def __init__(self, path="", max_threads=4, tmp_dir=None): """ Spliting sra into forward and reverse fastqs is default now. Here are some important differences to fastq-dump: The -Z|--stdout option does not work for split-3 and split-files. The tool will fall back to producing files in these cases. There is no --gzip|--bizp2 option, you have to compress your files explicitly after they have been written. There is no -A option for the accession; just specify the accession or the absolute path directly. fasterq-dump does not take multiple accessions, just one. There is no -N|--minSpotId and no -X|--maxSpotId option. fasterq-dump version 2.9.1 processes always the whole accession, although it may support partial access in future versions. fasterq-dump.2.9.1 was released only on Linux platforms, and is intended primarily for use under larger installations. Our next release should be available for Windows and MacOS. :param path: :param max_threads: """ Tool.__init__(self, "fasterq-dump", path=path, max_threads=max_threads, tmp_dir=tmp_dir)
def __init__(self, max_threads=4, max_memory=None, timelog=None): Tool.__init__(self, "gatk --java-options -Xmx%s CombineVariants" % max_memory if max_memory else "gatk CombineVariants", max_threads=max_threads, max_memory=max_memory, timelog=timelog)
def __init__(self, max_threads=4, max_memory=None, timelog=None): Tool.__init__(self, "gatk --java-options -Xmx%s BaseRecalibrator" % max_memory if max_memory else "gatk BaseRecalibrator", max_threads=max_threads, max_memory=max_memory, timelog=timelog)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "run_BUSCO.py", path=path, max_threads=max_threads) self.kingdoms = ["euk", "bac", "mito", "arc"] self.status_list = ["Complete", "Duplicated", "Fragmented", "Missing"]
def __init__(self, max_threads=1, max_memory=10, workdir="./"): Tool.__init__(self, cmd="", max_threads=max_threads, max_memory=max_memory) self.workdir = workdir self.dirs = None
def __init__(self, max_threads=4, max_memory=None, timelog=None): Tool.__init__( self, "gatk --java-options -Xmx%s FastaAlternateReferenceMaker" % max_memory if max_memory else "gatk FastaAlternateReferenceMaker", max_threads=max_threads, max_memory=max_memory, timelog=timelog)
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, "last", path=path, max_threads=max_threads) self.sequence_order_dict = { "input": "0", "name": "1", "length": "2", "alignment": "3" }
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, 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=1): Tool.__init__(self, "RepeatModeler", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "bedtools getfasta", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "TransDecoder", 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, "bam clipOverlap", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "exonerate", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "blastall", path=path, max_threads=max_threads)
parser.add_argument("-o", "--output", action="store", dest="output", help="Output file with allowed ids. Default - stdout") parser.add_argument( "-m", "--mode", action="store", dest="mode", default="common", help= "Operation mode. Possible variants: common, only_a, only_b, not_common, combine, count" ". Default - common") parser.add_argument( "-c", "--case_insensitive", action="store_true", dest="case_insensitive", help= "Case insensitive comparison. With this flag all ids are converted to upper case " "before comparison and are reported in upper case too. Default - False") args = parser.parse_args() Tool.intersect_ids_from_files(args.group_a_list, args.group_b_list, args.output, mode=args.mode, case_insensitive=args.case_insensitive)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "raxml", path=path, max_threads=max_threads)
def __init__(self, max_threads=4, max_memory=None, timelog=None): Tool.__init__(self, "gatk CombineGVCFs", max_threads=max_threads, max_memory=max_memory, timelog=timelog)
def __init__(self, max_threads=4, max_memory=None, timelog=None): Tool.__init__(self, "GenomeAnalysisTK.jar -T ValidateVariants", max_threads=max_threads, max_memory=max_memory, timelog=timelog)
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=4): Tool.__init__(self, "bowtie2", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "codeml", path=path, max_threads=max_threads) self.example = """
def __init__(self, path="", max_threads=4): Tool.__init__(self, "convert", 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, "SSPACE_Standard_v3.0.pl", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "SWAMP.py", path=path, max_threads=max_threads)
def __init__(self, path="", max_threads=4): Tool.__init__(self, "bedtools bamtofastq", path=path, max_threads=max_threads)