Arguments closer to original tool's

src/bbmap_bbsplit/config.vsh.yaml

@@ -21,20 +21,15 @@ argument_groups:
     type: file
     multiple: true
     description: Input fastq files, either one or two (paired), separated by ";".
-    multiple_sep: ","
     example: reads.fastq
-  - name: "--primary_ref"
+  - name: "--ref"
     type: file
-    description: Primary reference FASTA
-  - name: "--other_ref_names"
-    type: file
-    description: |
-      Path to comma-separated file containing a list of reference genomes to filter reads
-      against with BBSplit.
+    multiple: true
+    description: Reference FASTA files, separated by ";". The primary reference should be specified first.
   - name: "--only_build_index"
     type: boolean_true
     description: If set, only builds the index. Otherwise, mapping is performed.
-  - name: "--index"
+  - name: "--build"
     type: string
     description: |
       Designate index to use. Corresponds to the number specified when building the index.
@@ -112,22 +107,6 @@ argument_groups:
       Output file for read 2.
     direction: output
     example: read_out2.fastq
-  - name: "--primary_fastq"
-    type: file
-    description: |
-      Output reads that map to the primary reference.
-    direction: output
-    example: primary.fastq.gz
-  - name: "--all_fastq"
-    type: file
-    description: |
-      Output reads that map to the primary reference.
-    direction: output
-    example: all.fastq.gz
-  - name: "--ref_fasta_list"
-    type: file
-    description: |
-      Directory with index files.
   - name: "--sam2bam"
     alternatives: ["--bs"]
     type: file

src/bbmap_bbsplit/script.sh

@@ -18,56 +18,71 @@ for var in "${unset_if_false[@]}"; do
     fi
 done
 
-if [ ! -d "$par_index" ]; then
-    other_refs=()
-    while IFS="," read -r name path 
+if [ ! -d "$par_build" ]; then
+    IFS=";" read -ra ref_files <<< "$par_ref"
+    primary_ref="${ref_files[0]}"
+    refs=()
+    for file in "${ref_files[@]:1}"
     do
-        other_refs+=("ref_$name=$path")
-    done < "$par_ref_fasta_list"
+        name=$(basename "$file" | sed 's/\.[^.]*$//')
+        refs+=("ref_$name=$file")
+    done
 fi
 
 if $par_only_build_index; then
-    if [ -f "$par_primary_ref" ] && [ ${#other_refs[@]} -gt 0 ]; then
+    if [ ${#refs[@]} -gt 1 ]; then
         bbsplit.sh \
-            ref_primary="$par_primary_ref" "${other_refs[@]}" \
-            path=$par_index \
-            threads=${meta_cpus:-1}
+            --ref_primary="$primary_ref" \
+            "${refs[@]}" \
+            path=$par_build
     else
-        echo "ERROR: Please specify as input a primary fasta file along with names and paths to non-primary fasta files."
+        echo "ERROR: Please specify at least two reference fasta files."
     fi
 else
-    IFS="," read -ra input <<< "$par_input"
+    IFS=";" read -ra input <<< "$par_input"
     tmpdir=$(mktemp -d "$meta_temp_dir/$meta_functionality_name-XXXXXXXX")
     index_files=''
-    if [ -d "$par_index" ]; then
-        index_files="path=$par_index"
-    elif [ -f "$par_primary_ref" ] && [ ${#other_refs[@]} -gt 0 ]; then
-        index_files="ref_primary=$par_primary_ref ${other_refs[@]}"
+    if [ -d "$par_build" ]; then
+        index_files="path=$par_build"
+    elif [ ${#refs[@]} -gt 0 ]; then
+        index_files="--ref_primary=$primary_ref ${refs[*]}"
     else
-        echo "ERROR: Please either specify a BBSplit index as input or a primary fasta file along with names and paths to non-primary fasta files."
+        echo "ERROR: Please either specify a BBSplit index as input or at least two reference fasta files."
     fi
+
+    extra_args=""
+    if [ -n "$par_refstats" ]; then extra_args+=" --refstats $par_refstats"; fi
+    if [ -n "$par_ambiguous" ]; then extra_args+=" --ambiguous $par_ambiguous"; fi
+    if [ -n "$par_ambiguous2" ]; then extra_args+=" --ambiguous2 $par_ambiguous2"; fi
+    if [ -n "$par_minratio" ]; then extra_args+=" --minratio $par_minratio"; fi
+    if [ -n "$par_minhits" ]; then extra_args+=" --minhits $par_minhits"; fi
+    if [ -n "$par_maxindel" ]; then extra_args+=" --maxindel $par_maxindel"; fi
+    if [ -n "$par_qin" ]; then extra_args+=" --qin $par_qin"; fi
+    if [ -n "$par_qtrim" ]; then extra_args+=" --qtrim $par_qtrim"; fi
+    if [ "$par_interleaved" = true ]; then extra_args+=" --interleaved"; fi
+    if [ "$par_untrim" = true ]; then extra_args+=" --untrim"; fi
+    if [ "$par_nzo" = true ]; then extra_args+=" --nzo"; fi
+
     if $par_paired; then
         bbsplit.sh \
             $index_files \
-            threads=${meta_cpus:-1} \
             in=${input[0]} \
             in2=${input[1]} \
             basename=${tmpdir}/%_#.fastq \
-            refstats=bbsplit_stats.txt
+            $extra_args
         read1=$(find $tmpdir/ -iname primary_1*)
         read2=$(find $tmpdir/ -iname primary_2*)
         cp $read1 $par_fastq_1
         cp $read2 $par_fastq_2
     else
         bbsplit.sh \
             $index_files \
-            threads=${meta_cpus:-1} \
             in=${input[0]} \
             basename=${tmpdir}/%.fastq \
-            refstats=bbsplit_stats.txt
+            $extra_args
         read1=$(find $tmpdir/ -iname primary*)
         cp $read1 $par_fastq_1
     fi
 fi
 
-exit 0
+exit 0

src/bbmap_bbsplit/test.sh

@@ -2,11 +2,6 @@
 
 echo ">>> Test $meta_functionality_name"
 
-cat > bbsplit_fasta_list.txt << HERE
-sarscov2,sarscov2.fa
-human,human.fa
-HERE
-
 echo "> Prepare test data"
 
 cat > reads_R1.fastq <<'EOF'
@@ -58,10 +53,9 @@ EOF
 
 echo ">>> Building BBSplit index"
 "${meta_executable}" \
-  --primary_ref "genome.fasta" \
-  --ref_fasta_list bbsplit_fasta_list.txt \
+  --ref "genome.fasta;human.fa;sarscov2.fa" \
   --only_build_index \
-  --index "BBSplit_index" 
+  --build "BBSplit_index" 
 
 echo ">>> Check whether output exists"
 [ ! -d "BBSplit_index" ] && echo "BBSplit index does not exist!" && exit 1
@@ -73,8 +67,7 @@ echo ">>> Check whether output exists"
 echo ">>> Testing with single-end reads and primary/non-primary FASTA files"
 "${meta_executable}" \
   --input "reads_R1.fastq" \
-  --primary_ref "genome.fasta" \
-  --ref_fasta_list bbsplit_fasta_list.txt \
+  --ref "genome.fasta;human.fa;sarscov2.fa" \
   --fastq_1 "filtered_reads_R1.fastq"
 
 echo ">>> Check whether output exists"
@@ -91,9 +84,8 @@ rm filtered_reads_R1.fastq
 echo ">>> Testing with paired-end reads and primary/non-primary FASTA files"
 "${meta_executable}" \
   --paired \
-  --input "reads_R1.fastq,reads_R2.fastq" \
-  --primary_ref "genome.fasta" \
-  --ref_fasta_list "bbsplit_fasta_list.txt" \
+  --input "reads_R1.fastq;reads_R2.fastq" \
+  --ref "genome.fasta;human.fa;sarscov2.fa" \
   --fastq_1 "filtered_reads_R1.fastq" \
   --fastq_2 "filtered_reads_R2.fastq"
 
@@ -114,7 +106,7 @@ rm filtered_reads_R1.fastq filtered_reads_R2.fastq
 echo ">>> Testing with single-end reads and BBSplit index"
 "${meta_executable}" \
   --input "reads_R1.fastq" \
-  --index "BBSplit_index" \
+  --build "BBSplit_index" \
   --fastq_1 "filtered_reads_R1.fastq"
 
 echo ">>> Check whether output exists"
@@ -131,8 +123,8 @@ rm filtered_reads_R1.fastq
 echo ">>> Testing with paired-end reads and BBSplit index"
 "${meta_executable}" \
   --paired \
-  --input "reads_R1.fastq,reads_R2.fastq" \
-  --index "BBSplit_index" \
+  --input "reads_R1.fastq;reads_R2.fastq" \
+  --build "BBSplit_index" \
   --fastq_1 "filtered_reads_R1.fastq" \
   --fastq_2 "filtered_reads_R2.fastq"