Refactoring old stuff, general cleanup

gff_to_bed.py

@@ -47,4 +47,4 @@ def main(args):
 
 
 if __name__ == '__main__':
-    gff_to_bed(get_args())
+    main(get_args())

gtf_append_chr_ids.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python3
+# Author: Jeffrey Grover
+# Purpose: Append a string to all chromosome IDs
+# Created: 2019-03-14
+
+from argparse import ArgumentParser
+
+
+def append_chromosome(input_file, chrom_string):
+    with open(input_file, 'r') as input_handle:
+        for line in input_handle:
+            entry = line.strip().split('\t')
+            entry[0] = entry[0] + chrom_string
+            print('\t'.join(entry))
+
+
+# Parse command line options
+
+def get_args():
+    parser = ArgumentParser(
+        description='Appends a string to all chromosomes in a GTF file')
+    parser.add_argument('gtf', help='File to process', metavar='FILE.gtf')
+    parser.add_argument('--string',
+                        '-s',
+                        help='String to add to each chromosome ID')
+    return parser.parse_args()
+
+
+# Process file
+
+
+def main(args):
+    append_chromosome(args.gtf, args.string)
+
+
+if __name__ == '__main__':
+    main(get_args())

gtf_clean_ids.py

@@ -9,38 +9,45 @@
 from argparse import ArgumentParser
 
 
-def clean_gtf(input_file, cleaner_sep):
+def clean_gtf(input_file, cleaner_sep, chromosome, feature):
     with open(input_file, 'r') as input_handle:
         for line in input_handle:
-            entry = line.split('\t')
-            chrom = entry[0].split(cleaner_sep)[0]
-            source = entry[1]
-            feature = entry[2]
-            start = entry[3]
-            stop = entry[4]
-            score = entry[5]
-            strand = entry[6]
-            frame = entry[7]
+            entry = line.strip().split('\t')
+            if chromosome:
+                entry[0] = entry[0].split(cleaner_sep)[0]
             group = entry[8].split('; ')
-            transcript_id = group[0].split(cleaner_sep)[0]
-            gene_id = group[1].split(cleaner_sep)[0]
-            gene_name = group[2].split(cleaner_sep)[0]
-            print(chrom, source, feature, start, stop, score, strand, frame,
-                  sep='\t', end='\t')
-            print(transcript_id, gene_id, gene_name, sep='"; ', end='"\n')
+            if feature:
+                transcript_id = group[0].split(cleaner_sep)[0]
+                gene_id = group[1].split(cleaner_sep)[0]
+                gene_name = group[2].split(cleaner_sep)[0]
+                group = [transcript_id, gene_id, gene_name]
+            print('\t'.join(entry[0:8]), end='\t')
+            print('"; '.join(group), end='"\n')
 
 
 # Parse command line options
 
-parser = ArgumentParser(
-    description='Removes garbage from chromosome and gene IDs in a '
-    'gtf file. Works on at least the one file I needed it to')
-parser.add_argument('input_path', help='File to process', metavar='File')
-parser.add_argument('--sep', '-s', help='Separator to remove text after')
 
-input_path = parser.parse_args().input_path
-cleaner_sep = parser.parse_args().sep
+def get_args():
+    parser = ArgumentParser(
+        description='Removes garbage from chromosome and gene IDs in a gtf.')
+    parser.add_argument('gtf', help='File to process', metavar='FILE.gtf')
+    parser.add_argument('--sep', '-s', help='Separator to remove text after')
+    parser.add_argument('--chromosome', '-c',
+                        help='Clean chromosome IDs',
+                        action='store_true')
+    parser.add_argument('--feature', '-f',
+                        help='Clean feature IDs',
+                        action='store_true')
+    return parser.parse_args()
+
 
 # Process file
 
-clean_gtf(input_path, cleaner_sep)
+
+def main(args):
+    clean_gtf(args.gtf, args.sep, args.chromosome, args.feature)
+
+
+if __name__ == '__main__':
+    main(get_args())

methyldackel_conversion_calculator.py

@@ -4,7 +4,6 @@
 # Purpose: Determine bisulfite conversion rate from MethylDackel bedGraph files
 # Created: 2/2019
 
-import csv
 from argparse import ArgumentParser
 
 # Function block
@@ -14,20 +13,20 @@ def parse_bedgraph(input_context_bedgraph):
     met_count = 0
     unmet_count = 0
     with open(input_context_bedgraph, 'r') as input_handle:
-        bedgraph_reader = csv.reader(input_handle, delimiter='\t')
-        next(bedgraph_reader)  # Skip header
-        for line in bedgraph_reader:
-            met_count += int(line[4])
-            unmet_count += int(line[5])
+        next(input_handle)  # Skip header
+        for line in input_handle:
+            entry = line.strip().split()
+            met_count += int(entry[4])
+            unmet_count += int(entry[5])
     return [met_count, unmet_count]
 
 
 def conversion_calc(cg_counts, chg_counts, chh_counts):
     total_cg = cg_counts[0] + cg_counts[1]
     total_chg = chg_counts[0] + chg_counts[1]
     total_chh = chh_counts[0] + chh_counts[1]
-    conversion_rate = ( sum((cg_counts[1], chg_counts[1], chh_counts[1])) /
-                        sum((total_cg, total_chg, total_chh)) ) * 100
+    conversion_rate = (sum((cg_counts[1], chg_counts[1], chh_counts[1])) / sum(
+        (total_cg, total_chg, total_chh))) * 100
     print('CG Methylated/Total:\t', cg_counts[0], '/', total_cg)
     print('CHG Methylated/Total:\t', chg_counts[0], '/', total_chg)
     print('CHH Methylated/Total:\t', chh_counts[0], '/', total_chh)
@@ -36,21 +35,34 @@ def conversion_calc(cg_counts, chg_counts, chh_counts):
 
 # Command line parser
 
-parser = ArgumentParser(
-    description='Load CG, CHG, and CHH context bedGraph files from MethylDackel'
-    'and calculate bisulfite conversion rate.')
-parser.add_argument('--CG', help='CG Context bedGraph file.', metavar='File')
-parser.add_argument('--CHG', help='CHG context bedGraph file.', metavar='File')
-parser.add_argument('--CHH', help='CHH context bedGraph file.', metavar='File')
 
-cg_bedgraph = parser.parse_args().CG
-chg_bedgraph = parser.parse_args().CHG
-chh_bedgraph = parser.parse_args().CHH
+def get_args():
+    parser = ArgumentParser(
+        description=
+        'Load CG, CHG, and CHH context bedGraph files from MethylDackel'
+        'and calculate bisulfite conversion rate.')
+    parser.add_argument('--CG',
+                        help='CG Context bedGraph file.',
+                        metavar='FILE.bedGraph')
+    parser.add_argument('--CHG',
+                        help='CHG context bedGraph file.',
+                        metavar='FILE.bedGraph')
+    parser.add_argument('--CHH',
+                        help='CHH context bedGraph file.',
+                        metavar='FILE.bedGraph')
+    return parser.parse_args()
+
 
 # Process the files
 
-cg_counts = parse_bedgraph(cg_bedgraph)
-chg_counts = parse_bedgraph(chg_bedgraph)
-chh_counts = parse_bedgraph(chh_bedgraph)
 
-conversion_calc(cg_counts, chg_counts, chh_counts)
+def main(args):
+    cg_counts = parse_bedgraph(args.CG)
+    chg_counts = parse_bedgraph(args.CHG)
+    chh_counts = parse_bedgraph(args.CHH)
+
+    conversion_calc(cg_counts, chg_counts, chh_counts)
+
+
+if __name__ == '__main__':
+    main(get_args())

methyldackel_percent_methylation.py

@@ -5,54 +5,56 @@
 # Created: 2019-04-29
 
 from argparse import ArgumentParser
-
-# Function block
+from sys import exit
 
 
 def methyl_calc(input_bedgraph):
     met_c = 0
     unmet_c = 0
     with open(input_bedgraph, 'r') as input_handle:
         for line in input_handle:
-            if not line.startswith('track'):  # Skip header
-                met_c += int(line.split()[4])
-                unmet_c += int(line.split()[5])
+            next(input_handle)  # Skip header
+            met_c += int(line.split()[4])
+            unmet_c += int(line.split()[5])
     return (met_c / (met_c + unmet_c)) * 100
 
 
 # Command line parser
 
-parser = ArgumentParser(
-    description='Calculate percent methylation from a set of MethylDackel '
-    'bedGraphs files.')
-parser.add_argument('--CG',
-                    help='CG context bedGraph',
-                    default=None,
-                    metavar='File')
-parser.add_argument('--CHG',
-                    help='CHG context bedGraph',
-                    default=None,
-                    metavar='File')
-parser.add_argument('--CHH',
-                    help='CHH context bedGraph',
-                    default=None,
-                    metavar='File')
-
-cg_bedgraph = parser.parse_args().CG
-chg_bedgraph = parser.parse_args().CHG
-chh_bedgraph = parser.parse_args().CHH
+def get_args():
+    parser = ArgumentParser(
+        description='Calculate percent methylation from a set of MethylDackel '
+        'bedGraphs files.')
+    parser.add_argument('--CG',
+                        help='CG context bedGraph',
+                        default=None,
+                        metavar='FILE.bedGraph')
+    parser.add_argument('--CHG',
+                        help='CHG context bedGraph',
+                        default=None,
+                        metavar='FILE.bedGraph')
+    parser.add_argument('--CHH',
+                        help='CHH context bedGraph',
+                        default=None,
+                        metavar='FILE.bedGraph')
+    return parser.parse_args()
+
 
 # Process the files
 
-if not cg_bedgraph and not chg_bedgraph and not chh_bedgraph:
-    print('Without data how do you expect to do anything!')
-    exit
-if cg_bedgraph:
-    cg_methylation = methyl_calc(cg_bedgraph)
-    print('CG', cg_methylation, sep='\t')
-if chg_bedgraph:
-    chg_methylation = methyl_calc(chg_bedgraph)
-    print('CHG', chg_methylation, sep='\t')
-if chh_bedgraph:
-    chh_methylation = methyl_calc(chh_bedgraph)
-    print('CHH', chh_methylation, sep='\t')
+def main(args):
+    if not args.CG and not args.CHG and not args.CHH:
+        exit('Without data how do you expect to do anything!')
+    if args.CG:
+        cg_methylation = methyl_calc(args.CG)
+        print('CG', cg_methylation, sep='\t')
+    if args.CHG:
+        chg_methylation = methyl_calc(args.CHG)
+        print('CHG', chg_methylation, sep='\t')
+    if args.CHH:
+        chh_methylation = methyl_calc(args.CHH)
+        print('CHH', chh_methylation, sep='\t')
+
+
+if __name__ == '__main__':
+    main(get_args())

methylkit_analyze.r

@@ -155,16 +155,10 @@ get_args <- function () {
 
 # Main definition
 
-main <- function () {
-
-  # Get args
-
-  args <- get_args()
+main <- function (args) {
   control_files <- unlist(strsplit(args$control, ','))
   experimental_files <- unlist(strsplit(args$experimental, ','))
 
-  # Create out_dir
-
   output_dir <- 'methylkit_analyze'
   dir.create(output_dir)
 
@@ -179,4 +173,4 @@ main <- function () {
 
 # Call main
 
-main()
+main(get_args())

mosdepth_to_x_coverage.py

@@ -42,11 +42,11 @@ def get_args():
     parser.add_argument(
         '-f', '--fasta',
         help='.fasta file for genome',
-        metavar='File')
+        metavar='FILE.fasta')
     parser.add_argument(
         '-m', '--mosdepth',
         help='.bed.gz mosdepth output',
-        metavar='File')
+        metavar='FILE.bed.gz')
     return parser.parse_args()
 
 
@@ -65,5 +65,4 @@ def main(args):
 
 
 if __name__ == '__main__':
-    args = get_args()
-    main(args)
+    main(get_args())