| Previous changeset 11:ae65a43ed658 (2018-06-27) Next changeset 13:2c9208fe16a0 (2018-07-30) |
|
Commit message:
Uploaded |
|
added:
cravat_convert/__pycache__/base_converter.cpython-36.pyc cravat_convert/__pycache__/vcf_converter.cpython-36.pyc cravat_convert/base_converter.py cravat_convert/cravat_convert.py cravat_convert/cravat_convert.xml cravat_convert/vcf_converter.py |
|
removed:
cravat_submit/cravat_submit.py cravat_submit/cravat_submit.xml |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_convert/__pycache__/base_converter.cpython-36.pyc |
| b |
| Binary file cravat_convert/__pycache__/base_converter.cpython-36.pyc has changed |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_convert/__pycache__/vcf_converter.cpython-36.pyc |
| b |
| Binary file cravat_convert/__pycache__/vcf_converter.cpython-36.pyc has changed |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_convert/base_converter.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cravat_convert/base_converter.py Mon Jul 30 13:22:36 2018 -0400 |
| b |
| @@ -0,0 +1,22 @@ +class BaseConverter(object): + def __init__(self): + self.format_name = None + def check_format(self,*args,**kwargs): + err_msg = 'Converter for %s format has no method check_format' %\ + self.format_name + raise NotImplementedError(err_msg) + def setup(self,*args,**kwargs): + err_msg = 'Converter for %s format has no method setup' %\ + self.format_name + raise NotImplementedError(err_msg) + def convert_line(self,*args,**kwargs): + err_msg = 'Converter for %s format has no method convert_line' %\ + self.format_name + raise NotImplementedError(err_msg) + + +class BadFormatError(Exception): + def __init__(self, message, errors=None): + super(BadFormatError, self).__init__(message) + # Support for custom error codes, if added later + self.errors = errors \ No newline at end of file |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_convert/cravat_convert.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cravat_convert/cravat_convert.py Mon Jul 30 13:22:36 2018 -0400 |
| [ |
| @@ -0,0 +1,80 @@ +from __future__ import print_function +import os +import argparse +from vcf_converter import CravatConverter + +def get_vcf_mapping(): + """ : VCF Headers mapped to their index position in a row of VCF values. + : These are only the mandatory columns, per the VCF spec. + """ + return { + 'CHROM': 0, + 'POS': 1, + 'ID': 2, + 'REF': 3, + 'ALT': 4, + 'QUAL': 5, + 'FILTER': 6, + 'INFO': 7 + } + + +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 = None, + help = 'Output path to write the cravat file to') + return parser.parse_args() + + +def convert(in_path, out_path=None, cr_sep='\t', cr_newline='\n'): + """ : Convert a VCF file to a Cravat file. + : Arguments: + : in_path: <str> path to input vcf file + : out_path: <str> path to output cravat file. Will defualt to cravat_converted.txt in the input directory. + : cr_sep: <str> the value delimiter for the output cravat file. Default value of '\\t'. + : out_newline: <str> the newline delimiter in the output cravat file. Default of '\\n' + """ + 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() + # A dictionary of mandatory vcf headers mapped to their row indices + vcf_mapping = get_vcf_mapping() + + for line in in_file: + if line.startswith("#"): + continue + line = line.strip().split() + # 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() + if cli_args.output == None: + base, _ = os.path.split(cli_args.input) + cli_args.output = os.path.join(base, "cravat_converted.txt") + convert(in_path = cli_args.input, out_path = cli_args.output) |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_convert/cravat_convert.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cravat_convert/cravat_convert.xml Mon Jul 30 13:22:36 2018 -0400 |
| b |
| @@ -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> + |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_convert/vcf_converter.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cravat_convert/vcf_converter.py Mon Jul 30 13:22:36 2018 -0400 |
| [ |
| b'@@ -0,0 +1,243 @@\n+"""\r\n+A module originally obtained from the cravat package. Modified to use in the vcf\r\n+converter galaxy tool.\r\n+\r\n+\r\n+Register of changes made (Chris Jacoby):\r\n+ 1) Changed imports as galaxy tool won\'t have access to complete cravat python package\r\n+ 2) Defined BadFormatError in BaseConverted file, as I didn\'t have the BadFormatError module\r\n+"""\r\n+\r\n+from base_converter import BaseConverter, BadFormatError\r\n+import re\r\n+\r\n+class CravatConverter(BaseConverter):\r\n+ \r\n+ def __init__(self):\r\n+ self.format_name = \'vcf\'\r\n+ self.samples = []\r\n+ self.var_counter = 0\r\n+ self.addl_cols = [{\'name\':\'phred\',\r\n+ \'title\':\'Phred\',\r\n+ \'type\':\'string\'},\r\n+ {\'name\':\'filter\',\r\n+ \'title\':\'VCF filter\',\r\n+ \'type\':\'string\'},\r\n+ {\'name\':\'zygosity\',\r\n+ \'title\':\'Zygosity\',\r\n+ \'type\':\'string\'},\r\n+ {\'name\':\'alt_reads\',\r\n+ \'title\':\'Alternate reads\',\r\n+ \'type\':\'int\'},\r\n+ {\'name\':\'tot_reads\',\r\n+ \'title\':\'Total reads\',\r\n+ \'type\':\'int\'},\r\n+ {\'name\':\'af\',\r\n+ \'title\':\'Variant allele frequency\',\r\n+ \'type\':\'float\'}]\r\n+ \r\n+ def check_format(self, f): \r\n+ return f.readline().startswith(\'##fileformat=VCF\')\r\n+ \r\n+ def setup(self, f):\r\n+ \r\n+ vcf_line_no = 0\r\n+ for line in f:\r\n+ vcf_line_no += 1\r\n+ if len(line) < 6:\r\n+ continue\r\n+ if line[:6] == \'#CHROM\':\r\n+ toks = re.split(\'\\s+\', line.rstrip())\r\n+ if len(toks) > 8:\r\n+ self.samples = toks[9:]\r\n+ break\r\n+ \r\n+ def convert_line(self, l):\r\n+ if l.startswith(\'#\'): return None\r\n+ self.var_counter += 1\r\n+ toks = l.strip(\'\\r\\n\').split(\'\\t\')\r\n+ all_wdicts = []\r\n+ if len(toks) < 8:\r\n+ raise BadFormatError(\'Wrong VCF format\')\r\n+ [chrom, pos, tag, ref, alts, qual, filter, info] = toks[:8]\r\n+ if tag == \'\':\r\n+ raise BadFormatError(\'ID column is blank\')\r\n+ elif tag == \'.\':\r\n+ tag = \'VAR\' + str(self.var_counter)\r\n+ if chrom[:3] != \'chr\':\r\n+ chrom = \'chr\' + chrom\r\n+ alts = alts.split(\',\')\r\n+ len_alts = len(alts)\r\n+ if len(toks) == 8:\r\n+ for altno in range(len_alts):\r\n+ wdict = None\r\n+ alt = alts[altno]\r\n+ newpos, newref, newalt = self.extract_vcf_variant(\'+\', pos, ref, alt)\r\n+ wdict = {\'tags\':tag,\r\n+ \'chrom\':chrom,\r\n+ \'pos\':newpos,\r\n+ \'ref_base\':newref,\r\n+ \'alt_base\':newalt,\r\n+ \'sample_id\':\'no_sample\',\r\n+ \'phred\': qual,\r\n+ \'filter\': filter}\r\n+ all_wdicts.append(wdict)\r\n+ elif len(toks) > 8:\r\n+ sample_datas = toks[9:]\r\n+ genotype_fields = {}\r\n+ genotype_field_no = 0\r\n+ for genotype_field in toks[8].split(\':\'):\r\n+ genotype_fields[genotype_field] = genotype_field_no\r\n+ genotype_field_no += 1\r\n+ if not (\'GT\' in genotype_fields):\r\n+ raise BadFormatError(\'No GT Field\')\r\n+ gt_field_no = genotype_fields[\'GT\']\r\n+ for sample_no in range(len(sample_datas)):\r\n+ sample = self.samples[sample_no]\r\n+ sample_data = sample_datas[sample_no].split(\':\')\r\n+ gts = {}\r\n+ for gt in sample_data[gt_field_no].replace(\'/\', \'|\').split(\'|\'):\r\n+ '..b'\r\n+ ref_reads = sample_data[genotype_fields[\'AD\']].split(\',\')[0]\r\n+ alt_reads = sample_data[genotype_fields[\'AD\']].split(\',\')[1]\r\n+ elif gt == max(gts.keys()): \r\n+ #if geontype has multiple alt bases, then AD will have #alt1 reads, #alt2 reads\r\n+ alt_reads = sample_data[genotype_fields[\'AD\']].split(\',\')[1]\r\n+ else:\r\n+ alt_reads = sample_data[genotype_fields[\'AD\']].split(\',\')[0] \r\n+ \r\n+ if \'DP\' in genotype_fields and genotype_fields[\'DP\'] <= len(sample_data): \r\n+ depth = sample_data[genotype_fields[\'DP\']] \r\n+ elif alt_reads != \'\' and ref_reads != \'\':\r\n+ #if DP is not present but we have alt and ref reads count, dp = ref+alt\r\n+ depth = int(alt_reads) + int(ref_reads) \r\n+\r\n+ if \'AF\' in genotype_fields and genotype_fields[\'AF\'] <= len(sample_data):\r\n+ af = float(sample_data[genotype_fields[\'AF\']] )\r\n+ elif depth != \'\' and alt_reads != \'\':\r\n+ #if AF not specified, calc it from alt and ref reads\r\n+ af = float(alt_reads) / float(depth)\r\n+ \r\n+ return depth, alt_reads, af\r\n+ \r\n+ def extract_vcf_variant (self, strand, pos, ref, alt):\r\n+\r\n+ reflen = len(ref)\r\n+ altlen = len(alt)\r\n+ \r\n+ # Returns without change if same single nucleotide for ref and alt. \r\n+ if reflen == 1 and altlen == 1 and ref == alt:\r\n+ return pos, ref, alt\r\n+ \r\n+ # Trimming from the start and then the end of the sequence \r\n+ # where the sequences overlap with the same nucleotides\r\n+ new_ref2, new_alt2, new_pos = \\\r\n+ self.trimming_vcf_input(ref, alt, pos, strand)\r\n+ \r\n+ if new_ref2 == \'\':\r\n+ new_ref2 = \'-\'\r\n+ if new_alt2 == \'\':\r\n+ new_alt2 = \'-\'\r\n+ \r\n+ return new_pos, new_ref2, new_alt2\r\n+ \r\n+ # This function looks at the ref and alt sequences and removes \r\n+ # where the overlapping sequences contain the same nucleotide.\r\n+ # This trims from the end first but does not remove the first nucleotide \r\n+ # because based on the format of VCF input the \r\n+ # first nucleotide of the ref and alt sequence occur \r\n+ # at the position specified.\r\n+ # End removed first, not the first nucleotide\r\n+ # Front removed and position changed\r\n+ def trimming_vcf_input(self, ref, alt, pos, strand):\r\n+ pos = int(pos)\r\n+ reflen = len(ref)\r\n+ altlen = len(alt)\r\n+ minlen = min(reflen, altlen)\r\n+ new_ref = ref\r\n+ new_alt = alt\r\n+ new_pos = pos\r\n+ # Trims from the end. Except don\'t remove the first nucleotide. \r\n+ # 1:6530968 CTCA -> GTCTCA becomes C -> GTC.\r\n+ for nt_pos in range(0, minlen - 1): \r\n+ if ref[reflen - nt_pos - 1] == alt[altlen - nt_pos - 1]:\r\n+ new_ref = ref[:reflen - nt_pos - 1]\r\n+ new_alt = alt[:altlen - nt_pos - 1]\r\n+ else:\r\n+ break \r\n+ new_ref_len = len(new_ref)\r\n+ new_alt_len = len(new_alt)\r\n+ minlen = min(new_ref_len, new_alt_len)\r\n+ new_ref2 = new_ref\r\n+ new_alt2 = new_alt\r\n+ # Trims from the start. 1:6530968 G -> GT becomes 1:6530969 - -> T.\r\n+ for nt_pos in range(0, minlen):\r\n+ if new_ref[nt_pos] == new_alt[nt_pos]:\r\n+ if strand == \'+\':\r\n+ new_pos += 1\r\n+ elif strand == \'-\':\r\n+ new_pos -= 1\r\n+ new_ref2 = new_ref[nt_pos + 1:]\r\n+ new_alt2 = new_alt[nt_pos + 1:]\r\n+ else:\r\n+ new_ref2 = new_ref[nt_pos:]\r\n+ new_alt2 = new_alt[nt_pos:]\r\n+ break \r\n+ return new_ref2, new_alt2, new_pos\r\n+\r\n+\r\n+if __name__ == "__main__":\r\n+ c = CravatConverter()\n\\ No newline at end of file\n' |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_submit/cravat_submit.py --- a/cravat_submit/cravat_submit.py Wed Jun 27 17:54:15 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,103 +0,0 @@ -import requests -import json -import time -import urllib -import sys -import csv - -input_filename = sys.argv[1] -input_select_bar = sys.argv[2] -output_filename = sys.argv[3] - -# HACK: Input args corrections. -if input_select_bar == "None": - # The server represents an analyses of None as ""; however, submitting a blank string on command line throws off arg position - input_select_bar = "" - # The server represents the "Vest and Chasm" analyses as "VEST;CHASM; however, galaxy converts the semi-colon to an 'X'. Switch it back. -elif input_select_bar == "VESTXCHASM": - input_select_bar = "VEST;CHASM" - -write_header = True - -#plugs in params to given URL -submit = requests.post('http://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) + ', ') - 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://cravat.us/CRAVAT/results/" + jobid + "/" + "Variant.Result.tsv", file_1) -urllib.urlretrieve("http://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) \ No newline at end of file |
| b |
| diff -r ae65a43ed658 -r 2376854ac01f cravat_submit/cravat_submit.xml --- a/cravat_submit/cravat_submit.xml Wed Jun 27 17:54:15 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -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">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> |