Load feature annotation
Arguments
- assay
character, assay abbreviation, one of MotrpacRatTraining6moData::ASSAY_ABBREV
- scratchdir
character, local directory in which to download data from Google Cloud Storage. Current working directory by default. Not used if
assayis "TRNSCRPT", "IMMUNO", or "METAB".
See also
MotrpacRatTraining6moData::FEATURE_TO_GENE, MotrpacRatTraining6moData::FEATURE_TO_GENE_FILT, MotrpacRatTraining6moData::PROT_FEATURE_ANNOT, MotrpacRatTraining6moData::PHOSPHO_FEATURE_ANNOT, MotrpacRatTraining6moData::ACETYL_FEATURE_ANNOT, MotrpacRatTraining6moData::UBIQ_FEATURE_ANNOT, MotrpacRatTraining6moData::TRNSCRPT_FEATURE_ANNOT, MotrpacRatTraining6moData::ATAC_FEATURE_ANNOT, MotrpacRatTraining6moData::METHYL_FEATURE_ANNOT, MotrpacRatTraining6moData::METAB_FEATURE_ID_MAP
Examples
head(load_feature_annotation("UBIQ", scratchdir="/tmp"))
#> protein_id redundant_ids is_contaminant peptide_score
#> 1 XP_017456475.1 XP_017447817.1|XP_017456475.1 FALSE 0.04957858
#> 2 XP_017456475.1 XP_017456475.1|XP_017447817.1 FALSE 0.05035247
#> 3 XP_017456475.1 XP_017456475.1|XP_017447817.1 FALSE 0.03248863
#> 4 XP_017456475.1 XP_017456475.1|XP_017447817.1 FALSE 0.04591368
#> 5 XP_017456475.1 XP_017447817.1|XP_017456475.1 FALSE 0.06269592
#> 6 XP_017456475.1 XP_017447817.1|XP_017456475.1 FALSE 0.03202049
#> sequence organism_name ptm_id
#> 1 LMIPAVTkANSGR RATTUS NORVEGICUS XP_017456475.1_K72k
#> 2 VTGIPTPVVkFYR RATTUS NORVEGICUS XP_017456475.1_K136k
#> 3 ATSTADLLVQGEEVVPAkK RATTUS NORVEGICUS XP_017456475.1_K202k
#> 4 TkTIVSTAQISETR RATTUS NORVEGICUS XP_017456475.1_K205k
#> 5 kIEAHFDAR RATTUS NORVEGICUS XP_017456475.1_K224k
#> 6 SIATVEMVIDGATGQLPHkTPPR RATTUS NORVEGICUS XP_017456475.1_K251k
#> ptm_peptide confident_score confident_site
#> 1 XP_017456475.1_K72k-LMIPAVTkANSGR 99.000 TRUE
#> 2 XP_017456475.1_K136k-VTGIPTPVVkFYR 99.000 TRUE
#> 3 XP_017456475.1_K202k-ATSTADLLVQGEEVVPAkK 1.636 TRUE
#> 4 XP_017456475.1_K205k-TkTIVSTAQISETR 99.000 TRUE
#> 5 XP_017456475.1_K224k-kIEAHFDAR 99.000 TRUE
#> 6 XP_017456475.1_K251k-SIATVEMVIDGATGQLPHkTPPR 99.000 TRUE
#> tissue assay
#> 1 HEART UBIQ
#> 2 HEART UBIQ
#> 3 HEART UBIQ
#> 4 HEART UBIQ
#> 5 HEART UBIQ
#> 6 HEART UBIQ
head(load_feature_annotation("TRNSCRPT", scratchdir="/tmp"))
#> seqname source feature start end score strand frame
#> 1 AABR07022258.1 ensembl gene 405 848 . - .
#> 2 AABR07022620.1 ensembl gene 122 427 . - .
#> 3 AABR07022926.1 ensembl gene 18 85 . + .
#> 4 AABR07024031.1 ensembl gene 18673 58717 . - .
#> 5 AABR07024032.1 ensembl gene 17425 17528 . - .
#> 6 AABR07024040.1 ensembl gene 4281 5213 . + .
#> gene_id gene_version gene_name gene_source gene_biotype
#> 1 ENSRNOG00000055633 1 LOC100910067 ensembl protein_coding
#> 2 ENSRNOG00000058846 1 AABR07022620.1 ensembl protein_coding
#> 3 ENSRNOG00000055717 1 AABR07022926.1 ensembl miRNA
#> 4 ENSRNOG00000017648 7 Vom2r8 ensembl protein_coding
#> 5 ENSRNOG00000056404 1 RF00026 ensembl snRNA
#> 6 ENSRNOG00000061350 1 LOC103690271 ensembl protein_coding
head(load_feature_annotation("METAB"))
#> Using FEATURE_TO_GENE_FILT and METAB_FEATURE_ID_MAP
#> feature_ID kegg_id dataset metabolite_refmet
#> 1 1-Methylhistidine C01152 metab-t-amines 1-Methylhistidine
#> 2 1-methyladenosine C02494 metab-u-hilicpos 1-Methyladenosine
#> 3 1-methyladenosine C02494 metab-u-hilicpos 1-Methyladenosine
#> 4 1-methyladenosine C02494 metab-u-hilicpos 1-Methyladenosine
#> 5 1-methyladenosine C02494 metab-u-hilicpos 1-Methyladenosine
#> 6 1-methyladenosine C02494 metab-u-hilicpos 1-Methyladenosine
#> feature_ID_sample_data feature_ID_da feature_ID_metareg dataset_metareg
#> 1 1-Methylhistidine 1-Methylhistidine 1-Methylhistidine metab-t-amines
#> 2 1-methyladenosine 1-methyladenosine 1-methyladenosine metab-u-hilicpos
#> 3 1-methyladenosine 1-methyladenosine 1-methyladenosine metab-u-hilicpos
#> 4 1-methyladenosine 1-methyladenosine 1-methyladenosine metab-u-hilicpos
#> 5 1-methyladenosine 1-methyladenosine 1-methyladenosine metab-u-hilicpos
#> 6 1-methyladenosine 1-methyladenosine 1-methyladenosine metab-u-hilicpos
#> rt mz neutral_mass formula
#> 1 4.10 340.6000 169.0851 C7H11N3O2
#> 2 7.63 282.1189 281.1124 C11H15N5O4
#> 3 7.66 282.1191 281.1124 C11H15N5O4
#> 4 7.63 282.1191 281.1124 C11H15N5O4
#> 5 7.64 282.1192 281.1124 C11H15N5O4
#> 6 7.67 282.1190 281.1124 C11H15N5O4
#> tissue
#> 1 BAT,HEART,HIPPOC,KIDNEY,LIVER,LUNG,PLASMA,SKM-GN,WAT-SC
#> 2 ADRNL,VENACV
#> 3 BAT
#> 4 COLON
#> 5 CORTEX,OVARY
#> 6 HEART
head(load_feature_annotation("IMMUNO"))
#> Using FEATURE_TO_GENE_FILT and IMMUNO_NORM_DATA_FLAT
#> feature_ID dataset entrez_gene rgd_gene gene_symbol
#> 1 ACTH rat-pituitary 282839 628649 Mc2r
#> 2 ADIPONECTIN ADIPONECTIN 246253 628748 Adipoq
#> 3 AMYLIN rat-metabolic 24476 2854 Iapp
#> 4 BDNF rat-myokine,rat-pituitary 24225 2202 Bdnf
#> 5 C Peptide rat-metabolic 24505 2915 Ins1
#> 6 EGF rat-mag27plex 25313 2542 Egf
#> old_gene_symbol ensembl_gene
#> 1 <NA> ENSRNOG00000016681
#> 2 Acdc;Acrp30;Adid ENSRNOG00000001821
#> 3 DAP ENSRNOG00000012417
#> 4 MGC105254 ENSRNOG00000047466
#> 5 <NA> ENSRNOG00000012052
#> 6 LOC103691699 ENSRNOG00000053979