cell name method extracted to common 10x superclass

KrasnitzLab · May 28, 2020 · 0d9b34a · 0d9b34a
1 parent f861dda
commit 0d9b34a
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 28 deletions.
diff --git a/sgains/pipelines/extract_10x_pipeline.py b/sgains/pipelines/extract_10x_pipeline.py
@@ -40,6 +40,11 @@ def __init__(self, config):
         self.genome = Genome(self.config)
         assert self.genome is not None
 
+    @staticmethod
+    def _cell_name(cell_id):
+        cell_name = f"C{cell_id:0>8}"
+        return cell_name
+
 
 class Extract10xPipeline(Base10xPipeline):
 
@@ -108,11 +113,6 @@ def _process_segment(self, segment, region):
                     self._write_to_fastq(barcode, segment, records)
                 cell_records[barcode] = []
 
-    @staticmethod
-    def _cell_name(cell_id):
-        cell_name = f"C{cell_id:0>8}"
-        return cell_name
-
     def _cell_segment_filename(self, cell_id, segment):
         cell_name = self._cell_name(cell_id)
         segment_name = f"{segment:0>8}"

diff --git a/sgains/pipelines/varbin_10x_pipeline.py b/sgains/pipelines/varbin_10x_pipeline.py
@@ -83,21 +83,6 @@ def split_bins(self, bins_step, bins_region=None):
             for chrom, start, end in regions
         ]
 
-    # @staticmethod
-    # def compress_reads(reads):
-    #     if not reads:
-    #         return None
-    #     df = pd.DataFrame(reads, columns=['cell_id', 'chrom', 'pos'])
-    #     buff = BytesIO()
-    #     df.to_feather(buff)
-
-    #     return str(buff.getbuffer(), encoding='latin1')
-
-    @staticmethod
-    def _cell_name(cell_id):
-        cell_name = f"C{cell_id:0>8}"
-        return cell_name
-
     def _cell_reads_dirname(self, cell_id):
         cell_name = self._cell_name(cell_id)
         dirname = os.path.join(
@@ -160,14 +145,6 @@ def load_reads(self, cell_id):
             result_df = result_df.sort_values(by=["cell_id", "chrom", "pos"])
             return result_df
 
-    # @staticmethod
-    # def decompress_reads(data):
-    #     if data is None:
-    #         return None
-    #     buff = BytesIO(bytes(data, encoding='latin1'))
-    #     df = pd.read_feather(buff)
-    #     return df
-
     Read = namedtuple('Read', ['cell_id', 'chrom', 'pos'])
 
     def process_region_reads(self, region, region_index):