Mercurial > repos > in_silico > cravat_vcf_convert

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cravat_convert/cravat_convert.py	Tue Jun 12 11:05:27 2018 -0400
@@ -0,0 +1,80 @@
+'''
+Convert a VCF format file to Cravat format file
+'''
+
+import os
+import argparse
+from vcf_converter import CravatConverter
+###
+import ipdb
+
+
+# File read/write configuration variables
+vcf_sep = '\t'
+cr_sep = '\t'
+cr_newline = '\n'
+
+# VCF Headers mapped to their index position in a row of VCF values
+vcf_mapping = {
+    'CHROM': 0,
+    'POS': 1,
+    'ID': 2,
+    'REF': 3,
+    'ALT': 4,
+    'QUAL': 5,
+    'FILTER': 6,
+    'INFO': 7,
+    'FORMAT': 8,
+    'NA00001': 9,
+    'NA00002': 10,
+    'NA00003': 11
+}
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input',
+                            '-i',
+                            required = True,
+                            help='Input path to a VCF file for conversion',)
+    parser.add_argument('--output',
+                            '-o',
+                            default = os.path.join(os.getcwd(), "cravat_converted.txt"),
+                            help = 'Output path to write the cravat file to')
+    return parser.parse_args()
+
+
+def convert(in_path, out_path=None):
+    if not out_path:
+        base, _ = os.path.split(in_path)
+        out_path = os.path.join(base, "cravat_converted.txt")
+
+    with open(in_path, 'r') as in_file, \
+    open(out_path, 'w') as out_file:
+
+        # cr_count will be used to generate the 'TR' field of the cravat rows (first header)
+        cr_count = 0
+        # VCF lines are always assumed to be '+' strand, as VCF doesn't specify that attribute
+        strand = '+'
+        # VCF converter. Adjusts position, reference, and alternate for Cravat formatting.
+        converter = CravatConverter()
+
+        for line in in_file:
+            if line.startswith("#"):
+                continue
+            line = line.strip().split(vcf_sep)
+            # row is dict of VCF headers mapped to corresponding values of this line
+            row = { header: line[index] for header, index in vcf_mapping.items() }
+            for alt in row["ALT"].split(","):
+                new_pos, new_ref, new_alt = converter.extract_vcf_variant(strand, row["POS"], row["REF"], alt)
+                new_pos, new_ref, new_alt = str(new_pos), str(new_ref), str(new_alt)
+                cr_line = cr_sep.join([
+                    'TR' + str(cr_count), row['CHROM'], new_pos, strand, new_ref, new_alt, row['ID']
+                ])
+                out_file.write(cr_line + cr_newline)
+                cr_count += 1
+
+
+if __name__ == "__main__":
+    cli_args = get_args()
+    convert(cli_args.input, cli_args.output)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cravat_convert/cravat_convert.xml	Tue Jun 12 11:05:27 2018 -0400
@@ -0,0 +1,20 @@
+<tool id="cravat_convert" name="CRAVAT Convert" version="1.0.0">
+    <description>Converts a VCF format file to a Cravat format file</description>
+    <command interpreter="python">cravat_convert.py -i $input -o $output</command>
+
+    <inputs>
+        <param format="tabular" name="input" type="data" label="Source file"/>
+    </inputs>
+
+    <outputs>
+        <data format="tabular" name="output" />
+    </outputs>
+
+    <!-- <tests></tests> -->
+
+    <help>
+        Converts a VCF format file to a Cravat format file
+    </help>
+
+</tool>
+
--- a/cravat_submit/cravat_submit.py	Tue Jun 12 11:05:20 2018 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,136 +0,0 @@
-import requests
-import json
-import time
-import urllib
-import sys
-import csv
-import pdb
-
-input_filename = sys.argv[1]
-input_select_bar = sys.argv[2]
-output_filename = sys.argv[3]
-
-#in_file = open('input_call.txt', "r")
-#out_file = open('output_call.txt', "w")
-
-write_header = True
-
-#plugs in params to given URL
-submit = requests.post('http://staging.cravat.us/CRAVAT/rest/service/submit', files={'inputfile':open(input_filename)}, data={'email':'znylund@insilico.us.com', 'analyses': input_select_bar})
-#,'analysis':input_select_bar,'functionalannotation': "on"})
-#Makes the data a json dictionary, takes out only the job ID
-jobid = json.loads(submit.text)['jobid']
-#out_file.write(jobid)
-submitted = json.loads(submit.text)['status']
-#out_file.write('\t' + submitted)
-
-#loops until we find a status equal to Success, then breaks
-while True:
-    check = requests.get('http://staging.cravat.us/CRAVAT/rest/service/status', params={'jobid': jobid})
-    status = json.loads(check.text)['status']
-    resultfileurl = json.loads(check.text)['resultfileurl']
-    #out_file.write(str(status) + ', ')
-    pdb.set_trace()
-    if status == 'Success':
-        #out_file.write('\t' + resultfileurl)
-        break
-    else:
-        time.sleep(2)
-
-#out_file.write('\n')
-
-#creates three files
-file_1 = time.strftime("%H:%M") + '_Z_Variant_Result.tsv'
-file_2 = time.strftime("%H:%M") + '_Z_Additional_Details.tsv'
-file_3 = time.strftime("%H:%M") + 'Combined_Variant_Results.tsv'
-
-
-#Download the two results
-urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant.Result.tsv", file_1)
-urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant_Additional_Details.Result.tsv", file_2)
-
-headers = []
-duplicates = []
-
-#opens the Variant Result file and the Variant Additional Details file as csv readers, then opens the output file (galaxy) as a writer
-with open(file_1) as tsvin_1, open(file_2) as tsvin_2, open(output_filename, 'wb') as tsvout:
-    tsvreader_1 = csv.reader(tsvin_1, delimiter='\t')
-    tsvreader_2 = csv.reader(tsvin_2, delimiter='\t')
-    tsvout = csv.writer(tsvout, delimiter='\t')
-
-#loops through each row in the Variant Additional Details file
-    for row in tsvreader_2:
-        #sets row_2 equal to the same row in Variant Result file
-        row_2 = tsvreader_1.next()
-        #checks if row is empty or if the first term contains '#'
-        if row == [] or row[0][0] == '#':
-            continue
-        #checks if the row begins with input line
-        if row[0] == 'Input line':
-            #Goes through each value in the headers list in VAD
-            for value in row:
-                #Adds each value into headers
-                headers.append(value)
-            #Loops through the Keys in VR
-            for value in row_2:
-                #Checks if the value is already in headers
-                if value in headers:
-                    continue
-                #else adds the header to headers
-                else:
-                    headers.append(value)
-
-            print headers
-            tsvout.writerow(headers)
-
-
-        else:
-
-            cells = []
-            #Goes through each value in the next list
-            for value in row:
-                #adds it to cells
-                cells.append(value)
-            #Goes through each value from the VR file after position 11 (After it is done repeating from VAD file)
-            for value in row_2[11:]:
-                #adds in the rest of the values to cells
-                cells.append(value)
-
-            print  cells
-            tsvout.writerow(cells)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-#a = 'col1\tcol2\tcol3'
-#header_list = a.split('\t')
-
-#loop through the two results, when you first hit header you print out the headers in tabular form
-#Print out each header only once
-#Combine both headers into one output file
-#loop through the rest of the data and assign each value to its assigned header
-#combine this all into one output file
-
-
-
-
-
--- a/cravat_submit/cravat_submit.xml	Tue Jun 12 11:05:20 2018 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,34 +0,0 @@
-<tool id="cravat_submit" name="CRAVAT Submit, Check, and Retrieve" version="0.1.0">
-    <description>Submits, checks for, and retrieves data for cancer annotation</description>
-  <command interpreter="python">cravat_submit.py $input $dropdown $output</command>
-
-
-  <inputs>
-
-    <param format="tabular" name="input" type="data" label="Source file"> </param>
-    <param format="tabular" name="dropdown" type="select" label="Analysis Program">
-      <option value="">None</option>
-      <option value="VEST">VEST</option>
-      <option value="CHASM">CHASM</option>
-      <option value="VEST;CHASM">VEST and CHASM</option>
-    </param>
-
-
-  </inputs>
-
-  <outputs>
-    <data format="tabular" name="output" />
-  </outputs>
-
-  <tests>
-    <test>
-      <param name="input" value="fa_gc_content_input.fa"/>
-      <output name="out_file1" file="fa_gc_content_output.txt"/>
-    </test>
-  </tests>
-
-  <help>
- This tool submits, checks for, and retrieves data for cancer annotation.
-  </help>
-
-</tool>