GENE_CALL_DIR = "" # set by set method, via parameter list
HMM_OUT_DIR = "" # set by set method, via parameter list
PVOGS_OUT_DIR = "" # set by set method, via parameter list
PVOGS_FASTA_DB_NAME = "pVOGs.fasta"
HIT_COUNT_MAX = 50 # Put a limit on the number of hits that should be processed; let's not go over this
MAX_SEQ_HITS = 5 # HMM search can return many hits; report only top number designated; set default here
# output formats
TBL = 1
XML = 2
LIST = 3
# templates
annotation = phate_annotation.annotationRecord()
class multiHMM(object):
def __init__(self):
self.hmmProgram = 'jackhmmer' # Select from 'jackhmmer', 'hmmsearch', 'hmmbuild', 'hmmalign', 'hmmscan', 'phmmer'; default = jackhmmer
self.blastAnnotations = [
] # List of phate_annotation objects; blast output get temporarily stored here
# move to hit class: self.topHitList = [] #
self.geneCallDir = "" # needs to be set
self.hmmOutDir = "" # needs to be set
self.outputFormat = TBL # default format for jackhmmer output
self.pVOGsOutDir = "" # needs to be set
self.topHitCount = MAX_SEQ_HITS
self.NCBI_VIRUS_PROTEIN_HMM = False # ditto
self.NR_HMM = False # ditto
# Verbosity
CLEAN_RAW_DATA = os.environ["CLEAN_RAW_DATA"]
PHATE_WARNINGS = os.environ["PHATE_WARNINGS"]
PHATE_MESSAGES = os.environ["PHATE_MESSAGES"]
PHATE_PROGRESS = os.environ["PHATE_PROGRESS"]
DEBUG = False
#DEBUG = True
# For GFF output
GFF_COMMENT = "##gff-version 3"
# Templates
annotationObj = phate_annotation.annotationRecord()
fastaObj = phate_fastaSequence.fasta()
# Reverse complement
#complements = string.maketrans('acgtrymkbdhvACGTRYMKBDHV', 'tgcayrkmvhdbTGCAYRKMVHDB') # Python 2
complements = str.maketrans('acgtrymkbdhvACGTRYMKBDHV',
'tgcayrkmvhdbTGCAYRKMVHDB') # Python 3
class genome(object):
# Class genome uses fasta objects to represent a genome/chromosome or a plasmid and its genes and proteins.
# The chromosome's contig set, gene set, and protein set are each represented by multi-fasta objects.
def __init__(self):
self.filename = "" # name of file that contains the genome sequence