cleanup

tiger.py

@@ -7,25 +7,35 @@ import pandas as pd
 import tensorflow as tf
 from Bio import SeqIO
 
-GUIDE_LEN = 23
-CONTEXT_5P = 3
-CONTEXT_3P = 0
-TARGET_LEN = CONTEXT_5P + GUIDE_LEN + CONTEXT_3P
-NUCLEOTIDE_TOKENS = dict(zip(['A', 'C', 'G', 'T', 'N'], [0, 1, 2, 3, 255]))
-NUCLEOTIDE_COMPLEMENT = dict(zip(['A', 'C', 'G', 'T'], ['T', 'G', 'C', 'A']))
-NUM_TOP_GUIDES = 10
-NUM_MISMATCHES = 3
+# column names
 ID_COL = 'Transcript ID'
 SEQ_COL = 'Sequence'
 TARGET_COL = 'Target Sequence'
 GUIDE_COL = 'Guide Sequence'
 SCORE_COL = 'Guide Score'
-RUN_MODES = dict(all='All on-target guides per transcript', titration='Top guides per transcript')
+
+# nucleotide tokens
+NUCLEOTIDE_TOKENS = dict(zip(['A', 'C', 'G', 'T', 'N'], [0, 1, 2, 3, 255]))
+NUCLEOTIDE_COMPLEMENT = dict(zip(['A', 'C', 'G', 'T'], ['T', 'G', 'C', 'A']))
+
+# model hyper-parameters
+GUIDE_LEN = 23
+CONTEXT_5P = 3
+CONTEXT_3P = 0
+TARGET_LEN = CONTEXT_5P + GUIDE_LEN + CONTEXT_3P
+UNIT_INTERVAL_MAP = 'exp-lin-exp'
+
+# reference transcript files
 REFERENCE_TRANSCRIPTS = ('gencode.v19.pc_transcripts.fa.gz', 'gencode.v19.lncRNA_transcripts.fa.gz')
+
+# application configuration
 BATCH_SIZE_COMPUTE = 500
 BATCH_SIZE_SCAN = 20
 BATCH_SIZE_TRANSCRIPTS = 50
-UNIT_INTERVAL_MAP = 'exp-lin-exp'
+NUM_TOP_GUIDES = 10
+NUM_MISMATCHES = 3
+RUN_MODES = dict(all='All on-target guides per transcript', titration='Top guides per transcript')
+
 
 # configure GPUs
 for gpu in tf.config.list_physical_devices('GPU'):
@@ -198,7 +208,6 @@ def find_off_targets(top_guides: pd.DataFrame, status_bar, status_text):
 
     # loop over transcripts in batches
     i = 0
-    print('Scanning for off-targets')
     off_targets = pd.DataFrame()
     while i < len(reference_transcripts):
         # select batch