def __init__(self, source) :
"""Constructor.
Argument : a filename or a list of strings that represent sequences.
- mysequences = genepy.seqarray("from_genbank.gb") -- loads the sequences
in from_genbank.gb as BioPython Bio.Seq objects.
- mysequences = genepy.seqarray(seq_list), where seq_list is a list of
strings ( such as ["ACTG", "AGTA", "TTGC"] ) converts these to BioPython
Bio.Seq objects using the generic_dna alphabet ( for now ).
"""
# If we're reading in a sequence set from a file
if type(source) is str :
if os.path.isfile(source) :
self.seq = genepy.readalignment(source)
self.filename = source
else :
print "%s not found, aborting." % source
# If we're fed a list
elif type(source) is list :
self.seq = [SeqRecord.SeqRecord(s) for s in source]
self.filename = "genepy.fasta"
else :
raise TypeError("Expected a filename or a list of strings.")
# Generate static members
self.update()
def align(self, force = True, it = False, full = False, full_iter = False, auto = True, threads = False) : """Align the array of sequences using ClustalO. -- force : True / False; overwrite filename, if it exists -- it : False, integers > 0; iterate the guide tree -- full : True / False; use full distance matrix for guide-tree calculation -- full_iter : True / False; use full distance matrix during iteration only -- auto : True / False; automatically select options for speed and accuracy -- threads : False, integers > 0; limit the number of threads; False uses all """ # System call to ClustalO genepy.align(self.filename, force, threads, full, full_iter, it, auto) # Read aligned sequence array self.seq = genepy.readalignment(os.path.splitext(self.filename)[0] + "_aligned_genepy.phy") # Update static members self.update()
