In [2]:
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import numpy as np
In [4]:
integrins = pd.read_excel("/Users/reneewang/Downloads/gtex_integrin_7_organs.xlsx")
integrins
Out[4]:
| Unnamed: 0 | primary_site | ITGA10 | ITGAD | ITGAM | ITGA3 | ITGBL1 | ITGAE | ITGA2 | ITGB3 | ... | ITGA6 | ITGA2B | ITGB1 | ITGAL | ITGA9 | ITGB5 | ITGA8 | ITGA4 | ITGA1 | ITGA11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | GTEX-13QIC-0011-R1a-SM-5O9CJ | Brain | 0.5763 | -6.5064 | 2.2573 | 0.7832 | 1.0363 | 4.6035 | 2.5731 | -2.8262 | ... | 2.8562 | 1.3846 | 5.8430 | 1.1316 | -0.7108 | 3.5387 | -0.0725 | -0.4521 | 0.2029 | -2.8262 |
| 1 | GTEX-1399S-1726-SM-5L3DI | Lung | 4.9137 | -3.6259 | 4.7307 | 7.1584 | 1.7702 | 4.9556 | 1.9149 | 2.6067 | ... | 4.2412 | 4.1211 | 7.7256 | 4.4900 | 2.9281 | 6.1483 | 5.1867 | 2.6185 | 4.7856 | -0.0277 |
| 2 | GTEX-PWCY-1326-SM-48TCU | Ovary | 2.3953 | -5.0116 | 1.4547 | 4.2593 | -0.7346 | 4.4149 | 0.2642 | 1.5216 | ... | 3.6816 | 1.5465 | 7.2964 | -0.9406 | 2.7742 | 5.0414 | 2.0325 | 0.7579 | 2.2573 | 1.2516 |
| 3 | GTEX-QXCU-0626-SM-2TC69 | Lung | 4.0541 | -2.3147 | 4.5053 | 7.5651 | 4.1788 | 4.1772 | 5.3695 | 1.8444 | ... | 4.9631 | 1.9149 | 7.9947 | 3.3911 | 2.8462 | 6.7683 | 4.1636 | 2.7951 | 5.3284 | 1.2147 |
| 4 | GTEX-ZA64-1526-SM-5CVMD | Breast | 2.0569 | -2.4659 | 3.3993 | 3.1311 | 3.0074 | 4.4977 | -1.7809 | 2.7139 | ... | 4.7340 | 0.6332 | 7.3496 | -0.9406 | 2.5338 | 6.5696 | 1.7229 | -0.6416 | 3.1195 | 1.1050 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1982 | GTEX-QMRM-0826-SM-3NB33 | Lung | 5.3067 | -3.8160 | 4.9065 | 7.5810 | 5.8714 | 4.7345 | 2.6185 | 3.1095 | ... | 5.6080 | 3.7324 | 8.2849 | 4.6201 | 3.6440 | 6.7052 | 5.1094 | 3.3364 | 5.8153 | 1.6604 |
| 1983 | GTEX-YFCO-1626-SM-4W1Z3 | Prostate | 2.9581 | -4.6082 | 1.1641 | 4.6938 | 1.5902 | 5.8625 | -0.5125 | 1.7617 | ... | 3.8798 | -1.4699 | 7.5163 | -0.3752 | 2.9562 | 5.3035 | 4.4304 | -0.9406 | 3.6136 | 0.4233 |
| 1984 | GTEX-1117F-2826-SM-5GZXL | Breast | 4.3184 | -6.5064 | 1.0433 | 4.8440 | 3.5498 | 4.6809 | 1.0293 | 3.3478 | ... | 5.3256 | -0.0725 | 7.7516 | 1.1382 | 2.1411 | 7.1132 | 0.3796 | 0.0854 | 3.8650 | 1.0151 |
| 1985 | GTEX-Q2AG-2826-SM-2HMJQ | Brain | 3.4622 | -5.5735 | 1.5013 | 5.4835 | 1.7702 | 4.7517 | 0.6790 | -3.1714 | ... | 1.1960 | 4.1740 | 4.3002 | 0.5470 | -0.9971 | 3.7982 | -0.2498 | 1.4808 | -0.5125 | -0.5125 |
| 1986 | GTEX-XV7Q-0426-SM-4BRVN | Lung | 2.5585 | -1.7809 | 6.7916 | 6.5865 | 2.7051 | 4.9519 | 4.3618 | 3.1892 | ... | 3.5779 | 2.8974 | 7.7685 | 4.8294 | 1.9149 | 5.9989 | 2.4117 | 2.4198 | 4.2080 | 1.0007 |
1987 rows × 29 columns
In [5]:
#pd.set_option('display.max_rows', None) #shows all rows, no set maximum to the number of rows displayed
#pd.set_option('display.max_columns', None) #shows all rows, no set maximum to the number of rows displayed
#pd.reset_option('display.max_rows') #back to default settings for rows displayed
#pd.reset_option('display.max_columns') #back to default settings for columns displayed
brain_integrins = integrins[integrins['primary_site'] == 'Brain']
brain_integrins
Out[5]:
| Unnamed: 0 | primary_site | ITGA10 | ITGAD | ITGAM | ITGA3 | ITGBL1 | ITGAE | ITGA2 | ITGB3 | ... | ITGA6 | ITGA2B | ITGB1 | ITGAL | ITGA9 | ITGB5 | ITGA8 | ITGA4 | ITGA1 | ITGA11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | GTEX-13QIC-0011-R1a-SM-5O9CJ | Brain | 0.5763 | -6.5064 | 2.2573 | 0.7832 | 1.0363 | 4.6035 | 2.5731 | -2.8262 | ... | 2.8562 | 1.3846 | 5.8430 | 1.1316 | -0.7108 | 3.5387 | -0.0725 | -0.4521 | 0.2029 | -2.8262 |
| 8 | GTEX-N7MS-2526-SM-26GMA | Brain | 2.2960 | -9.9658 | 0.6608 | 5.2840 | 0.4233 | 4.8510 | -0.2671 | -0.1031 | ... | 1.5415 | 4.6623 | 3.4687 | 0.5666 | -0.0130 | 3.0654 | 0.7916 | 1.0433 | -0.7346 | -0.7588 |
| 10 | GTEX-N7MS-2526-SM-26GMR | Brain | -0.2498 | -9.9658 | -0.8863 | 3.1685 | -1.6394 | 2.8158 | -0.4719 | -1.1488 | ... | 1.6045 | 0.9268 | 2.8055 | -0.5973 | 0.4657 | 1.8918 | 0.3460 | 0.3907 | -1.9942 | -1.5522 |
| 12 | GTEX-NPJ7-0011-R6a-SM-2I3G7 | Brain | 1.6045 | -6.5064 | 2.3193 | 3.6335 | -2.3147 | 5.0670 | -0.8863 | -0.8084 | ... | 3.2018 | 1.7575 | 4.6894 | 0.4125 | -0.6643 | 3.6916 | -0.6193 | -2.2447 | 1.2023 | -1.9942 |
| 14 | GTEX-132Q8-3026-SM-5PNVG | Brain | 2.8974 | -6.5064 | 1.9601 | 4.1836 | -0.8084 | 4.5892 | -0.5543 | 0.3460 | ... | 3.6018 | 2.7931 | 4.7274 | -0.0574 | 1.2271 | 4.3793 | 0.8488 | -0.2159 | 2.1378 | -0.6416 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1977 | GTEX-13G51-0011-R6b-SM-5LZX4 | Brain | -0.3383 | -6.5064 | 1.6234 | 2.7487 | -2.2447 | 5.2415 | -0.8863 | -2.9324 | ... | 2.1988 | 0.4016 | 4.5142 | -1.1811 | -0.8084 | 3.9983 | -1.0862 | -3.1714 | -0.7588 | -1.9379 |
| 1978 | GTEX-YFC4-0011-R10a-SM-4SOK5 | Brain | 0.4447 | -5.5735 | 0.3231 | 3.5237 | -1.5105 | 4.9016 | 0.9419 | -2.7274 | ... | 2.8178 | 1.3567 | 4.4621 | -0.2845 | 1.0222 | 3.3336 | 0.1903 | -1.0559 | 0.0300 | -0.4719 |
| 1980 | GTEX-13112-0011-R4b-SM-5DUXL | Brain | 0.6969 | -6.5064 | -0.9686 | 2.3760 | -2.2447 | 4.0739 | -0.6193 | -4.0350 | ... | 2.7357 | 1.5806 | 4.6882 | -0.9971 | -0.5756 | 3.5136 | 0.9343 | -1.0862 | 0.4340 | -2.2447 |
| 1981 | GTEX-1313W-0011-R1b-SM-5EQ4A | Brain | 0.1124 | -5.0116 | 2.2482 | 2.8897 | -0.5125 | 4.6445 | 0.3115 | -3.6259 | ... | 2.1147 | 0.9716 | 5.1202 | 0.6608 | 0.4761 | 3.2343 | 0.8408 | -0.0574 | -0.1828 | -2.5479 |
| 1985 | GTEX-Q2AG-2826-SM-2HMJQ | Brain | 3.4622 | -5.5735 | 1.5013 | 5.4835 | 1.7702 | 4.7517 | 0.6790 | -3.1714 | ... | 1.1960 | 4.1740 | 4.3002 | 0.5470 | -0.9971 | 3.7982 | -0.2498 | 1.4808 | -0.5125 | -0.5125 |
1152 rows × 29 columns
In [7]:
#violin plot for all the genes of the brain
plt.figure(figsize = (16, 6))
sns.violinplot(data = brain_integrins)
plt.title("Integrin Genes of the Brain")
plt.xlabel("Integrin Genes")
plt.ylabel("Gene Expression Levels")
plt.show()
In [8]:
liver_integrins = integrins[integrins['primary_site'] == 'Liver']
liver_integrins
Out[8]:
| Unnamed: 0 | primary_site | ITGA10 | ITGAD | ITGAM | ITGA3 | ITGBL1 | ITGAE | ITGA2 | ITGB3 | ... | ITGA6 | ITGA2B | ITGB1 | ITGAL | ITGA9 | ITGB5 | ITGA8 | ITGA4 | ITGA1 | ITGA11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 13 | GTEX-WZTO-0626-SM-4PQYY | Liver | -0.0277 | -4.2934 | -0.3201 | 0.4340 | -1.2828 | 2.8055 | -2.9324 | -1.9379 | ... | 1.1960 | -2.6349 | 4.4758 | 2.8582 | -0.1031 | 4.0454 | -2.5479 | -1.0262 | 2.7465 | -2.8262 |
| 49 | GTEX-12WSM-0726-SM-5GCOW | Liver | -0.1828 | -0.8339 | -0.5973 | 0.5568 | 0.6880 | 3.1278 | -3.3076 | -0.7346 | ... | 1.0779 | -2.9324 | 5.3169 | 2.5213 | 0.7664 | 4.3958 | -0.7346 | -1.1488 | 3.0110 | -2.9324 |
| 62 | GTEX-12WSI-0226-SM-5GCNA | Liver | -1.4699 | -3.8160 | 0.5271 | 2.1313 | 2.9148 | 2.9984 | -1.9942 | -0.0277 | ... | 2.3164 | -1.7322 | 6.0885 | 2.2813 | 2.8462 | 5.4683 | -1.9942 | -1.1488 | 3.4183 | -0.0877 |
| 65 | GTEX-12696-0826-SM-5EGGE | Liver | -0.3940 | -4.6082 | 0.3346 | -0.1504 | -1.4699 | 2.6624 | -3.0469 | 0.5568 | ... | 0.4340 | -1.5522 | 5.4611 | 1.4704 | 0.3907 | 4.9538 | -3.4580 | -2.9324 | 3.4451 | -3.1714 |
| 83 | GTEX-1212Z-0226-SM-59HLF | Liver | -0.0425 | -1.1488 | -0.2498 | 0.5069 | 0.7916 | 2.9281 | -2.8262 | -0.4325 | ... | 1.4441 | 0.2400 | 5.1993 | 3.0287 | 0.9191 | 4.4932 | -2.5479 | 0.0014 | 3.3745 | -1.4699 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1923 | GTEX-ZF29-2026-SM-4WWB7 | Liver | -1.0559 | -2.3884 | 1.8078 | -0.0425 | -1.4305 | 2.5852 | -4.0350 | 0.2998 | ... | 2.1509 | -1.9942 | 6.6547 | 2.2513 | 2.1509 | 5.4283 | -2.6349 | -0.5973 | 3.9728 | -2.5479 |
| 1924 | GTEX-13NZB-0626-SM-5IFH6 | Liver | 0.8805 | -5.5735 | 0.8164 | 0.9642 | -1.9379 | 3.3952 | -3.6259 | -1.2828 | ... | 0.9862 | -2.4659 | 5.2510 | 2.0844 | 0.7146 | 5.1863 | -2.5479 | -1.9379 | 3.8401 | -1.5951 |
| 1930 | GTEX-14E1K-0326-SM-5S2PE | Liver | 0.6608 | -6.5064 | -0.1031 | -0.4325 | -2.2447 | 3.3076 | -3.6259 | -1.6394 | ... | 1.4652 | -0.9686 | 5.6221 | 2.0325 | 0.4761 | 4.9855 | -4.6082 | -1.6394 | 3.4251 | -3.1714 |
| 1954 | GTEX-ZVP2-0626-SM-51MSO | Liver | -1.1811 | -2.3884 | 0.7058 | 0.6239 | 1.2934 | 3.1813 | -3.4580 | -1.1172 | ... | 1.7141 | -1.7809 | 5.8746 | 2.5388 | 1.9302 | 5.1615 | -2.3884 | -0.5332 | 3.8126 | -1.0262 |
| 1969 | GTEX-13FTZ-0726-SM-5IFFY | Liver | -0.6873 | -3.4580 | -0.5125 | -0.3566 | -0.4921 | 3.0654 | -4.0350 | -1.5951 | ... | 0.9493 | -1.9942 | 5.2563 | 2.5924 | -0.3752 | 4.5053 | -4.6082 | -2.2447 | 3.1458 | -2.8262 |
110 rows × 29 columns
In [10]:
#violin plot for all the genes of the liver
plt.figure(figsize = (16, 6))
sns.violinplot(data = liver_integrins)
plt.title("Integrin Genes of the Liver")
plt.xlabel("Integrin Genes")
plt.ylabel("Gene Expression Levels")
plt.show()
In [23]:
brain_liver_integrins = integrins[integrins['primary_site'].isin(['Brain', 'Liver'])] #filter data by organ, display both brain and liver data
brain_liver_integrins
Out[23]:
| Unnamed: 0 | primary_site | ITGA10 | ITGAD | ITGAM | ITGA3 | ITGBL1 | ITGAE | ITGA2 | ITGB3 | ... | ITGA6 | ITGA2B | ITGB1 | ITGAL | ITGA9 | ITGB5 | ITGA8 | ITGA4 | ITGA1 | ITGA11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | GTEX-13QIC-0011-R1a-SM-5O9CJ | Brain | 0.5763 | -6.5064 | 2.2573 | 0.7832 | 1.0363 | 4.6035 | 2.5731 | -2.8262 | ... | 2.8562 | 1.3846 | 5.8430 | 1.1316 | -0.7108 | 3.5387 | -0.0725 | -0.4521 | 0.2029 | -2.8262 |
| 8 | GTEX-N7MS-2526-SM-26GMA | Brain | 2.2960 | -9.9658 | 0.6608 | 5.2840 | 0.4233 | 4.8510 | -0.2671 | -0.1031 | ... | 1.5415 | 4.6623 | 3.4687 | 0.5666 | -0.0130 | 3.0654 | 0.7916 | 1.0433 | -0.7346 | -0.7588 |
| 10 | GTEX-N7MS-2526-SM-26GMR | Brain | -0.2498 | -9.9658 | -0.8863 | 3.1685 | -1.6394 | 2.8158 | -0.4719 | -1.1488 | ... | 1.6045 | 0.9268 | 2.8055 | -0.5973 | 0.4657 | 1.8918 | 0.3460 | 0.3907 | -1.9942 | -1.5522 |
| 12 | GTEX-NPJ7-0011-R6a-SM-2I3G7 | Brain | 1.6045 | -6.5064 | 2.3193 | 3.6335 | -2.3147 | 5.0670 | -0.8863 | -0.8084 | ... | 3.2018 | 1.7575 | 4.6894 | 0.4125 | -0.6643 | 3.6916 | -0.6193 | -2.2447 | 1.2023 | -1.9942 |
| 13 | GTEX-WZTO-0626-SM-4PQYY | Liver | -0.0277 | -4.2934 | -0.3201 | 0.4340 | -1.2828 | 2.8055 | -2.9324 | -1.9379 | ... | 1.1960 | -2.6349 | 4.4758 | 2.8582 | -0.1031 | 4.0454 | -2.5479 | -1.0262 | 2.7465 | -2.8262 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1977 | GTEX-13G51-0011-R6b-SM-5LZX4 | Brain | -0.3383 | -6.5064 | 1.6234 | 2.7487 | -2.2447 | 5.2415 | -0.8863 | -2.9324 | ... | 2.1988 | 0.4016 | 4.5142 | -1.1811 | -0.8084 | 3.9983 | -1.0862 | -3.1714 | -0.7588 | -1.9379 |
| 1978 | GTEX-YFC4-0011-R10a-SM-4SOK5 | Brain | 0.4447 | -5.5735 | 0.3231 | 3.5237 | -1.5105 | 4.9016 | 0.9419 | -2.7274 | ... | 2.8178 | 1.3567 | 4.4621 | -0.2845 | 1.0222 | 3.3336 | 0.1903 | -1.0559 | 0.0300 | -0.4719 |
| 1980 | GTEX-13112-0011-R4b-SM-5DUXL | Brain | 0.6969 | -6.5064 | -0.9686 | 2.3760 | -2.2447 | 4.0739 | -0.6193 | -4.0350 | ... | 2.7357 | 1.5806 | 4.6882 | -0.9971 | -0.5756 | 3.5136 | 0.9343 | -1.0862 | 0.4340 | -2.2447 |
| 1981 | GTEX-1313W-0011-R1b-SM-5EQ4A | Brain | 0.1124 | -5.0116 | 2.2482 | 2.8897 | -0.5125 | 4.6445 | 0.3115 | -3.6259 | ... | 2.1147 | 0.9716 | 5.1202 | 0.6608 | 0.4761 | 3.2343 | 0.8408 | -0.0574 | -0.1828 | -2.5479 |
| 1985 | GTEX-Q2AG-2826-SM-2HMJQ | Brain | 3.4622 | -5.5735 | 1.5013 | 5.4835 | 1.7702 | 4.7517 | 0.6790 | -3.1714 | ... | 1.1960 | 4.1740 | 4.3002 | 0.5470 | -0.9971 | 3.7982 | -0.2498 | 1.4808 | -0.5125 | -0.5125 |
1262 rows × 29 columns
In [28]:
# First, define the data_brain_liver variable before using it
# For example, you might need to load your data from a file:
#data_brain_liver = pd.read_csv('/Users/reneewang/Downloads/gtex_integrin_7_organs.xlsx')
brain_liver_integrins_expression_only = brain_liver_integrins.iloc[:, 1:]
In [32]:
brain_liver_integrins = integrins[integrins['primary_site'].isin(['Brain', 'Liver'])] #filter data by organ, display both brain and liver data
#rearrange data
brain_liver_integrins_vertical = brain_liver_integrins_expression_only.melt(id_vars = 'primary_site', var_name = 'integrin_gene', value_name = 'expression_levels')
brain_liver_integrins_vertical
Out[32]:
| primary_site | integrin_gene | expression_levels | |
|---|---|---|---|
| 0 | Brain | ITGA10 | 0.5763 |
| 1 | Brain | ITGA10 | 2.2960 |
| 2 | Brain | ITGA10 | -0.2498 |
| 3 | Brain | ITGA10 | 1.6045 |
| 4 | Liver | ITGA10 | -0.0277 |
| ... | ... | ... | ... |
| 34069 | Brain | ITGA11 | -1.9379 |
| 34070 | Brain | ITGA11 | -0.4719 |
| 34071 | Brain | ITGA11 | -2.2447 |
| 34072 | Brain | ITGA11 | -2.5479 |
| 34073 | Brain | ITGA11 | -0.5125 |
34074 rows × 3 columns
In [33]:
plt.figure(figsize=(16, 6))
sns.violinplot(x = 'integrin_gene', y = 'expression_levels', hue = 'primary_site', data = brain_liver_integrins_vertical, split = True, inner = 'quartile')
plt.title("Integrin Genes of the Brain vs. the Liver")
plt.xlabel("Integrin Gene")
plt.ylabel("Gene Expression Levels")
plt.legend(title = 'primary_site')
plt.show()
In [ ]: