Merge pull request #99 from sanger-bentley-group/dev

Release Version 1.0.0-rc7

bin/get_lineage.sh

@@ -1,13 +1,16 @@
 # Run PopPUNK to assign GPSCs to samples
 
-# Add "prefix_" to all sample names in qfile to avoid poppunk_assign crashing due to sample name already exists in database
-# Remove "prefix_" from all sample names in the result
+# Assign sequential names (gps_pipeline_poppunk_query_<number>) to all sample names in qfile to avoid poppunk_assign crashing due to sample name already exists in database
+# Reassign original names back to all sample in the result
 
 # Save results of individual sample into .csv with its name as filename 
 
-sed 's/^/prefix_/' "$QFILE" > safe_qfile.txt
+awk -F '\t' '{ print "gps_pipeline_poppunk_query_" FNR "\t" $2 }' "$QFILE" > safe_qfile.txt
+
 poppunk_assign --db "${POPPUNK_DIR}/${DB_NAME}" --external-clustering "${EXT_CLUSTERS_DIR}/${EXT_CLUSTERS_FILE}" --query safe_qfile.txt --output output --threads "$(nproc)"
-sed 's/^prefix_//' output/output_external_clusters.csv > result.txt
 
+tail -n +2 output/output_external_clusters.csv | sort -V > result.txt
+
+paste <(cut -f 1 "$QFILE") <(cut -f 2 -d ',' result.txt) > renamed_result.txt
 
-awk -F , 'NR!=1 { print "\"GPSC\"\n" "\"" $2 "\"" > $1 ".csv" }' result.txt
+awk -F '\t' '{ print "\"GPSC\"\n" "\"" $2 "\"" > $1 ".csv" }' renamed_result.txt

main.nf

@@ -1,7 +1,7 @@
 #!/usr/bin/env nextflow
 
 // Version of this release
-pipelineVersion = '1.0.0-rc6'
+pipelineVersion = '1.0.0-rc7'
 
 // Import workflow modules
 include { PIPELINE } from "$projectDir/workflows/pipeline"