bugfix: metadata.duplicate_count instead of .count in KmerFrequencyEn…

…coder, update docs
uio-bmi · Feb 6, 2024 · df8d253 · df8d253
1 parent 751ae6b
commit df8d253
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 4 deletions.
diff --git a/immuneML/data_model/receptor/receptor_sequence/SequenceMetadata.py b/immuneML/data_model/receptor/receptor_sequence/SequenceMetadata.py
@@ -9,12 +9,11 @@
 class SequenceMetadata:
     """
     class modeling the existing knowledge about a receptor_sequence, should be stored according to
-    IMGT gene nomenclature (human can be found `here
-    <http://www.imgt.org/IMGTrepertoire/index.php?section=LocusGenes&repertoire=genetable&species=human&group=TRBV>`_):
+    AIRR nomenclature
         - v call
         - j call
         - chain
-        - count
+        - duplicate_count
         - region_type (e.g. IMGT_CDR3, IMGT_CDR1, FULL_SEQUENCE)
         - frame_type (e.g. IN, OUT, STOP)
         - sample

diff --git a/immuneML/encodings/kmer_frequency/KmerFrequencyEncoder.py b/immuneML/encodings/kmer_frequency/KmerFrequencyEncoder.py
@@ -287,7 +287,7 @@ def _encode_sequence(self, sequence: ReceptorSequence, params: EncoderParams, se
                 if self.reads == ReadsType.UNIQUE:
                     counts[i] += 1
                 elif self.reads == ReadsType.ALL:
-                    counts[i] += sequence.metadata.count
+                    counts[i] += sequence.metadata.duplicate_count
         return counts
 
     def get_additional_files(self) -> List[str]: