def setUp(self) -> None:
# noinspection DuplicatedCode
self.df = pd.DataFrame.from_dict(
{1: {'x': "a", 'y': 15, 'color': 'blue'},
2: {'x': "a", 'y': 16, 'color': 'blue'},
3: {'x': "b", 'y': 17, 'color': 'blue'},
4: {'x': "b", 'y': 18, 'color': 'blue'},
5: {'x': "a", 'y': 15, 'color': 'red'},
6: {'x': "a", 'y': 16, 'color': 'red'},
7: {'x': "b", 'y': 17, 'color': 'red'},
8: {'x': "b", 'y': 18, 'color': 'red'}
}).T
plotting = {
"data": self.df,
"x": "x",
"y": "y",
"hue": 'color'
}
self.ax = sns.boxplot(**plotting)
self.annotator = Annotator(
self.ax, pairs=[(("a", "blue"), ("a", "red")),
(("b", "blue"), ("b", "red")),
(("a", "blue"), ("b", "blue"))],
**plotting)
self.pvalues = [0.03, 0.04, 0.9]
def test_wrong_plotter_engine(self):
ax = sns.barplot(**self.plotting)
with self.assertRaisesRegex(NotImplementedError, "plotly"):
self.annotator = Annotator(
ax, plot="barplot", engine="plotly",
pairs=[(("a", "blue"), ("a", "red")),
(("b", "blue"), ("b", "red")),
(("a", "blue"), ("b", "blue"))],
**self.plotting)
def test_dodge_false_raises(self):
ax = sns.barplot(dodge=False, **self.plotting)
with self.assertRaisesRegex(ValueError, "dodge"):
self.annotator = Annotator(
ax, dodge=False, plot="barplot",
pairs=[(("a", "blue"), ("a", "red")),
(("b", "blue"), ("b", "red")),
(("a", "blue"), ("b", "blue"))],
**self.plotting)
def test_fixed_offset(self):
ax = sns.barplot(**self.plotting)
self.annotator = Annotator(
ax, plot="barplot",
pairs=[(("a", "blue"), ("a", "red")),
(("b", "blue"), ("b", "red")),
(("a", "blue"), ("b", "blue"))],
**self.plotting)
self.annotator.configure(test="Mann-Whitney", use_fixed_offset=True)
self.annotator.apply_and_annotate()
def boxplot_with_test(data, x, y, pairs):
plotting_parameters = {'data': data, 'x': x, 'y': y}
pvalues = [
mannwhitneyu(data[data[x] == pair[0]][y],
data[data[x] == pair[1]][y]).pvalue for pair in pairs
]
ax = sns.boxplot(**plotting_parameters)
# Add annotations
annotator = Annotator(ax, pairs, **plotting_parameters)
annotator.set_pvalues(pvalues)
annotator.annotate()
def test_orient_horizontal(self):
plotting = {**self.plotting, 'orient': 'h',
'x': 'y', 'y': 'x', 'dodge': True}
ax = sns.stripplot(**plotting)
self.annotator = Annotator(
ax, plot="stripplot",
pairs=[(("a", "blue"), ("a", "red")),
(("b", "blue"), ("b", "red")),
(("a", "blue"), ("b", "blue"))],
**plotting)
self.annotator.configure(test="Mann-Whitney")
self.annotator.apply_and_annotate()
def setUp(self) -> None:
self.df = pd.DataFrame.from_dict({
1: {
"x": "a",
"y": 15,
"color": "blue"
},
2: {
"x": "a",
"y": 16,
"color": "blue"
},
3: {
"x": "b",
"y": 17,
"color": "blue"
},
4: {
"x": "b",
"y": 18,
"color": "blue"
},
5: {
"x": "a",
"y": 15,
"color": "red"
},
6: {
"x": "a",
"y": 16,
"color": "red"
},
7: {
"x": "b",
"y": 17,
"color": "red"
},
8: {
"x": "b",
"y": 18,
"color": "red"
}
}).T
plotting = {"data": self.df, "x": "x", "y": "y", "hue": "color"}
self.ax = sns.boxplot(**plotting)
self.annotator = Annotator(self.ax,
pairs=[(("a", "blue"), ("a", "red")),
(("b", "blue"), ("b", "red")),
(("a", "blue"), ("b", "blue"))],
verbose=False,
**plotting)
self.pvalues = [0.03, 0.04, 0.9]
def test_plot_and_annotate_facets(self):
annotator = Annotator(None, self.simple_pairs)
g = sns.FacetGrid(self.params_df.pop("data"),
col=self.params_df.pop("hue"),
height=10,
sharey=False)
self.params_df.pop("hue_order")
g.map_dataframe(annotator.plot_and_annotate_facets,
plot="boxplot",
plot_params=self.params_df,
configuration={
'test': 'Mann-Whitney',
'text_format': 'simple'
},
annotation_func='apply_test',
ax_op_after=[['set_xlabel', ['Group'], None]],
annotation_params={'num_comparisons': 'auto'})
def test_order_in_x(self):
with self.assertRaisesRegex(ValueError, "(specified in `order`)"):
self.annot = Annotator(self.ax, [(0, 2)], data=self.data,
order=[0, 1, 2])
def test_unmatched_x_in_box_pairs_without_hue(self):
with self.assertRaisesRegex(ValueError, "(specified in `pairs`)"):
self.annot = Annotator(self.ax, [(0, 2)], data=self.data)
def test_init_barplot(self):
ax = sns.barplot(data=self.data)
self.annot = Annotator(ax, [(0, 1)], plot="barplot", data=self.data)
def test_init_df(self):
self.ax = sns.boxplot(**self.params_df)
self.annot = Annotator(self.ax, pairs=self.pairs_for_df,
**self.params_df)
def test_init_simple(self):
self.annot = Annotator(self.ax, [(0, 1)], data=self.data)
def test_comparisons_correction_by_name(self):
self.ax = sns.boxplot(ax=self.ax, data=self.data2)
annot = Annotator(self.ax, pairs=[("X", "Y")],
data=self.data2)
annot.configure(test="Mann-Whitney", comparisons_correction="BH")
annot.apply_and_annotate()
plotting_parameters = {
'data': tmp,
'x': 'classe_mortalidade',
'y': ind,
'order': ['A', 'B', 'C']
}
#tmp[['classe_mortalidade', i]].groupby('classe_mortalidade').mean()
pvalues = []
for p in pairs:
pvalues.append(
stats.ttest_ind(
tmp.loc[tmp.classe_mortalidade == p[0], ind],
tmp.loc[tmp.classe_mortalidade == p[1],
ind]).pvalue)
formatted_pvalues = [f"p={p:.2e}" for p in pvalues]
ax = get_log_ax()
sns.boxplot(**plotting_parameters).set_title(
'mz:{:.2f} rt:{:.2f}'.format(*data[k][0].loc[
ind, ['row m/z', 'row retention time']].tolist()))
sns.stripplot(**plotting_parameters)
annotator = Annotator(ax, pairs, **plotting_parameters)
annotator.set_pvalues(pvalues)
#annotator.set_custom_annotations(formatted_pvalues)
annotator.annotate()
#plt.savefig("plot1A.png", bbox_inches='tight')
pdf.savefig()
plt.close()
def main():
date = datetime.date.today().strftime("%Y%m%d")
# passages = "p2-p12"
# opv_passages = "p1-p7"
# pv_passages = "p3-p8"
# input_dir = "/Users/odedkushnir/Projects/fitness"
# rv_replica1_mutation_data = post_data_mutation("/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/"
# "20201008RV-202329127/merged/passages/fits_all_pos_at_once_sampling/"
# "replica1_syn/output/mutation/%s" % passages)
# rv_replica1_mutation_data["Virus"] = "RVB14 #1"
# rv_replica2_mutation_data = post_data_mutation("/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/"
# "20201008RV-202329127/merged/passages/fits_all_pos_at_once_sampling/"
# "replica2_syn/output/mutation/%s" % passages)
# rv_replica2_mutation_data["Virus"] = "RVB14 #2"
# rv_replica3_mutation_data = post_data_mutation("/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/"
# "20201008RV-202329127/merged/passages/fits_all_pos_at_once_sampling/"
# "replica3_syn/output/mutation/%s" % passages)
# rv_replica3_mutation_data["Virus"] = "RVB14 #3"
# cv_mutation_data = post_data_mutation("/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/190627_RV_CV"
# "/merged/CVB3/Rank0_data_mutation/fits/output/mutation/%s" % passages)
# cv_mutation_data["Virus"] = "CVB3"
# opv_mutataion_data = post_data_mutation("/Volumes/STERNADILABHOME$/volume3/okushnir/CirSeq/OPV/fits/output/mutation/"
# "all_positions_p1-p7")
# opv_mutataion_data["Virus"] = "OPV2"
#
# pv_mutataion_data = post_data_mutation("/Volumes/STERNADILABHOME$/volume3/okushnir/CirSeq/Mahoney/fits/output/"
# "mutation/p3-p8")
# pv_mutataion_data["Virus"] = "PV1"
#
#
#
# output_dir = "/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/20201008RV-202329127/merged/passages/" \
# "%s_fits_syn_plots" % date
# try:
# os.mkdir(output_dir)
# except OSError:
# print("Creation of the directory %s failed" % output_dir)
# else:
# print("Successfully created the directory %s " % output_dir)
#
# all_data = pd.concat([rv_replica1_mutation_data, rv_replica2_mutation_data, rv_replica3_mutation_data,
# cv_mutation_data, opv_mutataion_data, pv_mutataion_data], sort=False)
# all_data = all_data.rename(columns={"allele0_1": "Transition rate"})
# all_data["Transition rate"] = all_data["Transition rate"].astype(float)
# # print(all_data.to_string())
# # all_data = all_data.rename(columns={"inferred_mu": "Mutation rate"})
# # # print(all_data["Mutation rate"].dtype)
# # all_data["Mutation rate"] = all_data["Mutation rate"].map(lambda x: str(x).lstrip('*'))
# # all_data["Mutation rate"] = pd.to_numeric(all_data["Mutation rate"], errors='coerce')#.astype(float)
# # # print(all_data["Mutation rate"].dtype)
# # all_data["Mutation"] = all_data["Mutation"].apply(lambda x: x[0]+">"+x[1:]if len(x)<=2 else x)# if len(x)==2 else x[0]+">"+x[1:])
# # all_data["Mutation"] = all_data["Mutation"].apply(lambda x: x.split("_")[0] + "\n" + x.split("_")[-1] + "-like" if len(x)>3 else x)
# all_data["Mutation"] = np.where(all_data["Mutation"] == "nonadar", "A>G\nNon-ADAR-like", all_data["Mutation"])
# all_data["Mutation"] = np.where(all_data["Mutation"] == "adar", "A>G\nADAR-like", all_data["Mutation"])
# all_data["Mutation"] = np.where(all_data["Mutation"] == "AG", "A>G", all_data["Mutation"])
# all_data["Mutation"] = np.where(all_data["Mutation"] == "UC", "U>C", all_data["Mutation"])
# all_data["Mutation"] = np.where(all_data["Mutation"] == "GA", "G>A", all_data["Mutation"])
# all_data["Mutation"] = np.where(all_data["Mutation"] == "CU", "C>U", all_data["Mutation"])
# # all_data = all_data[(all_data["pos"] >= 5785) & (all_data["pos"] <= 7212)]
#
#
#
# # q1 = all_data["Transition rate"].quantile(0.25)
# # q3 = all_data["Transition rate"].quantile(0.75)
# # all_data = all_data[all_data["Transition rate"] > q1]
# # all_data = all_data[all_data["Transition rate"] < q3]
#
# all_data = all_data[all_data["Mutation"] != "A>G\nADAR-like"]
# all_data = all_data[all_data["Mutation"] != "A>G\nNon-ADAR-like"]
# print(all_data.shape[0])
# all_data.to_csv("/Users/odedkushnir/PhD_Projects/fitness/all_data.csv")
#Plots - local
all_data = pd.read_csv(
"/Users/odedkushnir/PhD_Projects/fitness/all_data.csv")
output_dir = "/Users/odedkushnir/PhD_Projects/fitness/{0}_fits_syn_plots".format(
date)
try:
os.mkdir(output_dir)
except OSError:
print("Creation of the directory %s failed" % output_dir)
else:
print("Successfully created the directory %s " % output_dir)
plt.style.use('classic')
sns.set_palette("Set2")
mutation_order = ["C>U", "G>A", "U>C", "A>G"]
virus_order = ["RVB14 #1", "RVB14 #2", "RVB14 #3", "CVB3", "OPV2", "PV1"]
g1 = sns.boxenplot(x="Mutation",
y="Transition rate",
data=all_data,
order=mutation_order,
hue="Virus",
hue_order=virus_order)
g1.set_yscale("log")
"""[((cat1, hue1), (cat2, hue2)), ((cat3, hue3), (cat4, hue4))]"""
pairs = [(("A>G", "RVB14 #1"), ("C>U", "RVB14 #1")),
(("A>G", "RVB14 #1"), ("G>A", "RVB14 #1")),
(("A>G", "RVB14 #2"), ("C>U", "RVB14 #2")),
(("A>G", "RVB14 #2"), ("G>A", "RVB14 #2")),
(("A>G", "RVB14 #3"), ("C>U", "RVB14 #3")),
(("A>G", "RVB14 #3"), ("G>A", "RVB14 #3")),
(("A>G", "CVB3"), ("C>U", "CVB3")),
(("A>G", "CVB3"), ("G>A", "CVB3")),
(("A>G", "OPV2"), ("C>U", "OPV2")),
(("A>G", "OPV2"), ("G>A", "OPV2")),
(("A>G", "PV1"), ("C>U", "PV1")),
(("A>G", "PV1"), ("G>A", "PV1")),
(("U>C", "RVB14 #1"), ("C>U", "RVB14 #1")),
(("U>C", "RVB14 #1"), ("G>A", "RVB14 #1")),
(("U>C", "RVB14 #2"), ("C>U", "RVB14 #2")),
(("U>C", "RVB14 #2"), ("G>A", "RVB14 #2")),
(("U>C", "RVB14 #3"), ("C>U", "RVB14 #3")),
(("U>C", "RVB14 #3"), ("G>A", "RVB14 #3")),
(("U>C", "CVB3"), ("C>U", "CVB3")),
(("U>C", "CVB3"), ("G>A", "CVB3")),
(("U>C", "OPV2"), ("C>U", "OPV2")),
(("U>C", "OPV2"), ("G>A", "OPV2")),
(("U>C", "PV1"), ("C>U", "PV1")),
(("U>C", "PV1"), ("G>A", "PV1"))]
annotator = Annotator(g1,
pairs,
x="Mutation",
y="Transition rate",
data=all_data,
order=mutation_order,
hue="Virus",
hue_order=virus_order)
annotator.configure(test='Mann-Whitney',
text_format='star',
loc='outside',
comparisons_correction="Bonferroni")
annotator.apply_and_annotate()
g1.set(xlabel="Type of mutation")
g1.set(ylabel="Mutation rate inferred")
g1.set_ylim(10**-10, 10**-1)
g1.legend(loc='center left',
bbox_to_anchor=(1.05, 0.5),
borderaxespad=0.,
fontsize=7)
plt.savefig(output_dir + "/%s_mutation_rate.png" % date,
dpi=600,
bbox_inches='tight')
plt.close()
def test_unmatched_x_in_box_pairs_with_hue(self):
with self.assertRaisesRegex(ValueError, "(specified in `pairs`)"):
self.annot = Annotator(self.ax, [(("c", "blue"), ("b", "blue"))],
data=self.df, x="x", y="y",
order=["a", "b"], hue='color',
hue_order=['red', 'blue'])
def test_working_hue_orders(self):
self.annot = Annotator(self.ax, [(("a", "blue"), ("b", "blue"))],
data=self.df, x="x", y="y",
order=["a", "b"], hue='color',
hue_order=['red', 'blue'])
def plots(input_dir, date, data_filter, virus, passage_order, transition_order, pairs, label_order, pairs_adar, filter_reads=None):
output_dir = input_dir + date + "_plots"
plus_minus = u"\u00B1"
try:
os.mkdir(output_dir)
except OSError:
print("Creation of the directory %s failed" % output_dir)
else:
print("Successfully created the directory %s " % output_dir)
if filter_reads is True:
data_filter["no_variants"] = np.where(data_filter["Prob"] < 0.95, 0, data_filter["no_variants"])
data_filter["Read_count"] = data_filter[data_filter["Read_count"] > 10000]
mutation_order = ["A>G", "U>C", "G>A", "C>U", "A>C", "U>G", "A>U", "U>A", "G>C", "C>G", "C>A", "G>U"]
type_order = ["Synonymous", "Non-Synonymous", "Premature Stop Codon"]
# g1 = sns.catplot("label", "frac_and_weight", data=data_filter, hue="Mutation", order=label_order, palette="tab20",
# kind="point", dodge=True, hue_order=mutation_order, join=False, estimator=weighted_varaint,
# orient="v")
# g1.set_axis_labels("Passage", "Variant Frequency {} CI=95%".format(plus_minus))
# g1.set_xticklabels(fontsize=9, rotation=45)
# g1.set(yscale='log')
# g1.set(ylim=(10**-5, 10**-1))
#
# # plt.show()
# g1.savefig(output_dir + "/All_Mutations_point_plot", dpi=300)
# plt.close()
data_filter["passage"] = data_filter["passage"].astype(str)
data_filter["passage"] = np.where(data_filter["passage"] != "RNA\nControl", "p" + data_filter["passage"], data_filter["passage"])
g2 = sns.catplot("passage", "frac_and_weight", data=data_filter, hue="Mutation", order=passage_order,
palette=mutation_palette(4)
, kind="point", dodge=0.5, hue_order=transition_order, join=False, estimator=weighted_varaint,
orient="v")
g2.set_axis_labels("Passage", "Variant Frequency {} CI=95%".format(plus_minus))
g2.set(yscale='log')
g2.set(ylim=(10 ** -6, 10 ** -2))
# g2.set_xticklabels(fontsize=10, rotation=45)
# g2.savefig("/Users/odedkushnir/Google Drive/Studies/PhD/Prgress reports/20200913 Final report/plots" +
# "/Transition_Mutations_point_plot_Mahoney", dpi=300)
g2.savefig(output_dir + "/Transition_Mutations_point_plot_{0}".format(virus), dpi=300)
plt.close()
passage_g = sns.boxplot(x="passage", y="Frequency", data=data_filter, hue="Mutation", order=passage_order,
palette=mutation_palette(4), dodge=True, hue_order=transition_order)
passage_g.set_yscale('log')
passage_g.set_ylim(10 ** -6, 10 ** -1)
passage_g.set(xlabel="Passage", ylabel="Variant Frequency")
annot = Annotator(passage_g, pairs, x="passage", y="Frequency", hue="Mutation", data=data_filter,
order=passage_order, hue_order=transition_order)
annot.configure(test='t-test_welch', text_format='star', loc='outside', verbose=2,
comparisons_correction="Bonferroni")
annot.apply_test()
file_path = output_dir + "/sts.csv"
with open(file_path, "w") as o:
with contextlib.redirect_stdout(o):
passage_g, test_results = annot.annotate()
plt.legend(bbox_to_anchor=(1.05, 0.5), loc=2, borderaxespad=0.)
plt.tight_layout()
plt.savefig(output_dir + "/Transition_Mutations_box_stat_plot_{0}".format(virus), dpi=300)
plt.close()
data_filter_synonymous = data_filter.loc[data_filter.Type == "Synonymous"]
data_filter_synonymous["Mutation"] = np.where(((data_filter_synonymous["Mutation"] == "A>G") &
(data_filter_synonymous["5`_ADAR_Preference"] == "High")),
"High\nADAR-like\nA>G", np.where(((data_filter_synonymous["Mutation"] == "A>G")
& (data_filter_synonymous["5`_ADAR_Preference"] == "Intermediate")),
"Intermediate\nADAR-like\nA>G",
np.where(((data_filter_synonymous["Mutation"] == "A>G") &
(data_filter_synonymous["5`_ADAR_Preference"] == "Low")),
"Low\nADAR-like\nA>G",
data_filter_synonymous["Mutation"])))
data_filter_synonymous["Mutation_adar"] = np.where(((data_filter_synonymous["Mutation"] == "U>C") &
(data_filter_synonymous["3`_ADAR_Preference"] == "High")),
"High\nADAR-like\nU>C", np.where(((data_filter_synonymous["Mutation"] == "U>C")
& (data_filter_synonymous["3`_ADAR_Preference"] == "Intermediate")),
"Intermediate\nADAR-like\nU>C",
np.where(((data_filter_synonymous["Mutation"] == "U>C") &
(data_filter_synonymous["3`_ADAR_Preference"] == "Low")),
"Low\nADAR-like\nU>C",
data_filter_synonymous["Mutation"])))
mutation_adar_order = ["High\nADAR-like\nA>G", "Low\nADAR-like\nA>G",
"High\nADAR-like\nU>C", "Low\nADAR-like\nU>C"]
data_filter_synonymous["passage"] = data_filter_synonymous["passage"].astype(str)
catplot_adar = sns.catplot(x="passage", y="frac_and_weight", data=data_filter_synonymous, hue="Mutation_adar",
order=passage_order, palette=mutation_palette(4, adar=True), kind="point", dodge=0.5,
hue_order=mutation_adar_order, join=False, estimator=weighted_varaint, orient="v",
legend=True)
catplot_adar.set_axis_labels("Passage", "Variant Frequency {0} CI=95%".format(plus_minus))
catplot_adar.set(yscale='log')
catplot_adar.set(ylim=(10 ** -6, 10 ** -2))
plt.savefig(output_dir + "/adar_pref_mutation_point_plot_{0}.png".format(virus), dpi=300)
plt.close()
adar_g = sns.boxplot(x="passage", y="Frequency", data=data_filter_synonymous, hue="Mutation_adar",
order=passage_order, palette=mutation_palette(4, adar=True), dodge=True,
hue_order=mutation_adar_order)
adar_g.set_yscale('log')
adar_g.set_ylim(10 ** -6, 10 ** -1)
adar_g.set(xlabel="Passage", ylabel="Variant Frequency")
annot = Annotator(adar_g, pairs_adar, x="passage", y="Frequency", hue="Mutation_adar",
data=data_filter_synonymous, hue_order=mutation_adar_order, order=passage_order)
annot.configure(test='t-test_welch', text_format='star', loc='outside', verbose=2,
comparisons_correction="Bonferroni")
annot.apply_test()
file_path = output_dir + "/sts_adar.csv"
with open(file_path, "w") as o:
with contextlib.redirect_stdout(o):
adar_g, test_results = annot.annotate()
plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
plt.tight_layout()
plt.savefig(output_dir + "/adar_pref_mutation_box_plot_{0}.png".format(virus), dpi=300)
plt.close()
def main():
# input_dir = "/Users/odedkushnir/Projects/fitness/AccuNGS/190627_RV_CV/RVB14/"
# input_dir = "/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/20201008RV-202329127/merged/patients/"
input_dir = "/Users/odedkushnir/PhD_Projects/After_review/AccuNGS/RV/patients/"
prefix = "inosine_predict_context_freq0.01"
date = datetime.today().strftime("%Y%m%d")
output_dir = input_dir + "{0}_{1}".format(date, prefix)
try:
os.mkdir(output_dir)
except OSError:
print("Creation of the directory %s failed" % output_dir)
else:
print("Successfully created the directory %s " % output_dir)
data_filter = pd.read_pickle(input_dir + prefix + "/data_filter.pkl")
data_filter_ag = pd.read_pickle(input_dir + prefix + "/data_filter_ag.pkl")
data_filter_uc = pd.read_pickle(input_dir + prefix + "/data_filter_uc.pkl")
data_filter["label"] = np.where(
data_filter["label"] == "RNA Control\nPrimer ID", "RNA\nControl",
data_filter["label"])
#Plots
label_order = [
"RNA\nControl", "p3 Cell Culture\nControl", "Patient-1", "Patient-4",
"Patient-5", "Patient-9", "Patient-16", "Patient-17", "Patient-20"
]
mutation_order = [
"A>G", "U>C", "G>A", "C>U", "A>C", "U>G", "A>U", "U>A", "G>C", "C>G",
"C>A", "G>U"
]
transition_order = ["A>G", "U>C", "G>A", "C>U"]
type_order1 = ["Synonymous", "Non-Synonymous", "Premature Stop Codon"]
context_order = ["UpA", "ApA", "CpA", "GpA"]
type_order2 = ["Synonymous", "Non-Synonymous"]
context_order_uc = ["UpA", "UpU", "UpG", "UpC"]
type_order_ag = ["Synonymous", "Non-Synonymous", "NonCodingRegion"]
adar_preference = ["High", "Intermediate", "Low"]
plus_minus = u"\u00B1"
pairs = [(("RNA\nControl", "A>G"), ("RNA\nControl", "G>A")),
(("p3 Cell Culture\nControl", "A>G"), ("p3 Cell Culture\nControl",
"G>A")),
(("Patient-1", "A>G"), ("Patient-1", "G>A")),
(("Patient-4", "A>G"), ("Patient-4", "G>A")),
(("Patient-5", "A>G"), ("Patient-5", "G>A")),
(("Patient-9", "A>G"), ("Patient-9", "G>A")),
(("Patient-16", "A>G"), ("Patient-16", "G>A")),
(("Patient-17", "A>G"), ("Patient-17", "G>A")),
(("Patient-20", "A>G"), ("Patient-20", "G>A")),
(("RNA\nControl", "A>G"), ("RNA\nControl", "U>C")),
(("p3 Cell Culture\nControl", "A>G"), ("p3 Cell Culture\nControl",
"U>C")),
(("Patient-1", "A>G"), ("Patient-1", "U>C")),
(("Patient-4", "A>G"), ("Patient-4", "U>C")),
(("Patient-5", "A>G"), ("Patient-5", "U>C")),
(("Patient-9", "A>G"), ("Patient-9", "U>C")),
(("Patient-16", "A>G"), ("Patient-16", "U>C")),
(("Patient-17", "A>G"), ("Patient-17", "U>C")),
(("Patient-20", "A>G"), ("Patient-20", "U>C")),
(("RNA\nControl", "A>G"), ("RNA\nControl", "C>U")),
(("p3 Cell Culture\nControl", "A>G"), ("p3 Cell Culture\nControl",
"C>U")),
(("Patient-1", "A>G"), ("Patient-1", "C>U")),
(("Patient-4", "A>G"), ("Patient-4", "C>U")),
(("Patient-5", "A>G"), ("Patient-5", "C>U")),
(("Patient-9", "A>G"), ("Patient-9", "C>U")),
(("Patient-16", "A>G"), ("Patient-16", "C>U")),
(("Patient-17", "A>G"), ("Patient-17", "C>U")),
(("Patient-20", "A>G"), ("Patient-20", "C>U"))]
# g1 = sns.catplot(x="label", y="frac_and_weight", data=data_filter, hue="Mutation", order=label_order, palette="tab20",
# kind="point", dodge=True, hue_order=mutation_order, join=False, estimator=weighted_varaint,
# orient="v")
# g1.set_axis_labels("", "Variant Frequency {} CI=95%".format(plus_minus))
# g1.set_xticklabels(fontsize=9, rotation=90)
# g1.set(yscale='log')
# # g1.set(ylim=(10**-7, 10**-3))
#
# # plt.show()
# g1.savefig(output_dir + "/All_Mutations_point_plot", dpi=300)
# plt.close()
g2 = sns.catplot(x="label",
y="frac_and_weight",
data=data_filter,
hue="Mutation",
order=label_order,
palette=mutation_palette(4),
kind="point",
dodge=0.5,
hue_order=transition_order,
join=False,
estimator=weighted_varaint,
orient="v",
legend=True)
g2.set_axis_labels("", "Variant Frequency {} CI=95%".format(plus_minus))
g2.set(yscale='log')
g2.set(ylim=(10**-5, 10**-3))
# g2.set_yticklabels(fontsize=12)
g2.set_xticklabels(fontsize=10, rotation=90)
# plt.show()
# g2.savefig("/Users/odedkushnir/Google Drive/Studies/PhD/MyPosters/20190924 GGE/plots/Transition_Mutations_point_plot_RV", dpi=300)
g2.savefig(output_dir + "/Transition_Mutations_point_plot", dpi=300)
# g2.savefig("/Users/odedkushnir/Google Drive/Studies/PhD/Prgress reports/20200913 Final report/plots" +
# "/Fig9a_Transition_Mutations_point_plot_Patients", dpi=300)
plt.close()
data_filter["label"] = data_filter["label"].astype(str)
data_filter["Frequency"] = data_filter["Frequency"].astype(float)
passage_g = sns.boxplot(x="label",
y="Frequency",
data=data_filter,
hue="Mutation",
order=label_order,
palette=mutation_palette(4),
dodge=True,
hue_order=transition_order)
passage_g.set_yscale('log')
passage_g.set_ylim(10**-6, 10**-1)
passage_g.set(xlabel="", ylabel="Variant Frequency")
passage_g.set_xticklabels(labels=label_order, fontsize=10, rotation=90)
annot = Annotator(passage_g,
pairs,
x="label",
y="Frequency",
hue="Mutation",
data=data_filter,
order=label_order,
hue_order=transition_order)
annot.configure(test='t-test_welch',
text_format='star',
loc='outside',
verbose=2,
comparisons_correction="Bonferroni")
annot.apply_test()
file_path = output_dir + "/sts.csv"
with open(file_path, "w") as o:
with contextlib.redirect_stdout(o):
passage_g, test_results = annot.annotate()
plt.legend(bbox_to_anchor=(1.05, 0.5), loc=2, borderaxespad=0.)
plt.tight_layout()
plt.savefig(output_dir + "/Transition_Mutations_box_stat_plot_patients",
dpi=300)
plt.close()
# g_rna = sns.catplot(x="RNA", y="frac_and_weight", data=data_filter, hue="Mutation", order=rna_order,
# palette="tab20", kind="point", dodge=True, hue_order=transition_order, join=False, estimator=weighted_varaint,
# orient="v", legend=True)
# g_rna.set_axis_labels("", "Variant Frequency")
# g_rna.set(yscale='log')
# g_rna.set(ylim=(10 ** -6, 10 ** -2))
# # g2.set_yticklabels(fontsize=12)
# g_rna.set_xticklabels(fontsize=10, rotation=45)
# plt.show()
# g2.savefig("/Users/odedkushnir/Google Drive/Studies/PhD/MyPosters/20190924 GGE/plots/Transition_Mutations_point_plot_RV", dpi=300)
# g_rna.savefig(output_dir + "/Transition_Mutations_point_RNA_plot", dpi=300)
# plt.close()
# A>G Prev Context
flatui = ["#3498db", "#9b59b6"]
g5 = sns.catplot("label",
"frac_and_weight",
data=data_filter_ag,
hue="ADAR_like",
order=label_order,
palette=mutation_palette(2),
kind="point",
dodge=True,
hue_order=[True, False],
estimator=weighted_varaint,
orient="v",
col="Type",
join=False,
col_order=type_order2)
g5.set_axis_labels("", "Variant Frequency {} CI=95%".format(plus_minus))
g5.set(yscale='log')
g5.set(ylim=(7 * 10**-7, 4 * 10**-3))
g5.set_xticklabels(rotation=90)
# plt.show()
g5.savefig(output_dir + "/Context_point_plot", dpi=300)
# g5.savefig("/Users/odedkushnir/Google Drive/Studies/PhD/Prgress reports/20200913 Final report/plots" +
# "/Fig9b_Context_point_plot_Patients", dpi=300)
plt.close()
mutation_ag = sns.catplot("label",
"frac_and_weight",
data=data_filter_ag,
hue="5`_ADAR_Preference",
palette=mutation_palette(3, adar=True, ag=True),
kind="point",
dodge=True,
estimator=weighted_varaint,
order=label_order,
orient="v",
col="Type",
join=False,
col_order=type_order_ag,
hue_order=adar_preference)
mutation_ag.set(yscale="log")
mutation_ag.set(ylim=(1 * 10**-5, 1 * 10**-2))
mutation_ag.set_xticklabels(rotation=90)
mutation_ag.fig.suptitle("A>G ADAR_like Mutation in RV patients", y=0.99)
plt.subplots_adjust(top=0.85)
mutation_ag.set_axis_labels(
"", "Variant Frequency {} CI=95%".format(plus_minus))
mutation_ag.savefig(output_dir + "/ag_ADAR_like_Mutation_col_patients.png",
dpi=300)
plt.close()
g6 = sns.catplot("label",
"frac_and_weight",
data=data_filter_ag,
hue="ADAR_like",
order=label_order,
palette=mutation_palette(2),
kind="point",
dodge=True,
hue_order=[True, False],
estimator=weighted_varaint,
orient="v",
join=False)
g6.set_axis_labels("", "Variant Frequency {} CI=95%".format(plus_minus))
g6.set(yscale='log')
g6.set(ylim=(7 * 10**-7, 4 * 10**-3))
g6.set_xticklabels(rotation=90)
# plt.show()
g6.savefig(output_dir + "/Context_point_all_mutations_type_plot", dpi=300)
plt.close()
g9 = sns.catplot("label",
"frac_and_weight",
data=data_filter_uc,
hue="Next",
order=label_order,
palette="tab20",
hue_order=context_order_uc,
estimator=weighted_varaint,
orient="v",
dodge=True,
kind="point",
col="Type",
join=False,
col_order=type_order2)
g9.set_axis_labels("", "Variant Frequency {} CI=95%".format(plus_minus))
g9.set(yscale='log')
g9.set(ylim=(10**-5, 10**-2))
g9.set_xticklabels(rotation=90)
# plt.show()
g9.savefig(output_dir + "/UC_Context_point_plot", dpi=300)
plt.close()
data_filter_ag_grouped = data_filter_ag.groupby(
["ADAR_like", "label",
"Type"])["frac_and_weight"].agg(lambda x: weighted_varaint(x))
data_filter_ag_grouped = data_filter_ag_grouped.reset_index()
data_filter_ag_grouped = data_filter_ag_grouped.rename(
columns={"frac_and_weight": "Frequency"})
data_filter_ag_grouped["Frequency"] = data_filter_ag_grouped[
"Frequency"].astype(float)
print(data_filter_ag_grouped.to_string())
data_filter_ag_grouped_silent = data_filter_ag_grouped[
data_filter_ag_grouped["Type"] == "Synonymous"]
data_filter_ag_grouped_silent = data_filter_ag_grouped_silent[
data_filter_ag_grouped_silent["label"] == "Cell Cultureֿ\nControl"]
def test_unmatched_hue_in_hue_order(self):
with self.assertRaisesRegex(ValueError, "(specified in `hue_order`)"):
self.annot = Annotator(self.ax, [(("a", "blue"), ("b", "blue"))],
data=self.df, x="x", y="y",
order=["a", "b"], hue='color',
hue_order=['red', 'yellow'])
def test_not_implemented_plot(self):
with self.assertRaises(NotImplementedError):
Annotator(self.ax, [(0, 1)], data=self.data, plot="thatplot")
def test_init_df_inverted(self):
box_pairs = self.pairs_for_df[::-1]
self.ax = sns.boxplot(**self.params_df)
self.annot = Annotator(self.ax, pairs=box_pairs, **self.params_df)
def test_valid_parameters_df_data_only(self):
self.ax = sns.boxplot(ax=self.ax, data=self.data2)
annot = Annotator(self.ax, pairs=[("X", "Y")],
data=self.data2)
annot.configure(test="Mann-Whitney").apply_and_annotate()
def context_boxplot(context_loadings,
metadict,
included_factors=None,
group_order=None,
statistical_test='Mann-Whitney',
pval_correction='benjamini-hochberg',
text_format='star',
nrows=1,
figsize=(12, 6),
cmap='tab10',
title_size=14,
axis_label_size=12,
group_label_rotation=45,
ylabel='Context Loadings',
dot_color='lightsalmon',
dot_edge_color='brown',
filename=None,
verbose=False):
'''
Plots a boxplot to compare the loadings of context groups in each
of the factors resulting from a tensor decomposition.
Parameters
----------
context_loadings : pandas.DataFrame
Dataframe containing the loadings of each of the contexts
from a tensor decomposition. Rows are contexts and columns
are the factors obtained.
metadict : dict
A dictionary containing the groups where each of the contexts
belong to. Keys corresponds to the indexes in `context_loadings`
and values are the respective groups. For example:
metadict={'Context 1' : 'Group 1', 'Context 2' : 'Group 1',
'Context 3' : 'Group 2', 'Context 4' : 'Group 2'}
included_factors : list, default=None
Factors to be included. Factor names must be the same as column elements
in the context_loadings.
group_order : list, default=None
Order of the groups to plot the boxplots. Considering the
example of the metadict, it could be:
group_order=['Group 1', 'Group 2'] or
group_order=['Group 2', 'Group 1']
If None, the order that groups are found in `metadict`
will be considered.
statistical_test : str, default='Mann-Whitney'
The statistical test to compare context groups within each factor.
Options include:
't-test_ind', 't-test_welch', 't-test_paired', 'Mann-Whitney',
'Mann-Whitney-gt', 'Mann-Whitney-ls', 'Levene', 'Wilcoxon', 'Kruskal'.
pval_correction : str, default='benjamini-hochberg'
Multiple test correction method to reduce false positives.
Options include:
'bonferroni', 'bonf', 'Bonferroni', 'holm-bonferroni', 'HB',
'Holm-Bonferroni', 'holm', 'benjamini-hochberg', 'BH', 'fdr_bh',
'Benjamini-Hochberg', 'fdr_by', 'Benjamini-Yekutieli', 'BY', None
text_format : str, default='star'
Format to display the results of the statistical test.
Options are:
- 'star', to display P- values < 1e-4 as "****"; < 1e-3 as "***";
< 1e-2 as "**"; < 0.05 as "*", and < 1 as "ns".
- 'simple', to display P-values < 1e-5 as "1e-5"; < 1e-4 as "1e-4";
< 1e-3 as "0.001"; < 1e-2 as "0.01"; and < 5e-2 as "0.05".
nrows : int, default=1
Number of rows to generate the subplots.
figsize : tuple, default=(12, 6)
Size of the figure (width*height), each in inches.
cmap : str, default='tab10'
Name of the color palette for coloring the major groups of contexts.
title_size : int, default=14
Font size of the title in each of the factor boxplots.
axis_label_size : int, default=12
Font size of the labels for X and Y axes.
group_label_rotation : int, default=45
Angle of rotation for the tick labels in the X axis.
ylabel : str, default='Context Loadings'
Label for the Y axis.
dot_color : str, default='lightsalmon'
A matplotlib color for the dots representing individual contexts
in the boxplot. For more info see:
https://matplotlib.org/stable/gallery/color/named_colors.html
dot_edge_color : str, default='brown'
A matplotlib color for the edge of the dots in the boxplot.
For more info see:
https://matplotlib.org/stable/gallery/color/named_colors.html
filename : str, default=None
Path to save the figure of the elbow analysis. If None, the figure is not
saved.
verbose : boolean, default=None
Whether printing out the result of the pairwise statistical tests
in each of the factors
Returns
-------
fig : matplotlib.figure.Figure
A matplotlib figure.
axes : matplotlib.axes.Axes or array of Axes
Matplotlib axes representing the subplots containing the boxplots.
'''
if group_order is not None:
assert len(set(group_order) & set(metadict.values())) == len(
set(metadict.values())
), "All groups in `metadict` must be contained in `group_order`"
else:
group_order = list(set(metadict.values()))
df = context_loadings.copy()
if included_factors is None:
factor_labels = list(df.columns)
else:
factor_labels = included_factors
rank = len(factor_labels)
df['Group'] = [metadict[idx] for idx in df.index]
nrows = min([rank, nrows])
ncols = int(np.ceil(rank / nrows))
fig, axes = plt.subplots(nrows=nrows,
ncols=ncols,
figsize=figsize,
sharey='none')
if rank == 1:
axs = np.array([axes])
else:
axs = axes.flatten()
for i, factor in enumerate(factor_labels):
ax = axs[i]
x, y = 'Group', factor
order = group_order
# Plot the boxes
ax = sns.boxplot(x=x,
y=y,
data=df,
order=order,
whis=[0, 100],
width=.6,
palette=cmap,
boxprops=dict(alpha=.5),
ax=ax)
# Plot the dots
sns.stripplot(x=x,
y=y,
data=df,
size=6,
order=order,
color=dot_color,
edgecolor=dot_edge_color,
linewidth=0.6,
jitter=False,
ax=ax)
if statistical_test is not None:
# Add annotations about statistical test
from itertools import combinations
pairs = list(combinations(order, 2))
annotator = Annotator(ax=ax,
pairs=pairs,
data=df,
x=x,
y=y,
order=order)
annotator.configure(test=statistical_test,
text_format=text_format,
loc='inside',
comparisons_correction=pval_correction,
verbose=verbose)
annotator.apply_and_annotate()
ax.set_title(factor, fontsize=title_size)
ax.set_xlabel('', fontsize=axis_label_size)
if (i == 0) | (((i) % ncols) == 0):
ax.set_ylabel(ylabel, fontsize=axis_label_size)
else:
ax.set_ylabel(' ', fontsize=axis_label_size)
ax.set_xticklabels(ax.get_xticklabels(),
rotation=group_label_rotation,
rotation_mode='anchor',
va='bottom',
ha='right')
# Remove extra subplots
for j in range(i + 1, axs.shape[0]):
ax = axs[j]
ax.axis(False)
if axes.shape[0] > 1:
axes = axes.reshape(axes.shape[0], -1)
fig.align_ylabels(axes[:, 0])
plt.tight_layout(rect=[0, 0.03, 1, 0.99])
if filename is not None:
plt.savefig(filename, dpi=300, bbox_inches='tight')
return fig, axes
def main():
# input_dir = "/Volumes/STERNADILABHOME$/volume3/okushnir/AccuNGS/20201008RV-202329127/merged/passages/"
"""Local"""
input_dir = "/Users/odedkushnir/PhD_Projects/After_review/AccuNGS/RV/passages/"
prefix = "inosine_predict_context"
date = datetime.today().strftime("%Y%m%d")
output_dir = input_dir + "{0}_{1}".format(date, prefix)
try:
os.mkdir(output_dir)
except OSError:
print("Creation of the directory %s failed" % output_dir)
else:
print("Successfully created the directory %s " % output_dir)
data_filter = pd.read_pickle(input_dir + prefix + "/data_filter.pkl")
data_filter_ag = pd.read_pickle(input_dir + prefix + "/data_filter_ag.pkl")
data_filter_uc = pd.read_pickle(input_dir + prefix + "/data_filter_uc.pkl")
data_filter["passage"] = data_filter["passage"].astype(int)
data_filter["no_variants"] = np.where(data_filter["Prob"] < 0.95, 0,
data_filter["no_variants"])
data_filter["Read_count"] = data_filter[data_filter["Read_count"] > 10000]
#Plots
label_order = [
"RNA Control\nRND", "RNA Control\nPrimer ID", "p2-1", "p2-2", "p2-3",
"p5-1", "p5-2", "p5-3", "p8-1", "p8-2", "p8-3", "p10-2", "p10-3",
"p12-1", "p12-2", "p12-3"
]
mutation_order = [
"A>G", "U>C", "G>A", "C>U", "A>C", "U>G", "A>U", "U>A", "G>C", "C>G",
"C>A", "G>U"
]
transition_order = ["A>G", "U>C", "G>A", "C>U"]
type_order = ["Synonymous", "Non-Synonymous", "Premature Stop Codon"]
type_order_ag = ["Synonymous", "Non-Synonymous"]
context_order = ["UpA", "ApA", "CpA", "GpA"]
context_order_uc = ["UpU", "UpA", "UpC", "UpG"]
adar_preference = ["High", "Intermediate", "Low"]
plus_minus = u"\u00B1"
# g1 = sns.catplot(x="label", y="frac_and_weight", data=data_filter, hue="Mutation", order=label_order,
# palette="Set2",
# kind="point", dodge=False, hue_order=mutation_order, join=True, estimator=weighted_varaint,
# orient="v")
# g1.set_axis_labels("", "Variant Frequency")
# g1.set_xticklabels(fontsize=9, rotation=45)
# g1.set(yscale='log')
# g1.set(ylim=(10 ** -7, 10 ** -3))
#
# # plt.show()
# g1.savefig(output_dir + "/All_Mutations_point_plot", dpi=300)
# plt.close()
#
# g2 = sns.catplot(x="label", y="frac_and_weight", data=data_filter, hue="Mutation", order=label_order,
# palette=mutation_palette(4), kind="point", dodge=True, hue_order=transition_order, join=False,
# estimator=weighted_varaint,
# orient="v", legend=True)
# g2.set_axis_labels("", "Variant Frequency")
# g2.set(yscale='log', ylim=(10 ** -6, 10 ** -2), xlim=(0, 12, 2))
# # g2.set_yticklabels(fontsize=12)
# g2.set_xticklabels(fontsize=9, rotation=90)
# plt.show()
# g2.savefig("/Users/odedkushnir/Google Drive/Studies/PhD/MyPosters/20190924 GGE/plots/Transition_Mutations_point_plot_RV", dpi=300)
# g2.savefig(output_dir + "/Transition_Mutations_point_plot", dpi=300)
# plt.close()
replica_lst = [1, 2, 3]
for replica in replica_lst:
data_filter_replica = data_filter[data_filter["replica"] == replica]
data_filter_replica["passage"] = data_filter_replica["passage"].astype(
str)
data_filter_replica["passage"] = "p" + data_filter_replica["passage"]
if replica == 2:
data_filter_replica = pd.read_pickle(input_dir + prefix +
"/data_filter.pkl")
data_filter_replica["passage"] = data_filter_replica[
"passage"].astype(int)
data_filter_replica["no_variants"] = np.where(
data_filter_replica["Prob"] < 0.95, 0,
data_filter_replica["no_variants"])
data_filter_replica["Read_count"] = data_filter_replica[
data_filter_replica["Read_count"] > 10000]
data_filter_replica["passage"] = data_filter_replica[
"passage"].astype(str)
data_filter_replica[
"passage"] = "p" + data_filter_replica["passage"]
data_filter_replica["replica"] = np.where(
data_filter_replica["passage"] == "p0", 2,
data_filter_replica["replica"])
data_filter_replica = data_filter_replica[
data_filter_replica["replica"] == replica]
data_filter_replica["passage"] = np.where(
data_filter_replica["passage"] == "p0", "RNA\nControl",
data_filter_replica["passage"])
if replica == 1:
passage_order = ["RNA\nControl", "p2", "p5", "p8", "p12"]
pairs = [(("RNA\nControl", "A>G"), ("RNA\nControl", "G>A")),
(("p2", "A>G"), ("p2", "G>A")),
(("p5", "A>G"), ("p5", "G>A")),
(("p8", "A>G"), ("p8", "G>A")),
(("p12", "A>G"), ("p12", "G>A")),
(("RNA\nControl", "A>G"), ("RNA\nControl", "U>C")),
(("p2", "A>G"), ("p2", "U>C")),
(("p5", "A>G"), ("p5", "U>C")),
(("p8", "A>G"), ("p8", "U>C")),
(("p12", "A>G"), ("p12", "U>C")),
(("RNA\nControl", "A>G"), ("RNA\nControl", "C>U")),
(("p2", "A>G"), ("p2", "C>U")),
(("p5", "A>G"), ("p5", "C>U")),
(("p8", "A>G"), ("p8", "C>U")),
(("p12", "A>G"), ("p12", "C>U"))]
pairs_adar = [(("RNA\nControl", "High\nADAR-like\nA>G"),
("RNA\nControl", "Low\nADAR-like\nA>G")),
(("p2", "High\nADAR-like\nA>G"),
("p2", "Low\nADAR-like\nA>G")),
(("p5", "High\nADAR-like\nA>G"),
("p5", "Low\nADAR-like\nA>G")),
(("p8", "High\nADAR-like\nA>G"),
("p8", "Low\nADAR-like\nA>G")),
(("p12", "High\nADAR-like\nA>G"),
("p12", "Low\nADAR-like\nA>G")),
(("p2", "High\nADAR-like\nU>C"),
("p2", "Low\nADAR-like\nU>C")),
(("p5", "High\nADAR-like\nU>C"),
("p5", "Low\nADAR-like\nU>C")),
(("p8", "High\nADAR-like\nU>C"),
("p8", "Low\nADAR-like\nU>C")),
(("p12", "High\nADAR-like\nU>C"),
("p12", "Low\nADAR-like\nU>C"))]
else:
passage_order = ["RNA\nControl", "p2", "p5", "p8", "p10", "p12"]
pairs = [(("RNA\nControl", "A>G"), ("RNA\nControl", "G>A")),
(("p2", "A>G"), ("p2", "G>A")),
(("p5", "A>G"), ("p5", "G>A")),
(("p8", "A>G"), ("p8", "G>A")),
(("p10", "A>G"), ("p10", "G>A")),
(("p12", "A>G"), ("p12", "G>A")),
(("RNA\nControl", "A>G"), ("RNA\nControl", "U>C")),
(("p2", "A>G"), ("p2", "U>C")),
(("p5", "A>G"), ("p5", "U>C")),
(("p8", "A>G"), ("p8", "U>C")),
(("p10", "A>G"), ("p10", "U>C")),
(("p12", "A>G"), ("p12", "U>C")),
(("RNA\nControl", "A>G"), ("RNA\nControl", "C>U")),
(("p2", "A>G"), ("p2", "C>U")),
(("p5", "A>G"), ("p5", "C>U")),
(("p8", "A>G"), ("p8", "C>U")),
(("p10", "A>G"), ("p10", "C>U")),
(("p12", "A>G"), ("p12", "C>U"))]
pairs_adar = [(("RNA\nControl", "High\nADAR-like\nA>G"),
("RNA\nControl", "Low\nADAR-like\nA>G")),
(("p2", "High\nADAR-like\nA>G"),
("p2", "Low\nADAR-like\nA>G")),
(("p5", "High\nADAR-like\nA>G"),
("p5", "Low\nADAR-like\nA>G")),
(("p8", "High\nADAR-like\nA>G"),
("p8", "Low\nADAR-like\nA>G")),
(("p10", "High\nADAR-like\nA>G"),
("p10", "Low\nADAR-like\nA>G")),
(("p12", "High\nADAR-like\nA>G"),
("p12", "Low\nADAR-like\nA>G")),
(("RNA\nControl", "High\nADAR-like\nU>C"),
("RNA\nControl", "Low\nADAR-like\nU>C")),
(("p2", "High\nADAR-like\nU>C"),
("p2", "Low\nADAR-like\nU>C")),
(("p5", "High\nADAR-like\nU>C"),
("p5", "Low\nADAR-like\nU>C")),
(("p8", "High\nADAR-like\nU>C"),
("p8", "Low\nADAR-like\nU>C")),
(("p10", "High\nADAR-like\nU>C"),
("p10", "Low\nADAR-like\nU>C")),
(("p12", "High\nADAR-like\nU>C"),
("p12", "Low\nADAR-like\nU>C"))]
passage_g = sns.catplot(x="passage",
y="frac_and_weight",
data=data_filter_replica,
hue="Mutation",
order=passage_order,
palette=mutation_palette(4),
kind="point",
dodge=0.5,
hue_order=transition_order,
join=False,
estimator=weighted_varaint,
orient="v",
legend=True)
passage_g.set_axis_labels(
"Passage", "Variant Frequency {} CI=95%".format(plus_minus))
passage_g.set(yscale='log', ylim=(10**-6, 10**-2))
plt.savefig(
output_dir +
"/Transition_Mutations_point_plot_RVB14_replica%s" % str(replica),
dpi=300)
plt.close()
passage_g1 = sns.boxplot(x="passage",
y="Frequency",
data=data_filter_replica,
hue="Mutation",
order=passage_order,
palette=mutation_palette(4),
dodge=True,
hue_order=transition_order)
passage_g1.set_yscale('log')
passage_g1.set_ylim(10**-6, 10**-2)
passage_g1.set(xlabel="Passage", ylabel="Variant Frequency")
annot = Annotator(passage_g1,
pairs,
x="passage",
y="Frequency",
hue="Mutation",
data=data_filter_replica,
order=passage_order,
hue_order=transition_order)
annot.configure(test='t-test_welch',
text_format='star',
loc='outside',
verbose=2,
comparisons_correction="Bonferroni")
annot.apply_test()
file_path = output_dir + "/sts{0}.csv".format(replica)
with open(file_path, "w") as o:
with contextlib.redirect_stdout(o):
passage_g1, test_results = annot.annotate()
plt.legend(bbox_to_anchor=(1.05, 0.5), loc=2, borderaxespad=0.)
plt.tight_layout()
plt.savefig(
output_dir +
"/Transition_Mutations_box_stat_plot_RVB14_replica{0}".format(
replica),
dpi=300)
plt.close()
# data_filter["passage"] = data_filter["passage"].astype(int)
#
#
# g4 = sns.relplot("passage", "frac_and_weight", data=data_filter, hue="Mutation", palette=mutation_palette(4),
# hue_order=transition_order, estimator=weighted_varaint, col="Type", kind="line",
# col_order=type_order)
#
# g4.axes.flat[0].set_yscale('symlog', linthreshy=10 ** -5)
# g4.set_axis_labels("Passage", "Variant Frequency")
# # plt.show()
# g4.savefig(output_dir + "/Time_Transition_Mutations_line_plot", dpi=300)
# plt.close()
"""ADAR preferences"""
data_filter_replica_synonymous = data_filter_replica.loc[
data_filter_replica.Type == "Synonymous"]
# data_filter_synonymous["ADAR_like"] = (data_filter_synonymous.Prev.str.contains('UpA') | data_filter_synonymous.Prev.str.contains('ApA'))
data_filter_replica_synonymous["Mutation"] = np.where(
((data_filter_replica_synonymous["Mutation"] == "A>G") &
(data_filter_replica_synonymous["5`_ADAR_Preference"] == "High")),
"High\nADAR-like\nA>G",
np.where(
((data_filter_replica_synonymous["Mutation"] == "A>G")
& (data_filter_replica_synonymous["5`_ADAR_Preference"]
== "Intermediate")), "Intermediate\nADAR-like\nA>G",
np.where(
((data_filter_replica_synonymous["Mutation"] == "A>G") &
(data_filter_replica_synonymous["5`_ADAR_Preference"]
== "Low")), "Low\nADAR-like\nA>G",
data_filter_replica_synonymous["Mutation"])))
data_filter_replica_synonymous["Mutation_adar"] = np.where(
((data_filter_replica_synonymous["Mutation"] == "U>C") &
(data_filter_replica_synonymous["3`_ADAR_Preference"] == "High")),
"High\nADAR-like\nU>C",
np.where(
((data_filter_replica_synonymous["Mutation"] == "U>C")
& (data_filter_replica_synonymous["3`_ADAR_Preference"]
== "Intermediate")), "Intermediate\nADAR-like\nU>C",
np.where(
((data_filter_replica_synonymous["Mutation"] == "U>C") &
(data_filter_replica_synonymous["3`_ADAR_Preference"]
== "Low")), "Low\nADAR-like\nU>C",
data_filter_replica_synonymous["Mutation"])))
mutation_adar_order = [
"High\nADAR-like\nA>G", "Low\nADAR-like\nA>G",
"High\nADAR-like\nU>C", "Low\nADAR-like\nU>C"
]
# data_filter_replica_synonymous["passage"] = data_filter_replica_synonymous["passage"].astype(str)
# data_filter_replica_synonymous["passage"] = "p" + data_filter_replica_synonymous["passage"]
catplot_adar = sns.catplot(x="passage",
y="frac_and_weight",
data=data_filter_replica_synonymous,
hue="Mutation_adar",
order=passage_order,
palette=mutation_palette(4, adar=True),
kind="point",
dodge=0.5,
hue_order=mutation_adar_order,
join=False,
estimator=weighted_varaint,
orient="v",
legend=True)
catplot_adar.set_axis_labels(
"Passage", "Variant Frequency {} CI=95%".format(plus_minus))
catplot_adar.set(yscale='log')
catplot_adar.set(ylim=(10**-6, 10**-2))
# catplot_adar.set_xticklabels(fontsize=8)
# plt.tight_layout()
plt.savefig(
output_dir +
"/adar_pref_mutation_point_plot_RVB14_replica{0}.png".format(
replica),
dpi=300)
plt.close()
adar_g = sns.boxplot(x="passage",
y="Frequency",
data=data_filter_replica_synonymous,
hue="Mutation_adar",
order=passage_order,
palette=mutation_palette(4, adar=True),
dodge=True,
hue_order=mutation_adar_order)
adar_g.set_yscale('log')
adar_g.set_ylim(10**-6, 10**-1)
adar_g.set(xlabel="Passage", ylabel="Variant Frequency")
annot = Annotator(adar_g,
pairs_adar,
x="passage",
y="Frequency",
hue="Mutation_adar",
data=data_filter_replica_synonymous,
hue_order=mutation_adar_order)
annot.configure(test='t-test_welch',
text_format='star',
loc='outside',
verbose=2,
comparisons_correction="Bonferroni")
annot.apply_test()
file_path = output_dir + "/sts_adar_{0}.csv".format(replica)
with open(file_path, "w") as o:
with contextlib.redirect_stdout(o):
adar_g, test_results = annot.annotate()
plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
plt.tight_layout()
plt.savefig(
output_dir +
"/adar_pref_mutation_box_stat_plot_RVB14_replica{0}".format(
replica),
dpi=300)
plt.close()