From ddcd9564248b38d9894286d59a12e59b58d08d01 Mon Sep 17 00:00:00 2001
From: eead-csic-compbio <bcontreras@eead.csic.es>
Date: Tue, 7 Nov 2023 11:34:35 +0100
Subject: [PATCH] annotate_cluster.pl -b -P prints total missense mutations
 instead of SNPS

---
 CHANGES.txt         |  2 ++
 annotate_cluster.pl | 54 ++++++++++++++++++++++++++++++++++++---------
 2 files changed, 45 insertions(+), 11 deletions(-)

diff --git a/CHANGES.txt b/CHANGES.txt
index ea9aa85..cea350e 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -413,3 +413,5 @@
 30062023: added parse_pangenome_matrix.pl -R, which modifies -P to control %PAV only for -B
 23102023: registered https://bio.tools/get_homologues 
 03112023: phyTools::same_sequence_order checks for internal STOP codons in translated sequences
+07112023: annotate_cluster.pl fails gracefully when no sequences are read
+07112023: annotate_cluster.pl -b -P prints total missense mutations instead of SNPS
diff --git a/annotate_cluster.pl b/annotate_cluster.pl
index 89859bb..278789d 100755
--- a/annotate_cluster.pl
+++ b/annotate_cluster.pl
@@ -88,12 +88,13 @@
   print   "-P sequences are peptides            (optional, uses BLASTP instead of BLASTN)\n";
   print   "-r reference sequence FASTA          (optional, aligns cluster sequences to this external seq)\n";
   print   "-D match Pfam domains                (optional, annotates longest seq, nucleotides on 6 frames)\n";
-  print   "-u print unaligned sequences         (optional, flips seqs, handy for multiple alignments, skips option below\n";
-  print   "-b blunt alignment borders           (optional, also annotates SNPs and parsimony-informative sites)\n";
+  print   "-u print unaligned sequences         (optional, flips seqs, handy for multiple alignments, skips option below)\n";
+  print   "-b blunt alignment borders           (optional, also annotates SNPs/missense mutations and parsimony-informative sites)\n";
   print   "-A file with taxon names of group A  (optional, identifies private variants of group A vs 'rest')\n";
   print   "-B file with taxon names of group B  (optional, requires -A, group B is used as 'rest')\n";
   print   "-c collapse overlapping fragments    (optional, example -c 40 for overlaps >= 40 residues, requires -o,\n";
-  print   "                                      this is useful to merge fragmented de-novo transcripts)\n\n$warning";
+  print   "                                      this is useful to merge fragmented de-novo transcripts)\n\n";
+  print   $warning;
   exit(0);
 }
 
@@ -251,6 +252,12 @@
   }
 }
 
+if(!defined($cluster_ref->[0]))
+{
+  printf(STDERR "# total   sequences: 0\n# exit\n");
+  exit(0);
+}
+
 printf(STDERR "\n# total   sequences: %d taxa: %d\n",
   $#{$cluster_ref}+1,scalar(keys(%intaxa)));
 printf(STDERR "# longest sequence: %d (%s)\n",
@@ -562,20 +569,45 @@
 ## extract SNPs, parsimony-informative sites, private variants and trim alignment if required
 my ($align_ref,$nSNPS,$npars,$npriv,$SNPs,$pars,$priv,$missA,$missB) = 
   check_variants_FASTA_alignment($filenamea,!$INP_nucleotides,$INP_blunt,\@listA,\@listB);
-  
-printf(STDERR "# aligned sequences: %d width:   %d\n\n",
-  $#{$align_ref}+1,length($align_ref->[0][SEQ])); 
+
+if(!defined($align_ref->[0]))
+{
+  printf(STDERR "# aligned sequences: 0\n# exit\n");
+  exit(0);
+} 
+else 
+{
+  printf(STDERR "# aligned sequences: %d width:   %d\n\n",
+    $#{$align_ref}+1,length($align_ref->[0][SEQ])); 
+}
 
 if($INP_includeA)
 {
-  printf(STDERR "# alignment sites: SNP=%d parsimony-informative=%d private=%d unaligned A=%d B=%d (%s)\n",
-    $nSNPS,$npars,$npriv,$missA,$missB,$INP_clusterfile);
-  printf(STDERR "# private sites=%s\n\n",$priv); 
+  if($INP_nucleotides) 
+  {
+    printf(STDERR "# alignment sites: SNP=%d parsimony-informative=%d private=%d unaligned A=%d B=%d (%s)\n",
+      $nSNPS,$npars,$npriv,$missA,$missB,$INP_clusterfile);
+    printf(STDERR "# private sites=%s\n\n",$priv); 
+  }
+  else
+  {
+    printf(STDERR "# alignment sites: missense=%d parsimony-informative=%d private=%d unaligned A=%d B=%d (%s)\n",
+      $nSNPS,$npars,$npriv,$missA,$missB,$INP_clusterfile);
+    printf(STDERR "# private sites=%s\n\n",$priv);
+  }
 }
 else
 {
-  printf(STDERR "# alignment sites: SNP=%d parsimony-informative=%d (%s)\n\n",
-    $nSNPS,$npars,$INP_clusterfile);
+  if($INP_nucleotides)
+  {
+    printf(STDERR "# alignment sites: SNP=%d parsimony-informative=%d (%s)\n\n",
+      $nSNPS,$npars,$INP_clusterfile);
+  }
+  else 
+  {
+    printf(STDERR "# alignment sites: missense=%d parsimony-informative=%d (%s)\n\n",
+      $nSNPS,$npars,$INP_clusterfile);
+  }
 }