| Previous changeset 13:20ebb3a5c1a4 (2018-06-12) Next changeset 15:a46b42bda5d7 (2018-06-12) |
|
Commit message:
Uploaded |
|
added:
cravat_annotate/cravat_annotate.py cravat_annotate/cravat_annotate.xml |
| b |
| diff -r 20ebb3a5c1a4 -r a28f1f52eb93 cravat_annotate/cravat_annotate.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cravat_annotate/cravat_annotate.py Tue Jun 12 12:04:45 2018 -0400 |
| [ |
| b'@@ -0,0 +1,246 @@\n+"""\n+A galaxy wrapper for the /rest/service/query API endpoint on Cravat.\n+\n+\n+Notes on Mapping:\n+-----------------\n+The CravatQuery class uses static method \'from_array\' to interpret an array of values\n+into a query string for the /rest/service/query API service on the cravat server.\n+This involves using a mapping dictionary to know how to associate the array\'s index positions\n+in to query-ing attributes, such as the chromosome, position, etc. The CravatQuery\n+class contains a default value (\'default_mapping\'); however, this could also be\n+offered as a user-configurable option.\n+"""\n+\n+\n+import requests\n+import json\n+import sys\n+import re\n+\n+\n+class CravatQueryException(Exception):\n+\n+\tdef __init__(self, message, errors=None):\t \n+\t\tsuper(CravatQueryException, self).__init__(message)\n+\t\t# Support for custom error codes\n+\t\tself.errors = errors\n+\n+\n+class CravatQuery(object):\n+\t"""\n+\t: A class for handling Cravat query strings.\n+\t: Args (all required):\n+\t:\tchr - Chromosome\n+\t:\tpos - Position\n+\t:\tstrand - Strand\n+\t:\tref - Reference Base\n+\t:\talt - Alternate Base\n+\t"""\n+\n+\t# The endpoint that CravatQuerys are submitted to\n+\tendpoint = \'http://cravat.us/CRAVAT/rest/service/query\'\n+\n+\t# The value delimiter used in the Cravat input file to delimit values\n+\tdelimiter = "\\t"\n+\n+\t# Defualt indices for intepretting a cravat file\'s row of data in to a CravatQuery\n+\tdefault_mapping = {\n+\t\t\'chromosome\': 1,\n+\t\t\'position\': 2,\n+\t\t\'strand\': 3,\n+\t\t\'reference\': 4,\n+\t\t\'alternate\': 5\n+\t}\n+\n+\t# Defualt values. Used as backup for CravatQuery to resolve query with incomplete information\n+\tdefault_values = {\n+\t\t\'strand\': \'+\'\n+\t}\n+\n+\t# The neccessary attributes neeeded to submit a query.\n+\tquery_keys = [\n+\t\t\'chromosome\', \'position\', \'strand\', \'reference\', \'alternate\'\n+\t]\n+\n+\t# Expected response keys from server. Ordered in list so that galaxy output has uniform column ordering run-to-run.\n+\t# If cravat server returns additional keys, they are appended to and included in output.\n+\tresponse_keys = [\n+\t\t"Chromosome", "Position", "Strand", "Reference base(s)", "Alternate base(s)",\n+\t \t"HUGO symbol", "S.O. transcript", "Sequence ontology protein change", "Sequence ontology",\n+\t\t"S.O. all transcripts", "gnomAD AF", "gnomAD AF (African)", "gnomAD AF (Amrican)",\n+\t\t"gnomAD AF (Ashkenazi Jewish)", "gnomAD AF (East Asian)", "gnomAD AF (Finnish)",\n+\t\t"gnomAD AF (Non-Finnish European)", "gnomAD AF (Other)", "gnomAD AF (South Asian)",\n+\t\t"1000 Genomes AF", "ESP6500 AF (average)", "ESP6500 AF (European American)",\n+\t\t"ESP6500 AF (African American)", "COSMIC transcript", "COSMIC protein change", \n+\t\t"COSMIC variant count [exact nucleotide change]", "cosmic_site_nt", "CGL driver class",\n+\t\t"TARGET", "dbSNP", "cgc_role", "cgc_inheritance", "cgc_tumor_type_somatic",\n+\t\t"cgc_tumor_type_germline", "ClinVar", "ClinVar disease identifier", "ClinVar XRef",\n+\t\t"GWAS Phenotype (GRASP)", "GWAS PMID (GRASP)", "Protein 3D variant"\n+\t]\n+\n+\n+\tdef __init__(self, _chr, pos, strand, ref, alt):\n+\t\t# \'_chr\' used to avoid naming confliction with python built-in \'chr\'\n+\t\tself.chromosome = CravatQuery.format_chromosome(_chr)\n+\t\tself.position = pos\n+\t\tself.strand = strand\n+\t\tself.reference = ref\n+\t\tself.alternate = alt\n+\t\tself.values = [self.chromosome, self.position, self.strand, self.reference, self.alternate]\n+\n+\n+\tdef __str__(self):\n+\t\t""" : Represent the CravatQuery as a valid query string for call to Cravat server """\n+\t\treturn "_".join(map(lambda x: str(x), self.values))\n+\n+\t\n+\tdef as_query_string(self):\n+\t\treturn str(self)\n+\n+\t\n+\t@staticmethod\n+\tdef from_dictionary(d):\n+\t\t"""\n+\t\t: Instantiate a CravatQuery from a dictionary representation.\n+\t\t: Args:\n+\t\t\t: d <dictionary>: A dictionary representing a CravatQuery, containing keys: [{}] \n+\t\t""".format(CravatQuery.query_keys)\n+\n+\t\tfor key in CravatQuery.query_keys:\n+\t\t\tif key not in d:\n+\t\t\t\traise CravatQueryException("CravatQuery.from_dictionary requires keys: [{}], however key: \'{}\' was not provided "\n+\t\t\t\t\t\t\t\t\t\t\t.for'..b' associated to \'fmt\'\n+\t\tif mapping == None:\n+\t\t\tmapping = CravatQuery.default_mapping\n+\t\t\t\n+\t\t# Build a dict of cravat querying keys to values.\n+\t\td = {}\n+\t\tfor key in CravatQuery.query_keys:\n+\t\t\t# Try to get index position from mapping by the key, and value from array by the index\n+\t\t\tif key in mapping:\n+\t\t\t\tindex = mapping[key]\n+\t\t\t\td[key] = array[index]\n+\t\t\t# If index not provided in mapping, check if there is a defualt value\n+\t\t\telif key in CravatQuery.default_values:\n+\t\t\t\td[key] = CravatQuery.default_values[key]\n+\t\t\t# Unable to get value for querying key, meaning can\'t construct the minimum requirements for query\n+\t\t\telse:\n+\t\t\t\traise CravatQueryException("CravatQuery.from_array requires a mapping index for key: \'{}\', however value was not provided".format(key))\n+\t\treturn CravatQuery.from_dictionary(d)\n+\n+\n+\n+\t@staticmethod\n+\tdef format_chromosome(_chr):\n+\t\t"""\n+\t\t: Format a chromosome for use as query parameter. \'_chr\' name used to avoid python built-in name confliction.\n+\t\t: Args:\n+\t\t\t: _chr - Either an interger [1,23], or \'x\'/\'X\', or \'y\'/\'Y\', or a string of the form\n+\t\t\t: \t\t\'chr<z>\' where \'<z>\' is one of the previously described values \n+\t\t"""\n+\t\tinRange = lambda x: 1 <= x and x <= 23\n+\t\t_chr = _chr.lower()\n+\t\t_chr = _chr.strip(\'chr\')\n+\t\t# Handler interger chromosomes 1 to 23\n+\t\ttry:\n+\t\t\t_chr = int(_chr)\n+\t\t\tif inRange(_chr):\n+\t\t\t\treturn \'chr\' + str(_chr)\n+\t\t\telse:\n+\t\t\t\traise CravatQueryException("Chromsomme of \'{}\' was out of range [1,23]".format(_chr))\n+\t\texcept:\n+\t\t\tpass\n+\t\t# Handle chromosomes chromosomes x and y\n+\t\tif _chr == \'x\' or _chr == \'y\':\n+\t\t\treturn \'chr\' + _chr\n+\t\traise CravatQueryException("Unable to resolve input: \'{}\' into a valid chromosome representation".format(_chr))\n+\n+\n+\t@staticmethod\n+\tdef jump_header(in_file, out_file, headerlines=0):\n+\t\t"""\n+\t\t: Jumps over a header space of line number \'headerlines\'. Sets up in_file so that\n+\t\t: the next execution of in_file.readline() will return the first non-header line.\n+\t\t"""\n+\t\tin_file.seek(0)\n+\t\tfor line in range(headerlines):\n+\t\t\tin_file.readline()\n+\n+\n+def main(in_path, out_path, pre_callback=None, user_mapping=None):\n+\t"""\n+\t: Read the file line by line and use data to query cravat server.\n+\t: Args:\n+\t\t: fmt <str>: \'cr\' or \'vcf\'. The input format\n+\t\t: in_path <str>: Path to input file\n+\t\t: in_path <str>: Path to output file\n+\t\t: header_callback <function>: A function to handle the header space. Executed\n+\t\t\tbefore main loop. Recieves in_file, out_file, and fmt as argumnets\n+\t"""\n+\n+\twith open(in_path, \'r\') as in_file, \\\n+\topen(out_path, \'w\') as out_file:\n+\n+\t\t# Perform any pre-processing steps, such as jumping a header space\n+\t\tif pre_callback:\n+\t\t\tpre_callback(in_file, out_file, fmt)\n+\n+\t\t# main loop\n+\t\tfor line in in_file:\n+\n+\t\t\t# Create query from line of input data\n+\t\t\tline = line.strip().split(\'\\t\')\n+\t\t\tquery = CravatQuery.from_array(line, user_mapping)\n+\t\t\t# Make request, and write respone data\n+\t\t\tcall = requests.get(CravatQuery.endpoint, params={ \'mutation\': query.as_query_string })\n+\t\t\ttry:\n+\t\t\t\tif call.status_code != 200 or call.text == "":\n+\t\t\t\t\traise CravatQueryException("Bad Server Response. Respone code: \'{}\', Response Text: \'{}\'".format(call.status_code, call.text))\n+\t\t\t\tjson_response = json.loads(call.text)\n+\t\t\t\twrote = False\n+\t\t\t\tfor key, val in json_response.items():\n+\t\t\t\t\t# Set numeric values to uniform format\n+\t\t\t\t\ttry:\n+\t\t\t\t\t\tval = float(val)\n+\t\t\t\t\t\tval = format(val, ".4f")\n+\t\t\t\t\texcept:\n+\t\t\t\t\t\tpass\n+\t\t\t\t\tif wrote:\n+\t\t\t\t\t\tout_file.write("\\t")\n+\t\t\t\t\tout_file.write(val)\n+\t\t\t\t\twrote = True\n+\t\t\t\tout_file.write("\\n")\n+\t\t\texcept CravatQueryException as e:\n+\t\t\t\tprint(e)\n+\t\t\t\t\n+\t\t\n+\n+\n+if __name__ == "__main__":\n+\n+\t# Input and output file paths, obtained form command line\n+\tin_path = sys.argv[1]\n+\tout_path = sys.argv[2]\n+\n+\t# Possibly allow user mapping configuration thourgh here. Not fully implemented\n+\tif len(sys.argv) > 2:\n+\t\tuser_mapping = sys.argv[3]\n+\n+\t# Run the main operation\n+\tmain(in_path, out_path)\n\\ No newline at end of file\n' |
| b |
| diff -r 20ebb3a5c1a4 -r a28f1f52eb93 cravat_annotate/cravat_annotate.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cravat_annotate/cravat_annotate.xml Tue Jun 12 12:04:45 2018 -0400 |
| [ |
| @@ -0,0 +1,25 @@ +<tool id="cravat_query" name="CRAVAT Query" version="1.0.0"> + <description>Queries CRAVAT for cancer annotation</description> + <command interpreter="python">cravat_annotate.py $input $output</command> + + <inputs> + <param format="tabular" name="input" type="data" label="Source file"/> + </inputs> + + <outputs> + <data format="tabular" name="output" /> + </outputs> + + <tests> + <test> + <param name="input" value="input_call.txt"/> + <output name="output" file="Galaxy23-[CRAVAT_Query_on_data_22].tabular"/> + </test> + </tests> + + <help> + This tool queries CRAVAT for cancer annotation. + </help> + +</tool> + |