def __init__(self, path="", max_threads=1):
Tool.__init__(self, "repeatmasker", path=path, max_threads=max_threads)
self.repeat_classes_used_for_gene_annotation = [
"DNA", "DNA\?", "LINE", "LINE\?", "LTR", "LTR\?", "RC", "RC\?",
"Retroposon", "Retroposon\?", "SINE", "SINE\?", "Helitron",
"Helitron\?"
]
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "repeatmasker", path=path, max_threads=max_threads)
self.repeat_classes_used_for_gene_annotation = [
"DNA", "DNA\?", "LINE", "LINE\?", "LTR", "LTR\?", "RC", "RC\?",
"Retroposon", "Retroposon\?", "SINE", "SINE\?", "Helitron",
"Helitron\?"
]
self.repeat_classes_used_for_gene_annotation_expanded_set = self.repeat_classes_used_for_gene_annotation + [
"Unknown", "Other", "ARTEFACT"
]
def __init__(self,
path="",
max_threads=4,
max_memory="100G",
max_per_thread_memory="5G"):
Tool.__init__(self,
"plink",
path=path,
max_threads=max_threads,
max_memory=max_memory,
max_per_thread_memory=max_per_thread_memory)
def __init__(self,
java_path="",
max_threads=4,
jar_path="",
max_memory="1g"):
jar = "GenomeAnalysisTK.jar"
Tool.__init__(self,
"java",
path=java_path,
max_threads=max_threads,
jar_path=jar_path,
jar=jar,
max_memory=max_memory)
def __init__(self, path="", max_threads=4):
"""
USAGE
dustmasker [-h] [-help] [-xmlhelp] [-in input_file_name]
[-out output_file_name] [-window window_size] [-level level]
[-linker linker] [-infmt input_format] [-outfmt output_format]
[-parse_seqids] [-version-full]
DESCRIPTION
Low complexity region masker based on Symmetric DUST algorithm
OPTIONAL ARGUMENTS
-h
Print USAGE and DESCRIPTION; ignore all other parameters
-help
Print USAGE, DESCRIPTION and ARGUMENTS; ignore all other parameters
-xmlhelp
Print USAGE, DESCRIPTION and ARGUMENTS in XML format; ignore all other
parameters
-in <File_In>
input file name
Default = `-'
-out <File_Out>
output file name
Default = `-'
-window <Integer>
DUST window length
Default = `64'
-level <Integer>
DUST level (score threshold for subwindows)
Default = `20'
-linker <Integer>
DUST linker (how close masked intervals should be to get merged together).
Default = `1'
-infmt <String>
input format (possible values: fasta, blastdb)
Default = `fasta'
-outfmt <String, `acclist', `fasta', `interval', `maskinfo_asn1_bin',
`maskinfo_asn1_text', `maskinfo_xml', `seqloc_asn1_bin',
`seqloc_asn1_text', `seqloc_xml'>
output format
Default = `interval'
-parse_seqids
Parse Seq-ids in FASTA input
-version-full
Print extended version data; ignore other arguments
"""
Tool.__init__(self, "dustmasker", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "samtools", path=path, max_threads=max_threads)
# bam/sam flag values:
self.bam_flags = {
"read_paired": 1,
"read_mapped_in_proper_pair": 2,
"read_unmapped": 4,
"mate_unmapped": 8,
"read_reverse_strand": 16,
"mate_reverse_strand": 32,
"first_in_pair": 64,
"second_in_pair": 128,
"not_primary_alignment": 256,
"read_fails_platform/vendor_quality_checks": 512,
"read_is_PCR_or_optical_duplicate": 1024,
"supplementary_alignment": 2048
}
def __init__(self,
path="",
max_threads=4,
max_memory="100G",
max_per_thread_memory="5G"):
Tool.__init__(self,
"plink",
path=path,
max_threads=max_threads,
max_memory=max_memory,
max_per_thread_memory=max_per_thread_memory)
# constants for PLINK bed file
self.samples_per_byte = 4
self.signature_byte_number = 3
# constans for PLINK bim file
self.allel_columns_in_bim_file = (4, 5)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "jellyfish", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "cookiecutter", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "htseq-count", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "facut", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "guidance.pl", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "blastdbcmd", path=path, max_threads=max_threads)
dest="prefix",
help="Prefix of output files")
parser.add_argument("-o",
"--output_directory",
action="store",
dest="output_dir",
help="Directory to write output files")
parser.add_argument("-n",
"--num_of_records_per_file",
action="store",
dest="num_of_records_per_file",
type=int,
help="Number of sequences per output file")
parser.add_argument("-f",
"--num_of_out_files",
action="store",
dest="num_of_out_files",
type=int,
help="Number of output files")
args = parser.parse_args()
if args.num_of_records_per_file and args.num_of_out_files:
raise ValueError("Options -n and -f can't be set simultaneously")
Tool.split_fasta(args.input,
args.output_dir,
num_of_recs_per_file=args.num_of_records_per_file,
num_of_files=args.num_of_out_files,
output_prefix=args.prefix)
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "V2_trim.exe", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "prank", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "cufflinks", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "gtf_to_sam", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "cuffcompare", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=1):
Tool.__init__(self, "nextclip", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "featureCounts", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "platanus", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self,
"SSPACE_Standard_v3.0.pl",
path=path,
max_threads=max_threads)
def __init__(self, path="", max_threads=4, max_memory=None):
Tool.__init__(self, "longranger", path=path, max_threads=max_threads, max_memory=max_memory)
def __init__(self, path="", max_threads=4):
"""
USAGE
makeblastdb [-h] [-help] [-in input_file] [-input_type type]
-dbtype molecule_type [-title database_title] [-parse_seqids]
[-hash_index] [-mask_data mask_data_files] [-mask_id mask_algo_ids]
[-mask_desc mask_algo_descriptions] [-gi_mask]
[-gi_mask_name gi_based_mask_names] [-out database_name]
[-max_file_sz number_of_bytes] [-logfile File_Name] [-taxid TaxID]
[-taxid_map TaxIDMapFile] [-version]
DESCRIPTION
Application to create BLAST databases, version 2.2.30+
REQUIRED ARGUMENTS
-dbtype <String, `nucl', `prot'>
Molecule type of target db
OPTIONAL ARGUMENTS
-h
Print USAGE and DESCRIPTION; ignore all other parameters
-help
Print USAGE, DESCRIPTION and ARGUMENTS; ignore all other parameters
-version
Print version number; ignore other arguments
*** Input options
-in <File_In>
Input file/database name
Default = `-'
-input_type <String, `asn1_bin', `asn1_txt', `blastdb', `fasta'>
Type of the data specified in input_file
Default = `fasta'
*** Configuration options
-title <String>
Title for BLAST database
Default = input file name provided to -in argument
-parse_seqids
Option to parse seqid for FASTA input if set, for all other input types
seqids are parsed automatically
-hash_index
Create index of sequence hash values.
*** Sequence masking options
-mask_data <String>
Comma-separated list of input files containing masking data as produced by
NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)
-mask_id <String>
Comma-separated list of strings to uniquely identify the masking algorithm
* Requires: mask_data
* Incompatible with: gi_mask
-mask_desc <String>
Comma-separated list of free form strings to describe the masking algorithm
details
* Requires: mask_id
-gi_mask
Create GI indexed masking data.
* Requires: parse_seqids
* Incompatible with: mask_id
-gi_mask_name <String>
Comma-separated list of masking data output files.
* Requires: mask_data, gi_mask
*** Output options
-out <String>
Name of BLAST database to be created
Default = input file name provided to -in argumentRequired if multiple
file(s)/database(s) are provided as input
-max_file_sz <String>
Maximum file size for BLAST database files
Default = `1GB'
-logfile <File_Out>
File to which the program log should be redirected
*** Taxonomy options
-taxid <Integer, >=0>
Taxonomy ID to assign to all sequences
* Incompatible with: taxid_map
-taxid_map <File_In>
Text file mapping sequence IDs to taxonomy IDs.
Format:<SequenceId> <TaxonomyId><newline>
* Requires: parse_seqids
* Incompatible with: taxid
"""
Tool.__init__(self, "makeblastdb", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "mcmctree", path=path, max_threads=max_threads)
self.example = """
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "windowmasker", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "primer3_core", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "trf", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4):
Tool.__init__(self, "exonerate", path=path, max_threads=max_threads)
