factR-meta.RdA factRObject-class contains different types of data at the gene, transcript, alternative splicing (AS) and protein domain levels. The functions below are designed to display specific contents of a factRObject.
# S4 method for factR
granges(object, ..., set = NULL)
# S4 method for factR
activeSet(object)
# S4 method for factR
activeSet(object) <- value
# S4 method for factR
listSets(object)
# S4 method for factR
features(object, ..., set = NULL, show_more = FALSE)
# S4 method for factR
genes(object, ..., show_more = FALSE)
# S4 method for factR
gns(object, ..., show_more = FALSE)
# S4 method for factR
transcripts(object, ..., show_more = FALSE)
# S4 method for factR
txs(object, ..., show_more = FALSE)
# S4 method for factR
ase(object, ..., show_more = FALSE)
# S4 method for factR
domains(object, ...)factRObject
One or more features to display. Can be the following:
gene_id: ID of gene to plot
gene_name: Name of gene to plot
transcript_id: ID of transcript to plot
Set metadata to display. Can be "gene", "transcript" or "AS".
Character value of one of the following: "gene", "transcript" or "AS"
`granges`: GenomicRanges object of selected features
`activeSet` and `listSets`: Character value/vector
All other functions: Tibble dataframe containing metadata of selected features
### Load sample factRObject
data("factRsample")
## Prints out activeSet
activeSet(factRsample)
#> [1] "AS"
## Change activeSet
activeSet(factRsample) <- "transcript"
## Returns coordinates and metadata of features as a GenomicRanges object
granges(factRsample) # from activeSet
#> GRanges object with 1149 ranges and 13 metadata columns:
#> seqnames ranges strand | gene_id source
#> <Rle> <IRanges> <Rle> | <character> <factor>
#> [1] chr15 3180731-3180944 * | MSTRG.14523 StringTie
#> [2] chr15 3180731-3180944 * | MSTRG.14523 StringTie
#> [3] chr15 3268547-3277274 + | ENSMUSG00000064373.12 StringTie
#> [4] chr15 3268547-3268768 + | ENSMUSG00000064373.12 StringTie
#> [5] chr15 3274661-3274876 + | ENSMUSG00000064373.12 StringTie
#> ... ... ... ... . ... ...
#> [1145] chr15 7305070-7398395 - | ENSMUSG00000042961.13 StringTie
#> [1146] chr15 7305070-7305219 - | ENSMUSG00000042961.13 StringTie
#> [1147] chr15 7316399-7316482 - | ENSMUSG00000042961.13 StringTie
#> [1148] chr15 7318241-7318350 - | ENSMUSG00000042961.13 StringTie
#> [1149] chr15 7397988-7398395 - | ENSMUSG00000042961.13 StringTie
#> type gene_name match_level score phase
#> <factor> <character> <numeric> <numeric> <integer>
#> [1] transcript <NA> 5 1000 <NA>
#> [2] exon <NA> 5 1000 <NA>
#> [3] transcript Selenop 1 1000 <NA>
#> [4] exon Selenop 1 1000 <NA>
#> [5] exon Selenop 1 1000 <NA>
#> ... ... ... ... ... ...
#> [1145] transcript Egflam 1 1000 <NA>
#> [1146] exon Egflam 1 1000 <NA>
#> [1147] exon Egflam 1 1000 <NA>
#> [1148] exon Egflam 1 1000 <NA>
#> [1149] exon Egflam 1 1000 <NA>
#> transcript_id exon_number ref_gene_id old_gene_id
#> <character> <character> <character> <character>
#> [1] MSTRG.14523.1 <NA> <NA> MSTRG.14523
#> [2] MSTRG.14523.1 1 <NA> MSTRG.14523
#> [3] ENSMUST00000160787.8 <NA> ENSMUSG00000064373.12 MSTRG.14525
#> [4] ENSMUST00000160787.8 1 ENSMUSG00000064373.12 MSTRG.14525
#> [5] ENSMUST00000160787.8 2 ENSMUSG00000064373.12 MSTRG.14525
#> ... ... ... ... ...
#> [1145] ENSMUST00000159726.1 <NA> ENSMUSG00000042961.13 MSTRG.14582
#> [1146] ENSMUST00000159726.1 1 ENSMUSG00000042961.13 MSTRG.14582
#> [1147] ENSMUST00000159726.1 2 ENSMUSG00000042961.13 MSTRG.14582
#> [1148] ENSMUST00000159726.1 3 ENSMUSG00000042961.13 MSTRG.14582
#> [1149] ENSMUST00000159726.1 4 ENSMUSG00000042961.13 MSTRG.14582
#> AStype AS_id
#> <character> <character>
#> [1] <NA> <NA>
#> [2] <NA> <NA>
#> [3] <NA> <NA>
#> [4] <NA> <NA>
#> [5] <NA> <NA>
#> ... ... ...
#> [1145] <NA> <NA>
#> [1146] <NA> <NA>
#> [1147] <NA> <NA>
#> [1148] <NA> <NA>
#> [1149] <NA> <NA>
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
granges(factRsample, "Dab2") # specific features
#> GRanges object with 142 ranges and 13 metadata columns:
#> seqnames ranges strand | gene_id source
#> <Rle> <IRanges> <Rle> | <character> <factor>
#> [1] chr15 6299788-6435800 + | ENSMUSG00000022150.16 StringTie
#> [2] chr15 6299788-6299899 + | ENSMUSG00000022150.16 StringTie
#> [3] chr15 6416806-6416994 + | ENSMUSG00000022150.16 StringTie
#> [4] chr15 6418230-6418369 + | ENSMUSG00000022150.16 StringTie
#> [5] chr15 6419739-6419837 + | ENSMUSG00000022150.16 StringTie
#> ... ... ... ... . ... ...
#> [138] chr15 6424635-6426667 + | ENSMUSG00000022150.16 StringTie
#> [139] chr15 6321926-6322138 * | ENSMUSG00000022150.16 StringTie
#> [140] chr15 6321926-6322138 * | ENSMUSG00000022150.16 StringTie
#> [141] chr15 6408725-6408926 * | ENSMUSG00000022150.16 StringTie
#> [142] chr15 6408725-6408926 * | ENSMUSG00000022150.16 StringTie
#> type gene_name match_level score phase
#> <factor> <character> <numeric> <numeric> <integer>
#> [1] transcript Dab2 1 1000 <NA>
#> [2] exon Dab2 1 1000 <NA>
#> [3] exon Dab2 1 1000 <NA>
#> [4] exon Dab2 1 1000 <NA>
#> [5] exon Dab2 1 1000 <NA>
#> ... ... ... ... ... ...
#> [138] exon Dab2 1 1000 <NA>
#> [139] transcript Dab2 4 1000 <NA>
#> [140] exon Dab2 4 1000 <NA>
#> [141] transcript Dab2 4 1000 <NA>
#> [142] exon Dab2 4 1000 <NA>
#> transcript_id exon_number ref_gene_id old_gene_id
#> <character> <character> <character> <character>
#> [1] ENSMUST00000159552.1 <NA> ENSMUSG00000022150.16 MSTRG.14562
#> [2] ENSMUST00000159552.1 1 ENSMUSG00000022150.16 MSTRG.14562
#> [3] ENSMUST00000159552.1 2 ENSMUSG00000022150.16 MSTRG.14562
#> [4] ENSMUST00000159552.1 3 ENSMUSG00000022150.16 MSTRG.14562
#> [5] ENSMUST00000159552.1 4 ENSMUSG00000022150.16 MSTRG.14562
#> ... ... ... ... ...
#> [138] ENSMUST00000161558.1 4 ENSMUSG00000022150.16 MSTRG.14562
#> [139] MSTRG.14564.1 <NA> <NA> MSTRG.14564
#> [140] MSTRG.14564.1 1 <NA> MSTRG.14564
#> [141] MSTRG.14566.1 <NA> <NA> MSTRG.14566
#> [142] MSTRG.14566.1 1 <NA> MSTRG.14566
#> AStype AS_id
#> <character> <character>
#> [1] <NA> <NA>
#> [2] <NA> <NA>
#> [3] <NA> <NA>
#> [4] <NA> <NA>
#> [5] <NA> <NA>
#> ... ... ...
#> [138] <NA> <NA>
#> [139] <NA> <NA>
#> [140] <NA> <NA>
#> [141] <NA> <NA>
#> [142] <NA> <NA>
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
granges(factRsample, "Dab2", set = "gene") # specific features from different Set
#> GRanges object with 1 range and 13 metadata columns:
#> seqnames ranges strand | gene_id source type
#> <Rle> <IRanges> <Rle> | <character> <factor> <factor>
#> [1] chr15 6299788-6440712 + | ENSMUSG00000022150.16 factR2 gene
#> gene_name match_level score phase transcript_id exon_number
#> <character> <numeric> <numeric> <integer> <character> <character>
#> [1] Dab2 4 NA <NA> <NA> <NA>
#> ref_gene_id old_gene_id AStype AS_id
#> <character> <character> <character> <character>
#> [1] <NA> <NA> <NA> <NA>
#> -------
#> seqinfo: 1 sequence from an unspecified genome; no seqlengths
## Returns metadata of features
features(factRsample) # from activeSet
#> ℹ Set `show_more to TRUE to show more info`
#> # A tibble: 154 × 8
#> transcript_id gene_id gene_name strand width novel cds nmd
#> <chr> <chr> <chr> <fct> <int> <chr> <chr> <chr>
#> 1 ENSMUST00000022746.12 ENSMUSG000000… Osmr - 5491 no no no
#> 2 ENSMUST00000175862.7 ENSMUSG000000… Osmr - 2837 no no no
#> 3 ENSMUST00000176554.1 ENSMUSG000000… Osmr - 908 no no no
#> 4 ENSMUST00000176826.1 ENSMUSG000000… Osmr - 4028 no no no
#> 5 ENSMUST00000177263.1 ENSMUSG000000… Osmr - 6160 no no no
#> 6 ENSMUST00000177478.1 ENSMUSG000000… Osmr - 1727 no no no
#> 7 MSTRG.14573.1 ENSMUSG000000… Osmr * 877 yes no no
#> 8 ENSMUST00000090461.11 ENSMUSG000000… Fyb + 2678 no no no
#> 9 ENSMUST00000159604.1 ENSMUSG000000… Fyb + 771 no no no
#> 10 ENSMUST00000159714.1 ENSMUSG000000… Fyb + 2170 no no no
#> # ℹ 144 more rows
features(factRsample, "Dab2") # specific features
#> ℹ Set `show_more to TRUE to show more info`
#> # A tibble: 16 × 8
#> transcript_id gene_id gene_name strand width novel cds nmd
#> <chr> <chr> <chr> <fct> <int> <chr> <chr> <chr>
#> 1 ENSMUST00000078019.12 ENSMUSG000000… Dab2 + 3793 no no no
#> 2 ENSMUST00000080880.11 ENSMUSG000000… Dab2 + 4670 no no no
#> 3 ENSMUST00000110663.8 ENSMUSG000000… Dab2 + 3838 no no no
#> 4 ENSMUST00000110664.8 ENSMUSG000000… Dab2 + 4457 no no no
#> 5 ENSMUST00000159046.1 ENSMUSG000000… Dab2 + 438 no no no
#> 6 ENSMUST00000159490.7 ENSMUSG000000… Dab2 + 444 no no no
#> 7 ENSMUST00000159552.1 ENSMUSG000000… Dab2 + 922 no no no
#> 8 ENSMUST00000160134.7 ENSMUSG000000… Dab2 + 1460 no no no
#> 9 ENSMUST00000161040.7 ENSMUSG000000… Dab2 + 1184 no no no
#> 10 ENSMUST00000161558.1 ENSMUSG000000… Dab2 + 2119 no no no
#> 11 ENSMUST00000161812.7 ENSMUSG000000… Dab2 + 3774 no no no
#> 12 ENSMUST00000162094.2 ENSMUSG000000… Dab2 + 737 no no no
#> 13 ENSMUST00000162140.1 ENSMUSG000000… Dab2 + 1406 no no no
#> 14 ENSMUST00000163082.1 ENSMUSG000000… Dab2 + 3839 no no no
#> 15 MSTRG.14564.1 ENSMUSG000000… Dab2 * 213 yes no no
#> 16 MSTRG.14566.1 ENSMUSG000000… Dab2 * 202 yes no no
features(factRsample, "Dab2", set = "gene") # specific features from different Set
#> ℹ Set `show_more to TRUE to show more info`
#> # A tibble: 1 × 5
#> gene_id gene_name strand width match_level
#> <chr> <chr> <fct> <int> <dbl>
#> 1 ENSMUSG00000022150.16 Dab2 + 140925 4
### This is the same as:
genes(factRsample, "Dab2")
#> ℹ Set `show_more to TRUE to show more info`
#> # A tibble: 1 × 5
#> gene_id gene_name strand width match_level
#> <chr> <chr> <fct> <int> <dbl>
#> 1 ENSMUSG00000022150.16 Dab2 + 140925 4
## To return protein-coding domains, the protein-coding domains need to be predicted first:
factRsample <- buildCDS(factRsample)
factRsample <- getAAsequence(factRsample)
factRsample <- predictDomains(factRsample, "Dab2")
#> ℹ Set `show_more to TRUE to show more info`
#> Warning: Skipped 6 non-coding transcripts
## Then, the domains of the selected gene can be printed as such:
domains(factRsample, "Dab2")
#> # A tibble: 8 × 6
#> type description eval begin end transcript_id
#> <chr> <chr> <chr> <dbl> <dbl> <chr>
#> 1 DOMAIN PH domain-like 2.7e-42 33 180 ENSMUST00000078019.12
#> 2 DOMAIN PH domain-like 4.9e-42 33 180 ENSMUST00000080880.11
#> 3 DOMAIN PH domain-like 2.7e-42 33 180 ENSMUST00000110663.8
#> 4 DOMAIN PH domain-like 4.7e-42 33 180 ENSMUST00000110664.8
#> 5 DOMAIN PH domain-like 3.9e-43 33 180 ENSMUST00000160134.7
#> 6 DOMAIN PH domain-like 3.8e-43 33 180 ENSMUST00000161040.7
#> 7 DOMAIN PH domain-like 2.5e-42 33 180 ENSMUST00000161812.7
#> 8 DOMAIN PH domain-like 2.6e-21 35 110 ENSMUST00000162094.2
## All outputs can be assigned to a variable and manipulated further using other functions:
ase(factRsample) %>% dplyr::filter(AStype == "CE")
#> ℹ Set `show_more to TRUE to show more info`
#> # A tibble: 37 × 7
#> AS_id gene_id gene_name coord AStype strand width
#> <chr> <chr> <chr> <chr> <fct> <fct> <int>
#> 1 AS00005 ENSMUSG00000064373.12 Selenop chr15:3272755-32… CE + 51
#> 2 AS00029 ENSMUSG00000022186.14 Oxct1 chr15:4059936-40… CE + 61
#> 3 AS00030 ENSMUSG00000022186.14 Oxct1 chr15:4091168-40… CE + 108
#> 4 AS00031 ENSMUSG00000022186.14 Oxct1 chr15:4092411-40… CE + 115
#> 5 AS00033 ENSMUSG00000022186.14 Oxct1 chr15:4094015-40… CE + 95
#> 6 AS00034 ENSMUSG00000022186.14 Oxct1 chr15:4096472-40… CE + 49
#> 7 AS00035 ENSMUSG00000022186.14 Oxct1 chr15:4101127-41… CE + 73
#> 8 AS00036 ENSMUSG00000022186.14 Oxct1 chr15:4101804-41… CE + 76
#> 9 AS00037 ENSMUSG00000022186.14 Oxct1 chr15:4128834-41… CE + 90
#> 10 AS00039 ENSMUSG00000022186.14 Oxct1 chr15:4142792-41… CE + 81
#> # ℹ 27 more rows