Add Median Intensity to mass_dataset Object

Source: R/mutate_median_intensity.R

This function calculates the median intensity for each variable in the mass_dataset object based on the specified samples and adds it as a new column to the variable information.

mutate_median_intensity(object, according_to_samples = "all", na.rm = TRUE)

Arguments

object

A mass_dataset object.

according_to_samples

A character vector specifying the samples to consider for the median calculation. Default is "all".

na.rm

Logical, whether to remove NA values before calculating the median. Default is TRUE.

Value

A modified mass_dataset object with added median intensity information.

Author

Xiaotao Shen shenxt1990@outlook.com

Examples

data("expression_data")
data("sample_info")
data("variable_info")

object =
  create_mass_dataset(
    expression_data = expression_data,
    sample_info = sample_info,
    variable_info = variable_info,
  )

object
#> -------------------- 
#> massdataset version: 1.0.33 
#> -------------------- 
#> 1.expression_data:[ 1000 x 8 data.frame]
#> 2.sample_info:[ 8 x 4 data.frame]
#> 8 samples:Blank_3 Blank_4 QC_1 ... PS4P3 PS4P4
#> 3.variable_info:[ 1000 x 3 data.frame]
#> 1000 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M232T937_POS M301T277_POS
#> 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
#> 1 processings in total
#> create_mass_dataset ---------- 
#>       Package         Function.used                Time
#> 1 massdataset create_mass_dataset() 2024-09-06 08:49:53

##calculate median intensity according to all the samples
object2 =
  mutate_median_intensity(object = object, na.rm = TRUE)

object2
#> -------------------- 
#> massdataset version: 1.0.33 
#> -------------------- 
#> 1.expression_data:[ 1000 x 8 data.frame]
#> 2.sample_info:[ 8 x 4 data.frame]
#> 8 samples:Blank_3 Blank_4 QC_1 ... PS4P3 PS4P4
#> 3.variable_info:[ 1000 x 4 data.frame]
#> 1000 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M232T937_POS M301T277_POS
#> 4.sample_info_note:[ 4 x 2 data.frame]
#> 5.variable_info_note:[ 4 x 2 data.frame]
#> 6.ms2_data:[ 0 variables x 0 MS2 spectra]
#> -------------------- 
#> Processing information
#> 2 processings in total
#> create_mass_dataset ---------- 
#>       Package         Function.used                Time
#> 1 massdataset create_mass_dataset() 2024-09-06 08:49:53
#> mutate_median_intensity ---------- 
#>       Package             Function.used                Time
#> 1 massdataset mutate_median_intensity() 2024-09-06 08:49:53

head(extract_variable_info(object))
#>     variable_id        mz        rt
#> 1 M136T55_2_POS 136.06140  54.97902
#> 2    M79T35_POS  79.05394  35.36550
#> 3  M307T548_POS 307.14035 547.56641
#> 4  M183T224_POS 183.06209 224.32777
#> 5   M349T47_POS 349.01584  47.00262
#> 6  M182T828_POS 181.99775 828.35712
head(extract_variable_info(object2))
#>                 variable_id        mz        rt median_intensity
#> M136T55_2_POS M136T55_2_POS 136.06140  54.97902        1676180.4
#> M79T35_POS       M79T35_POS  79.05394  35.36550        2777897.0
#> M307T548_POS   M307T548_POS 307.14035 547.56641         273687.8
#> M183T224_POS   M183T224_POS 183.06209 224.32777        5103244.9
#> M349T47_POS     M349T47_POS 349.01584  47.00262        7169041.1
#> M182T828_POS   M182T828_POS 181.99775 828.35712        4433034.2

##calculate median intensity according to only QC samples
object3 =
  mutate_median_intensity(object = object2,
                according_to_samples =
              get_sample_id(object)[extract_sample_info(object)$class == "QC"])

object3
#> -------------------- 
#> massdataset version: 1.0.33 
#> -------------------- 
#> 1.expression_data:[ 1000 x 8 data.frame]
#> 2.sample_info:[ 8 x 4 data.frame]
#> 8 samples:Blank_3 Blank_4 QC_1 ... PS4P3 PS4P4
#> 3.variable_info:[ 1000 x 5 data.frame]
#> 1000 variables:M136T55_2_POS M79T35_POS M307T548_POS ... M232T937_POS M301T277_POS
#> 4.sample_info_note:[ 4 x 2 data.frame]
#> 5.variable_info_note:[ 5 x 2 data.frame]
#> 6.ms2_data:[ 0 variables x 0 MS2 spectra]
#> -------------------- 
#> Processing information
#> 2 processings in total
#> create_mass_dataset ---------- 
#>       Package         Function.used                Time
#> 1 massdataset create_mass_dataset() 2024-09-06 08:49:53
#> mutate_median_intensity ---------- 
#>       Package             Function.used                       Time
#> 1 massdataset mutate_median_intensity() 2024-09-06 08:49:53.576429
#> 2 massdataset mutate_median_intensity() 2024-09-06 08:49:53.589569

head(extract_variable_info(object3))
#>                 variable_id        mz        rt median_intensity
#> M136T55_2_POS M136T55_2_POS 136.06140  54.97902        1676180.4
#> M79T35_POS       M79T35_POS  79.05394  35.36550        2777897.0
#> M307T548_POS   M307T548_POS 307.14035 547.56641         273687.8
#> M183T224_POS   M183T224_POS 183.06209 224.32777        5103244.9
#> M349T47_POS     M349T47_POS 349.01584  47.00262        7169041.1
#> M182T828_POS   M182T828_POS 181.99775 828.35712        4433034.2
#>               median_intensity.1
#> M136T55_2_POS          1447844.3
#> M79T35_POS             2063212.8
#> M307T548_POS            342037.7
#> M183T224_POS                  NA
#> M349T47_POS            6417851.6
#> M182T828_POS           3662819.1