def process(filename):
print("Processing " + filename)
sequence_record_list = []
# print(os.getcwd())
for record in SeqIO.parse(filename, "fasta"):
sequence_record_list.append(record.seq)
print("Sequences Extracted!")
sequence_record = ''.join(str(e) for e in sequence_record_list)
atree = ATree()
print(str(len(sequence_record)) + "-->" + str(atree))
for subsequence_chunks in break_sequence(sequence_record, 8):
atree.process_subsequence(subsequence_chunks)
atree.dump_to_file(filename + "_TREE")
print("Ensuring correct File System Navigation: " + os.getcwd())
atree.pickle_into_file("GenomeDataset/Processing/" +
os.path.basename(filename) + "_pTREE")
subprocess.call([
"rsync", "-az", "GenomeDataset/Processing/",
"[email protected]:~/Documents/master-GSAFv2/gsaf-2.0/GenomeDataset/Processing/"
])
return len(sequence_record)
def __init__(self):
self.eigen_exists = False
self.eigen_values = []
# statistical_inferences attribute used for storing mean, mode, median, min, max, average
self.statistical_inferences_exist = False
self.statistical_inferences = {
"mean": 0,
"mode": 0,
'median': 0,
'min': 0,
'max': 0,
'range': 0
}
self.has_been_analyzed = False
self.gmap_exists = False
self.gmap = np.zeros((340, 340), dtype=np.int)
self.lookup_table = []
self.new_tree = ATree()
