fix module for downloading PACBIO data

README.md

@@ -41,7 +41,7 @@ It wraps up the following software:
 | :--- | :---- |
 | SRA NBCI fetch | [Entrez-direct](https://anaconda.org/bioconda/entrez-direct) & [sra-tools](https://github.com/ncbi/sra-tools) |
 | Illumina pre-processing | [Fastp](https://github.com/OpenGene/fastp) |
-| Nanopore pre-processing | [Porechop](https://github.com/rrwick/Porechop), [pycoQC](https://github.com/tleonardi/pycoQC), [NanoPack](https://github.com/wdecoster/nanopack) |
+| Nanopore pre-processing | [Porechop](https://github.com/rrwick/Porechop), [Porechop ABI](https://github.com/bonsai-team/Porechop_ABI), [pycoQC](https://github.com/tleonardi/pycoQC), [NanoPack](https://github.com/wdecoster/nanopack) |
 | Pacbio pre-processing | [bam2fastx](https://github.com/PacificBiosciences/pbtk#bam2fastx), [bax2bam](https://anaconda.org/bioconda/bax2bam), [lima](https://github.com/PacificBiosciences/barcoding), [pacbio ccs](https://ccs.how/) |
 
 ## Further reading

modules/get_fastq.nf

@@ -15,7 +15,6 @@ process GET_FASTQ {
   def sra_ids = "${sra_ids.replaceAll(~/\s/,'')}"
   """
   fasterq-dump \\
-    --include-technical \\
     --split-files \\
     --threads $task.cpus \\
     --outdir ./${sra_ids}_data \\
@@ -26,12 +25,25 @@ process GET_FASTQ {
   if [ \$(grep -ic "is PACBIO, please use fastq-dump instead" fasterq-dump.err) -eq 1 ]
   then
       fastq-dump \\
-        --split-files \\
+        --gzip \\
         --outdir ./${sra_ids}_data \\
         $sra_ids
   else
     echo "fasterq-dump error was:"
     cat fasterq-dump.err
   fi
+
+  # make sure they have right extension
+  for i in \$( find ./${sra_ids}_data -name "*.fq" ) ; do
+    mv \$i \${i%%.fq}.fastq ;
+  done
+  for i in \$( find ./${sra_ids}_data -name "*.fq.gz" ) ; do
+    mv \$i \${i%%.fq.gz}.fastq.gz ;
+  done
+
+  # make sure data is compressed
+  for i in \$( find ./${sra_ids}_data -name "*.fastq" ) ; do
+    gzip \$i ;
+  done
   """
 }