add subsample_reads

Author: antgonza

src/qp_klp/Assays.py

@@ -166,6 +166,7 @@ def execute_pipeline(self):
             self.convert_raw_to_fastq()
             self.integrate_results()
             self.generate_sequence_counts()
+            self.subsample_reads()
 
         self.update_status("QC-ing reads", 2, 9)
         if "NuQCJob" not in self.skip_steps:

src/qp_klp/Protocol.py

@@ -9,6 +9,8 @@
 from os import makedirs, rename, walk
 from metapool import load_sample_sheet
 from metapool.sample_sheet import PROTOCOL_NAME_ILLUMINA, PROTOCOL_NAME_TELLSEQ
+import pandas as pd
+from glob import glob
 
 
 PROTOCOL_NAME_NONE = "None"
@@ -22,6 +24,15 @@ class Protocol():
      initialization.
     """
     protocol_type = PROTOCOL_NAME_NONE
+    MAX_READS = 1
+
+    def subsample_reads(self):
+        df = pd.read_csv(self.reports_path)
+        df = df[df.raw_reads_r1r2 > self.MAX_READS]
+        if df.shape[0]:
+            for sn in df.Sample_ID:
+                files = glob(f'{self.pipeline.output_path}/*/{sn}*.fastq.gz')
+                print(sn, files)
 
 
 class Illumina(Protocol):