changeset 15:a46b42bda5d7 draft

Uploaded

--- a/cravat_annotate/cravat_annotate.py	Tue Jun 12 12:04:45 2018 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,246 +0,0 @@
-"""
-A galaxy wrapper for the /rest/service/query API endpoint on Cravat.
-
-
-Notes on Mapping:
------------------
-The CravatQuery class uses static method 'from_array' to interpret an array of values
-into a query string for the /rest/service/query API service on the cravat server.
-This involves using a mapping dictionary to know how to associate the array's index positions
-in to query-ing attributes, such as the chromosome, position, etc. The CravatQuery
-class contains a default value ('default_mapping'); however, this could also be
-offered as a user-configurable option.
-"""
-
-
-import requests
-import json
-import sys
-import re
-
-
-class CravatQueryException(Exception):
-
-	def __init__(self, message, errors=None):	 
-		super(CravatQueryException, self).__init__(message)
-		# Support for custom error codes
-		self.errors = errors
-
-
-class CravatQuery(object):
-	"""
-	: A class for handling Cravat query strings.
-	: Args (all required):
-	:	chr - Chromosome
-	:	pos - Position
-	:	strand - Strand
-	:	ref - Reference Base
-	:	alt - Alternate Base
-	"""
-
-	# The endpoint that CravatQuerys are submitted to
-	endpoint = 'http://cravat.us/CRAVAT/rest/service/query'
-
-	# The value delimiter used in the Cravat input file to delimit values
-	delimiter = "\t"
-
-	# Defualt indices for intepretting a cravat file's row of data in to a CravatQuery
-	default_mapping = {
-		'chromosome': 1,
-		'position': 2,
-		'strand': 3,
-		'reference': 4,
-		'alternate': 5
-	}
-
-	# Defualt values. Used as backup for CravatQuery to resolve query with incomplete information
-	default_values = {
-		'strand': '+'
-	}
-
-	# The neccessary attributes neeeded to submit a query.
-	query_keys = [
-		'chromosome', 'position', 'strand', 'reference', 'alternate'
-	]
-
-	# Expected response keys from server. Ordered in list so that galaxy output has uniform column ordering run-to-run.
-	# If cravat server returns additional keys, they are appended to and included in output.
-	response_keys = [
-		"Chromosome", "Position", "Strand", "Reference base(s)", "Alternate base(s)",
-	 	"HUGO symbol", "S.O. transcript", "Sequence ontology protein change", "Sequence ontology",
-		"S.O. all transcripts", "gnomAD AF", "gnomAD AF (African)", "gnomAD AF (Amrican)",
-		"gnomAD AF (Ashkenazi Jewish)", "gnomAD AF (East Asian)", "gnomAD AF (Finnish)",
-		"gnomAD AF (Non-Finnish European)", "gnomAD AF (Other)", "gnomAD AF (South Asian)",
-		"1000 Genomes AF", "ESP6500 AF (average)", "ESP6500 AF (European American)",
-		"ESP6500 AF (African American)", "COSMIC transcript", "COSMIC protein change", 
-		"COSMIC variant count [exact nucleotide change]", "cosmic_site_nt", "CGL driver class",
-		"TARGET", "dbSNP", "cgc_role", "cgc_inheritance", "cgc_tumor_type_somatic",
-		"cgc_tumor_type_germline", "ClinVar", "ClinVar disease identifier", "ClinVar XRef",
-		"GWAS Phenotype (GRASP)", "GWAS PMID (GRASP)", "Protein 3D variant"
-	]
-
-
-	def __init__(self, _chr, pos, strand, ref, alt):
-		# '_chr' used to avoid naming confliction with python built-in 'chr'
-		self.chromosome = CravatQuery.format_chromosome(_chr)
-		self.position = pos
-		self.strand = strand
-		self.reference = ref
-		self.alternate = alt
-		self.values = [self.chromosome, self.position, self.strand, self.reference, self.alternate]
-
-
-	def __str__(self):
-		""" : Represent the CravatQuery as a valid query string for call to Cravat server """
-		return "_".join(map(lambda x: str(x), self.values))
-
-	
-	def as_query_string(self):
-		return str(self)
-
-	
-	@staticmethod
-	def from_dictionary(d):
-		"""
-		: Instantiate a CravatQuery from a dictionary representation.
-		: Args:
-			: d <dictionary>: A dictionary representing a CravatQuery, containing keys: [{}] 
-		""".format(CravatQuery.query_keys)
-
-		for key in CravatQuery.query_keys:
-			if key not in d:
-				raise CravatQueryException("CravatQuery.from_dictionary requires keys: [{}], however key: '{}' was not provided "
-											.format(CravatQuery.query_keys, key))
-		return CravatQuery(d["chromosome"], d["position"], d["strand"], d["reference"], d["alternate"])
-
-
-	@staticmethod
-	def from_array(array, mapping=None):
-		"""
-		: Instantiate a CravatQuery from an array of values. Useful when translating read lines from a file.
-		: Args:
-			: fmt <str> - Either 'cr' or 'vcf', describing input format
-			: array <list> - The values to instantiate the CravatQuery from
-			: mapping <dict> - Optional. A dictionary associating cravat parameters to indicies in the array.
-								Valid values are: 'chromosome', 'position', 'strand', 'reference', 'alternate'
-		"""
-		
-		# Set the mapping value. Either recieved from user, or obtained via defualt associated to 'fmt'
-		if mapping == None:
-			mapping = CravatQuery.default_mapping
-			
-		# Build a dict of cravat querying keys to values.
-		d = {}
-		for key in CravatQuery.query_keys:
-			# Try to get index position from mapping by the key, and value from array by the index
-			if key in mapping:
-				index = mapping[key]
-				d[key] = array[index]
-			# If index not provided in mapping, check if there is a defualt value
-			elif key in CravatQuery.default_values:
-				d[key] = CravatQuery.default_values[key]
-			# Unable to get value for querying key, meaning can't construct the minimum requirements for query
-			else:
-				raise CravatQueryException("CravatQuery.from_array requires a mapping index for key: '{}', however value was not provided".format(key))
-		return CravatQuery.from_dictionary(d)
-
-
-
-	@staticmethod
-	def format_chromosome(_chr):
-		"""
-		: Format a chromosome for use as query parameter. '_chr' name used to avoid python built-in name confliction.
-		: Args:
-			: _chr - Either an interger [1,23], or 'x'/'X', or 'y'/'Y', or a string of the form
-			: 		'chr<z>' where '<z>' is one of the previously described values 
-		"""
-		inRange = lambda x: 1 <= x and x <= 23
-		_chr = _chr.lower()
-		_chr = _chr.strip('chr')
-		# Handler interger chromosomes 1 to 23
-		try:
-			_chr = int(_chr)
-			if inRange(_chr):
-				return 'chr' + str(_chr)
-			else:
-				raise CravatQueryException("Chromsomme of '{}' was out of range [1,23]".format(_chr))
-		except:
-			pass
-		# Handle chromosomes chromosomes x and y
-		if _chr == 'x' or _chr == 'y':
-			return 'chr' + _chr
-		raise CravatQueryException("Unable to resolve input: '{}' into a valid chromosome representation".format(_chr))
-
-
-	@staticmethod
-	def jump_header(in_file, out_file, headerlines=0):
-		"""
-		: Jumps over a header space of line number 'headerlines'. Sets up in_file so that
-		: the next execution of in_file.readline() will return the first non-header line.
-		"""
-		in_file.seek(0)
-		for line in range(headerlines):
-			in_file.readline()
-
-
-def main(in_path, out_path, pre_callback=None, user_mapping=None):
-	"""
-	: Read the file line by line and use data to query cravat server.
-	: Args:
-		: fmt <str>: 'cr' or 'vcf'. The input format
-		: in_path <str>: Path to input file
-		: in_path <str>: Path to output file
-		: header_callback <function>: A function to handle the header space. Executed
-			before main loop. Recieves in_file, out_file, and fmt as argumnets
-	"""
-
-	with open(in_path, 'r') as in_file, \
-	open(out_path, 'w') as out_file:
-
-		# Perform any pre-processing steps, such as jumping a header space
-		if pre_callback:
-			pre_callback(in_file, out_file, fmt)
-
-		# main loop
-		for line in in_file:
-
-			# Create query from line of input data
-			line = line.strip().split('\t')
-			query = CravatQuery.from_array(line, user_mapping)
-			# Make request, and write respone data
-			call = requests.get(CravatQuery.endpoint, params={ 'mutation': query.as_query_string })
-			try:
-				if call.status_code != 200 or call.text == "":
-					raise CravatQueryException("Bad Server Response. Respone code: '{}', Response Text: '{}'".format(call.status_code, call.text))
-				json_response = json.loads(call.text)
-				wrote = False
-				for key, val in json_response.items():
-					# Set numeric values to uniform format
-					try:
-						val = float(val)
-						val = format(val, ".4f")
-					except:
-						pass
-					if wrote:
-						out_file.write("\t")
-					out_file.write(val)
-					wrote = True
-				out_file.write("\n")
-			except CravatQueryException as e:
-				print(e)
-				
-		
-
-
-if __name__ == "__main__":
-
-	# Input and output file paths, obtained form command line
-	in_path = sys.argv[1]
-	out_path = sys.argv[2]
-
-	# Possibly allow user mapping configuration thourgh here. Not fully implemented
-	if len(sys.argv) > 2:
-		user_mapping = sys.argv[3]
-
-	# Run the main operation
-	main(in_path, out_path)
\ No newline at end of file

--- a/cravat_annotate/cravat_annotate.xml	Tue Jun 12 12:04:45 2018 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,25 +0,0 @@
-<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>
-

--- a/cravat_convert/base_converter.py	Tue Jun 12 12:04:45 2018 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,22 +0,0 @@
-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

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cravat_submit/cravat_submit.py	Tue Jun 12 12:05:40 2018 -0400
@@ -0,0 +1,103 @@
+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://staging.cravat.us/CRAVAT/rest/service/submit', files={'inputfile':open(input_filename)}, data={'email':'[e-mail]', '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://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)
\ No newline at end of file

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cravat_submit/cravat_submit.xml	Tue Jun 12 12:05:40 2018 -0400
@@ -0,0 +1,34 @@
+<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>