producing FASTA dataset based on requestd codon positions

VoSeq · Feb 4, 2015 · 5ecc010 · 5ecc010
1 parent 845efb1
commit 5ecc010
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 6 deletions.
diff --git a/voseq/create_dataset/forms.py b/voseq/create_dataset/forms.py
@@ -25,7 +25,7 @@ class CreateDatasetForm(BaseDatasetForm):
     )
 
     positions = forms.MultipleChoiceField(
-        label='Positions',
+        label='Codon Positions',
         help_text='Codon positions to keep and write into datasets',
         choices=[
             ('ALL', 'all'),
@@ -34,7 +34,7 @@ class CreateDatasetForm(BaseDatasetForm):
             ('3rd', '3rd'),
         ],
         widget=forms.CheckboxSelectMultiple(),
-        initial='ALL',
+        initial=['ALL'],
         required=True,
     )
 

diff --git a/voseq/create_dataset/templates/create_dataset/index.html b/voseq/create_dataset/templates/create_dataset/index.html
@@ -65,6 +65,9 @@ <h3 class="panel-title"><b>Enter the required info to make yourself a ready-to-r
                 Amino Acids->Special->Degen->All->1st—2nd,3rd):
               </td>
               <td>
+                {% for error in form.positions.errors %}
+                <p class="text-danger">{{ error }}</p>
+                {% endfor %}
                 <b>{{ form.positions.label }}</b>
                 {{ form.positions }}
 

diff --git a/voseq/create_dataset/utils.py b/voseq/create_dataset/utils.py
@@ -24,13 +24,13 @@ def __init__(self, cleaned_data):
         print(">>>>>>_init", cleaned_data)
         self.errors = []
         self.seq_objs = dict()
+        self.codon_positions = cleaned_data['positions']
         self.cleaned_data = cleaned_data
         self.voucher_codes = get_voucher_codes(cleaned_data)
         self.gene_codes = get_gene_codes(cleaned_data)
+        self.reading_frames = self.get_reading_frames()
         self.taxon_names = cleaned_data['taxon_names']
         self.dataset_str = self.create_dataset()
-        self.codon_positions = cleaned_data['positions']
-        self.reading_frames = self.get_reading_frames()
 
     def create_dataset(self):
         self.voucher_codes = get_voucher_codes(self.cleaned_data)
@@ -86,7 +86,8 @@ def from_seq_objs_to_fasta(self):
                     this_gene = seq_record.name
                     seq_str = '>' + this_gene + '\n' + '--------------------'
                     append(seq_str)
-                seq_str = '>' + seq_record.id + '\n' + str(seq_record.seq)
+                seq_record_seq_str = str(self.get_sequence_based_on_codon_positions(this_gene, seq_record.seq))
+                seq_str = '>' + seq_record.id + '\n' + seq_record_seq_str
                 append(seq_str)
 
         return '\n'.join(fasta_str)
@@ -137,7 +138,7 @@ def get_sequence_based_on_codon_positions(self, gene_code, seq):
 
         :param gene_code: as lower case
         :param seq: as BioPython seq object.
-        :return: sequence as string with codon positions removed, if needed.
+        :return: sequence as Seq object with codon positions requested by user.
 
         Example:
             If reading frame is 2: ATGGGG becomes TGGGG. Then the sequence is