R Data Analysis Solutions

---

Go back to the main page
Go back to the R overview page

---

R

Data Analysis Exercises

Import Tidyverse:

library(tidyverse)

The following function is used to print tibbles in a proper way for the web. You can skip the use of this function to print tibbles to your screen in R Markdown documents.

library(knitr)
library(kableExtra)
library(pillar)

formatted_table <- function(df) {
  col_types <- sapply(df, pillar::type_sum)
  new_col_names <- paste0(names(df), "<br>", "<span style='font-weight: normal;'>", col_types, "</span>")
  kbl(df, 
      col.names = new_col_names, 
      escape = FALSE, # This is crucial to allow the <br> tag to work
      format = "html" # Ensure HTML format, although often auto-detected
      ) %>%
    kable_styling(bootstrap_options = c("striped", "hover", "responsive"))
}

This file can be downloaded here

In order to compare the analysis in R with Excel, the exercises where kept as similar as possible.

Exercise 1

Import the Mice Protein Expression dataset in R. It contains data on the levels of protein expression of mice proteins in different mice. Perform the following calculations on this data frame and display them as a table:

• Calculate the minimum, maximum, average, median from the columns CDK5_N and Tau_N. Display the answers in a data frame.

file_path <- "./files_10_data_analysis_exercises/exercise01/Data_Cortex_Nuclear.csv"
df <- read_csv(file_path)
formatted_table(head(df))

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
309_1	0.5036439	0.7471932	0.4301753	2.816329	5.990152	0.2188300	0.1775655	2.373744	0.2322238	1.750936	0.6879062	0.3063817	0.4026984	0.2969273	1.0220603	0.6056726	1.877684	2.308745	0.4415994	0.8593658	0.4162891	0.3696080	0.1789443	1.866358	3.685247	1.537227	0.2645263	0.3196770	0.8138665	0.1658460	0.4539098	3.037621	0.3695096	0.4585385	0.3353358	0.8251920	0.5769155	0.4480993	0.5862714	0.3947213	0.3395706	0.4828639	0.2941698	0.1821505	0.8427252	0.1926084	1.443091	0.2947000	0.3546045	1.339070	0.1701188	0.1591024	0.1888517	0.1063052	0.1449893	0.1766677	0.1251904	0.1152909	0.2280435	0.1427556	0.4309575	0.2475378	1.603310	2.014875	0.1082343	1.0449792	0.8315565	0.1888517	0.1226520	NA	0.1063052	0.1083359	0.4270992	0.1147832	0.1317900	0.1281856	1.675652	Control	Memantine	C/S	c-CS-m
309_2	0.5146171	0.6890635	0.4117703	2.789514	5.685038	0.2116362	0.1728170	2.292150	0.2269721	1.596377	0.6950062	0.2990511	0.3859868	0.2813189	0.9566759	0.5875587	1.725774	2.043036	0.4452219	0.8346593	0.4003642	0.3561775	0.1736797	1.761047	3.485287	1.509249	0.2557270	0.3044187	0.7805042	0.1571935	0.4309403	2.921883	0.3422793	0.4235599	0.3248347	0.7617176	0.5450973	0.4208761	0.5450973	0.3682546	0.3219592	0.4545193	0.2764306	0.1820863	0.8476146	0.1948153	1.439460	0.2940598	0.3545483	1.306323	0.1714271	0.1581289	0.1845700	0.1065922	0.1504709	0.1783090	0.1342751	0.1182345	0.2380731	0.1420366	0.4571562	0.2576322	1.671738	2.004605	0.1097485	1.0098831	0.8492704	0.2004036	0.1166822	NA	0.1065922	0.1043154	0.4415813	0.1119735	0.1351030	0.1311187	1.743610	Control	Memantine	C/S	c-CS-m
309_3	0.5091831	0.7302468	0.4183088	2.687201	5.622058	0.2090109	0.1757222	2.283336	0.2302468	1.561316	0.6773484	0.2912761	0.3810025	0.2817103	1.0036350	0.6024488	1.731873	2.017984	0.4676679	0.8143294	0.3998469	0.3680888	0.1739047	1.765544	3.571456	1.501243	0.2596135	0.3117467	0.7851540	0.1608954	0.4231873	2.944136	0.3436962	0.4250048	0.3248517	0.7570308	0.5436197	0.4046298	0.5529941	0.3638799	0.3130859	0.4471972	0.2566482	0.1843877	0.8561658	0.2007373	1.524364	0.3018807	0.3860868	1.279600	0.1854563	0.1486963	0.1905322	0.1083031	0.1453302	0.1762129	0.1325604	0.1177602	0.2448173	0.1424450	0.5104723	0.2553430	1.663550	2.016831	0.1081962	0.9968476	0.8467087	0.1936845	0.1185082	NA	0.1083031	0.1062193	0.4357769	0.1118829	0.1333618	0.1274311	1.926427	Control	Memantine	C/S	c-CS-m
309_4	0.4421067	0.6170762	0.3586263	2.466947	4.979503	0.2228858	0.1764626	2.152301	0.2070042	1.595086	0.5832768	0.2967287	0.3770870	0.3138320	0.8753903	0.5202932	1.566852	2.132754	0.4776707	0.7277046	0.3856387	0.3629700	0.1794489	1.286277	2.970137	1.419709	0.2595358	0.2792181	0.7344917	0.1622099	0.4106149	2.500204	0.3445093	0.4292113	0.3301208	0.7469798	0.5467626	0.3868603	0.5478485	0.3667707	0.3284919	0.4426497	0.3985340	0.1617677	0.7602335	0.1841694	1.612382	0.2963818	0.2906795	1.198765	0.1597991	0.1661123	0.1853235	0.1031838	0.1406558	0.1638042	0.1232096	0.1174394	0.2349467	0.1450682	0.4309959	0.2511031	1.484624	1.957233	0.1198832	0.9902247	0.8332768	0.1921119	0.1327812	NA	0.1031838	0.1112620	0.3916910	0.1304053	0.1474442	0.1469011	1.700563	Control	Memantine	C/S	c-CS-m
309_5	0.4349402	0.6174298	0.3588022	2.365785	4.718679	0.2131059	0.1736270	2.134014	0.1921579	1.504230	0.5509601	0.2869612	0.3635021	0.2779643	0.8649120	0.5079898	1.480059	2.013697	0.4834161	0.6877937	0.3675305	0.3553109	0.1748355	1.324695	2.896334	1.359876	0.2507050	0.2736672	0.7026991	0.1548274	0.3985498	2.456560	0.3291258	0.4087552	0.3134148	0.6919565	0.5368605	0.3608164	0.5128240	0.3515510	0.3122063	0.4190949	0.3934470	0.1602002	0.7681129	0.1857183	1.645807	0.2968294	0.3093450	1.206995	0.1646503	0.1606870	0.1882214	0.1047838	0.1419830	0.1677096	0.1368377	0.1160478	0.2555277	0.1408705	0.4812265	0.2517730	1.534835	2.009109	0.1195244	0.9977750	0.8786678	0.2056042	0.1299541	NA	0.1047838	0.1106939	0.4341538	0.1184814	0.1403143	0.1483799	1.839730	Control	Memantine	C/S	c-CS-m
309_6	0.4475064	0.6281758	0.3673881	2.385939	4.807635	0.2185778	0.1762334	2.141282	0.1951875	1.442398	0.5663396	0.2898239	0.3638930	0.2668369	0.8591209	0.5213066	1.538244	1.968275	0.4959000	0.6724022	0.3694045	0.3571717	0.1797285	1.227450	2.956984	1.447910	0.2508402	0.2840436	0.7043958	0.1568759	0.3910472	2.467133	0.3275978	0.4044899	0.2962764	0.6744186	0.5397231	0.3542143	0.5143164	0.3472241	0.3031321	0.4128243	0.3825783	0.1623303	0.7796946	0.1867930	1.634615	0.2880373	0.3323671	1.123445	0.1756929	0.1505939	0.1838235	0.1064762	0.1395645	0.1748445	0.1305147	0.1152432	0.2368495	0.1364536	0.4785775	0.2444853	1.507777	2.003535	0.1206872	0.9201782	0.8436793	0.1904695	0.1315752	NA	0.1064762	0.1094457	0.4398331	0.1166572	0.1407664	0.1421804	1.816389	Control	Memantine	C/S	c-CS-m

The calculations of the minimum, maximum, average and median of these two proteins:

min_CDK5_N <- min(df$CDK5_N)
max_CDK5_N <- max(df$CDK5_N)
mean_CDK5_N <- mean(df$CDK5_N)
median_CDK5_N <- median(df$CDK5_N)

min_Tau_N <- min(df$Tau_N)
max_Tau_N <- max(df$Tau_N)
mean_Tau_N <- mean(df$Tau_N)
median_Tau_N <- median(df$Tau_N)

results_ex1 <- tibble("measure" = c("minimum", "maximum", "mean", "median"), 
                      "CDK5_N" = c(min_CDK5_N, max_CDK5_N, mean_CDK5_N, median_CDK5_N),
                      "Tau_N" = c(min_Tau_N, max_Tau_N, mean_Tau_N, median_Tau_N)
                      )

formatted_table(results_ex1)

measure chr	CDK5_N dbl	Tau_N dbl
minimum	0.1811570	0.0962328
maximum	0.8174018	0.6027681
mean	0.2924341	0.2104892
median	0.2938195	0.1886295

Exercise 2

Index, filter and sort your data frame to answer the following questions:
1. Which mouse has the highest expression of the Tau protein?
2. What is the relative expression value of this protein in this particular mouse?
3. Which mouse has the lowest expression of the pAKT protein?
4. How many empty cells (NA) are in the BAD column? Use the summary function to find the amount of empty cells.
5. Which mouse of the Ts65Dn genotype group has the highest Tau expression (use multi-sorting)?
6. Which mouse of the Ts65Dn genotype, and saline treatment group has the highest Tau expression (use multi-sorting)?

Mouse with the highest expression of the protein Tau_N:

df %>%
  filter(`Tau_N` == max(df$Tau_N)) %>%
  formatted_table()

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
3516_12	0.1847187	0.300084	0.2303946	1.605206	2.353988	0.1748111	0.1407221	2.582368	0.159026	0.8243493	0.2082284	0.2288833	0.2129303	0.2099076	0.6481948	0.5418976	1.11419	0.7277918	0.3983207	0.5694374	0.1838791	0.3036104	0.1449202	0.9286314	1.42754	0.6048699	0.1692695	0.1895886	0.4267003	0.1326616	0.2609572	1.479261	0.5465995	0.3877414	0.418136	0.6283795	0.4498741	0.2653233	0.4574307	0.2458438	0.2577666	0.3361881	0.3242653	0.1699014	0.8671651	0.1592428	1.247216	0.2446707	0.6259943	0.8515749	1.156856	0.2020363	0.1662424	0.136812	0.1854916	0.1783328	0.6027681	0.1492205	0.2268533	0.1172447	0.7629653	0.3020999	1.478206	2.270283	0.2068088	1.160197	0.7424435	0.2378301	0.1878778	0.163538	0.136812	0.1808781	0.3919822	NA	0.298441	0.3736876	1.014795	Control	Saline	S/C	c-SC-s

The relative expression value for this protein in this particular mouse. First, we need to find in which row the maximum value for the highest expression of the Tau protein is stored. First we calculate the max value for this column:

max(df$Tau_N)

## [1] 0.6027681

Then we create a logical factor to match the highest number.

head(df$Tau_N == max(df$Tau_N)) # Somewhere the value will be TRUE

## [1] FALSE FALSE FALSE FALSE FALSE FALSE

Then we can search in the data frame for the row that matches the logical.

df[df$Tau_N == max(df$Tau_N), ]

## # A tibble: 1 × 82
##   MouseID DYRK1A_N ITSN1_N BDNF_N NR1_N NR2A_N pAKT_N pBRAF_N pCAMKII_N pCREB_N
##   <chr>      <dbl>   <dbl>  <dbl> <dbl>  <dbl>  <dbl>   <dbl>     <dbl>   <dbl>
## 1 3516_12    0.185   0.300  0.230  1.61   2.35  0.175   0.141      2.58   0.159
## # ℹ 72 more variables: pELK_N <dbl>, pERK_N <dbl>, pJNK_N <dbl>, PKCA_N <dbl>,
## #   pMEK_N <dbl>, pNR1_N <dbl>, pNR2A_N <dbl>, pNR2B_N <dbl>, pPKCAB_N <dbl>,
## #   pRSK_N <dbl>, AKT_N <dbl>, BRAF_N <dbl>, CAMKII_N <dbl>, CREB_N <dbl>,
## #   ELK_N <dbl>, ERK_N <dbl>, GSK3B_N <dbl>, JNK_N <dbl>, MEK_N <dbl>,
## #   TRKA_N <dbl>, RSK_N <dbl>, APP_N <dbl>, Bcatenin_N <dbl>, SOD1_N <dbl>,
## #   MTOR_N <dbl>, P38_N <dbl>, pMTOR_N <dbl>, DSCR1_N <dbl>, AMPKA_N <dbl>,
## #   NR2B_N <dbl>, pNUMB_N <dbl>, RAPTOR_N <dbl>, TIAM1_N <dbl>, …

Or tidyverse style:

df %>%
  slice_max(Tau_N) %>%
  formatted_table()

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
3516_12	0.1847187	0.300084	0.2303946	1.605206	2.353988	0.1748111	0.1407221	2.582368	0.159026	0.8243493	0.2082284	0.2288833	0.2129303	0.2099076	0.6481948	0.5418976	1.11419	0.7277918	0.3983207	0.5694374	0.1838791	0.3036104	0.1449202	0.9286314	1.42754	0.6048699	0.1692695	0.1895886	0.4267003	0.1326616	0.2609572	1.479261	0.5465995	0.3877414	0.418136	0.6283795	0.4498741	0.2653233	0.4574307	0.2458438	0.2577666	0.3361881	0.3242653	0.1699014	0.8671651	0.1592428	1.247216	0.2446707	0.6259943	0.8515749	1.156856	0.2020363	0.1662424	0.136812	0.1854916	0.1783328	0.6027681	0.1492205	0.2268533	0.1172447	0.7629653	0.3020999	1.478206	2.270283	0.2068088	1.160197	0.7424435	0.2378301	0.1878778	0.163538	0.136812	0.1808781	0.3919822	NA	0.298441	0.3736876	1.014795	Control	Saline	S/C	c-SC-s

Mouse with the lowest expression of the pAKT protein. There are NA values in this column, so will have to use the na.rm = argument in the calculation:

formatted_table(filter(df, `pAKT_N` == min(df$pAKT_N, na.rm = TRUE))) # this will remove all NA values and then show the mouse with minimal value for pAKT

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
3479_9	0.4087756	0.5339571	0.3169866	2.163252	3.720761	0.063236	0.0640426	2.488143	0.1808356	1.2794	0.4644297	0.0556541	0.3815131	0.0696887	0.7394741	0.5015325	1.399419	2.17519	0.0974351	0.0711405	0.3747379	0.3311824	0.1574447	NA	2.483465	1.277303	0.0462978	NA	0.6483304	0.1466366	0.370705	2.034038	0.3095661	0.4453944	0.3910308	0.667527	0.5713825	0.3474754	0.5373447	0.3365059	0.3202129	0.4149056	0.7280206	0.149593	0.6998213	0.1568394	2.467143	0.2811197	0.3685726	1.511118	0.1496923	0.1470121	0.1822513	0.1137582	0.1585269	0.1625968	0.1704388	0.1183244	0.2510423	0.1312289	0.4688307	0.3281715	1.252829	2.065118	0.142843	0.9968235	0.8511018	0.2282112	NA	NA	0.1137582	0.1168354	0.4192972	0.1396665	NA	0.1834425	1.42158	Control	Saline	C/S	c-CS-s

Or tidyverse style:

df %>%
  slice_min(pAKT_N) %>%
  formatted_table()

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
3479_9	0.4087756	0.5339571	0.3169866	2.163252	3.720761	0.063236	0.0640426	2.488143	0.1808356	1.2794	0.4644297	0.0556541	0.3815131	0.0696887	0.7394741	0.5015325	1.399419	2.17519	0.0974351	0.0711405	0.3747379	0.3311824	0.1574447	NA	2.483465	1.277303	0.0462978	NA	0.6483304	0.1466366	0.370705	2.034038	0.3095661	0.4453944	0.3910308	0.667527	0.5713825	0.3474754	0.5373447	0.3365059	0.3202129	0.4149056	0.7280206	0.149593	0.6998213	0.1568394	2.467143	0.2811197	0.3685726	1.511118	0.1496923	0.1470121	0.1822513	0.1137582	0.1585269	0.1625968	0.1704388	0.1183244	0.2510423	0.1312289	0.4688307	0.3281715	1.252829	2.065118	0.142843	0.9968235	0.8511018	0.2282112	NA	NA	0.1137582	0.1168354	0.4192972	0.1396665	NA	0.1834425	1.42158	Control	Saline	C/S	c-CS-s

Amount of empty cells (NA) in the BAD column:

summary(df$BAD_N)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##  0.0883  0.1364  0.1523  0.1579  0.1740  0.2820     213

The amount of empty cells is in the last column.

Or:

sum(is.na(df$BAD_N))

## [1] 213

Mouse of the Ts65Dn genotype group with the highest Tau expression:

df %>% 
  arrange(desc(Genotype), desc(Tau_N)) %>%
  slice_head(n = 6) %>%
  formatted_table()

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
293_15	0.2095214	0.4619390	0.2940739	2.100917	2.607736	0.2873791	0.2062980	3.364741	0.2444830	1.1919167	0.2303496	0.3431689	0.2757253	0.3032482	0.7827920	0.7354327	1.429209	1.0151252	0.4986363	0.6640218	0.2987850	0.4125961	0.2077858	0.9707414	2.005703	0.9186710	0.2303496	0.2670469	0.6335234	0.2097694	0.3520952	1.799157	1.0292586	0.4160674	0.3568063	0.7706422	0.6241012	0.3245723	0.5643442	0.3047359	0.3223407	0.3788743	0.3927597	0.1849418	0.8912880	0.1781825	1.625986	0.2472775	0.5383027	1.105145	0.9179497	0.2114157	0.1697334	0.1378145	0.1937664	0.1856928	0.5137063	0.1314307	0.1802478	0.1030792	0.6845663	0.3133684	1.793842	2.458881	0.1749906	1.443860	0.8561772	0.2069095	0.1684191	0.1378145	0.1378145	0.1182876	0.4990612	0.4355989	0.2005257	0.3332707	1.2829516	Ts65Dn	Memantine	S/C	t-SC-m
293_14	0.1914640	0.4432523	0.2627563	1.998093	2.582260	0.2610873	0.1921793	3.230567	0.2546495	1.1826419	0.2401049	0.3106819	0.2713400	0.2901764	0.7663329	0.6950405	1.324511	0.9439676	0.4530281	0.6254173	0.2804006	0.3786361	0.1890796	0.9711493	1.920839	0.8738674	0.2603720	0.2396280	0.6096805	0.2041011	0.3218884	1.715785	0.9983309	0.3781593	0.3593228	0.7157845	0.6120649	0.3061516	0.5202670	0.3004292	0.3090129	0.3667144	0.3500238	0.1781214	0.8953799	0.1798396	1.663230	0.2338679	0.5282551	1.157885	0.9320351	0.2191676	0.1876670	0.1397480	0.1905307	0.1880489	0.5036273	0.1307751	0.1895762	0.1191294	0.6922490	0.3077511	1.730622	2.410271	0.1914853	1.411989	0.8669339	0.2037037	0.1611302	0.1586483	0.1397480	0.1357388	0.4854906	0.4797633	0.2042764	0.3193967	1.2997327	Ts65Dn	Memantine	S/C	t-SC-m
293_13	0.2274182	0.4440069	0.3101157	2.093035	2.882599	0.2739355	0.2035442	3.312577	0.2569530	1.2109279	0.2562146	0.3138075	0.2818115	0.2914103	0.7839035	0.7238494	1.352941	0.9822791	0.4902781	0.6793010	0.3416195	0.3780458	0.1912380	1.0620231	1.994339	0.8949052	0.2284027	0.2483387	0.6330298	0.2156042	0.3465420	1.765690	1.0750677	0.4056116	0.4009353	0.7615063	0.6032488	0.3066699	0.5291656	0.3364509	0.3337435	0.3760768	0.3359587	0.1756604	0.8732075	0.1784906	1.650377	0.2616981	0.5164151	1.174906	0.9371698	0.2158491	0.1737736	0.1307547	0.1858491	0.1722642	0.4681132	0.1290566	0.1845283	0.1024528	0.6741509	0.3056604	1.727359	2.335094	0.1762264	1.383585	0.8177358	0.2128302	0.1566038	0.1383019	0.1307547	0.1332075	0.4681132	0.4550943	0.2018868	0.3094340	1.2694340	Ts65Dn	Memantine	S/C	t-SC-m
3418_12	0.2657622	0.3982442	0.2952913	1.913009	2.715350	0.2537909	0.1987231	2.067039	0.1931365	1.2096302	0.2657622	0.2942272	0.3139133	0.2889066	0.7509976	0.6515031	1.287576	0.8704443	0.3830806	0.5810056	0.2197393	0.3506252	0.1785049	0.9481245	1.499335	0.8047353	0.2149508	0.2580474	0.5086459	0.1633413	0.4192604	1.673051	0.7584464	0.5293961	0.5921788	0.8233573	0.6914073	0.4519819	0.6254323	0.3761639	0.4418728	0.5014632	0.5243416	0.1554742	0.7367919	0.1542011	1.408975	0.2530236	0.2870783	1.072565	0.9000637	0.2345640	0.1830045	0.1352642	0.1721833	0.2021006	0.4194780	0.1421069	0.1871419	0.1288988	0.5300764	0.2969446	1.569542	1.974857	0.2005092	1.214672	0.7184914	0.2210376	NA	NA	0.1352642	0.1592934	0.3965627	NA	NA	0.3820815	0.8026735	Ts65Dn	Memantine	S/C	t-SC-m
293_12	0.2264906	0.4789916	0.2745098	2.087635	2.906163	0.2593037	0.1902761	3.491597	0.2310924	1.1068427	0.2733093	0.3173269	0.2697079	0.2939176	0.7741096	0.7430972	1.436775	0.9261705	0.4881953	0.6036415	0.2639056	0.3707483	0.2062825	0.9809924	2.065626	0.9267707	0.2214886	0.2484994	0.6270508	0.1846739	0.3633453	1.944178	0.9469788	0.3975590	0.3541417	0.7490996	0.5732293	0.3065226	0.5308123	0.2943177	0.3001200	0.3617447	0.3321329	0.1764966	0.8731937	0.1741374	1.564730	0.2595105	0.5535240	1.115748	0.8498968	0.1906517	0.1773813	0.1383073	0.1893247	0.1838691	0.4189030	0.1360955	0.1884400	0.1182542	0.6483338	0.2965202	1.839723	2.503391	0.1585078	1.450015	0.8428192	0.2198467	0.1368328	0.1263639	0.1383073	0.1138307	0.4899735	0.4535535	0.1964022	0.3164258	1.2547921	Ts65Dn	Memantine	S/C	t-SC-m
J3295_14	0.2212424	0.4128944	0.2439741	1.876347	2.384088	0.2088967	0.1736234	2.086028	0.1920439	0.9225946	0.2306486	0.2631785	0.2243778	0.2774838	0.6650990	0.4795219	1.077014	1.1150304	0.4346463	0.5647658	0.2567117	0.3131491	0.1722516	0.7818930	1.558887	0.8728199	0.2380952	0.2704292	0.5851460	0.1634333	0.3411719	1.571821	0.6984127	0.3564570	0.3084460	0.5457574	0.4805017	0.2580835	0.4266118	0.2584754	0.2159514	0.3015873	0.4904958	0.1975667	0.7848193	0.1754131	2.659706	0.3410205	0.6426366	0.783185	0.5382241	0.2120937	0.1614309	0.1252951	0.1725077	0.1937534	0.4142001	0.1492646	0.2044670	0.1245687	0.6217541	0.3522789	1.498820	2.609769	0.1850372	1.301071	0.9892864	0.3067006	0.2222626	NA	0.1252951	0.1962956	0.3976757	0.3359361	0.2513165	0.3653532	1.4040312	Ts65Dn	Saline	S/C	t-SC-s

Or to filter for the row:

my_answer <- df %>% 
  filter(Genotype == "Ts65Dn") %>%
  filter(Tau_N == max(Tau_N, na.rm = T))
formatted_table(my_answer)

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
293_15	0.2095214	0.461939	0.2940739	2.100917	2.607736	0.2873791	0.206298	3.364741	0.244483	1.191917	0.2303496	0.3431689	0.2757253	0.3032482	0.782792	0.7354327	1.429209	1.015125	0.4986363	0.6640218	0.298785	0.4125961	0.2077858	0.9707414	2.005703	0.918671	0.2303496	0.2670469	0.6335234	0.2097694	0.3520952	1.799157	1.029259	0.4160674	0.3568063	0.7706422	0.6241012	0.3245723	0.5643442	0.3047359	0.3223407	0.3788743	0.3927597	0.1849418	0.891288	0.1781825	1.625986	0.2472775	0.5383027	1.105145	0.9179497	0.2114157	0.1697334	0.1378145	0.1937664	0.1856928	0.5137063	0.1314307	0.1802478	0.1030792	0.6845663	0.3133684	1.793842	2.458881	0.1749906	1.44386	0.8561772	0.2069095	0.1684191	0.1378145	0.1378145	0.1182876	0.4990612	0.4355989	0.2005257	0.3332707	1.282952	Ts65Dn	Memantine	S/C	t-SC-m

Mouse of the Ts65Dn genotype, and saline treatment group with the highest Tau expression (use multi-sorting):

df %>% 
  arrange(desc(Genotype), desc(Treatment), desc(Tau_N)) %>%
  slice_head(n = 6) %>%
  formatted_table()

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
J3295_14	0.2212424	0.4128944	0.2439741	1.876347	2.384088	0.2088967	0.1736234	2.086028	0.1920439	0.9225946	0.2306486	0.2631785	0.2243778	0.2774838	0.6650990	0.4795219	1.077014	1.115030	0.4346463	0.5647658	0.2567117	0.3131491	0.1722516	0.7818930	1.558887	0.8728199	0.2380952	0.2704292	0.5851460	0.1634333	0.3411719	1.571821	0.6984127	0.3564570	0.3084460	0.5457574	0.4805017	0.2580835	0.4266118	0.2584754	0.2159514	0.3015873	0.4904958	0.1975667	0.7848193	0.1754131	2.659706	0.3410205	0.6426366	0.7831850	0.5382241	0.2120937	0.1614309	0.1252951	0.1725077	0.1937534	0.4142001	0.1492646	0.2044670	0.1245687	0.6217541	0.3522789	1.498820	2.609769	0.1850372	1.301071	0.9892864	0.3067006	0.2222626	NA	0.1252951	0.1962956	0.3976757	0.3359361	0.2513165	0.3653532	1.404031	Ts65Dn	Saline	S/C	t-SC-s
J3295_4	0.3560120	0.5851106	0.3136203	2.545074	3.794452	0.2211174	0.1765014	3.232369	0.2311919	1.1564831	0.3342928	0.3078634	0.2894152	0.2881068	0.9255528	0.6481748	1.468533	1.370012	0.4508701	0.7078372	0.2580139	0.3812639	0.1690436	1.2771163	2.544420	1.1822583	0.2701819	0.2984430	0.7913123	0.1725762	0.4359545	2.507131	1.1441842	0.4316368	0.3643857	0.6835012	0.5479524	0.3324611	0.5781761	0.3110035	0.2629857	0.4164595	0.5737276	0.2348905	0.9843509	0.1625809	2.392229	0.3113629	0.6788467	0.8755011	0.5740826	0.1790009	0.1871724	0.1258094	0.1652791	0.2077552	0.4128122	0.1212612	0.2247148	0.1396855	0.5862627	0.3575393	1.508017	2.502081	0.1549491	1.238128	0.9303885	0.2401326	0.1686710	NA	0.1258094	0.1125501	0.4282300	0.2957909	0.1809282	0.2553191	1.379201	Ts65Dn	Saline	S/C	t-SC-s
J3295_11	0.2548604	0.4635914	0.2548604	2.092082	2.600035	0.2117356	0.1712619	2.483740	0.2073171	1.0579710	0.2656416	0.2940969	0.2499116	0.2612230	0.7462001	0.5106045	1.220926	1.241958	0.4227642	0.6382114	0.2557441	0.3308590	0.1901732	0.8964298	1.822906	0.9931071	0.2363026	0.2492047	0.6417462	0.1656062	0.3722163	1.828208	0.8200778	0.3801697	0.3204312	0.5993284	0.5081301	0.2700601	0.4379639	0.2605161	0.2391304	0.3407565	0.5270414	0.2094329	0.7879001	0.1781303	2.630825	0.3190623	0.6545480	0.7372263	0.5329871	0.1966592	0.1827625	0.1158057	0.1603032	0.1893599	0.4112858	0.1348961	0.2077485	0.1344750	0.5036496	0.3263616	1.323554	2.578046	0.1671814	1.261651	0.9629422	0.2755474	0.1904829	NA	0.1158057	0.1833240	0.3740876	0.3187816	0.2046603	0.3283268	1.364823	Ts65Dn	Saline	S/C	t-SC-s
J3295_12	0.2721980	0.4741630	0.2516376	2.161390	2.801492	0.2512737	0.1824964	2.512736	0.2163392	1.0811499	0.2703785	0.2851164	0.2498180	0.2525473	0.7498180	0.5243814	1.218705	1.361354	0.4152111	0.6451965	0.2520015	0.3386099	0.1812227	0.9588792	1.879913	0.9748908	0.2454512	0.2621907	0.6935953	0.1915939	0.3609898	1.883370	0.8542576	0.3802766	0.3382460	0.6146288	0.5191048	0.2734716	0.5800582	0.2758370	0.2350801	0.3462518	0.5183770	0.1943331	0.7630961	0.1704216	2.593227	0.3188666	0.6320663	0.7560470	0.5466482	0.1883898	0.1669661	0.1136144	0.1615757	0.1871458	0.4020733	0.1306151	0.2051140	0.1221838	0.5126469	0.3441603	1.275605	2.534347	0.1695923	1.254872	0.9836904	0.2832066	0.1904630	NA	0.1136144	0.1756738	0.3752592	0.3256393	0.2004147	0.2934347	1.364478	Ts65Dn	Saline	S/C	t-SC-s
J3295_7	0.3184478	0.5097013	0.2905759	2.314752	3.041115	0.2291346	0.1758546	2.881429	0.2060363	1.0883893	0.3058208	0.2996612	0.2814906	0.2770249	0.8500154	0.5708346	1.367570	1.271943	0.4317832	0.6510625	0.2597783	0.3429319	0.1806283	1.0418848	2.218509	1.0734524	0.2389898	0.2796427	0.7283646	0.1707730	0.3948260	2.175239	0.9675085	0.4006775	0.3341546	0.6458269	0.5249461	0.2958115	0.5637512	0.2858023	0.2510009	0.3657222	0.5617493	0.2189847	0.9053770	0.1639131	2.497146	0.3221188	0.6628617	0.8015420	0.5495144	0.1802343	0.1786322	0.1278662	0.1638130	0.1964554	0.4020226	0.1273656	0.2155803	0.1356764	0.5640332	0.3415440	1.410534	2.482728	0.1564033	1.196055	0.8810454	0.2363072	0.1724242	NA	0.1278662	0.1272654	0.4051267	0.3071994	0.1923501	0.2699509	1.340743	Ts65Dn	Saline	S/C	t-SC-s
J3295_5	0.3298292	0.5730618	0.3346912	2.548357	3.808279	0.2290407	0.1816032	3.299343	0.2289093	1.1930355	0.3294350	0.3137976	0.2854139	0.2696452	0.8884363	0.6582129	1.516557	1.417608	0.4536137	0.7105125	0.2588699	0.3609724	0.1877792	1.2617608	2.520631	1.1777924	0.2703022	0.2965834	0.7871222	0.1681997	0.4554534	2.487516	1.1074901	0.4323259	0.3796321	0.6919842	0.5484888	0.3224704	0.5802891	0.3137976	0.2693824	0.4143233	0.5582129	0.2278800	0.9874800	0.1523017	2.410184	0.3088785	0.6921139	0.8786930	0.5841667	0.1784869	0.1871135	0.1215360	0.1630659	0.1999389	0.3983510	0.1223758	0.2089472	0.1368043	0.5514925	0.3497977	1.440644	2.160165	0.1533705	1.189480	0.9071685	0.2410871	0.1633712	NA	0.1215360	0.1067257	0.3974349	0.2977327	0.1782579	0.2462783	1.390946	Ts65Dn	Saline	S/C	t-SC-s

Or to filter for the row:

my_answer <- df %>% 
  filter(Genotype == "Ts65Dn") %>%
  filter(Treatment == "Saline") %>%
  filter(Tau_N == max(Tau_N, na.rm = T))
formatted_table(my_answer)

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
J3295_14	0.2212424	0.4128944	0.2439741	1.876347	2.384088	0.2088967	0.1736234	2.086028	0.1920439	0.9225946	0.2306486	0.2631785	0.2243778	0.2774838	0.665099	0.4795219	1.077014	1.11503	0.4346463	0.5647658	0.2567117	0.3131491	0.1722516	0.781893	1.558887	0.8728199	0.2380952	0.2704292	0.585146	0.1634333	0.3411719	1.571821	0.6984127	0.356457	0.308446	0.5457574	0.4805017	0.2580835	0.4266118	0.2584754	0.2159514	0.3015873	0.4904958	0.1975667	0.7848193	0.1754131	2.659706	0.3410205	0.6426366	0.783185	0.5382241	0.2120937	0.1614309	0.1252951	0.1725077	0.1937534	0.4142001	0.1492646	0.204467	0.1245687	0.6217541	0.3522789	1.49882	2.609769	0.1850372	1.301071	0.9892864	0.3067006	0.2222626	NA	0.1252951	0.1962956	0.3976757	0.3359361	0.2513165	0.3653532	1.404031	Ts65Dn	Saline	S/C	t-SC-s

Exercise 3

1. An relative expression level > 0.5 would be considered a high expression level. How many mice do have a high expression level for DYRK1A?
   
2. Apply this calculation for all proteins. For which protein do you observe a count of 218? Hint: you can calculate the mean and the sum for multiple columns at once with the colMeans and colSums functions.
   
3. The average pELK expression is higher than pERK. But how many mice do have higher expression levels for pELK than 0.75 AND higher expression levels for pERK than 0.25?

You can use the sum function to count how many times the value for DYRK1A is higher than 0.5. However, there are NA values in this column, so you will have to use the na.rm = argument in the sum function.

summary(df$DYRK1A_N) # to check whether there NA values in this column

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##  0.1453  0.2881  0.3664  0.4258  0.4877  2.5164       3

print("Yes, there are 3 NA values in this column!")

## [1] "Yes, there are 3 NA values in this column!"

sum(df$DYRK1A_N > 0.5, na.rm = TRUE)

## [1] 255

Note: the nrow function does not work in this case, because it will include the rows with NA values. Compare with the previous answer:

nrow(df[df$DYRK1A_N > 0.5, ])

## [1] 258

The protein that has a higher relative expression value than 0.5 in 218 mice.

only_nums <- select_if(df, is.numeric) # select only columns with numeric values
colSums(only_nums > 0.5, na.rm = TRUE)

##        DYRK1A_N         ITSN1_N          BDNF_N           NR1_N          NR2A_N 
##             255             726               0            1077            1077 
##          pAKT_N         pBRAF_N       pCAMKII_N         pCREB_N          pELK_N 
##               1               0            1077               0            1076 
##          pERK_N          pJNK_N          PKCA_N          pMEK_N          pNR1_N 
##             449               0               0               0            1077 
##         pNR2A_N         pNR2B_N        pPKCAB_N          pRSK_N           AKT_N 
##             952            1074            1077             195            1009 
##          BRAF_N        CAMKII_N          CREB_N           ELK_N           ERK_N 
##             167              12               0            1061            1077 
##         GSK3B_N           JNK_N           MEK_N          TRKA_N           RSK_N 
##            1076               0               0            1003               0 
##           APP_N      Bcatenin_N          SOD1_N          MTOR_N           P38_N 
##              71            1062             506             225             165 
##         pMTOR_N         DSCR1_N         AMPKA_N          NR2B_N         pNUMB_N 
##            1062             922              39             868              22 
##        RAPTOR_N         TIAM1_N        pP70S6_N          NUMB_N         P70S6_N 
##               5             126             229               0            1077 
##        pGSK3B_N         pPKCG_N          CDK5_N            S6_N        ADARB1_N 
##               0            1080               1             347            1080 
##    AcetylH3K9_N          RRP1_N           BAX_N           ARC_N         ERBB4_N 
##              79               1               0               0               0 
##          nNOS_N           Tau_N          GFAP_N         GluR3_N         GluR4_N 
##               0               7               0               0               1 
##          IL1B_N         P3525_N        pCASP9_N         PSD95_N          SNCA_N 
##             669               0            1080            1080               0 
##     Ubiquitin_N pGSK3B_Tyr216_N           SHH_N           BAD_N          BCL2_N 
##            1080            1080               0               0               0 
##           pS6_N         pCFOS_N           SYP_N       H3AcK18_N          EGR1_N 
##               0               0             218               0               0 
##        H3MeK4_N          CaNA_N 
##               0            1080

Or in tidyverse style:

df %>%
  summarise(
    across(
      .cols = where(is.numeric),
      .fns = ~ sum(. > 0.5, na.rm = TRUE)
    )
  )

## # A tibble: 1 × 77
##   DYRK1A_N ITSN1_N BDNF_N NR1_N NR2A_N pAKT_N pBRAF_N pCAMKII_N pCREB_N pELK_N
##      <int>   <int>  <int> <int>  <int>  <int>   <int>     <int>   <int>  <int>
## 1      255     726      0  1077   1077      1       0      1077       0   1076
## # ℹ 67 more variables: pERK_N <int>, pJNK_N <int>, PKCA_N <int>, pMEK_N <int>,
## #   pNR1_N <int>, pNR2A_N <int>, pNR2B_N <int>, pPKCAB_N <int>, pRSK_N <int>,
## #   AKT_N <int>, BRAF_N <int>, CAMKII_N <int>, CREB_N <int>, ELK_N <int>,
## #   ERK_N <int>, GSK3B_N <int>, JNK_N <int>, MEK_N <int>, TRKA_N <int>,
## #   RSK_N <int>, APP_N <int>, Bcatenin_N <int>, SOD1_N <int>, MTOR_N <int>,
## #   P38_N <int>, pMTOR_N <int>, DSCR1_N <int>, AMPKA_N <int>, NR2B_N <int>,
## #   pNUMB_N <int>, RAPTOR_N <int>, TIAM1_N <int>, pP70S6_N <int>, …

Also here, you can use the sum function to count how many times the value for pELK is higher than 0.75 anf for pERK is lower than 0.25.

sum(df$pELK_N > 0.75 & df$pERK_N > 0.25, na.rm = T)

## [1] 1040

Exersise 4

Note that this exercise differs a bit from the Excel counterpart. We do not use conditional formatting but selection of rows instead.

1. Select rows with a relative expression value higher than 2.3 for the pCASP9 protein. Which treatment is mostly found for these selected proteins?
   
2. Select rows with duplicate MouseIDs. Are there any duplicate MouseIDs?
   
3. Select the following columns: MouseID, APP_N, NR1_N, pCREB_N, S6_N, and Genotype.
   
4. Select everything but the columns with relative expression measurements. Hint: the column names of the column with relative expression values all have something in common.

Select rows with a relative expression value higher than 2.3 for the pCASP9 protein:

df %>%
  filter(pCASP9_N > 2.3) %>%
  formatted_table()

MouseID chr	DYRK1A_N dbl	ITSN1_N dbl	BDNF_N dbl	NR1_N dbl	NR2A_N dbl	pAKT_N dbl	pBRAF_N dbl	pCAMKII_N dbl	pCREB_N dbl	pELK_N dbl	pERK_N dbl	pJNK_N dbl	PKCA_N dbl	pMEK_N dbl	pNR1_N dbl	pNR2A_N dbl	pNR2B_N dbl	pPKCAB_N dbl	pRSK_N dbl	AKT_N dbl	BRAF_N dbl	CAMKII_N dbl	CREB_N dbl	ELK_N dbl	ERK_N dbl	GSK3B_N dbl	JNK_N dbl	MEK_N dbl	TRKA_N dbl	RSK_N dbl	APP_N dbl	Bcatenin_N dbl	SOD1_N dbl	MTOR_N dbl	P38_N dbl	pMTOR_N dbl	DSCR1_N dbl	AMPKA_N dbl	NR2B_N dbl	pNUMB_N dbl	RAPTOR_N dbl	TIAM1_N dbl	pP70S6_N dbl	NUMB_N dbl	P70S6_N dbl	pGSK3B_N dbl	pPKCG_N dbl	CDK5_N dbl	S6_N dbl	ADARB1_N dbl	AcetylH3K9_N dbl	RRP1_N dbl	BAX_N dbl	ARC_N dbl	ERBB4_N dbl	nNOS_N dbl	Tau_N dbl	GFAP_N dbl	GluR3_N dbl	GluR4_N dbl	IL1B_N dbl	P3525_N dbl	pCASP9_N dbl	PSD95_N dbl	SNCA_N dbl	Ubiquitin_N dbl	pGSK3B_Tyr216_N dbl	SHH_N dbl	BAD_N dbl	BCL2_N dbl	pS6_N dbl	pCFOS_N dbl	SYP_N dbl	H3AcK18_N dbl	EGR1_N dbl	H3MeK4_N dbl	CaNA_N dbl	Genotype chr	Treatment chr	Behavior chr	class chr
3420_14	0.2295362	0.3843793	0.3359482	1.893929	2.663711	0.2854707	0.2476126	4.316508	0.2738745	1.413711	0.3502729	0.3925648	0.3110505	0.3325375	0.7288540	1.0088677	1.352660	1.194748	0.4737381	0.6330150	0.3250341	0.4331514	0.2752387	0.941678	1.361869	0.8489086	0.2592087	0.3011596	0.6091405	0.2302183	0.3639154	1.570941	0.6821282	0.4965894	0.5303547	0.8932469	0.6811050	0.3465211	0.6306276	0.3574352	0.4004093	0.3772169	0.4662347	0.1480992	0.8403306	0.1778512	1.930578	0.1811570	0.2667769	1.146446	0.2066116	0.2614876	0.1685950	0.1295868	0.1788430	0.1742149	0.2122314	0.1523967	0.2109091	0.0942149	0.8423141	0.3474380	2.322314	2.553058	0.2366942	1.732893	0.9213223	0.3147107	NA	NA	0.1295868	0.2565289	0.5576860	0.3454545	NA	NA	1.196364	Control	Memantine	S/C	c-SC-m
50810A_1	0.4881485	0.8672636	0.4385041	3.174743	4.158349	0.2057545	0.2028575	2.522979	0.2948380	1.441072	0.8847775	0.3774691	0.4076903	0.3078746	1.1045562	1.1848170	2.245523	2.386423	0.4309982	0.9236239	0.3325652	0.3791151	0.1958125	2.658019	4.180932	1.4288912	0.2921385	0.3907032	0.9341585	0.1949565	0.4581248	3.011391	0.3738478	0.4870951	0.4511456	0.8756913	0.5021728	0.4751778	0.5950751	0.4124967	0.3076771	0.4814986	0.2313010	0.3165753	1.6799532	0.2532101	1.245096	0.4141955	0.7393868	1.240746	0.1093730	0.1947802	0.2166548	0.1386089	0.1876699	0.2607386	0.1814798	0.1447154	0.2858338	0.1874608	0.5735497	0.3517504	2.454892	2.503200	0.1558827	1.216613	1.0035551	0.2533774	0.1550044	0.1476850	0.1386089	0.1500690	0.7595884	0.1483124	0.1650006	0.1867498	2.077084	Control	Saline	C/S	c-CS-s
50810A_2	0.4354220	0.8313117	0.4191440	2.987430	3.968701	0.1933882	0.2067123	2.352209	0.2939476	1.393187	0.8817799	0.3580542	0.3979637	0.3175790	1.0576331	1.1102382	2.062095	2.284206	0.4153730	0.8756835	0.3214129	0.3670417	0.1847778	2.524480	3.766451	1.2825090	0.2811891	0.3677330	0.8855509	0.1756018	0.4402615	2.795047	0.3505751	0.4626988	0.3819370	0.8191188	0.4962604	0.4457294	0.5760794	0.3882220	0.2908051	0.4562253	0.2179624	0.3064755	1.6075684	0.2443093	1.234654	0.3953077	0.7156710	1.128277	0.1097872	0.1908949	0.2080697	0.1409730	0.1856767	0.2602925	0.1685841	0.1462322	0.2811653	0.1809927	0.5739584	0.3440710	2.403115	2.530611	0.1687485	1.234120	1.0073137	0.2577451	0.1523133	0.1597502	0.1409730	0.1452872	0.7406525	0.1609828	0.1891281	0.1637768	1.963432	Control	Saline	C/S	c-CS-s
50810A_3	0.4136435	0.7912498	0.4016512	2.889177	3.806858	0.1885621	0.1807280	2.248283	0.3057732	1.321080	0.8312643	0.3380740	0.3679041	0.2703989	1.0279017	1.0762324	2.032120	2.243642	0.3883934	0.8290346	0.3067976	0.3527781	0.1771725	2.393154	3.820718	1.2399060	0.2686513	0.3576594	0.8547668	0.1727130	0.4163553	2.697843	0.3430758	0.4338918	0.3569965	0.7841388	0.4714957	0.4226226	0.5488731	0.3598891	0.2722068	0.4374473	0.2042907	0.3052795	1.5755662	0.2277986	1.305402	0.3834936	0.7287355	1.165187	0.1072185	0.1851882	0.2109744	0.1337380	0.1911765	0.2529738	0.1780593	0.1402966	0.2948916	0.1862474	0.5672560	0.3589702	2.379379	2.484764	0.1578133	1.237086	1.0220792	0.2486557	0.1480365	0.1487290	0.1337380	0.1385856	0.7221362	0.1409076	0.1791592	0.1566726	2.024808	Control	Saline	C/S	c-CS-s
50810A_4	0.3600464	0.6400364	0.3548307	2.699478	4.402931	0.2106962	0.1717030	2.901565	0.2272539	1.164914	0.6811822	0.3307393	0.3759417	0.2709661	0.9158871	0.9795513	1.933687	2.232718	0.4766951	0.7734912	0.2701383	0.3371140	0.1634241	1.739548	3.440434	1.3392665	0.2514281	0.3252753	0.8003146	0.1537379	0.3813230	2.543174	0.3090488	0.4282639	0.3742032	0.7936087	0.4825731	0.3795016	0.5368822	0.3617021	0.2734498	0.3912576	0.2045699	0.2809826	1.4262243	0.2269172	1.651199	0.4062779	0.6088919	1.247021	0.1025143	0.1847147	0.2150543	0.1337463	0.1798331	0.2559971	0.1764212	0.1388379	0.3046559	0.1889140	0.5641699	0.3257572	2.586216	2.465277	0.1479712	1.307700	0.9955383	0.2398824	0.1468164	0.1328014	0.1337463	0.1453992	0.5572411	0.1258202	0.1608315	0.1640859	2.068763	Control	Saline	C/S	c-CS-s
50810A_5	0.3663776	0.6423766	0.3448164	2.688741	4.172732	0.2096944	0.1646267	2.844289	0.2396855	1.140553	0.6505633	0.3290103	0.3683229	0.2571128	0.9310205	0.9391262	1.880117	2.085920	0.4599984	0.7416714	0.2618951	0.3282808	0.1592770	1.750344	3.361757	1.2805382	0.2481154	0.3407636	0.7752290	0.1507660	0.3667018	2.417768	0.3008835	0.4124990	0.3434384	0.7497771	0.4651050	0.3787793	0.5188457	0.3627300	0.2627057	0.3850207	0.2024803	0.2691700	1.3581291	0.2143985	1.560605	0.3834004	0.5993275	1.074031	0.1033270	0.1792429	0.2117491	0.1328272	0.1813318	0.2430835	0.1649259	0.1426097	0.2932185	0.1854079	0.5847047	0.3447802	2.531411	2.535996	0.1543282	1.259540	1.0195139	0.2414531	0.1389413	0.1255413	0.1328272	0.1374637	0.5304428	0.1355785	0.1756254	0.1536149	2.115555	Control	Saline	C/S	c-CS-s
50810A_6	0.3614875	0.5740795	0.3106038	2.393446	3.940574	0.1854934	0.1494845	2.576362	0.2126657	1.096245	0.5949926	0.2953608	0.3343888	0.2335788	0.8557437	0.8695876	1.653755	2.033800	0.4104566	0.6837261	0.2379234	0.2974963	0.1448454	1.668630	3.048822	1.2189249	0.2221649	0.2864507	0.7020619	0.1392489	0.3455817	2.284757	0.2701767	0.3740059	0.2911635	0.6865979	0.4427099	0.3336524	0.4701767	0.3154639	0.2322533	0.3476436	0.1790133	0.2664596	1.4208839	0.2132478	1.586131	0.3800481	0.6130875	1.015583	0.0972041	0.1759695	0.2080369	0.1267662	0.1831847	0.2431105	0.1716605	0.1300230	0.2975248	0.1791262	0.5724020	0.3221766	2.510121	2.738902	0.1456559	1.222768	1.0239503	0.2383004	0.1326285	0.1259645	0.1267662	0.1271169	0.5402846	0.1229081	0.1570799	0.1481611	2.015833	Control	Saline	C/S	c-CS-s

It seems that in this selection of mice most are treated with Saline.

Select rows with duplicate MouseIDs. Are there any duplicate MouseIDs?

df %>%
  group_by(MouseID) %>%
  filter(n() > 1)

## # A tibble: 0 × 82
## # Groups:   MouseID [0]
## # ℹ 82 variables: MouseID <chr>, DYRK1A_N <dbl>, ITSN1_N <dbl>, BDNF_N <dbl>,
## #   NR1_N <dbl>, NR2A_N <dbl>, pAKT_N <dbl>, pBRAF_N <dbl>, pCAMKII_N <dbl>,
## #   pCREB_N <dbl>, pELK_N <dbl>, pERK_N <dbl>, pJNK_N <dbl>, PKCA_N <dbl>,
## #   pMEK_N <dbl>, pNR1_N <dbl>, pNR2A_N <dbl>, pNR2B_N <dbl>, pPKCAB_N <dbl>,
## #   pRSK_N <dbl>, AKT_N <dbl>, BRAF_N <dbl>, CAMKII_N <dbl>, CREB_N <dbl>,
## #   ELK_N <dbl>, ERK_N <dbl>, GSK3B_N <dbl>, JNK_N <dbl>, MEK_N <dbl>,
## #   TRKA_N <dbl>, RSK_N <dbl>, APP_N <dbl>, Bcatenin_N <dbl>, SOD1_N <dbl>, …

There are no duplicates!

Select the following columns: MouseID, APP_N, NR1_N, pCREB_N, S6_N, and Genotype.

df %>% 
  select(MouseID, APP_N, NR1_N, pCREB_N, S6_N, Genotype) %>%
  slice_head(n = 6) %>%
  formatted_table()

MouseID chr	APP_N dbl	NR1_N dbl	pCREB_N dbl	S6_N dbl	Genotype chr
309_1	0.4539098	2.816329	0.2322238	0.3546045	Control
309_2	0.4309403	2.789514	0.2269721	0.3545483	Control
309_3	0.4231873	2.687201	0.2302468	0.3860868	Control
309_4	0.4106149	2.466947	0.2070042	0.2906795	Control
309_5	0.3985498	2.365785	0.1921579	0.3093450	Control
309_6	0.3910472	2.385939	0.1951875	0.3323671	Control

Select everything but the columns with relative expression measurements.

df %>%
  select(-ends_with("_N")) %>%
  slice_head(n = 6) %>%
  formatted_table()

MouseID chr	Genotype chr	Treatment chr	Behavior chr	class chr
309_1	Control	Memantine	C/S	c-CS-m
309_2	Control	Memantine	C/S	c-CS-m
309_3	Control	Memantine	C/S	c-CS-m
309_4	Control	Memantine	C/S	c-CS-m
309_5	Control	Memantine	C/S	c-CS-m
309_6	Control	Memantine	C/S	c-CS-m

Exercise 5

Note that this exercise differs a bit from the Excel counterpart. We do not use a pivot table but the results will be similar.

Group the genotypes of the mice.
Calculate the standard deviation, average and the median of the relative expression of the following genes: - PKCA
- RRP1
- BRAF
- JNK

Round the values to 3 decimals.

First, check whether the columns contain NA values:

proteins <- c("PKCA_N", "RRP1_N", "BRAF_N", "JNK_N") # make a selection of columns to check if there are NA values
summary(df[proteins]) # check the selected columns for NA values

##      PKCA_N           RRP1_N             BRAF_N           JNK_N       
##  Min.   :0.1914   Min.   :-0.06201   Min.   :0.1439   Min.   :0.0463  
##  1st Qu.:0.2818   1st Qu.: 0.14902   1st Qu.:0.2643   1st Qu.:0.2204  
##  Median :0.3130   Median : 0.16210   Median :0.3267   Median :0.2449  
##  Mean   :0.3179   Mean   : 0.16663   Mean   :0.3785   Mean   :0.2416  
##  3rd Qu.:0.3523   3rd Qu.: 0.17741   3rd Qu.:0.4136   3rd Qu.:0.2633  
##  Max.   :0.4740   Max.   : 0.61238   Max.   :2.1334   Max.   :0.3872  
##  NA's   :3                           NA's   :3        NA's   :3

The summary gives the mean and median for these proteins. However, this is the mean and median for all measurements (not for the groups (Saline en Memantine treated) that we are interested in) It seems that only the column of the RRP1 protein does not contain NA values. This means that we have to use the na.rm = argument to calculate the standard deviation for the other three proteins:

df %>%
    group_by(Genotype) %>%
    summarize("St.Dev PKCA" = round(sd(PKCA_N, na.rm = T), 3),
              "Mean PKCA" = round(mean(PKCA_N, na.rm = T), 3),
              "Median PKCA" = round(median(PKCA_N, na.rm = T), 3),
              "SD.Dev RRP1" = round(sd(RRP1_N), 3),
              "Mean RRP1" = round(mean(RRP1_N, na.rm = T), 3),
              "Median RRP1" = round(median(RRP1_N, na.rm = T), 3),
              "SD.Dev BRAF" = round(sd(BRAF_N, na.rm = T), 3),
              "Mean BRAF" = round(mean(BRAF_N, na.rm = T), 3),
              "Median BRAF" = round(median(BRAF_N, na.rm = T), 3),
              "SD.Dev JNK" = round(sd(JNK_N, na.rm = T), 3),
              "Mean JNK" = round(mean(JNK_N, na.rm = T), 3),
              "Median JNK" = round(median(JNK_N, na.rm = T), 3)
              ) %>%
  formatted_table()

Genotype chr	St.Dev PKCA dbl	Mean PKCA dbl	Median PKCA dbl	SD.Dev RRP1 dbl	Mean RRP1 dbl	Median RRP1 dbl	SD.Dev BRAF dbl	Mean BRAF dbl	Median BRAF dbl	SD.Dev JNK dbl	Mean JNK dbl	Median JNK dbl
Control	0.048	0.318	0.312	0.034	0.165	0.159	0.265	0.371	0.302	0.036	0.241	0.247
Ts65Dn	0.057	0.318	0.315	0.029	0.169	0.164	0.143	0.387	0.353	0.031	0.243	0.244

---

Go back to the main page
Go back to the R overview page
⬆️ Back to Top

---

This web page is distributed under the terms of the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Creative Commons License: CC BY-SA 4.0.