coolneng
/
adapter-parser
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Discard reports without overrepresented sequences

This commit is contained in:
coolneng 2021-12-01 15:50:33 +01:00
parent e59683b925
commit 52eaee4568
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
parser.py
View File

@ -14,8 +14,9 @@ def extract_adapters(files) -> Tuple[Series, List]:
all_adapters = DataFrame()
for entry in files:
tables = read_html(entry)
adapter_sequences = tables[1].Sequence
all_adapters = all_adapters.append(adapter_sequences)
if len(tables) > 1:
adapter_sequences = tables[1].Sequence
all_adapters = all_adapters.append(adapter_sequences)
processed_adapters = preprocess_dataframe(all_adapters)
stats = [
processed_adapters.str.len().mean(),