version bump. entire sequence description, rather than just the ident…

…ifier, is kept in the output files of ClipKIT
JLSteenwyk · Dec 7, 2021 · be991d7 · be991d7
1 parent 001f251
commit be991d7
Show file tree

Hide file tree

Showing 37 changed files with 660 additions and 286 deletions.
diff --git a/change_log.txt b/change_log.txt
@@ -1,8 +1,11 @@
 Major changes to ClipKIT are summarized here.
 
+1.3.0
+long description of sequences, rather than identifiers, are kept in the ClipKIT output
+
+1.1.5
+carried over code base to biopython, v1.79
+
 1.1.0
 smart-gap trimming is introduced and is now the default trimming approach used in ClipKIT.
 smart-gap trimming is a dynamic approach to determine the appropriate gaps threshold for an alignment.
-
-1.1.5
-carried over code base to biopython, v1.79
diff --git a/clipkit/helpers.py b/clipkit/helpers.py
@@ -106,12 +106,11 @@ def populate_empty_keepD_and_trimD(alignment):
         biopython multiple sequence alignment object
     """
     keepD = {}
-    alignment_length = alignment.get_alignment_length()
-    for entry in alignment:
-        keepD[entry.id] = np.zeros([alignment_length], dtype=bytes)
     trimD = {}
+    alignment_length = alignment.get_alignment_length()
     for entry in alignment:
-        trimD[entry.id] = np.zeros([alignment_length], dtype=bytes)
+        keepD[entry.description] = np.zeros([alignment_length], dtype=bytes)
+        trimD[entry.description] = np.zeros([alignment_length], dtype=bytes)
 
     return keepD, trimD
 

diff --git a/clipkit/modes.py b/clipkit/modes.py
@@ -80,7 +80,7 @@ def trim(
     # save to keepD
     if shouldKeep(mode, parsimony_informative, constant_site, gappyness, gaps):
         for entry in alignment:
-            keepD[entry.id][alignment_position] = entry.seq._data[alignment_position:alignment_position+1]
+            keepD[entry.description][alignment_position] = entry.seq._data[alignment_position:alignment_position+1]
         if use_log:
             if constant_site:
                 logger.debug(f"{str(alignment_position + 1)} keep Const {gappyness}")
@@ -93,7 +93,7 @@ def trim(
     # save to trimD
     else:
         for entry in alignment:
-            trimD[entry.id][alignment_position] = entry.seq._data[alignment_position:alignment_position+1]
+            trimD[entry.description][alignment_position] = entry.seq._data[alignment_position:alignment_position+1]
         if use_log:
             if constant_site:
                 logger.debug(f"{str(alignment_position + 1)} trim Const {gappyness}")

diff --git a/clipkit/version.py b/clipkit/version.py
@@ -1 +1 @@
-__version__ = '1.2.0'
+__version__ = '1.3.0'
diff --git a/docs/change_log/index.rst b/docs/change_log/index.rst
@@ -8,6 +8,12 @@ Change log
 
 Major changes to ClipKIT are summarized here.
 
+**1.3.0**
+long description of sequences, rather than identifiers, are kept in the ClipKIT output
+
+**1.1.5**
+carried over code base to biopython, v1.79
+
 **1.1.0:**
 smart-gap trimming is introduced and is now the default trimming approach used in ClipKIT.
 smart-gap trimming is a dynamic approach to determine the appropriate gaps threshold for an alignment.
diff --git a/tests/integration/expected/simple_long_description.clustal b/tests/integration/expected/simple_long_description.clustal
@@ -0,0 +1,10 @@
+CLUSTAL X (1.81) multiple sequence alignment
+
+
+1_extra_info                        A-GTAT
+2_extra_info                        A-G-AT
+3_extra_info                        A-G-TA
+4_extra_info                        AGA-TA
+5_extra_info                        ACa-T-
+
+
diff --git a/tests/integration/expected/simple_long_description.fa.clipkit b/tests/integration/expected/simple_long_description.fa.clipkit
@@ -0,0 +1,10 @@
+>1 extra_info
+A-GTAT
+>2 extra_info
+A-G-AT
+>3 extra_info
+A-G-TA
+>4 extra_info
+AGA-TA
+>5 extra_info
+ACa-T-
diff --git a/tests/integration/expected/simple_long_description.fa.clipkit.log b/tests/integration/expected/simple_long_description.fa.clipkit.log
@@ -0,0 +1,6 @@
+1 keep Const 0.0
+2 keep nConst,nPI 0.6
+3 keep PI 0.0
+4 keep nConst,nPI 0.8
+5 keep PI 0.0
+6 keep PI 0.2
diff --git a/tests/integration/expected/simple_long_description.fa_gappy b/tests/integration/expected/simple_long_description.fa_gappy
@@ -0,0 +1,10 @@
+>1 extra_info
+A-GTAT
+>2 extra_info
+A-G-AT
+>3 extra_info
+A-G-TA
+>4 extra_info
+AGA-TA
+>5 extra_info
+ACa-T-
diff --git a/tests/integration/expected/simple_long_description.fa_gappy.complement b/tests/integration/expected/simple_long_description.fa_gappy.complement
@@ -0,0 +1,5 @@
+>1 extra_info
+>2 extra_info
+>3 extra_info
+>4 extra_info
+>5 extra_info
diff --git a/tests/integration/expected/simple_long_description.fa_kpi b/tests/integration/expected/simple_long_description.fa_kpi
@@ -0,0 +1,10 @@
+>1 extra_info
+GAT
+>2 extra_info
+GAT
+>3 extra_info
+GTA
+>4 extra_info
+ATA
+>5 extra_info
+aT-
diff --git a/tests/integration/expected/simple_long_description.fa_kpi_gappy b/tests/integration/expected/simple_long_description.fa_kpi_gappy
@@ -0,0 +1,10 @@
+>1 extra_info
+GAT
+>2 extra_info
+GAT
+>3 extra_info
+GTA
+>4 extra_info
+ATA
+>5 extra_info
+aT-
diff --git a/tests/integration/expected/simple_long_description.fa_kpi_smart_gaps b/tests/integration/expected/simple_long_description.fa_kpi_smart_gaps
@@ -0,0 +1,10 @@
+>1 extra_info
+GAT
+>2 extra_info
+GAT
+>3 extra_info
+GTA
+>4 extra_info
+ATA
+>5 extra_info
+aT-
diff --git a/tests/integration/expected/simple_long_description.fa_kpic b/tests/integration/expected/simple_long_description.fa_kpic
@@ -0,0 +1,10 @@
+>1 extra_info
+AGAT
+>2 extra_info
+AGAT
+>3 extra_info
+AGTA
+>4 extra_info
+AATA
+>5 extra_info
+AaT-
diff --git a/tests/integration/expected/simple_long_description.fa_kpic_gappy b/tests/integration/expected/simple_long_description.fa_kpic_gappy
@@ -0,0 +1,10 @@
+>1 extra_info
+AGAT
+>2 extra_info
+AGAT
+>3 extra_info
+AGTA
+>4 extra_info
+AATA
+>5 extra_info
+AaT-
diff --git a/tests/integration/expected/simple_long_description.fa_kpic_smart_gaps b/tests/integration/expected/simple_long_description.fa_kpic_smart_gaps
@@ -0,0 +1,10 @@
+>1 extra_info
+AGAT
+>2 extra_info
+AGAT
+>3 extra_info
+AGTA
+>4 extra_info
+AATA
+>5 extra_info
+AaT-
diff --git a/tests/integration/expected/simple_long_description.fa_smart_gaps b/tests/integration/expected/simple_long_description.fa_smart_gaps
@@ -0,0 +1,10 @@
+>1 extra_info
+A-GAT
+>2 extra_info
+A-GAT
+>3 extra_info
+A-GTA
+>4 extra_info
+AGATA
+>5 extra_info
+ACaT-
diff --git a/tests/integration/expected/simple_long_description.maf b/tests/integration/expected/simple_long_description.maf
@@ -0,0 +1,10 @@
+##maf version=1 scoring=none
+# generated by Biopython
+
+a score=0.00
+s 1_extra_info                                           0     5 +               0 A-GTAT
+s 2_extra_info                                           0     4 +               0 A-G-AT
+s 3_extra_info                                           0     4 +               0 A-G-TA
+s 4_extra_info                                           0     5 +               0 AGA-TA
+s 5_extra_info                                           0     4 +               0 ACa-T-
+
diff --git a/tests/integration/expected/simple_long_description.mauve b/tests/integration/expected/simple_long_description.mauve
@@ -0,0 +1,17 @@
+#FormatVersion Mauve1
+#Sequence1Entry	1
+#Sequence2Entry	2
+#Sequence3Entry	3
+#Sequence4Entry	4
+#Sequence5Entry	5
+> 1:0-0 + <unknown name>.fa # 1 extra_info
+A-GTAT
+> 2:0-0 + <unknown name>.fa # 2 extra_info
+A-G-AT
+> 3:0-0 + <unknown name>.fa # 3 extra_info
+A-G-TA
+> 4:0-0 + <unknown name>.fa # 4 extra_info
+AGA-TA
+> 5:0-0 + <unknown name>.fa # 5 extra_info
+ACa-T-
+=
diff --git a/tests/integration/expected/simple_long_description.phylip b/tests/integration/expected/simple_long_description.phylip
@@ -0,0 +1,6 @@
+ 5 6
+1 extra_in A-GTAT
+2 extra_in A-G-AT
+3 extra_in A-G-TA
+4 extra_in AGA-TA
+5 extra_in ACa-T-
diff --git a/tests/integration/expected/simple_long_description.phylip-relaxed b/tests/integration/expected/simple_long_description.phylip-relaxed
diff --git a/tests/integration/expected/simple_long_description.phylip-sequential b/tests/integration/expected/simple_long_description.phylip-sequential
@@ -0,0 +1,6 @@
+ 5 6
+1 extra_inA-GTAT
+2 extra_inA-G-AT
+3 extra_inA-G-TA
+4 extra_inAGA-TA
+5 extra_inACa-T-
diff --git a/tests/integration/expected/simple_long_description.stockholm b/tests/integration/expected/simple_long_description.stockholm
@@ -0,0 +1,13 @@
+# STOCKHOLM 1.0
+#=GF SQ 5
+1_extra_info A-GTAT
+#=GS 1_extra_info AC 1 extra_info
+2_extra_info A-G-AT
+#=GS 2_extra_info AC 2 extra_info
+3_extra_info A-G-TA
+#=GS 3_extra_info AC 3 extra_info
+4_extra_info AGA-TA
+#=GS 4_extra_info AC 4 extra_info
+5_extra_info ACa-T-
+#=GS 5_extra_info AC 5 extra_info
+//
diff --git a/tests/integration/samples/simple_long_description.fa b/tests/integration/samples/simple_long_description.fa
@@ -0,0 +1,10 @@
+>1 extra_info
+A-GTAT
+>2 extra_info
+A-G-AT
+>3 extra_info
+A-G-TA
+>4 extra_info
+AGA-TA
+>5 extra_info
+ACa-T-
diff --git a/tests/integration/samples/simple_long_description.fa.clipkit b/tests/integration/samples/simple_long_description.fa.clipkit
@@ -0,0 +1,10 @@
+>1 extra_info
+A-GAT
+>2 extra_info
+A-GAT
+>3 extra_info
+A-GTA
+>4 extra_info
+AGATA
+>5 extra_info
+ACaT-
diff --git a/tests/integration/test_complementary_output.py b/tests/integration/test_complementary_output.py
@@ -41,6 +41,37 @@ def test_simple_complement(self):
 
         assert expected_content == output_content
 
+    def test_simple_long_description_complement(self):
+        """
+        test complementary output file with a simple case
+        usage: clipkit simple_long_description.fa -c
+        """
+        output_file = "output/simple_long_description.fa_gappy"
+        complement_out_file = f"{output_file}.complement"
+
+        kwargs = dict(
+            input_file=f"{here.parent}/samples/simple_long_description.fa",
+            output_file=output_file,
+            input_file_format='fasta',
+            output_file_format='fasta',
+            complement=True,
+            gaps=0.9,
+            mode=TrimmingMode.gappy,
+            use_log=False,
+        )
+
+        execute(**kwargs)
+
+        with open(
+            f"{here.parent}/expected/simple_long_description.fa_gappy.complement", "r"
+        ) as expected:
+            expected_content = expected.read()
+
+        with open(complement_out_file, "r") as out_file:
+            output_content = out_file.read()
+
+        assert expected_content == output_content
+
     def test_12_YIL115C_Anc_2_253_aa_aln_complement(self):
         """
         test complementary output file for amino acid yeast sequences