fixed name of reads arg

isovar/reference_coding_sequence_key.py

@@ -40,9 +40,9 @@ class ReferenceCodingSequenceKey(
                 "amino_acids_before_variant"))):
 
     """
-    Includes all the fields of a ReferenceSequenceKey, and adds on top of those
-    a reading frame and information about where the start codon / 5' UTR are
-    relative to this sequence fragment.
+    ReferenceCodingSequenceKey includes all the fields of a ReferenceSequenceKey,
+    and additionally tracks the reading frame and information about where the
+    start codon and 5' UTR are relative to this sequence fragment.
     """
 
     @classmethod

isovar/reference_context.py

@@ -34,19 +34,31 @@
 #
 ##########################
 
-ReferenceContext = namedtuple(
-    "ReferenceContext",
-    ReferenceCodingSequenceKey._fields + (
-        "variant",
-        "transcripts")
-)
-
-def sort_key_decreasing_max_length_transcript_cds(reference_context):
-    """
-    Used to sort a sequence of ReferenceContext objects by the longest CDS
-    in each context's list of transcripts.
-    """
-    return -max(len(t.coding_sequence) for t in reference_context.transcripts)
+class ReferenceContext(namedtuple(
+        "ReferenceContext",
+        ReferenceCodingSequenceKey._fields + ("variant", "transcripts"))):
+
+    @classmethod
+    def from_reference_coding_sequence_key(cls, key, variant, transcripts):
+        return cls(
+            strand=key.strand,
+            sequence_before_variant_locus=key.sequence_before_variant_locus,
+            sequence_at_variant_locus=key.sequence_at_variant_locus,
+            sequence_after_variant_locus=key.sequence_after_variant_locus,
+            offset_to_first_complete_codon=key.offset_to_first_complete_codon,
+            contains_start_codon=key.contains_start_codon,
+            overlaps_start_codon=key.overlaps_start_codon,
+            contains_five_prime_utr=key.contains_five_prime_utr,
+            amino_acids_before_variant=key.amino_acids_before_variant,
+            variant=variant,
+            transcripts=transcripts)
+
+    def sort_key_decreasing_max_length_transcript_cds(self):
+        """
+        Used to sort a sequence of ReferenceContext objects by the longest CDS
+        in each context's list of transcripts.
+        """
+        return -max(len(t.coding_sequence) for t in self.transcripts)
 
 def reference_contexts_for_variant(
         variant,
@@ -83,21 +95,12 @@ def reference_contexts_for_variant(
             sequence_groups[sequence_key_with_reading_frame].append(transcript)
 
     reference_contexts = [
-        ReferenceContext(
-            strand=key.strand,
-            sequence_before_variant_locus=key.sequence_before_variant_locus,
-            sequence_at_variant_locus=key.sequence_at_variant_locus,
-            sequence_after_variant_locus=key.sequence_after_variant_locus,
-            offset_to_first_complete_codon=key.offset_to_first_complete_codon,
-            contains_start_codon=key.contains_start_codon,
-            overlaps_start_codon=key.overlaps_start_codon,
-            contains_five_prime_utr=key.contains_five_prime_utr,
-            amino_acids_before_variant=key.amino_acids_before_variant,
-            variant=variant,
-            transcripts=matching_transcripts)
+        ReferenceContext.from_reference_coding_sequence_key(
+            key, variant, matching_transcripts)
         for (key, matching_transcripts) in sequence_groups.items()
     ]
-    reference_contexts.sort(key=sort_key_decreasing_max_length_transcript_cds)
+    reference_contexts.sort(
+        key=ReferenceContext.sort_key_decreasing_max_length_transcript_cds)
     return reference_contexts
 
 def reference_contexts_for_variants(

isovar/translation.py

@@ -26,7 +26,7 @@
 from skbio import DNA
 
 from .reference_context import reference_contexts_for_variant
-from .variant_sequences import supporting_reads_to_variant_sequences
+from .variant_sequences import reads_to_variant_sequences
 
 from .default_parameters import (
     MIN_TRANSCRIPT_PREFIX_LENGTH,
@@ -553,8 +553,9 @@ def translate_variant_reads(
     # need to clip nucleotides at the start/end of the sequence
     cdna_sequence_length = (protein_sequence_length + 1) * 3
 
-    variant_sequences = supporting_reads_to_variant_sequences(
-        variant_reads=variant_reads,
+    variant_sequences = reads_to_variant_sequences(
+        variant=variant,
+        reads=variant_reads,
         preferred_sequence_length=cdna_sequence_length,
         min_reads_supporting_cdna_sequence=min_reads_supporting_cdna_sequence,
         variant_cdna_sequence_assembly=variant_cdna_sequence_assembly)

test/test_allele_counts.py

@@ -12,7 +12,7 @@ def test_allele_count_dataframe():
     ]
     df = allele_counts_dataframe([(variant, reads)])
     assert len(df) == 1, "Wrong number of rows in DataFrame: %s" % (df,)
-    row = df.irow(0)
+    row = df.iloc[0]
     eq_(row.n_ref, 2)
     eq_(row.n_alt, 1)
     eq_(row.n_other, 0)

test/test_variant_sequences.py

@@ -16,7 +16,7 @@
 
 from nose.tools import eq_
 from varcode import Variant
-from isovar.variant_sequences import supporting_reads_to_variant_sequences
+from isovar.variant_sequences import reads_to_variant_sequences
 from isovar.variant_reads import reads_supporting_variant
 
 from testing_helpers import load_bam
@@ -34,8 +34,9 @@ def test_sequence_counts_snv():
         chromosome=chromosome,
         variant=variant)
 
-    variant_sequences = supporting_reads_to_variant_sequences(
-        variant_reads,
+    variant_sequences = reads_to_variant_sequences(
+        variant=variant,
+        reads=variant_reads,
         preferred_sequence_length=61)
     assert len(variant_sequences) == 1
     for variant_sequence in variant_sequences: