removing defunct option for setting file compression

jared/vcf_ref_to_seq.py

@@ -3,7 +3,7 @@
 import argparse
 import os.path
 import logging
-from logging_module import initLogger
+from logging_module import initLogger, logArgs
 from random import sample
 from gene_region import Region, RegionList
 import vcf_reader_func as vf
@@ -35,9 +35,6 @@ def createParser():
                         "Comma-separated list of columns for gene region "
                         " data, format is start/end if no chromosome "
                         " data, start/end/chrom if so"))
-    parser.add_argument("--ext", dest="var_ext", help=(
-                        "Format for variant file if filename doesn't "
-                        "contain extension"))
     parser.add_argument("--compress-vcf", dest="compress_flag",
                         action="store_true", help=("If input VCF is not "
                         "compressed, will compress and use zip search"))
@@ -47,6 +44,9 @@ def createParser():
                         action="store_false", help=("Prevents exception "
                         "generated by mismatched reference alleles from "
                         "VCF file compared to reference"))
+    parser.add_argument("--ima", dest="ima", action="store_true",
+                        help=("If set, will output IMa-format instead of "
+                              "FASTA format"))
     subsamp_group = parser.add_mutually_exclusive_group()
     subsamp_group.add_argument('--subsamp-list', dest="subsamp_fn",
                                help="List of sample names to be used")
@@ -56,11 +56,6 @@ def createParser():
     return parser
 
 
-def logArgs(args):
-    logging.info('Arguments for vcf_to_seq:')
-    for k in vars(args):
-        logging.info('Argument %s: %s' % (k, vars(args)[k]))
-
 def validateFiles(args):
     """Validates that files provided to args all exist on users system"""
     for var in ['vcfname', 'refname', 'genename']:
@@ -144,7 +139,6 @@ def generateSequence(rec_list, ref_seq, fasta_ref,
         return seq[:len(ref_seq)]
     return seq
 
-
 def getHeader(record_count, chrom, region, oneidx=False, halfopen=True):
     start = region.start
     end = region.end
@@ -155,6 +149,24 @@ def getHeader(record_count, chrom, region, oneidx=False, halfopen=True):
         start -= 1
     return '>'+str(record_count)+' '+chrom+' '+str(start)+':'+str(end)
 
+#def getHeader(record_count, chrom, region, oneidx=False, halfopen=True,
+#              pop=None, indiv=None):
+#    start = region.start
+#    end = region.end
+#    if oneidx:
+#        start += 1
+#        end += 1
+#    if not halfopen:
+#        start -= 1
+#    coords = chrom+':'+str(start)+':'+str(end)
+#    header = '>'+str(record_count)+' '+coords+'|'
+#    if pop is not None:
+#        header+=str(pop)
+#    header += '|'
+#    if indiv is not None:
+#        header+=str(indiv)
+#    return header
+
 
 def getFastaFilename(args):
     vcfname = args.vcfname
@@ -205,8 +217,6 @@ def vcf_to_seq(sys_args):
         coordinates of a region. If length 3, the third element
         specifies the index of the chromosome column. Default is "1,2,0",
         to match column order in a BED file.
-    --ext : str ['vcf','vcf.gz'], optional
-        Required if VCF filename does not end with the typical extension.
 
 
 

jared/vcf_to_ima.py

@@ -16,9 +16,10 @@
 
 
 def createParser():
-    parser = argparse.ArgumentParser(description=("Generates sequences from"
-                                     " samples from a VCF file, a reference"
-                                     " genome, and a list of gene regions."))
+    parser = argparse.ArgumentParser(description=("Generates an IMa input "
+                                     "file from a VCF file, a reference"
+                                     " genome, a list of gene regions, "
+                                     "and a population info file."))
     parser.add_argument("vcfname", help="Input VCF filename")
     parser.add_argument("refname", help="Reference FASTA file")
     parser.add_argument("genename", help="Name of gene region file")
@@ -38,9 +39,6 @@ def createParser():
                         "Comma-separated list of columns for gene region "
                         " data, format is start/end if no chromosome "
                         " data, start/end/chrom if so"))
-    parser.add_argument("--ext", dest="var_ext", help=(
-                        "Format for variant file if filename doesn't "
-                        "contain extension"))
     parser.add_argument("--compress-vcf", dest="compress_flag",
                         action="store_true", help=("If input VCF is not "
                         "compressed, will compress and use zip search"))
@@ -64,7 +62,7 @@ def createParser():
 
 def validateFiles(args):
     """Validates that files provided to args all exist on users system"""
-    for var in ['vcfname', 'refname', 'genename']:
+    for var in ['vcfname', 'refname', 'genename','popname']:
         f = vars(args)[var]
         if not os.path.exists(f):
             raise ValueError('Filepath for %s not found at %s' %
@@ -83,8 +81,7 @@ def readSuperPop(pop_fn):
     pop_file = open(pop_fn)
     pop_fns = [l.strip() for l in pop_file.readlines()]
     for pop in pop_fns:
-        popname = pop.strip('.txt')
-        #pop_list.append(pop)
+        popname = os.path.splitext(os.path.basename(pop))[0]
         t_pop = [popname]
         t_sample = []
         popf = open(pop,'r')
@@ -114,15 +111,6 @@ def getMaxAlleleLength(alleles):
     return max([len(r) for r in alleles])
 
 
-def getNextIdx(rec, prev_indiv, prev_idx):
-    """Using record sample array, find individual and haplotype indices for
-    next sample. Will work for any ploidy. Returns -1's when all haplotypes
-    have been iterated through"""
-    if len(rec.samples[prev_indiv].alleles) > prev_idx + 1:
-        return prev_indiv, prev_idx+1
-    if len(rec.samples) > prev_indiv+1:
-        return prev_indiv+1, 0
-    return -1, -1
 
 def getNextIdxName(rec, prev_pop, prev_indiv, prev_idx, pop_data):
 
@@ -265,8 +253,6 @@ def vcf_to_ima(sys_args):
         coordinates of a region. If length 3, the third element
         specifies the index of the chromosome column. Default is "1,2,0",
         to match column order in a BED file.
-    --ext : str ['vcf','vcf.gz'], optional
-        Required if VCF filename does not end with the typical extension.