routine sync

gather-fastqs

@@ -36,7 +36,8 @@ sub main {
 	}
 
 	# find fastqs in given directory
-	my $find_fastq_cmd = 'find -L ' . $search_dir . ' -maxdepth 2 -type f -name "*_R1*.fastq.gz" -or -name "*_1.fastq.gz" | LC_ALL=C sort';
+	my $find_fastq_cmd_names = "-name '*_R1_0*.fastq.gz' -or -name '*_R1.fastq.gz' -or -name '*_1.fastq.gz'";
+	my $find_fastq_cmd = "find -L $search_dir -maxdepth 2 -type f $find_fastq_cmd_names | LC_ALL=C sort";
 	my @fastqs = `$find_fastq_cmd`;
 
 	# counter single and paired reads

scripts/dge-deseq2.R

@@ -9,7 +9,7 @@
 
 
 # increase output width
-options(width = 150)
+options(width = 120)
 
 # java heap size
 options(java.parameters = "-Xmx8G")

segments/align-bwa-mem.sh

@@ -87,7 +87,7 @@ fi
 
 module load bwa/0.7.13
 
-sambamba_bin="/ifs/home/id460/bin/sambamba"
+sambamba_bin="/ifs/home/id460/software/sambamba/sambamba_v0.6.6"
 
 echo " * bwa: $(readlink -f $(which bwa)) "
 echo " * bwa version: $(bwa 2>&1 | grep -m 1 'Version') "

segments/bam-dedup-sambamba.sh

@@ -77,7 +77,7 @@ fi
 
 # sambamba markdup
 
-sambamba_bin="/ifs/home/id460/bin/sambamba"
+sambamba_bin="/ifs/home/id460/software/sambamba/sambamba_v0.6.6"
 
 echo " * sambamba: $(readlink -f $(which $sambamba_bin)) "
 echo " * sambamba version: $($sambamba_bin 2>&1 | head -1) "
@@ -88,8 +88,8 @@ bash_cmd="
 $sambamba_bin markdup \
 --remove-duplicates \
 --nthreads $threads \
---hash-table-size 1500000 \
---overflow-list-size 1500000 \
+--hash-table-size 525000 \
+--overflow-list-size 525000 \
 $bam \
 $bam_dd \
 2> $bam_dd_log

segments/fastq-clean.sh

@@ -164,6 +164,22 @@ cat ${summary_dir}/*.${segment_name}.csv | LC_ALL=C sort -t ',' -k1,1 | uniq > "
 #########################
 
 
+# exit if FASTQ has very few reads
+
+if [ $reads_R1 -lt 10000 ] ; then
+	echo -e "\n $script_name ERROR: FASTQ $fastq_R1_clean IS TOO SHORT \n" >&2
+	# delete FASTQs since they are not useable
+	rm -fv "$fastq_R1_clean"
+	if [ -s "$fastq_R2_clean" ] ; then
+		rm -fv "$fastq_R2_clean"
+	fi
+	exit 1
+fi
+
+
+#########################
+
+
 # add sample and FASTQ to sample sheet
 echo "${sample},${fastq_R1_clean},${fastq_R2_clean}" >> "$samples_csv_clean"