Update manifest (#41)

* Update manifest * Changed code to use openpyxl to open excel files * Changed test file for formatting/annotating UAS Sample Details Report * Removed old UAS Sample Details Report for testing * Fixed error for DXS7423 * Added new observed alleles for a few loci * Updated test files * Updated test file * fixed bugs with running multiple SR files at once * Updated snp data * Updated test files * Sort snp output files * Sorted UAS output Co-authored-by: Rebecca Mitchell <[email protected]>
bioforensics · Feb 16, 2021 · 83a6170 · 83a6170
1 parent 6c3a74f
commit 83a6170
Show file tree

Hide file tree

Showing 17 changed files with 9,114 additions and 9,069 deletions.
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -1,6 +1,8 @@
 include versioneer.py
 include lusSTR/_version.py
 include lusSTR/str_markers.json
+include lusSTR/snp_data.json
 include lusSTR/tests/data/*
 include lusSTR/tests/data/STRait_Razor_test_output/*
 include lusSTR/tests/data/UAS_bulk_input/*
+include lusSTR/tests/data/snps/*
diff --git a/lusSTR/format.py b/lusSTR/format.py
@@ -10,6 +10,7 @@
 import lusSTR
 import argparse
 import glob
+import openpyxl
 import os
 import pandas as pd
 import sys
@@ -27,7 +28,6 @@ def uas_load(inpath, sexloci=False):
         sex_strs = pd.DataFrame() if sexloci is True else None
         files = glob.glob(os.path.join(inpath, '*.xlsx'))
         for filename in sorted(files):
-            print(filename)
             autodata, sexdata = uas_format(filename, sexloci)
             auto_strs = auto_strs.append(autodata)
             if sexloci is True:
@@ -38,21 +38,23 @@ def uas_load(inpath, sexloci=False):
 
 
 def parse_str_table_from_sheet(infile, sheet, exclude=None):
-    table = pd.read_excel(io=infile, sheet_name=sheet)
+    file = openpyxl.load_workbook(infile)
+    file_sheet = file[sheet]
+    table = pd.DataFrame(file_sheet.values)
     offset = table[table.iloc[:, 0] == "Coverage Information"].index.tolist()[0]
     data = table.iloc[offset + 2:]
     data.columns = table.iloc[offset + 1]
     if exclude is not None:
         data = data[~data.Locus.isin(exclude)]
     data = data[['Locus', 'Reads', 'Repeat Sequence']]
-    data['SampleID'] = table.iloc[1, 1]
-    data['Project'] = table.iloc[2, 1]
-    data['Analysis'] = table.iloc[3, 1]
+    data['SampleID'] = table.iloc[2, 1]
+    data['Project'] = table.iloc[3, 1]
+    data['Analysis'] = table.iloc[4, 1]
     return data
 
 
 def uas_format(infile, sexloci=False):
-    auto_strs = parse_str_table_from_sheet(infile, sheet=0, exclude=['Amelogenin'])
+    auto_strs = parse_str_table_from_sheet(infile, sheet='Autosomal STRs', exclude=['Amelogenin'])
     sex_strs = None
     if sexloci is True:
         y_strs = parse_str_table_from_sheet(infile, 'Y STRs')

diff --git a/lusSTR/snp_data.json b/lusSTR/snp_data.json
@@ -68,7 +68,7 @@
     "rs1357617": {
         "Type": "i",
         "Alleles": ["A", "T"],
-        "ReverseCompNeeded": "No",
+        "ReverseCompNeeded": "Yes",
         "Coord": 60
     },
     "rs4364205": {
@@ -362,7 +362,7 @@
     "rs1454361": {
         "Type": "i",
         "Alleles": ["T", "A"],
-        "ReverseCompNeeded": "No",
+        "ReverseCompNeeded": "Yes",
         "Coord": 46
     },
     "rs722290": {
@@ -494,7 +494,7 @@
     "rs445251": {
         "Type": "i",
         "Alleles": ["G", "C"],
-        "ReverseCompNeeded": "No",
+        "ReverseCompNeeded": "Yes",
         "Coord": 43
     },
     "rs1005533": {