LiftOver TAB pipeline user Kantale

Documentation

Liftover tab separated files between different references.

Parameters

Input filename:
output filename:
Column index (starting from 0) where the chromosome information is:
Column index (starting from 0) where the position information is:
Column index (starting from 0) where the reference information is:
Temporary directory for intermediate files. Leave empty for /tmp:
Source reference: hg18 hg19
Target reference: hg19 hg18
Article that contains the constant values:
Execute environment: shell pbs nowhere

<inputs>
<param name="input_filename" type="file" value="" label="Input filename: "/>
<param name="output_filename" type="data" value="" label="output filename: "/>
<param name="chromosome_column" type="eval" value="0" label="Column index (starting from 0) where the chromosome information is: "/>
<param name="position_column" type="eval" value="1" label="Column index (starting from 0) where the position information is: "/>
<param name="reference_column" type="eval" value="2" label="Column index (starting from 0) where the reference information is: "/>
<param name="temp_dir" type="data" value="" label="Temporary directory for intermediate files. Leave empty for /tmp: "/>
<param name="source_reference" type="select" label="Source reference: ">
	<option value="hg18">hg18</option>
	<option value="hg19">hg19</option>
	</param>
<param name="target_reference" type="select" label="Target reference: ">
	<option value="hg19">hg19</option>
	<option value="hg18">hg18</option>
	</param>
<param name="constants" type="data" value="" label="Article that contains the constant values: "/>
<param name="execute_environment" type="select" label="Execute environment: ">
	<option value="shell">remote shell</option>
	<option value="pbs">pbs Cluster</option>
	<option value="nowhere">do not execute</option>
	</param>
</inputs>

Return

A list that contains the pipeline.

See also

Genetic_liftover_user_Kantale, Run_pipeline_user_Kantale

Code

def LiftOver_TAB_pipeline_user_Kantale(
	input_filename = None,
	output_filename = None,
	chromosome_column = None,
	position_column = None,
	reference_column = None,
	source_reference = None,
	target_reference = None,
	temp_dir = None,
	constants = None,
	execute_environment = "nowhere",
):

	if not temp_dir:
		temp_dir = Request_temporary_directory_user_Kantale()

	if type(constants).__name__ == "str":
		if constants.strip():
			constants = Import_WikiPL_article_user_Kantale(constants)()
		else:
			raise Exception("Constants have not been set")

	if source_reference == "hg18" and target_reference == "hg19":
		chain_file = constants["path_to_hg18ToHg19.over.chain"]
	elif source_reference == "hg19" and target_reference == "hg18":
		chain_file = constants["path_to_hg19ToHg18.over.chain"]
	else:
		raise Exception("Invalid source / target selection")
	
	if source_reference == "hg18":
#		fasta_source_path = constants["path_to_fasta_hg18"]
		fasta_source_path = constants["path_to_fasta_hg18_2"]

	elif source_reference == "hg19":
#		fasta_source_path = constants["path_to_fasta_hg19"]
		fasta_source_path = constants["path_to_fasta_hg19_g1k"]
	else:
		raise Exception("Invalid selection for parameter: source_reference. Available values: hg18 and hg19")
	
	if target_reference == "hg18":
		dict_target_path = constants["path_to_dict_hg18_2"]
	elif target_reference == "hg19":
		dict_target_path = constants["path_to_dict_hg19_2"]
	else:
		raise Exception("Invalid selection for parameter: target_reference. Available values: hg18 and hg19")

	Execute_command_user_Kantale(command = "mkdir -p " + temp_dir)

	input_basename = Get_basename_of_filename_user_Kantale(input_filename)

	pipeline = []

	if execute_environment == "pbs":
		pipeline += [{
				"name" : "Push the button",
				"command" : "Wait_while_file_exists",
				"params" : {
					"filename" : temp_dir + "/delete.me",
					"create_file" : True
					},
				"prereq" : [],
				"mem" : "1GB",
				"walltime" : "1:00:00",
			}]

	pipeline += [{
			"name" : "Convert tab to to VCF",
			"command" : "Convert_tab_file_to_VCF_user_Kantale",
			"params" : {
					"input_filename" : input_filename,
					"tab_format" : {"chromosome" : chromosome_column, "position" : position_column, "rs" : reference_column},
					"output_filename" : temp_dir + "/" + input_basename + ".vcf",
				},
			"prereq" : ["Push the button"] if execute_environment == "pbs" else [],
			"mem" : "4gb",
			"walltime" : "24:00:00",
		}]

	pipeline += [{
		"name" : "LiftOver VCF",
		"command" : "Genetic_liftover_user_Kantale",
		"params" : {
			"input_VCF_filename"  : temp_dir  + "/" + input_basename + ".vcf",
			"output_VCF_filename" :  temp_dir  + "/" + input_basename + ".lo.vcf",
			"chain_file" : chain_file,
			"temp_dir" : temp_dir,
			"path_to_GATK" : constants["path_to_GATK"],
			"path_to_vcf_sort" : constants["path_to_vcf_sort"],
			"fasta_source_path" : fasta_source_path,
			"dict_target_path" : dict_target_path,
			"replace_arithmetic_to_chr" : False,
			"filter_new_reference" : False,
			},
		"prereq" : ["Convert tab to to VCF"],
		"mem" : "16GB",
		"walltime" : "24:00:00",
	}]

	vcf_to_tab = constants["path_to_vcf_to_tab"]
	vcf_to_tab_path = Get_path_of_filename_user_Kantale(vcf_to_tab)
	vcf_to_tab_basename = Get_basename_of_filename_user_Kantale(vcf_to_tab)

#To use vcftools run the command:
#	"command" = "cd " + vcf_to_tab_path + " ; cat " + temp_dir  + "/" + input_basename + ".lo.vcf | perl " + vcf_to_tab_basename + " > " + output_filename ,

	pipeline += [{
		"name" : "Convert liftovered VCF to tab",
		"command" : "Convert_VCF_to_TAB_user_Kantale",
		"params" : {
				"input_filename"  : temp_dir  + "/" + input_basename + ".lo.vcf",
				"output_filename" : temp_dir + "/" + input_basename + ".lo.tab",
				"print_header" : True,
			},
		"prereq" : ["LiftOver VCF"],
		"mem" : "4GB",
		"walltime" : "24:00:00",
	}]


	pipeline += [{
		"name" : "Create output file",
		"command" : "Merge_columns_of_files_user_Kantale",
		"params": {
				"input_filenames" : [temp_dir + "/" + input_basename + ".lo.tab"],
				"input_columns"   : [[(0,0), (1,1), (2,2)]],
				"ignore_first_lines" : [None],
				"output_filename" : output_filename
			},
		"prereq" : ["Convert liftovered VCF to tab"],
		"mem" : "4GB",
		"walltime" : "24:00:00",
		}]

	if execute_environment == "shell":
		Run_pipeline_user_Kantale(
			pipeline = pipeline,
			temp_dir = temp_dir + "/shell",
			push_the_button = temp_dir + "/delete.me",
			)
	elif execute_environment == "pbs":
		Run_pipeline_user_Kantale(
			pipeline = pipeline,
			temp_dir = temp_dir + "/pbs",
			push_the_button = temp_dir + "/delete.me",
			pbsStats = constants["pbsStats"],
			delay = 5,
			)
	elif execute_environment == "nowhere":
		pass #Do nothing
	else:
		raise Exception("Unknown Execution environment: " + str(execute_environment))

	return pipeline

Unit Tests

def uni1():
	return True

Development Code

def LiftOver_TAB_pipeline_user_Kantale():
	pass

Permissions

Documentation Permissions

Kantale

Code Permissions

Kantale

Unit Tests Permissions

Kantale

Permissions Permissions

Kantale