add realtime to summary file

bin/count_realtime_job.py

@@ -25,5 +25,5 @@ def extract_realtime_column(file_path):
 total = sum(realtime_columns)/60000 #convert to minutes
 total_tcoffee = sum(realtimes_tcoffee_columns)/60000 #convert to minutes
 
-print(f"Total realtime: {round(total)} minutes")
-print(f"Total realtime {prop_of_interest} only: {round(total_tcoffee)} minutes")
+print(f"* Total runtime (without queue time): {round(total)} minutes")
+print(f"* Total runtime {prop_of_interest} only: {round(total_tcoffee)} minutes")

bin/sequence_identity.py

@@ -45,8 +45,8 @@
 av_id = round(100*sum(id_ratios)/len(id_ratios) ,2)
 #print (av_id)
 
-line = 'The final alignment contains ' +str(common_counter)+ ' conserved positions and ' +str(occupied)+ ' gapless positions of '+str(positions)+ ' total positions.'
-line2 = 'The average pairwise sequence identity in the final alignment is ' +str(av_id) + '%. Gaps were treated as missmatch.'
+line = '* The final alignment contains ' +str(common_counter)+ ' conserved positions and ' +str(occupied)+ ' gapless positions of '+str(positions)+ ' total positions.'
+line2 = '* The average pairwise sequence identity in the final alignment is ' +str(av_id) + '%. Gaps were treated as missmatch.'
 
 print(line)
 print(line2)

modules/utils.nf

@@ -156,6 +156,7 @@ process createSummary{
 
     val reorder
     val convert  // convertMSA
+    val commandline
 
     output:
     path "*.md"
@@ -170,6 +171,8 @@ process createSummary{
     echo "Find detailed explations for each step on [GitHub](https://github.com/Bio2Byte/simsapiper) "
 
     echo '\n All output files can be found here: ' $outdir
+
+    echo '\n The command executed was: ' $commandline
     
     echo "# Input sequences files "
     echo '* No. of sequences in inputfile(s): ' $foundSequencesCount
@@ -199,7 +202,7 @@ process createSummary{
     fi
 
     echo "## 1.3 Invalid sequences "
-    echo '* $seqsInvalidCount sequences removed because they contained more then $seqQC % non-standard or unresolved amino acids'
+    echo '* Sequences removed because they contained more then $seqQC % non-standard or unresolved amino acids: ' $seqsInvalidCount
     if (( $seqsInvalidCount != 0 ));then
         echo '* Find invalid sequences here:' $outdir/seqs/too_many_unknown_characters.fasta
     fi
@@ -269,7 +272,7 @@ process createSummary{
         echo '## 7.2 Squeeze MSA towards conserved secondary structure elements' 
         echo '* Categories selected for squeezing: ' $squeeze
         echo '* Threshold for region to be considered conserved: ' $squeezePerc
-        echo '* Squeezed alignemnt: '$outdir/msas/squeezed_merged*.fasta
+        echo '* Squeezed alignment: ' $outdir/msas/squeezed_merged*.fasta
 
         echo '## 7.3 Map DSSP to squeezed MSA'
         echo '* DSSP codes mapped to merged alignment:' $outdir/msas/dssp_squeezed_merged*.fasta
@@ -301,11 +304,15 @@ process createSummary{
         echo '# 9 Convert MSA'
         echo '* Converted MSA to ' $convert 'format' 
         echo '* Converted MSA: ' $outdir/msas/converted*.fasta
-    else
-        echo '# 9 Convert MSA: false'
     fi
 
 
+    for i in $outdir/resources*.txt ; do
+        echo '# Execution time'
+        python3 $projectDir/bin/count_realtime_job.py \$i
+    done
+
+
     cp .command.out \$outfile
     
     """    

simsapiper.nf

@@ -391,7 +391,8 @@ workflow {
         params.squeeze ,
         params.squeezePerc ,
         params.reorder ,
-        params.convertMSA
+        params.convertMSA,
+        "$workflow.commandLine"
         )
 
 }