Pymaceuticals Inc

---

Analysis

• Overall, it is clear that Capomulin outperforms all other treatment options in the screen.
• Capomulin was the only treatment to reduce tumor volume. It held to a 19% reduction in tumor volume over the course of trial, whereas all other drugs were correlated with an increase in tumor volume by roughly 40-50%.
• Capomulin greatly limited the spread of the tumor compared to other treatment options. By study end, the average mouse on Capomulin had only 1 new metastatic site, as opposed to the average 2-3 found in mice of other treatment options.
• Lastly, mice on the Capomulin treatment had the highest survival rate of any treatment in the screen. Over 90% of mice treated by Capomulin survived the full duration of the trial, compared to only 35-45% of mice on other treatment options.

# Dependencies and Setup
%matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

# Incorporate Seaborn if preferred
# import seaborn as sns

# File to Load (Remember to Change These)
mouse_drug_data_to_load = "raw_data/mouse_drug_data.csv"
clinical_trial_data_to_load = "raw_data/clinicaltrial_data.csv"

# Read the Mouse and Drug Data and the Clinical Trial Data
mouse_drug_data = pd.read_csv(mouse_drug_data_to_load)
clinical_data = pd.read_csv(clinical_trial_data_to_load)

# Combine the data into a single dataset
clinical_data_complete = pd.merge(clinical_data, mouse_drug_data, how="left", on=["Mouse ID", "Mouse ID"])

# Display the data table for preview
clinical_data_complete.head()

	Mouse ID	Timepoint	Tumor Volume (mm3)	Metastatic Sites	Drug
0	b128	0	45.0	0	Capomulin
1	f932	0	45.0	0	Ketapril
2	g107	0	45.0	0	Ketapril
3	a457	0	45.0	0	Ketapril
4	c819	0	45.0	0	Ketapril

Tumor Response to Treatment

# Store the Mean Tumor Volume Data Grouped by Drug and Timepoint
tumor_vols_mean = clinical_data_complete.groupby(["Drug", "Timepoint"]).mean()["Tumor Volume (mm3)"]

# Convert to DataFrame
tumor_vols_mean = pd.DataFrame(tumor_vols_mean)

# Preview DataFrame
tumor_vols_mean

		Tumor Volume (mm3)
Drug	Timepoint
Capomulin	0	45.000000
	5	44.266086
	10	43.084291
	15	42.064317
	20	40.716325
	25	39.939528
	30	38.769339
	35	37.816839
	40	36.958001
	45	36.236114
Ceftamin	0	45.000000
	5	46.503051
	10	48.285125
	15	50.094055
	20	52.157049
	25	54.287674
	30	56.769517
	35	58.827548
	40	61.467895
	45	64.132421
Infubinol	0	45.000000
	5	47.062001
	10	49.403909
	15	51.296397
	20	53.197691
	25	55.715252
	30	58.299397
	35	60.742461
	40	63.162824
	45	65.755562
...	...	...
Ramicane	0	45.000000
	5	43.944859
	10	42.531957
	15	41.495061
	20	40.238325
	25	38.974300
	30	38.703137
	35	37.451996
	40	36.574081
	45	34.955595
Stelasyn	0	45.000000
	5	47.527452
	10	49.463844
	15	51.529409
	20	54.067395
	25	56.166123
	30	59.826738
	35	62.440699
	40	65.356386
	45	68.438310
Zoniferol	0	45.000000
	5	46.851818
	10	48.689881
	15	50.779059
	20	53.170334
	25	55.432935
	30	57.713531
	35	60.089372
	40	62.916692
	45	65.960888

100 rows × 1 columns

# Store the Standard Error of Tumor Volumes Grouped by Drug and Timepoint
tumor_vols_sem = clinical_data_complete.groupby(["Drug", "Timepoint"]).sem()["Tumor Volume (mm3)"]

# Convert to DataFrame
tumor_vols_sem = pd.DataFrame(tumor_vols_sem)

# Preview DataFrame
tumor_vols_sem.head()

		Tumor Volume (mm3)
Drug	Timepoint
Capomulin	0	0.000000
	5	0.448593
	10	0.702684
	15	0.838617
	20	0.909731

# Minor Data Munging to Re-Format the Data Frames
tumor_vols_mean = tumor_vols_mean.reset_index()
tumor_vols_pivot_mean = tumor_vols_mean.pivot(index="Timepoint", columns="Drug")["Tumor Volume (mm3)"]

tumor_vols_sem = tumor_vols_sem.reset_index()
tumor_vols_pivot_sem = tumor_vols_sem.pivot(index="Timepoint", columns="Drug")["Tumor Volume (mm3)"]

# Preview that Reformatting worked
tumor_vols_pivot_mean.head()

Drug	Capomulin	Ceftamin	Infubinol	Ketapril	Naftisol	Placebo	Propriva	Ramicane	Stelasyn	Zoniferol
Timepoint
0	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000
5	44.266086	46.503051	47.062001	47.389175	46.796098	47.125589	47.248967	43.944859	47.527452	46.851818
10	43.084291	48.285125	49.403909	49.582269	48.694210	49.423329	49.101541	42.531957	49.463844	48.689881
15	42.064317	50.094055	51.296397	52.399974	50.933018	51.359742	51.067318	41.495061	51.529409	50.779059
20	40.716325	52.157049	53.197691	54.920935	53.644087	54.364417	53.346737	40.238325	54.067395	53.170334

# Generate the Plot (with Error Bars)
plt.errorbar(tumor_vols_pivot_mean.index, tumor_vols_pivot_mean["Capomulin"], yerr=tumor_vols_pivot_sem["Capomulin"], color="r", marker="o", markersize=5, linestyle="dashed", linewidth=0.50)
plt.errorbar(tumor_vols_pivot_mean.index, tumor_vols_pivot_mean["Infubinol"], yerr=tumor_vols_pivot_sem["Infubinol"], color="b", marker="^", markersize=5, linestyle="dashed", linewidth=0.50)
plt.errorbar(tumor_vols_pivot_mean.index, tumor_vols_pivot_mean["Ketapril"], yerr=tumor_vols_pivot_sem["Ketapril"], color="g", marker="s", markersize=5, linestyle="dashed", linewidth=0.50)
plt.errorbar(tumor_vols_pivot_mean.index, tumor_vols_pivot_mean["Placebo"], yerr=tumor_vols_pivot_sem["Placebo"], color="k", marker="d", markersize=5, linestyle="dashed", linewidth=0.50)

plt.title("Tumor Response to Treatment")
plt.ylabel("Tumor Volume (mm3)")
plt.xlabel("Time (Days)")
plt.grid(True)
plt.legend(loc="best", fontsize="small", fancybox=True)

# Save the Figure
plt.savefig("analysis/Fig1.png")

# Show the Figure
plt.show()

Metastatic Response to Treatment

# Store the Mean Met. Site Data Grouped by Drug and Timepoint
met_sites_mean = clinical_data_complete.groupby(["Drug", "Timepoint"]).mean()["Metastatic Sites"]

# Convert to DataFrame
met_sites_mean = pd.DataFrame(met_sites_mean)

# Preview DataFrame
met_sites_mean.head()

		Metastatic Sites
Drug	Timepoint
Capomulin	0	0.000000
	5	0.160000
	10	0.320000
	15	0.375000
	20	0.652174

# Store the Standard Error associated with Met. Sites Grouped by Drug and Timepoint
met_sites_sem = clinical_data_complete.groupby(["Drug", "Timepoint"]).sem()["Metastatic Sites"]

# Convert to DataFrame
met_sites_sem = pd.DataFrame(met_sites_sem)

# Preview DataFrame
met_sites_sem.head()

		Metastatic Sites
Drug	Timepoint
Capomulin	0	0.000000
	5	0.074833
	10	0.125433
	15	0.132048
	20	0.161621

# Minor Data Munging to Re-Format the Data Frames
met_sites_mean = met_sites_mean.reset_index()
met_sites_pivot_mean = met_sites_mean.pivot(index="Timepoint", columns="Drug")["Metastatic Sites"]

met_sites_sem = met_sites_sem.reset_index()
met_sites_pivot_sem = met_sites_sem.pivot(index="Timepoint", columns="Drug")["Metastatic Sites"]

# Preview that Reformatting worked
tumor_vols_pivot_mean.head()

Drug	Capomulin	Ceftamin	Infubinol	Ketapril	Naftisol	Placebo	Propriva	Ramicane	Stelasyn	Zoniferol
Timepoint
0	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000	45.000000
5	44.266086	46.503051	47.062001	47.389175	46.796098	47.125589	47.248967	43.944859	47.527452	46.851818
10	43.084291	48.285125	49.403909	49.582269	48.694210	49.423329	49.101541	42.531957	49.463844	48.689881
15	42.064317	50.094055	51.296397	52.399974	50.933018	51.359742	51.067318	41.495061	51.529409	50.779059
20	40.716325	52.157049	53.197691	54.920935	53.644087	54.364417	53.346737	40.238325	54.067395	53.170334

# Generate the Plot (with Error Bars)
plt.errorbar(met_sites_pivot_mean.index, met_sites_pivot_mean["Capomulin"], yerr=met_sites_pivot_sem["Capomulin"], color="r", marker="o", markersize=5, linestyle="dashed", linewidth=0.50)
plt.errorbar(met_sites_pivot_mean.index, met_sites_pivot_mean["Infubinol"], yerr=met_sites_pivot_sem["Infubinol"], color="b", marker="^", markersize=5, linestyle="dashed", linewidth=0.50)
plt.errorbar(met_sites_pivot_mean.index, met_sites_pivot_mean["Ketapril"], yerr=met_sites_pivot_sem["Ketapril"], color="g", marker="s", markersize=5, linestyle="dashed", linewidth=0.50)
plt.errorbar(met_sites_pivot_mean.index, met_sites_pivot_mean["Placebo"], yerr=met_sites_pivot_sem["Placebo"], color="k", marker="d", markersize=5, linestyle="dashed", linewidth=0.50)

plt.title("Metastatic Spread During Treatment")
plt.ylabel("Met. Sites")
plt.xlabel("Treatment Duration (Days)")
plt.grid(True)
plt.legend(loc="best", fontsize="small", fancybox=True)

# Save the Figure
plt.savefig("analysis/Fig2.png")

# Show the Figure
plt.show()

Survival Rates

# Store the Count of Mice Grouped by Drug and Timepoint (W can pass any metric)
survival_count = clinical_data_complete.groupby(["Drug", "Timepoint"]).count()["Tumor Volume (mm3)"]

# Convert to DataFrame
survival_count = pd.DataFrame({"Mouse Count": survival_count})

# Preview DataFrame
survival_count.head()

		Mouse Count
Drug	Timepoint
Capomulin	0	25
	5	25
	10	25
	15	24
	20	23

# Minor Data Munging to Re-Format the Data Frames
survival_count = survival_count.reset_index()
survival_count_pivot = survival_count.pivot(index="Timepoint", columns="Drug")["Mouse Count"]

# Preview the Data Frame
survival_count_pivot.head()

Drug	Capomulin	Ceftamin	Infubinol	Ketapril	Naftisol	Placebo	Propriva	Ramicane	Stelasyn	Zoniferol
Timepoint
0	25	25	25	25	25	25	26	25	26	25
5	25	21	25	23	23	24	25	25	25	24
10	25	20	21	22	21	24	23	24	23	22
15	24	19	21	19	21	20	17	24	23	21
20	23	18	20	19	20	19	17	23	21	17

# Generate the Plot (Accounting for percentages)
plt.plot(100 * survival_count_pivot["Capomulin"] / 25, "ro", linestyle="dashed", markersize=5, linewidth=0.50)
plt.plot(100 * survival_count_pivot["Infubinol"] / 25, "b^", linestyle="dashed", markersize=5, linewidth=0.50)
plt.plot(100 * survival_count_pivot["Ketapril"] / 25, "gs", linestyle="dashed", markersize=5, linewidth=0.50)
plt.plot(100 * survival_count_pivot["Placebo"] / 25 , "kd", linestyle="dashed", markersize=6, linewidth=0.50)
plt.title("Survival During Treatment")
plt.ylabel("Survival Rate (%)")
plt.xlabel("Time (Days)")
plt.grid(True)
plt.legend(loc="best", fontsize="small", fancybox=True)

# Save the Figure
plt.savefig("analysis/Fig3.png")

# Show the Figure
plt.show()

Summary Bar Graph

# Calculate the percent changes for each drug
tumor_pct_change =  100 * (tumor_vols_pivot_mean.iloc[-1] - tumor_vols_pivot_mean.iloc[0]) / tumor_vols_pivot_mean.iloc[0]
tumor_pct_change_sem =  100 * (tumor_vols_pivot_sem.iloc[-1] - tumor_vols_pivot_sem.iloc[0]) / tumor_vols_pivot_sem.iloc[0]

# Display the data to confirm
tumor_pct_change

Drug
Capomulin   -19.475303
Ceftamin     42.516492
Infubinol    46.123472
Ketapril     57.028795
Naftisol     53.923347
Placebo      51.297960
Propriva     47.241175
Ramicane    -22.320900
Stelasyn     52.085134
Zoniferol    46.579751
dtype: float64

# Store all Relevant Percent Changes into a Tuple
pct_changes = (tumor_pct_change["Capomulin"],
               tumor_pct_change["Infubinol"],
               tumor_pct_change["Ketapril"],
               tumor_pct_change["Placebo"])

# Splice the data between passing and failing drugs
fig, ax = plt.subplots()
ind = np.arange(len(pct_changes))
width = 1
rectsPass = ax.bar(ind[0], pct_changes[0], width, color='green')
rectsFail = ax.bar(ind[1:], pct_changes[1:], width, color='red')

# Orient widths. Add labels, tick marks, etc.
ax.set_ylabel('% Tumor Volume Change')
ax.set_title('Tumor Change Over 45 Day Treatment')
ax.set_xticks(ind + 0.5)
ax.set_xticklabels(('Capomulin', 'Infubinol', 'Ketapril', 'Placebo'))
ax.set_autoscaley_on(False)
ax.set_ylim([-30,70])
ax.grid(True)

# Use functions to label the percentages of changes
def autolabelFail(rects):
    for rect in rects:
        height = rect.get_height()
        ax.text(rect.get_x() + rect.get_width()/2., 3,
                '%d%%' % int(height),
                ha='center', va='bottom', color="white")

def autolabelPass(rects):
    for rect in rects:
        height = rect.get_height()
        ax.text(rect.get_x() + rect.get_width()/2., -8,
                '-%d%% ' % int(height),
                ha='center', va='bottom', color="white")

# Call functions to implement the function calls
autolabelPass(rectsPass)
autolabelFail(rectsFail)

# Save the Figure
fig.savefig("analysis/Fig4.png")

# Show the Figure
fig.show()

C:\Users\Ahmed\Anaconda3\envs\PythonData\lib\site-packages\matplotlib\figure.py:397: UserWarning: matplotlib is currently using a non-GUI backend, so cannot show the figure
  "matplotlib is currently using a non-GUI backend, "