def composite_correlation(df, size=(12, 8)):
""" Plot composite correlation figure
"""
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 2), (0, 0))
ax2 = plt.subplot2grid((2, 2), (0, 1))
ax3 = plt.subplot2grid((2, 2), (1, 0))
ax4 = plt.subplot2grid((2, 2), (1, 1))
chemistry = ["V1", "V2", "V2.5", float("nan")]
colors = sns.color_palette("Set2", 8)
color_map = dict(zip(chemistry, colors))
age_label = "Chronological age (yr)"
ax1.scatter(df["hli_calc_age_sample_taken"],
df["teloLength"],
s=10,
marker='.',
color=df["Chemistry"].map(color_map))
ax1.set_ylim(0, 15)
ax1.set_ylabel("Telomere length (Kb)")
ax2.scatter(df["hli_calc_age_sample_taken"],
df["ccn.chrX"],
s=10,
marker='.',
color=df["Chemistry"].map(color_map))
ax2.set_ylim(1.8, 2.1)
ax2.set_ylabel("ChrX copy number")
ax4.scatter(df["hli_calc_age_sample_taken"],
df["ccn.chrY"],
s=10,
marker='.',
color=df["Chemistry"].map(color_map))
ax4.set_ylim(0.8, 1.1)
ax4.set_ylabel("ChrY copy number")
ax3.scatter(df["hli_calc_age_sample_taken"],
df["TRA.PPM"],
s=10,
marker='.',
color=df["Chemistry"].map(color_map))
ax3.set_ylim(0, 250)
ax3.set_ylabel("$TCR-\\alpha$ deletions (count per million reads)")
from matplotlib.lines import Line2D
legend_elements = [Line2D([0], [0], marker='.', color='w', label=chem,
markerfacecolor=color, markersize=16) \
for (chem, color) in zip(chemistry, colors)[:3]]
for ax in (ax1, ax2, ax3, ax4):
ax.set_xlabel(age_label)
ax.legend(handles=legend_elements, loc="upper right")
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = ((.02, .98, "A"), (.52, .98, "B"), (.02, .5, "C"), (.52, .5, "D"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite_correlation(df, size=(12, 8)):
""" Plot composite correlation figure
"""
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 2), (0, 0))
ax2 = plt.subplot2grid((2, 2), (0, 1))
ax3 = plt.subplot2grid((2, 2), (1, 0))
ax4 = plt.subplot2grid((2, 2), (1, 1))
chemistry = ["V1", "V2", "V2.5", float("nan")]
colors = sns.color_palette("Set2", 8)
color_map = dict(zip(chemistry, colors))
age_label = "Chronological age (yr)"
ax1.scatter(df["hli_calc_age_sample_taken"], df["teloLength"],
s=10, marker='.',
color=df["Chemistry"].map(color_map))
ax1.set_ylim(0, 15)
ax1.set_ylabel("Telomere length (Kb)")
ax2.scatter(df["hli_calc_age_sample_taken"], df["ccn.chrX"],
s=10, marker='.',
color=df["Chemistry"].map(color_map))
ax2.set_ylim(1.8, 2.1)
ax2.set_ylabel("ChrX copy number")
ax4.scatter(df["hli_calc_age_sample_taken"], df["ccn.chrY"],
s=10, marker='.',
color=df["Chemistry"].map(color_map))
ax4.set_ylim(0.8, 1.1)
ax4.set_ylabel("ChrY copy number")
ax3.scatter(df["hli_calc_age_sample_taken"], df["TRA.PPM"],
s=10, marker='.',
color=df["Chemistry"].map(color_map))
ax3.set_ylim(0, 250)
ax3.set_ylabel("$TCR-\\alpha$ deletions (count per million reads)")
from matplotlib.lines import Line2D
legend_elements = [Line2D([0], [0], marker='.', color='w', label=chem,
markerfacecolor=color, markersize=16) \
for (chem, color) in zip(chemistry, colors)[:3]]
for ax in (ax1, ax2, ax3, ax4):
ax.set_xlabel(age_label)
ax.legend(handles=legend_elements, loc="upper right")
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = ((.02, .98, "A"),
(.52, .98, "B"),
(.02, .5, "C"),
(.52, .5, "D"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite(df, sameGenderMZ, sameGenderDZ, size=(16, 24)):
"""Embed both absdiff figures and heritability figures.
"""
fig = plt.figure(1, size)
ax1a = plt.subplot2grid((6, 4), (0, 0), rowspan=2, colspan=1)
ax2a = plt.subplot2grid((6, 4), (0, 1), rowspan=2, colspan=1)
ax3a = plt.subplot2grid((6, 4), (0, 2), rowspan=2, colspan=1)
ax4a = plt.subplot2grid((6, 4), (0, 3), rowspan=2, colspan=1)
ax1b = plt.subplot2grid((6, 4), (2, 0), rowspan=2, colspan=2)
ax2b = plt.subplot2grid((6, 4), (2, 2), rowspan=2, colspan=2)
ax3b = plt.subplot2grid((6, 4), (4, 0), rowspan=2, colspan=2)
ax4b = plt.subplot2grid((6, 4), (4, 2), rowspan=2, colspan=2)
# Telomeres
telomeres = extract_trait(df, "Sample name", "telomeres.Length")
mzTelomeres = extract_twin_values(sameGenderMZ, telomeres)
dzTelomeres = extract_twin_values(sameGenderDZ, telomeres)
plot_paired_values(ax1b, mzTelomeres, dzTelomeres, label="Telomere length")
plot_abs_diff(ax1a, mzTelomeres, dzTelomeres, label="Telomere length")
# CCNX
CCNX = extract_trait(df, "Sample name", "ccn.chrX")
mzCCNX = extract_twin_values(sameGenderMZ, CCNX, gender="Female")
dzCCNX = extract_twin_values(sameGenderDZ, CCNX, gender="Female")
dzCCNX = filter_low_values(dzCCNX, 1.75)
plot_paired_values(ax2b, mzCCNX, dzCCNX, gender="Female only", label="ChrX copy number")
plot_abs_diff(ax2a, mzCCNX, dzCCNX, label="ChrX copy number")
# CCNY
CCNY = extract_trait(df, "Sample name", "ccn.chrY")
mzCCNY = extract_twin_values(sameGenderMZ, CCNY, gender="Male")
dzCCNY = extract_twin_values(sameGenderDZ, CCNY, gender="Male")
dzCCNY = filter_low_values(dzCCNY, .75)
plot_paired_values(ax3b, mzCCNY, dzCCNY, gender="Male only", label="ChrY copy number")
plot_abs_diff(ax3a, mzCCNY, dzCCNY, label="ChrY copy number")
# CCNY
TRA = extract_trait(df, "Sample name", "TRA.PPM")
mzTRA = extract_twin_values(sameGenderMZ, TRA)
dzTRA = extract_twin_values(sameGenderDZ, TRA)
plot_paired_values(ax4b, mzTRA, dzTRA, label="TCR-$\\alpha$ deletions")
plot_abs_diff(ax4a, mzTRA, dzTRA, label="TCR-$\\alpha$ deletions")
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
# ABCD absdiff, EFGH heritability
labels = ((.03, .99, 'A'), (.27, .99, 'B'), (.53, .99, 'C'), (.77, .99, 'D'),
(.03, .67, 'E'), (.53, .67, 'F'),
(.03, .34, 'G'), (.53, .34, 'H'))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite_qc(df_orig, size=(16, 12)):
""" Plot composite QC figures
"""
df = df_orig.rename(columns={"hli_calc_age_sample_taken": "Age",
"hli_calc_gender": "Gender",
"eth7_max": "Ethnicity",
"MeanCoverage": "Mean coverage",
"Chemistry": "Sequencing chemistry",
"Release Client": "Cohort",
})
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 7), (0, 0), rowspan=1, colspan=2)
ax2 = plt.subplot2grid((2, 7), (0, 2), rowspan=1, colspan=2)
ax3 = plt.subplot2grid((2, 7), (0, 4), rowspan=1, colspan=3)
ax4 = plt.subplot2grid((2, 7), (1, 0), rowspan=1, colspan=2)
ax5 = plt.subplot2grid((2, 7), (1, 2), rowspan=1, colspan=2)
ax6 = plt.subplot2grid((2, 7), (1, 4), rowspan=1, colspan=3)
sns.distplot(df["Age"].dropna(), kde=False, ax=ax1)
sns.countplot(x="Gender", data=df, ax=ax2)
sns.countplot(x="Ethnicity", data=df, ax=ax3,
order = df['Ethnicity'].value_counts().index)
sns.distplot(df["Mean coverage"].dropna(), kde=False, ax=ax4)
ax4.set_xlim(0, 100)
sns.countplot(x="Sequencing chemistry", data=df, ax=ax5)
sns.countplot(x="Cohort", data=df, ax=ax6,
order = df['Cohort'].value_counts().index)
# Anonymize the cohorts
cohorts = ax6.get_xticklabels()
newCohorts = []
for i, c in enumerate(cohorts):
if c.get_text() == "Spector":
c = "TwinsUK"
elif c.get_text() != "Health Nucleus":
c = "C{}".format(i + 1)
newCohorts.append(c)
ax6.set_xticklabels(newCohorts)
for ax in (ax6,):
ax.set_xticklabels(ax.get_xticklabels(), ha="right", rotation=30)
for ax in (ax1, ax2, ax3, ax4, ax5, ax6):
ax.set_title(ax.get_xlabel())
ax.set_xlabel("")
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = ((.02, .96, "A"),
(.3, .96, "B"),
(.6, .96, "C"),
(.02, .52, "D"),
(.3, .52, "E"),
(.6, .52, "F"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite(df, sameGenderMZ, sameGenderDZ, size=(16, 24)):
"""Embed both absdiff figures and heritability figures."""
fig = plt.figure(1, size)
ax1a = plt.subplot2grid((6, 4), (0, 0), rowspan=2, colspan=1)
ax2a = plt.subplot2grid((6, 4), (0, 1), rowspan=2, colspan=1)
ax3a = plt.subplot2grid((6, 4), (0, 2), rowspan=2, colspan=1)
ax4a = plt.subplot2grid((6, 4), (0, 3), rowspan=2, colspan=1)
ax1b = plt.subplot2grid((6, 4), (2, 0), rowspan=2, colspan=2)
ax2b = plt.subplot2grid((6, 4), (2, 2), rowspan=2, colspan=2)
ax3b = plt.subplot2grid((6, 4), (4, 0), rowspan=2, colspan=2)
ax4b = plt.subplot2grid((6, 4), (4, 2), rowspan=2, colspan=2)
# Telomeres
telomeres = extract_trait(df, "Sample name", "telomeres.Length")
mzTelomeres = extract_twin_values(sameGenderMZ, telomeres)
dzTelomeres = extract_twin_values(sameGenderDZ, telomeres)
plot_paired_values(ax1b, mzTelomeres, dzTelomeres, label="Telomere length")
plot_abs_diff(ax1a, mzTelomeres, dzTelomeres, label="Telomere length")
# CCNX
CCNX = extract_trait(df, "Sample name", "ccn.chrX")
mzCCNX = extract_twin_values(sameGenderMZ, CCNX, gender="Female")
dzCCNX = extract_twin_values(sameGenderDZ, CCNX, gender="Female")
dzCCNX = filter_low_values(dzCCNX, 1.75)
plot_paired_values(ax2b,
mzCCNX,
dzCCNX,
gender="Female only",
label="ChrX copy number")
plot_abs_diff(ax2a, mzCCNX, dzCCNX, label="ChrX copy number")
# CCNY
CCNY = extract_trait(df, "Sample name", "ccn.chrY")
mzCCNY = extract_twin_values(sameGenderMZ, CCNY, gender="Male")
dzCCNY = extract_twin_values(sameGenderDZ, CCNY, gender="Male")
dzCCNY = filter_low_values(dzCCNY, 0.75)
plot_paired_values(ax3b,
mzCCNY,
dzCCNY,
gender="Male only",
label="ChrY copy number")
plot_abs_diff(ax3a, mzCCNY, dzCCNY, label="ChrY copy number")
# CCNY
TRA = extract_trait(df, "Sample name", "TRA.PPM")
mzTRA = extract_twin_values(sameGenderMZ, TRA)
dzTRA = extract_twin_values(sameGenderDZ, TRA)
plot_paired_values(ax4b, mzTRA, dzTRA, label="TCR-$\\alpha$ deletions")
plot_abs_diff(ax4a, mzTRA, dzTRA, label="TCR-$\\alpha$ deletions")
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
# ABCD absdiff, EFGH heritability
labels = (
(0.03, 0.99, "A"),
(0.27, 0.99, "B"),
(0.53, 0.99, "C"),
(0.77, 0.99, "D"),
(0.03, 0.67, "E"),
(0.53, 0.67, "F"),
(0.03, 0.34, "G"),
(0.53, 0.34, "H"),
)
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite_qc(df_orig, size=(16, 12)):
"""Plot composite QC figures"""
df = df_orig.rename(
columns={
"hli_calc_age_sample_taken": "Age",
"hli_calc_gender": "Gender",
"eth7_max": "Ethnicity",
"MeanCoverage": "Mean coverage",
"Chemistry": "Sequencing chemistry",
"Release Client": "Cohort",
})
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 7), (0, 0), rowspan=1, colspan=2)
ax2 = plt.subplot2grid((2, 7), (0, 2), rowspan=1, colspan=2)
ax3 = plt.subplot2grid((2, 7), (0, 4), rowspan=1, colspan=3)
ax4 = plt.subplot2grid((2, 7), (1, 0), rowspan=1, colspan=2)
ax5 = plt.subplot2grid((2, 7), (1, 2), rowspan=1, colspan=2)
ax6 = plt.subplot2grid((2, 7), (1, 4), rowspan=1, colspan=3)
sns.distplot(df["Age"].dropna(), kde=False, ax=ax1)
sns.countplot(x="Gender", data=df, ax=ax2)
sns.countplot(x="Ethnicity",
data=df,
ax=ax3,
order=df["Ethnicity"].value_counts().index)
sns.distplot(df["Mean coverage"].dropna(), kde=False, ax=ax4)
ax4.set_xlim(0, 100)
sns.countplot(x="Sequencing chemistry", data=df, ax=ax5)
sns.countplot(x="Cohort",
data=df,
ax=ax6,
order=df["Cohort"].value_counts().index)
# Anonymize the cohorts
cohorts = ax6.get_xticklabels()
newCohorts = []
for i, c in enumerate(cohorts):
if c.get_text() == "Spector":
c = "TwinsUK"
elif c.get_text() != "Health Nucleus":
c = "C{}".format(i + 1)
newCohorts.append(c)
ax6.set_xticklabels(newCohorts)
for ax in (ax6, ):
ax.set_xticklabels(ax.get_xticklabels(), ha="right", rotation=30)
for ax in (ax1, ax2, ax3, ax4, ax5, ax6):
ax.set_title(ax.get_xlabel())
ax.set_xlabel("")
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = (
(0.02, 0.96, "A"),
(0.3, 0.96, "B"),
(0.6, 0.96, "C"),
(0.02, 0.52, "D"),
(0.3, 0.52, "E"),
(0.6, 0.52, "F"),
)
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite_ccn(df, size=(12, 8)):
"""Plot composite ccn figure"""
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 2), (0, 0))
ax2 = plt.subplot2grid((2, 2), (0, 1))
ax3 = plt.subplot2grid((2, 2), (1, 0))
ax4 = plt.subplot2grid((2, 2), (1, 1))
mf = df[df["hli_calc_gender"] == "Male"]
age_label = "Chronological age (yr)"
ax1.scatter(
mf["hli_calc_age_sample_taken"],
mf["ccn.chrX"],
s=10,
marker=".",
color="lightslategray",
)
ax1.set_ylim(0.8, 1.1)
plot_fit_line(ax1, mf["hli_calc_age_sample_taken"], mf["ccn.chrX"])
ax1.set_ylabel("ChrX copy number")
ax1.set_title("ChrX copy number in Male")
ax2.scatter(
mf["hli_calc_age_sample_taken"],
mf["ccn.chrY"],
s=10,
marker=".",
color="lightslategray",
)
plot_fit_line(ax2, mf["hli_calc_age_sample_taken"], mf["ccn.chrY"])
ax2.set_ylim(0.8, 1.1)
ax2.set_ylabel("ChrY copy number")
ax2.set_title("ChrY copy number in Male")
ax3.scatter(
df["hli_calc_age_sample_taken"],
df["ccn.chr1"],
s=10,
marker=".",
color="lightslategray",
)
plot_fit_line(ax3, df["hli_calc_age_sample_taken"], df["ccn.chr1"])
ax3.set_ylim(1.8, 2.1)
ax3.set_ylabel("Chr1 copy number")
ax3.set_title("Chr1 copy number")
ax4.scatter(
df["hli_calc_age_sample_taken"],
df["ccn.chrM"],
s=10,
marker=".",
color="lightslategray",
)
plot_fit_line(ax4, df["hli_calc_age_sample_taken"], df["ccn.chrM"])
ax4.set_ylim(0, 400)
ax4.set_ylabel("Mitochondria copy number")
ax4.set_title("Mitochondria copy number")
from matplotlib.lines import Line2D
for ax in (ax1, ax2, ax3, ax4):
ax.set_xlabel(age_label)
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = ((0.02, 0.98, "A"), (0.52, 0.98, "B"), (0.02, 0.5, "C"),
(0.52, 0.5, "D"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite_ccn(df, size=(12, 8)):
""" Plot composite ccn figure
"""
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 2), (0, 0))
ax2 = plt.subplot2grid((2, 2), (0, 1))
ax3 = plt.subplot2grid((2, 2), (1, 0))
ax4 = plt.subplot2grid((2, 2), (1, 1))
chemistry = ["V1", "V2", "V2.5", float("nan")]
colors = sns.color_palette("Set2", 8)
color_map = dict(zip(chemistry, colors))
mf = df[df["hli_calc_gender"] == "Male"]
age_label = "Chronological age (yr)"
ax1.scatter(mf["hli_calc_age_sample_taken"],
mf["ccn.chrX"],
s=10,
marker='.',
color='lightslategray')
ax1.set_ylim(0.8, 1.1)
plot_fit_line(ax1, mf["hli_calc_age_sample_taken"], mf["ccn.chrX"])
ax1.set_ylabel("ChrX copy number")
ax1.set_title("ChrX copy number in Male")
ax2.scatter(mf["hli_calc_age_sample_taken"],
mf["ccn.chrY"],
s=10,
marker='.',
color='lightslategray')
plot_fit_line(ax2, mf["hli_calc_age_sample_taken"], mf["ccn.chrY"])
ax2.set_ylim(0.8, 1.1)
ax2.set_ylabel("ChrY copy number")
ax2.set_title("ChrY copy number in Male")
ax3.scatter(df["hli_calc_age_sample_taken"],
df["ccn.chr1"],
s=10,
marker='.',
color='lightslategray')
plot_fit_line(ax3, df["hli_calc_age_sample_taken"], df["ccn.chr1"])
ax3.set_ylim(1.8, 2.1)
ax3.set_ylabel("Chr1 copy number")
ax3.set_title("Chr1 copy number")
ax4.scatter(df["hli_calc_age_sample_taken"],
df["ccn.chrM"],
s=10,
marker='.',
color='lightslategray')
plot_fit_line(ax4, df["hli_calc_age_sample_taken"], df["ccn.chrM"])
ax4.set_ylim(0, 400)
ax4.set_ylabel("Mitochondria copy number")
ax4.set_title("Mitochondria copy number")
from matplotlib.lines import Line2D
legend_elements = [Line2D([0], [0], marker='.', color='w', label=chem,
markerfacecolor=color) \
for (chem, color) in zip(chemistry, colors)[:3]]
for ax in (ax1, ax2, ax3, ax4):
ax.set_xlabel(age_label)
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = ((.02, .98, "A"), (.52, .98, "B"), (.02, .5, "C"), (.52, .5, "D"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()
def composite_ccn(df, size=(12, 8)):
""" Plot composite ccn figure
"""
fig = plt.figure(1, size)
ax1 = plt.subplot2grid((2, 2), (0, 0))
ax2 = plt.subplot2grid((2, 2), (0, 1))
ax3 = plt.subplot2grid((2, 2), (1, 0))
ax4 = plt.subplot2grid((2, 2), (1, 1))
chemistry = ["V1", "V2", "V2.5", float("nan")]
colors = sns.color_palette("Set2", 8)
color_map = dict(zip(chemistry, colors))
mf = df[df["hli_calc_gender"] == "Male"]
age_label = "Chronological age (yr)"
ax1.scatter(mf["hli_calc_age_sample_taken"], mf["ccn.chrX"],
s=10, marker='.',
color='lightslategray')
ax1.set_ylim(0.8, 1.1)
plot_fit_line(ax1, mf["hli_calc_age_sample_taken"], mf["ccn.chrX"])
ax1.set_ylabel("ChrX copy number")
ax1.set_title("ChrX copy number in Male")
ax2.scatter(mf["hli_calc_age_sample_taken"], mf["ccn.chrY"],
s=10, marker='.',
color='lightslategray')
plot_fit_line(ax2, mf["hli_calc_age_sample_taken"], mf["ccn.chrY"])
ax2.set_ylim(0.8, 1.1)
ax2.set_ylabel("ChrY copy number")
ax2.set_title("ChrY copy number in Male")
ax3.scatter(df["hli_calc_age_sample_taken"], df["ccn.chr1"],
s=10, marker='.',
color='lightslategray')
plot_fit_line(ax3, df["hli_calc_age_sample_taken"], df["ccn.chr1"])
ax3.set_ylim(1.8, 2.1)
ax3.set_ylabel("Chr1 copy number")
ax3.set_title("Chr1 copy number")
ax4.scatter(df["hli_calc_age_sample_taken"], df["ccn.chrM"],
s=10, marker='.',
color='lightslategray')
plot_fit_line(ax4, df["hli_calc_age_sample_taken"], df["ccn.chrM"])
ax4.set_ylim(0, 400)
ax4.set_ylabel("Mitochondria copy number")
ax4.set_title("Mitochondria copy number")
from matplotlib.lines import Line2D
legend_elements = [Line2D([0], [0], marker='.', color='w', label=chem,
markerfacecolor=color) \
for (chem, color) in zip(chemistry, colors)[:3]]
for ax in (ax1, ax2, ax3, ax4):
ax.set_xlabel(age_label)
plt.tight_layout()
root = fig.add_axes((0, 0, 1, 1))
labels = ((.02, .98, "A"),
(.52, .98, "B"),
(.02, .5, "C"),
(.52, .5, "D"))
panel_labels(root, labels)
root.set_xlim(0, 1)
root.set_ylim(0, 1)
root.set_axis_off()