From a13baa5fb98d8167e70df7008d0d07b40a05a6b9 Mon Sep 17 00:00:00 2001
From: DannyArends
Date: Tue, 22 Mar 2016 23:37:13 +0100
Subject: Adding the geno file parser from Zach

---
 wqflask/utility/genofile_parser.py | 96 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)
 create mode 100644 wqflask/utility/genofile_parser.py

(limited to 'wqflask/utility/genofile_parser.py')

diff --git a/wqflask/utility/genofile_parser.py b/wqflask/utility/genofile_parser.py
new file mode 100644
index 00000000..9dd7b08b
--- /dev/null
+++ b/wqflask/utility/genofile_parser.py
@@ -0,0 +1,96 @@
+# CTL analysis for GN2
+# Author / Maintainer: Danny Arends <Danny.Arends@gmail.com>
+
+from __future__ import print_function, division, absolute_import
+import sys
+import os
+import glob
+import traceback
+import gzip
+
+import simplejson as json
+
+from pprint import pformat as pf
+
+class Marker(object):
+  def __init__(self):
+    self.name = None
+    self.chr = None
+    self.cM = None
+    self.Mb = None
+    self.genotypes = []
+
+
+class ConvertGenoFile(object):
+
+  def __init__(self, input_file):
+    self.mb_exists = False
+    self.cm_exists = False
+    self.markers = []
+    
+    self.latest_row_pos = None
+    self.latest_col_pos = None
+    
+    self.latest_row_value = None
+    self.latest_col_value = None
+    self.input_fh = open(input_file)
+    print("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!")
+    self.haplotype_notation = {
+      '@mat': "3",
+      '@pat': "1",
+      '@het': "2",
+      '@unk': "NA"
+    }
+    self.configurations = {}
+
+  def process_rows(self):
+    for self.latest_row_pos, row in enumerate(self.input_fh):
+        self.latest_row_value = row
+        # Take care of headers
+        if not row.strip():
+            continue
+        if row.startswith('#'):
+            continue
+        if row.startswith('Chr'):
+            if 'Mb' in row.split():
+                self.mb_exists = True
+            if 'cM' in row.split():
+                self.cm_exists = True
+            continue
+        if row.startswith('@'):
+            key, _separater, value = row.partition(':')
+            key = key.strip()
+            value = value.strip()
+            if key in self.haplotype_notation:
+                self.configurations[value] = self.haplotype_notation[key]
+            continue
+        if not len(self.configurations):
+            raise EmptyConfigurations
+        yield row
+
+  def process_csv(self):
+    for row_count, row in enumerate(self.process_rows()):
+      row_items = row.split("\t")
+
+      this_marker = Marker()
+      this_marker.name = row_items[1]
+      this_marker.chr = row_items[0]
+      if self.cm_exists and self.mb_exists:
+        this_marker.cM = row_items[2]
+        this_marker.Mb = row_items[3]
+        genotypes = row_items[4:]
+      elif self.cm_exists:
+          this_marker.cM = row_items[2]
+          genotypes = row_items[3:]
+      elif self.mb_exists:
+          this_marker.Mb = row_items[2]
+          genotypes = row_items[3:]
+      else:
+        genotypes = row_items[2:]
+      for item_count, genotype in enumerate(genotypes):
+        if genotype.upper() in self.configurations:
+          this_marker.genotypes.append(self.configurations[genotype.upper()])
+        else:
+          this_marker.genotypes.append("NA")
+      self.markers.append(this_marker.__dict__)
+
-- 
cgit v1.2.3


From 3d505d997511cd8f7b9f14510059cb2983edc6d4 Mon Sep 17 00:00:00 2001
From: DannyArends
Date: Wed, 23 Mar 2016 23:07:16 +0100
Subject: Parsing the names of the individuals, and coding H as -999

---
 wqflask/utility/genofile_parser.py | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

(limited to 'wqflask/utility/genofile_parser.py')

diff --git a/wqflask/utility/genofile_parser.py b/wqflask/utility/genofile_parser.py
index 9dd7b08b..67b84dc9 100644
--- a/wqflask/utility/genofile_parser.py
+++ b/wqflask/utility/genofile_parser.py
@@ -8,6 +8,7 @@ import glob
 import traceback
 import gzip
 
+
 import simplejson as json
 
 from pprint import pformat as pf
@@ -34,12 +35,12 @@ class ConvertGenoFile(object):
     self.latest_row_value = None
     self.latest_col_value = None
     self.input_fh = open(input_file)
-    print("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!")
+    print("!!!!!!!!!!!!!!!!PARSER!!!!!!!!!!!!!!!!!!")
     self.haplotype_notation = {
-      '@mat': "3",
-      '@pat': "1",
-      '@het': "2",
-      '@unk': "NA"
+      '@mat': "1",
+      '@pat': "2",
+      '@het': "-999",
+      '@unk': "-999"
     }
     self.configurations = {}
 
@@ -56,6 +57,8 @@ class ConvertGenoFile(object):
                 self.mb_exists = True
             if 'cM' in row.split():
                 self.cm_exists = True
+            skip = 2 + self.cm_exists + self.mb_exists
+            self.individuals = row.split()[skip:]
             continue
         if row.startswith('@'):
             key, _separater, value = row.partition(':')
@@ -88,9 +91,10 @@ class ConvertGenoFile(object):
       else:
         genotypes = row_items[2:]
       for item_count, genotype in enumerate(genotypes):
-        if genotype.upper() in self.configurations:
-          this_marker.genotypes.append(self.configurations[genotype.upper()])
+        if genotype.upper().strip() in self.configurations:
+          this_marker.genotypes.append(self.configurations[genotype.upper().strip()])
         else:
+          print("WARNING:", genotype.upper())
           this_marker.genotypes.append("NA")
       self.markers.append(this_marker.__dict__)
 
-- 
cgit v1.2.3