Mercurial > repos > in_silico > cravat_score_and_annotate

changeset 10:435b5bb17d01 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author in_silico
date Wed, 27 Jun 2018 17:54:05 -0400
parents 6b607ebcd674
children ae65a43ed658
files cravat_annotate/cravat_annotate.py cravat_annotate/cravat_annotate.xml cravat_submit/cravat_submit.py cravat_submit/cravat_submit.xml
diffstat 4 files changed, 153 insertions(+), 137 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cravat_annotate/cravat_annotate.py	Wed Jun 27 17:54:05 2018 -0400
@@ -0,0 +1,128 @@
+"""
+A galaxy wrapper for the /rest/service/query API endpoint on Cravat.
+"""
+
+
+import requests
+import json
+import sys
+import re
+import argparse
+import ipdb
+
+
+# The endpoint that CravatQuerys are submitted to
+endpoint = 'http://www.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
+cr_mapping = {
+	'chromosome': 1,
+	'position': 2,
+	'strand': 3,
+	'reference': 4,
+	'alternate': 5
+}
+
+
+# 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 get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input',
+                            '-i',
+                            required = True,
+                            help='Input path to a cravat file for querying',)
+    parser.add_argument('--output',
+                            '-o',
+                            default = None,
+                            help = 'Output path to write results from query')
+    return parser.parse_args()
+
+
+def format_chromosome(chrom):
+	""" : Ensure chromosome entry is propely formatted for use as querying attribute. """
+	if chrom[0:3] == 'chr':
+		return chrom
+	return 'chr' + str(chrom)
+
+
+def get_query_string(row):
+	""" : From a row dict, return a query string for the Cravat server.
+		: The row dict is cravat headeres associated to their values of that row.
+	"""
+	return '_'.join([ row['chromosome'], row['position'], row['strand'], row['reference'], row['alternate'] ])
+
+
+def query(in_path, out_path):
+	""" : From a Cravat the file at in_path, query each line on the Cravat server.
+		: Write the response values to file at out_path.
+	"""
+
+	with open(in_path, 'r') as in_file, \
+	open(out_path, 'w') as out_file:
+
+		for line in in_file:
+			line = line.strip().split('\t')
+			# row is dict of cravat col headers assioted values in this line
+			row = { header: line[index] for header, index in cr_mapping.items() }
+			row['chromosome'] = format_chromosome(row['chromosome'])
+			query_string = get_query_string(row)
+			call = requests.get(endpoint, params={ 'mutation': query_string })
+			if call.status_code != 200 or call.text == "":
+				raise requests.RequestException("Bad Server Response. Respone code: '{}', Response Text: '{}'".format(call.status_code, call.text))
+			json_response = json.loads(call.text)
+			# See if server returned additional json key-val paris not expected in response_keys
+			for key in json_response:
+				if key not in response_keys:
+					response_keys.append(key)
+			# Write key in order of response_keys to standardize order of output columns
+			wrote = False
+			for key in response_keys:
+				if key not in json_response:
+					val = None
+				val = json_response[key]
+				# Format standardization for numerics
+				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")		
+
+
+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") 
+	query(cli_args.input, cli_args.output)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cravat_annotate/cravat_annotate.xml	Wed Jun 27 17:54:05 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 -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>
+    <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_submit/cravat_submit.py	Tue Jun 12 12:06:28 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://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) + ', ')
-    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
--- a/cravat_submit/cravat_submit.xml	Tue Jun 12 12:06:28 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">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>