diff options
author | zsloan | 2019-05-24 11:35:12 -0500 |
---|---|---|
committer | zsloan | 2019-05-24 11:35:12 -0500 |
commit | e304c2cfdf1b38da483efa607a2acd72b66ad0de (patch) | |
tree | 90197932aa4f867bd710afaefe6e59082689279c /wqflask | |
parent | 338521197f5de79bafa8f230c692d3efab0da9c1 (diff) | |
download | genenetwork2-e304c2cfdf1b38da483efa607a2acd72b66ad0de.tar.gz |
Replaced qtlreaper Dataset object with python object
Diffstat (limited to 'wqflask')
-rw-r--r-- | wqflask/base/data_set.py | 7 | ||||
-rw-r--r-- | wqflask/utility/gen_geno_ob.py | 135 |
2 files changed, 140 insertions, 2 deletions
diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index beb2a8a2..b324ac74 100644 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -43,6 +43,7 @@ from db import webqtlDatabaseFunction from utility import webqtlUtil from utility.benchmark import Bench from utility import chunks +from utility import gen_geno_ob from utility.tools import locate, locate_ignore_error, flat_files from maintenance import get_group_samplelists @@ -388,14 +389,16 @@ class DatasetGroup(object): #genotype_1 is Dataset Object without parents and f1 #genotype_2 is Dataset Object with parents and f1 (not for intercross) - genotype_1 = reaper.Dataset() + #genotype_1 = reaper.Dataset() # reaper barfs on unicode filenames, so here we ensure it's a string if self.genofile: full_filename = str(locate(self.genofile, 'genotype')) else: full_filename = str(locate(self.name + '.geno', 'genotype')) - genotype_1.read(full_filename) + #genotype_1.read(full_filename) + + genotype_1 = gen_geno_ob.genotype(full_filename) if genotype_1.type == "group" and self.parlist: genotype_2 = genotype_1.add(Mat=self.parlist[0], Pat=self.parlist[1]) #, F1=_f1) diff --git a/wqflask/utility/gen_geno_ob.py b/wqflask/utility/gen_geno_ob.py new file mode 100644 index 00000000..5824b0b3 --- /dev/null +++ b/wqflask/utility/gen_geno_ob.py @@ -0,0 +1,135 @@ +from __future__ import absolute_import, division, print_function
+
+class genotype(object):
+ """
+ Replacement for reaper.Dataset so we can remove qtlreaper use while still generating mapping output figure
+ """
+
+ def __init__(self, filename):
+ self.group = None
+ self.type = "riset"
+ self.prgy = []
+ self.nprgy = 0
+ self.mat = -1
+ self.pat = 1
+ self.het = 0
+ self.unk = "U"
+ self.filler = False
+ self.mb_exists = False
+
+ #ZS: This is because I'm not sure if some files switch the column that contains Mb/cM positions; might be unnecessary
+ self.cm_column = 2
+ self.mb_column = 3
+
+ self.chromosomes = []
+
+ self.read_file(filename)
+
+ def __iter__(self):
+ return iter(self.chromosomes)
+
+ def __getitem__(self, index):
+ return self.chromosomes[index]
+
+ def __len__(self):
+ return len(self.chromosomes)
+
+ def read_file(self, filename):
+
+ with open(filename, 'r') as geno_file:
+ lines = geno_file.readlines()
+
+ this_chr = "" #ZS: This is so it can track when the chromosome changes as it iterates through markers
+ chr_ob = None
+ for line in lines:
+ if line[0] == "#":
+ continue
+ elif line[0] == "@":
+ label = line.split(":")[0][1:]
+ if label == "name":
+ self.group = line.split(":")[1]
+ elif label == "filler":
+ if line.split(":")[1] == "yes":
+ self.filler = True
+ elif label == "type":
+ self.type = line.split(":")[1]
+ elif label == "mat":
+ self.mat = line.split(":")[1]
+ elif label == "pat":
+ self.pat = line.split(":")[1]
+ elif label == "het":
+ self.het = line.split(":")[1]
+ elif label == "unk":
+ self.unk = line.split(":")[1]
+ else:
+ continue
+ elif line[:3] == "Chr":
+ header_row = line.split("\t")
+ if header_row[2] == "Mb":
+ self.mb_exists = True
+ self.mb_column = 2
+ self.cm_column = 3
+ elif header_row[3] == "Mb":
+ self.mb_exists = True
+ self.mb_column = 3
+ elif header_row[2] == "cM":
+ self.cm_column = 2
+
+ if self.mb_exists:
+ self.prgy = header_row[4:]
+ else:
+ self.prgy = header_row[3:]
+ self.nprgy = len(self.prgy)
+ else:
+ if line.split("\t")[0] != this_chr:
+ if this_chr != "":
+ self.chromosomes.append(chr_ob)
+ this_chr = line.split("\t")[0]
+ chr_ob = Chr(line.split("\t")[0], self)
+ chr_ob.add_marker(line.split("\t"))
+
+class Chr(object):
+ def __init__(self, name, geno_ob):
+ self.name = name
+ self.loci = []
+ self.mb_exists = geno_ob.mb_exists
+ self.cm_column = geno_ob.cm_column
+ self.mb_column = geno_ob.mb_column
+ self.geno_ob = geno_ob
+
+ def __iter__(self):
+ return iter(self.loci)
+
+ def __getitem__(self, index):
+ return self.loci[index]
+
+ def __len__(self):
+ return len(self.loci)
+
+ def add_marker(self, marker_row):
+ self.loci.append(Locus(marker_row, self.geno_ob))
+
+class Locus(object):
+ def __init__(self, marker_row, geno_ob):
+ self.chr = marker_row[0]
+ self.name = marker_row[1]
+ self.cM = float(marker_row[geno_ob.cm_column])
+ self.Mb = float(marker_row[geno_ob.mb_column]) if geno_ob.mb_exists else None
+
+ geno_table = {
+ geno_ob.mat: -1,
+ geno_ob.pat: 1,
+ geno_ob.het: 0,
+ geno_ob.unk: "U"
+ }
+
+ self.genotype = []
+ if geno_ob.mb_exists:
+ start_pos = 4
+ else:
+ start_pos = 3
+ for allele in marker_row[start_pos:]:
+ if allele in geno_table.keys():
+ self.genotype.append(geno_table[allele])
+ else: #ZS: Some genotype appears that isn't specified in the metadata, make it unknown
+ self.genotype.append("U")
\ No newline at end of file |