = $inputline2;
 			$fastq{'sequence'} = $1;
 
+		#print $1."\n";
+		
 			$patternlength = length($1);
 
 			$fastq{'seqvalid'}=1;
@@ -155,17 +159,21 @@ sub reverse_complement_IUPAC {
 		# check nextline
 		$inputline2 = <$readfastq>;
 
-		if($inputline2=~m/^\+$/ && $fastq{'seqvalid'}==1 && $fastq{'count'}==2)
+		if($inputline2=~m/^\+.*$/ && $fastq{'seqvalid'}==1 && $fastq{'count'}==2)
 		{
 			# look for the + only to know that next line is QC
 			$fastq{'qcfound'}=1;
 			$fastq{'count'}=3;
+			
+			#print "fuound qc\n";
 		}	
 		# check nextline
+		
+		
 		$inputline2 = <$readfastq>;
 		if ($inputline2=~m/.{2,}/ && $fastq{'seqvalid'}==1 && $fastq{'qcfound'}== 1 && $fastq{'count'}==3)
 			{
-			
+			#print "check nextline\n";
 				$fastq{'valid'}=1;	
 				$fastq{'quality'} = substr($inputline2, $fastq{'stringstart'}, $patternlength);
 
@@ -177,7 +185,9 @@ sub reverse_complement_IUPAC {
 
 				#write to new fastqfile
 				print $fastqout "@".$fastq{'readID'}."\n".$fastq{'sequence'}."\n+\n".$fastq{'quality'}."\n";
-		
+				
+				#print "@".$fastq{'readID'}."\n".$fastq{'sequence'}."\n+\n".$fastq{'quality'}."\n";
+				
 				## Free space		
 				%fastq=();
 				$fastq{'qcfound'}=0;