def generate_2x0(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listVariants = []
for i, base in enumerate(seq[:-1]):
for newBase1 in seqlib.allBases(rna):
for newBase2 in seqlib.allBases(rna):
variant = seq[:i+1] + newBase1 + newBase2 + seq[i+1:]
listVariants.append(variant)
return listVariants
def generate_2x0(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listVariants = []
for i, base in enumerate(seq[:-1]):
for newBase1 in seqlib.allBases(rna):
for newBase2 in seqlib.allBases(rna):
variant = seq[:i + 1] + newBase1 + newBase2 + seq[i + 1:]
listVariants.append(variant)
return listVariants
def generate_4x4(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listVariants = []
for i, base in enumerate(seq[:-3]):
nextBase = seq[i+1]
nextNextBase = seq[i+2]
nextNextNextBase = seq[i+3]
for otherBase1 in seqlib.allOtherBases(base, rna):
for newBase2 in seqlib.allBases(rna):
for newBase3 in seqlib.allBases(rna):
for otherBase4 in seqlib.allOtherBases(nextNextNextBase, rna):
variant = seq[:i] + otherBase1 + newBase2 + newBase3 + otherBase4 + seq[i+4:]
listVariants.append(variant)
return listVariants
def generateSatLib(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listListMutations = [seqlib.allBases(rna=False)
if base == 'N' else [base]
for base in list(consensus)]
listVariants = [''.join(seq) for seq in list(product(*listListMutations))]
return listVariants
def generate_4x4(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listVariants = []
for i, base in enumerate(seq[:-3]):
nextBase = seq[i + 1]
nextNextBase = seq[i + 2]
nextNextNextBase = seq[i + 3]
for otherBase1 in seqlib.allOtherBases(base, rna):
for newBase2 in seqlib.allBases(rna):
for newBase3 in seqlib.allBases(rna):
for otherBase4 in seqlib.allOtherBases(
nextNextNextBase, rna):
variant = seq[:
i] + otherBase1 + newBase2 + newBase3 + otherBase4 + seq[
i + 4:]
listVariants.append(variant)
return listVariants
def generate_1x3(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listVariants = []
for i, base in enumerate(seq[:-2]):
for newBase in seqlib.allBases(rna):
variant = seq[:i] + newBase + seq[i + 3:]
listVariants.append(variant)
return listVariants
def generateSatLib(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listListMutations = [
seqlib.allBases(rna=False) if base == 'N' else [base]
for base in list(consensus)
]
listVariants = [''.join(seq) for seq in list(product(*listListMutations))]
return listVariants
def generate_1x3(consensus, rna=False):
seq = seqlib.standardize(consensus, rna)
listVariants = []
for i, base in enumerate(seq[:-2]):
for newBase in seqlib.allBases(rna):
variant = seq[:i] + newBase + seq[i+3:]
listVariants.append(variant)
return listVariants
def seqCompo(seqs, libSeq=None, startPos=1, norm=True, RNA=False, legendloc=2):
"""Plot sequence composition as a line graph"""
# Generate default libSeq
if libSeq is None:
libSeq = 'N' * len(seqs[0])
# Get library positions
libPos = [i for (i, base) in enumerate(libSeq.upper()) if base == 'N']
xTickLabels = [str(i+startPos) for i in libPos]
# Convert to pd.series if not already
seqs = pd.Series(seqs)
# Constants
allBases = seqlib.allBases(RNA)
numSeqs = len(seqs)
numPos = len(libPos)
colors = sns.color_palette("Paired", 12)
# Compute sequence composition matrix
compo = pd.DataFrame(index=libPos, columns=allBases)
for pos in libPos:
for base in allBases:
compo[base][pos] = np.sum(seqs.str[pos] == base)
if norm:
compo = compo / numSeqs * 100
ylabel = 'Sequence content (%)'
else:
ylabel = 'Sequence content (count)'
# Plot
for i, base in enumerate(allBases):
plt.plot(range(0, numPos), compo[base], color=colors[2*i+1], linewidth=3, label=base)
# Add legend and axis labels, and change x tick labels
setproperties(legend=True, legendloc=legendloc,
xlabel='Position', ylabel=ylabel)
plt.xticks(range(0, numPos), xTickLabels)
return plt.gca()