add_pcs.RdAdd Principal Components Analysis Loadings to a tidy or triple omics dataset.
add_pcs(
tomic,
value_var = NULL,
center_rows = TRUE,
npcs = NULL,
missing_val_method = "drop_samples",
label_percent_varex = TRUE,
verbose = TRUE
)Either a tidy_omic or triple_omic object
An abundance value to use with hclust
center rows before performing PCA
number of principal component loadings to add to samples (default is number of samples)
Approach to remove missing values:
Drop features with missing values
Drop samples which are missing all features, then drop features
Impute missing values
If true then PCs will be labelled by the percent of variability they explain.
extra reporting messages
A tomic object with principal components added to samples.
add_pcs(brauer_2008_triple, npcs = 5)
#> 40 features dropped due to missing values
#> $features
#> # A tibble: 460 × 4
#> name BP MF systematic_name
#> <chr> <chr> <chr> <chr>
#> 1 YOL029C biological process unknown mole… YOL029C
#> 2 SCW11 cytokinesis, completion of separation gluc… YGL028C
#> 3 YHR036W biological process unknown mole… YHR036W
#> 4 BGL2 cell wall organization and biogenesis gluc… YGR282C
#> 5 ACT1 cell wall organization and biogenesis* stru… YFL039C
#> 6 FKH1 pseudohyphal growth* tran… YIL131C
#> 7 HOC1 cell wall mannoprotein biosynthesis* tran… YJR075W
#> 8 CSN12 adaptation to pheromone during conjugation wit… mole… YJR084W
#> 9 YAL046C biological process unknown mole… YAL046C
#> 10 SLG1 cell wall organization and biogenesis* tran… YOR008C
#> # ℹ 450 more rows
#>
#> $samples
#> # A tibble: 36 × 8
#> sample nutrient DR `PC1 (30%)` `PC2 (24%)` `PC3 (14%)` `PC4 (8%)`
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 G0.05 G 0.05 -0.252 0.00514 0.317 0.0234
#> 2 G0.1 G 0.1 -0.169 -0.0478 0.272 -0.104
#> 3 G0.15 G 0.15 -0.177 -0.0824 0.272 -0.0165
#> 4 G0.2 G 0.2 -0.153 -0.109 0.257 -0.00839
#> 5 G0.25 G 0.25 -0.0111 -0.177 0.179 0.00250
#> 6 G0.3 G 0.3 0.0561 -0.213 0.154 0.0247
#> 7 N0.05 N 0.05 -0.380 0.153 -0.175 0.427
#> 8 N0.1 N 0.1 -0.284 0.0849 -0.255 0.323
#> 9 N0.15 N 0.15 -0.0754 0.0482 -0.320 0.0141
#> 10 N0.2 N 0.2 -0.0200 -0.0235 -0.311 0.0379
#> # ℹ 26 more rows
#> # ℹ 1 more variable: `PC5 (6%)` <dbl>
#>
#> $measurements
#> # A tibble: 16,560 × 3
#> name sample expression
#> <chr> <chr> <dbl>
#> 1 YOL029C G0.05 -0.22
#> 2 SCW11 G0.05 -0.67
#> 3 YHR036W G0.05 -0.91
#> 4 BGL2 G0.05 -0.08
#> 5 ACT1 G0.05 -0.04
#> 6 FKH1 G0.05 -0.57
#> 7 HOC1 G0.05 -0.42
#> 8 CSN12 G0.05 -0.49
#> 9 YAL046C G0.05 0.05
#> 10 SLG1 G0.05 -0.06
#> # ℹ 16,550 more rows
#>
#> $design
#> $design$features
#> # A tibble: 4 × 2
#> variable type
#> <chr> <chr>
#> 1 name feature_primary_key
#> 2 systematic_name character
#> 3 BP character
#> 4 MF character
#>
#> $design$samples
#> # A tibble: 9 × 2
#> variable type
#> <chr> <chr>
#> 1 sample sample_primary_key
#> 2 nutrient character
#> 3 DR numeric
#> 4 PC1 (30%) numeric
#> 5 PC2 (24%) numeric
#> 6 PC3 (14%) numeric
#> 7 PC4 (8%) numeric
#> 8 PC5 (6%) numeric
#> 9 sample numeric
#>
#> $design$measurements
#> # A tibble: 3 × 2
#> variable type
#> <chr> <chr>
#> 1 name feature_primary_key
#> 2 sample sample_primary_key
#> 3 expression numeric
#>
#> $design$feature_pk
#> [1] "name"
#>
#> $design$sample_pk
#> [1] "sample"
#>
#>
#> $unstructured
#> $unstructured$scree_df
#> # A tibble: 36 × 4
#> pc_number eigenvalue fraction_varex pc_label
#> <int> <dbl> <dbl> <glue>
#> 1 1 38.9 0.302 PC1 (30%)
#> 2 2 33.9 0.230 PC2 (24%)
#> 3 3 25.6 0.131 PC3 (14%)
#> 4 4 19.1 0.0730 PC4 (8%)
#> 5 5 18.1 0.0653 PC5 (6%)
#> 6 6 14.9 0.0444 PC6 (4%)
#> 7 7 12.4 0.0305 PC7 (4%)
#> 8 8 11.9 0.0283 PC8 (2%)
#> 9 9 9.73 0.0189 PC9 (2%)
#> 10 10 8.15 0.0133 PC10 (2%)
#> # ℹ 26 more rows
#>
#>
#> attr(,"class")
#> [1] "triple_omic" "tomic" "general"