cor_mass_dataset
cor_mass_dataset(
x,
y = NULL,
margin = c("variable", "sample"),
use = c("everything", "all.obs", "complete.obs", "na.or.complete",
"pairwise.complete.obs"),
method = c("spearman", "pearson", "kendall"),
data_type = c("wider", "longer"),
p_adjust_method = c(c("BH", "holm", "hochberg", "hommel", "bonferroni", "BY", "fdr",
"none"))
)mass_dataset class
NULL
sample or variable
an optional character string giving a method for computing covariances in the presence of missing values. This must be (an abbreviation of) one of the strings "everything", "all.obs", "complete.obs", "na.or.complete", or "pairwise.complete.obs".
a character string indicating which correlation coefficient (or covariance) is to be computed. One of "pearson" (default), "kendall", or "spearman": can be abbreviated.
wider or longer
see ?p.adjust
dist returns an object of class "dist".
library(massdataset)
library(magrittr)
library(dplyr)
data("liver_aging_pos")
liver_aging_pos
#> --------------------
#> massdataset version: 0.01
#> --------------------
#> 1.expression_data:[ 21607 x 24 data.frame]
#> 2.sample_info:[ 24 x 4 data.frame]
#> 3.variable_info:[ 21607 x 3 data.frame]
#> 4.sample_info_note:[ 4 x 2 data.frame]
#> 5.variable_info_note:[ 3 x 2 data.frame]
#> 6.ms2_data:[ 0 variables x 0 MS2 spectra]
#> --------------------
#> Processing information (extract_process_info())
#> 1 processings in total
#> Creation ----------
#> Package Function.used Time
#> 1 massdataset create_mass_dataset() 2021-12-23 00:24:02
qc_id <-
liver_aging_pos %>%
activate_mass_dataset(what = "sample_info") %>%
dplyr::filter(group == "QC") %>%
dplyr::pull(sample_id)
object <-
mutate_rsd(liver_aging_pos, according_to_samples = qc_id)
###only remain the features with rt > 100, mz > 150 and rsd < 30
object <-
object %>%
activate_mass_dataset(what = "variable_info") %>%
dplyr::filter(rt > 100) %>%
dplyr::filter(mz > 150) %>%
dplyr::filter(rsd < 30)
##only remain the week 24 samples
object <-
object %>%
activate_mass_dataset(what = "sample_info") %>%
dplyr::filter(group == "24W")
dim(object)
#> variables samples
#> 751 10
object <-
object %>%
`+`(1) %>%
log(10) %>%
scale_data(method = "auto")
cor_data <-
object %>%
cor_mass_dataset(margin = "variable", data_type = "wider")
head(cor_data$correlation[,1:5])
#> M150T707 M151T618 M151T609 M152T412 M153T518
#> M150T707 1.00000000 0.2727273 -0.2000000 0.2848485 0.1151515
#> M151T618 0.27272727 1.0000000 -0.2363636 0.6969697 0.1151515
#> M151T609 -0.20000000 -0.2363636 1.0000000 -0.4909091 0.3939394
#> M152T412 0.28484848 0.6969697 -0.4909091 1.0000000 -0.1030303
#> M153T518 0.11515152 0.1151515 0.3939394 -0.1030303 1.0000000
#> M153T577 0.04242424 -0.1757576 0.1636364 -0.3090909 -0.3818182
head(cor_data$p_value[,1:5])
#> M150T707 M151T618 M151T609 M152T412 M153T518
#> M150T707 NA 0.44583834 0.5795840 0.42503815 0.7514197
#> M151T618 0.4458383 NA 0.5108853 0.02509668 0.7514197
#> M151T609 0.5795840 0.51088532 NA 0.14965567 0.2599978
#> M152T412 0.4250382 0.02509668 0.1496557 NA 0.7769985
#> M153T518 0.7514197 0.75141965 0.2599978 0.77699846 NA
#> M153T577 0.9073638 0.62718834 0.6514773 0.38484123 0.2762553
head(cor_data$n[,1:5])
#> M150T707 M151T618 M151T609 M152T412 M153T518
#> M150T707 10 10 10 10 10
#> M151T618 10 10 10 10 10
#> M151T609 10 10 10 10 10
#> M152T412 10 10 10 10 10
#> M153T518 10 10 10 10 10
#> M153T577 10 10 10 10 10
cor_data <-
object %>%
cor_mass_dataset(margin = "variable", data_type = "longer")
head(cor_data)
#> from to correlation p_value number p_adjust
#> 1 M151T618 M150T707 0.2727273 0.44583834 10 0.9625970
#> 2 M151T609 M150T707 -0.2000000 0.57958400 10 0.9723318
#> 3 M151T609 M151T618 -0.2363636 0.51088532 10 0.9683021
#> 4 M152T412 M150T707 0.2848485 0.42503815 10 0.9614259
#> 5 M152T412 M151T618 0.6969697 0.02509668 10 0.6847366
#> 6 M152T412 M151T609 -0.4909091 0.14965567 10 0.8874314