def test_cai():
# first, make sure all arguments get the same result
assert (CAI("AAC", reference=["AAC"]) == CAI("AAC", RSCUs=RSCU([
"AAC"
])) == CAI("AAC", weights=relative_adaptiveness(sequences=["AAC"])) == 1.0)
# check other sequences
assert CAI("AAT", reference=["AAC"]) == 0.5
assert CAI("AATAAT", reference=["AAC"]) == 0.5
assert CAI("AAT" * 100, reference=["AAC"]) == 0.5
def calc_CAI(self,dataa):
self.__geneCount=len(self.__bacteriaORF)
concatORF=[]
for i in range(self.__geneCount):
currentORF=self.get_ORF()[i].get_ORF()
concatORF.append(currentORF)
weights = relative_adaptiveness(concatORF)
cursor = dataa.cursor()
for i in range(self.__geneCount):
currentCAIvalue=CAI(str(self.get_ORF()[i].get_ORF()), weights=weights)
sql='INSERT INTO geneExpressionEstimations(bacteriaID, geneID, CAI) VALUES (' + str(self.__bacteriaID) + ' ,' + str(self.get_UTR5()[i].get_geneID()) + ' ,' + str(currentCAIvalue) + ')'
cursor.execute(sql)
dataa.commit()
from Bio import SeqIO
from CAI import CAI, RSCU, relative_adaptiveness
sequences = []
for seq_record in SeqIO.parse(
"RhodosporidiumToruloidesRPGenes.fasta", "fasta"
): #change file name #Change File Name depending on organism
dnaSeq = str(seq_record.seq.lower())
if len(dnaSeq) % 3 != 0:
print(seq_record.id)
else:
sequences.append(dnaSeq)
weights = relative_adaptiveness(sequences=sequences)
print(weights)
for seq_record in SeqIO.parse(
"RhodosporidiumToruloidesRPGenes.fasta",
"fasta"): #changw file name depending on organism
dnaSeq = str(seq_record.seq.lower())
if len(dnaSeq) % 3 != 0:
print(seq_record.id)
else:
print(CAI(dnaSeq, weights=weights))
def test_alternate_genetic_code():
assert relative_adaptiveness(sequences=["AAC"], genetic_code=10) == {
"AAA": 1.0,
"AAC": 1.0,
"AAG": 1.0,
"AAT": (0.5 / (0.5 * (1 + 0.5))) / (1 / (0.5 * (1 + 0.5))),
"ACA": 1.0,
"ACC": 1.0,
"ACG": 1.0,
"ACT": 1.0,
"AGA": 1.0,
"AGC": 1.0,
"AGG": 1.0,
"AGT": 1.0,
"ATA": 1.0,
"ATC": 1.0,
"ATG": 1.0,
"ATT": 1.0,
"CAA": 1.0,
"CAC": 1.0,
"CAG": 1.0,
"CAT": 1.0,
"CCA": 1.0,
"CCC": 1.0,
"CCG": 1.0,
"CCT": 1.0,
"CGA": 1.0,
"CGC": 1.0,
"CGG": 1.0,
"CGT": 1.0,
"CTA": 1.0,
"CTC": 1.0,
"CTG": 1.0,
"CTT": 1.0,
"GAA": 1.0,
"GAC": 1.0,
"GAG": 1.0,
"GAT": 1.0,
"GCA": 1.0,
"GCC": 1.0,
"GCG": 1.0,
"GCT": 1.0,
"GGA": 1.0,
"GGC": 1.0,
"GGG": 1.0,
"GGT": 1.0,
"GTA": 1.0,
"GTC": 1.0,
"GTG": 1.0,
"GTT": 1.0,
"TAC": 1.0,
"TAT": 1.0,
"TCA": 1.0,
"TCC": 1.0,
"TCG": 1.0,
"TCT": 1.0,
"TGA": 1.0, # this is not a stop codon in genetic code 10
"TGC": 1.0,
"TGG": 1.0,
"TGT": 1.0,
"TTA": 1.0,
"TTC": 1.0,
"TTG": 1.0,
"TTT": 1.0,
}
def test_bad_args():
# make sure bad arguments raise errors
with pytest.raises(TypeError):
relative_adaptiveness()
with pytest.raises(TypeError):
relative_adaptiveness(sequences=["AAC"], RSCUs=RSCU(["AAC"]))
def test_weights():
assert relative_adaptiveness(sequences=["AAC"]) == {
"AAA": 1.0,
"AAC": 1.0,
"AAG": 1.0,
"AAT": (0.5 / (0.5 * (1 + 0.5))) / (1 / (0.5 * (1 + 0.5))),
"ACA": 1.0,
"ACC": 1.0,
"ACG": 1.0,
"ACT": 1.0,
"AGA": 1.0,
"AGC": 1.0,
"AGG": 1.0,
"AGT": 1.0,
"ATA": 1.0,
"ATC": 1.0,
"ATG": 1.0,
"ATT": 1.0,
"CAA": 1.0,
"CAC": 1.0,
"CAG": 1.0,
"CAT": 1.0,
"CCA": 1.0,
"CCC": 1.0,
"CCG": 1.0,
"CCT": 1.0,
"CGA": 1.0,
"CGC": 1.0,
"CGG": 1.0,
"CGT": 1.0,
"CTA": 1.0,
"CTC": 1.0,
"CTG": 1.0,
"CTT": 1.0,
"GAA": 1.0,
"GAC": 1.0,
"GAG": 1.0,
"GAT": 1.0,
"GCA": 1.0,
"GCC": 1.0,
"GCG": 1.0,
"GCT": 1.0,
"GGA": 1.0,
"GGC": 1.0,
"GGG": 1.0,
"GGT": 1.0,
"GTA": 1.0,
"GTC": 1.0,
"GTG": 1.0,
"GTT": 1.0,
"TAC": 1.0,
"TAT": 1.0,
"TCA": 1.0,
"TCC": 1.0,
"TCG": 1.0,
"TCT": 1.0,
"TGC": 1.0,
"TGG": 1.0,
"TGT": 1.0,
"TTA": 1.0,
"TTC": 1.0,
"TTG": 1.0,
"TTT": 1.0,
}
def test_arg_equivalence():
# should be able to take either reference sequences or an RSCU dict
assert relative_adaptiveness(sequences=["AAC"]) == relative_adaptiveness(
RSCUs=RSCU(["AAC"]))
import argparse
from CAI import relative_adaptiveness
import os
import json
from Bio import SeqIO
parser = argparse.ArgumentParser()
parser.add_argument(
"ref_fasta",
help="fasta file containing reference sequences for given species")
args = parser.parse_args()
outfile = os.path.splitext(os.path.basename(args.ref_fasta))[0] + ".wts"
sequence = [
str(seq.seq) for seq in SeqIO.parse(args.ref_fasta, "fasta")
if len(seq) % 3 == 0
] #bit of a hack
wts_dict = relative_adaptiveness(sequences=sequence)
with open(outfile, 'w+') as out:
json.dump(wts_dict, out)
def test_alternate_genetic_code():
assert relative_adaptiveness(sequences=["AAC"], genetic_code=10) == {
'AAA': 1.0,
'AAC': 1.0,
'AAG': 1.0,
'AAT': (0.5 / (0.5 * (1 + 0.5))) / (1 / (0.5 * (1 + 0.5))),
'ACA': 1.0,
'ACC': 1.0,
'ACG': 1.0,
'ACT': 1.0,
'AGA': 1.0,
'AGC': 1.0,
'AGG': 1.0,
'AGT': 1.0,
'ATA': 1.0,
'ATC': 1.0,
'ATG': 1.0,
'ATT': 1.0,
'CAA': 1.0,
'CAC': 1.0,
'CAG': 1.0,
'CAT': 1.0,
'CCA': 1.0,
'CCC': 1.0,
'CCG': 1.0,
'CCT': 1.0,
'CGA': 1.0,
'CGC': 1.0,
'CGG': 1.0,
'CGT': 1.0,
'CTA': 1.0,
'CTC': 1.0,
'CTG': 1.0,
'CTT': 1.0,
'GAA': 1.0,
'GAC': 1.0,
'GAG': 1.0,
'GAT': 1.0,
'GCA': 1.0,
'GCC': 1.0,
'GCG': 1.0,
'GCT': 1.0,
'GGA': 1.0,
'GGC': 1.0,
'GGG': 1.0,
'GGT': 1.0,
'GTA': 1.0,
'GTC': 1.0,
'GTG': 1.0,
'GTT': 1.0,
'TAC': 1.0,
'TAT': 1.0,
'TCA': 1.0,
'TCC': 1.0,
'TCG': 1.0,
'TCT': 1.0,
'TGA': 1.0, # this is not a stop codon in genetic code 10
'TGC': 1.0,
'TGG': 1.0,
'TGT': 1.0,
'TTA': 1.0,
'TTC': 1.0,
'TTG': 1.0,
'TTT': 1.0
}
def test_weights():
assert relative_adaptiveness(sequences=["AAC"]) == {
'AAA': 1.0,
'AAC': 1.0,
'AAG': 1.0,
'AAT': (0.5 / (0.5 * (1 + 0.5))) / (1 / (0.5 * (1 + 0.5))),
'ACA': 1.0,
'ACC': 1.0,
'ACG': 1.0,
'ACT': 1.0,
'AGA': 1.0,
'AGC': 1.0,
'AGG': 1.0,
'AGT': 1.0,
'ATA': 1.0,
'ATC': 1.0,
'ATG': 1.0,
'ATT': 1.0,
'CAA': 1.0,
'CAC': 1.0,
'CAG': 1.0,
'CAT': 1.0,
'CCA': 1.0,
'CCC': 1.0,
'CCG': 1.0,
'CCT': 1.0,
'CGA': 1.0,
'CGC': 1.0,
'CGG': 1.0,
'CGT': 1.0,
'CTA': 1.0,
'CTC': 1.0,
'CTG': 1.0,
'CTT': 1.0,
'GAA': 1.0,
'GAC': 1.0,
'GAG': 1.0,
'GAT': 1.0,
'GCA': 1.0,
'GCC': 1.0,
'GCG': 1.0,
'GCT': 1.0,
'GGA': 1.0,
'GGC': 1.0,
'GGG': 1.0,
'GGT': 1.0,
'GTA': 1.0,
'GTC': 1.0,
'GTG': 1.0,
'GTT': 1.0,
'TAC': 1.0,
'TAT': 1.0,
'TCA': 1.0,
'TCC': 1.0,
'TCG': 1.0,
'TCT': 1.0,
'TGC': 1.0,
'TGG': 1.0,
'TGT': 1.0,
'TTA': 1.0,
'TTC': 1.0,
'TTG': 1.0,
'TTT': 1.0
}