updated modules to not have md5s, added decision logic to processing …

…module, updated snpashots

RESUME

@@ -4,7 +4,9 @@ set -euo pipefail
 
 #nextflow run main.nf -profile docker,local,test --clean false -resume
 
-nextflow run main.nf --input all-fqs.csv -profile docker,local --clean false -resume --r_processing true \
+#nextflow run main.nf --input all-fqs.csv -profile docker,local --clean false -resume --r_processing true \
+
+nextflow run main.nf --input all-fqs.csv -profile docker,local --clean false -resume \
    --FW_primer "ATGCGATACTTGGTGTGAAT" --RV_primer "GCATATCAATAAGCGGAGGA" --single_end false --retain_untrimmed true \
    --fastq_maxee 0.5 --fastq_minlen 250 --fastq_maxns 0 --fasta_width 0 \
    --minuniquesize 2 --derep_strand "plus" --sizeout \

modules/local/processing.nf

@@ -7,17 +7,16 @@ process PROCESSING {
     input:
     tuple val(meta), path(sintax_tsv)
 
+    //Only process files that have taxonomy predictions 
+    when:
+    sintax_tsv.size() > 0
+
     output:
     tuple val(meta), path('*.classified.tsv')   , emit: fasta
 
     script:
     """
-    if [ ! -s ${sintax_tsv} ]; then
-        echo "${sintax_tsv} has no sintax predictions" > "${meta.id}.classified.tsv"
-    else
-        echo -e "sample\tkingdom\tprob_kingdom\tdivision\tprob_division\tclade\tprob_clade\torder\tprob_order\tfamily\tprob_family\tgenus\tprob_genus\tspecies\tprob_species\tsize" > "${meta.id}.classified.tsv"
-        while read id size <&3 && read k p c o f g s <&4; do echo -e "\${id}\t\$(echo \${k} | sed 's/k://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${p} | sed 's/p://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${c} | sed 's/c://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${o} | sed 's/o://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${f} | sed 's/f://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${g} | sed 's/g://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${s} | sed 's/s://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${size} | sed 's/size=//g')"; done 3< <(cut -f 1 ${sintax_tsv} | tr ";" "\t") 4< <(cut -f 2 ${sintax_tsv} | tr "," "\t") >> "${meta.id}.classified.tsv"
-    fi
-    md5sum "${meta.id}.classified.tsv" > "${meta.id}.classified.tsv.md5"
+    echo -e "sample\tkingdom\tprob_kingdom\tdivision\tprob_division\tclade\tprob_clade\torder\tprob_order\tfamily\tprob_family\tgenus\tprob_genus\tspecies\tprob_species\tsize" > "${meta.id}.classified.tsv"
+    while read id size <&3 && read k p c o f g s <&4; do echo -e "\${id}\t\$(echo \${k} | sed 's/k://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${p} | sed 's/p://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${c} | sed 's/c://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${o} | sed 's/o://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${f} | sed 's/f://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${g} | sed 's/g://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${s} | sed 's/s://g' | sed 's/)//g' | tr "(" "\t")\t\$(echo \${size} | sed 's/size=//g')"; done 3< <(cut -f 1 ${sintax_tsv} | tr ";" "\t") 4< <(cut -f 2 ${sintax_tsv} | tr "," "\t") >> "${meta.id}.classified.tsv"
     """
 }

modules/local/vsearch_derep.nf

@@ -31,9 +31,6 @@ process VSEARCH_DEREP_FULL_LENGTH {
         --uc ${prefix}.derep.uc \\
         --output ${prefix}.derep.fasta 2>&1 | tee ${prefix}.derep.log
 
-    md5sum "${prefix}.derep.fasta" > "${prefix}.derep.fasta.md5"
-    md5sum "${prefix}.derep.uc" > "${prefix}.derep.uc.md5"
-
     cat <<-END_VERSIONS > versions.yml
 
     "${task.process}":

modules/local/vsearch_fastq_filter.nf

@@ -27,8 +27,6 @@ process VSEARCH_FASTQ_FILTER {
         $args \\
         --fastaout ${prefix}.filtered.fasta 2>&1 | tee ${prefix}.filtered.log
 
-    md5sum "${prefix}.filtered.fasta" > "${prefix}.filtered.fasta.md5"
-
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         vsearch: \$(vsearch --version 2>&1 | head -n 1 | sed 's/vsearch //g' | sed 's/,.*//g' | sed 's/^v//' | sed 's/_.*//')

tests/modules/local/processing.nf.test.snap

@@ -26,6 +26,6 @@
             "nf-test": "0.8.4",
             "nextflow": "23.10.1"
         },
-        "timestamp": "2024-03-18T14:36:04.799821"
+        "timestamp": "2024-03-20T11:34:38.230732"
     }
 }

tests/modules/local/r_processing.nf.test

@@ -24,7 +24,7 @@ nextflow_process {
               assert fasta.size() == 1
               assert fasta[0].size() == 2
               assert fasta[0][0].size() == 2
-              assert path(fasta[0].get(1)).md5 == '608d9417c5fc59d20087c3575935cec3'
+              assert path(fasta[0].get(1)).md5 == 'd7536874f239e304cca7667dc1ffde4d'
             }
         }
 

tests/modules/local/r_processing.nf.test.snap

@@ -8,30 +8,24 @@
                             "id": "ERR2537816",
                             "single_end": false
                         },
-                        "ERR2537816.classified.tsv:md5,608d9417c5fc59d20087c3575935cec3"
+                        "ERR2537816.classified.tsv:md5,d7536874f239e304cca7667dc1ffde4d"
                     ]
                 ],
-                "1": [
-                    "versions.yml:md5,c5cafb5677872ce5c2c7cd3e9bd13e19"
-                ],
                 "fasta": [
                     [
                         {
                             "id": "ERR2537816",
                             "single_end": false
                         },
-                        "ERR2537816.classified.tsv:md5,608d9417c5fc59d20087c3575935cec3"
+                        "ERR2537816.classified.tsv:md5,d7536874f239e304cca7667dc1ffde4d"
                     ]
-                ],
-                "versions": [
-                    "versions.yml:md5,c5cafb5677872ce5c2c7cd3e9bd13e19"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.8.4",
             "nextflow": "23.10.1"
         },
-        "timestamp": "2024-03-18T14:36:08.809864"
+        "timestamp": "2024-03-20T11:13:21.069775"
     }
 }