rsnps tutorial

Install and load library

When available on CRAN

install.packages("rsnps")

Or get from Github

install.packages("devtools")
devtools::install_github("ropensci/rsnps")
library(rsnps)

OpenSNP data

All Genotypes

Get genotype data for all users at a particular SNP from OpenSNP:

x <- allgensnp(snp='rs7412')
head(x)
#>     name chromosome position                name   id genotype_id local_genotype
#> 1 rs7412         19 44908822        R.M. Holston   22           8             CC
#> 2 rs7412         19 44908822 Charles G. Sullivan 5326        3834             CC
#> 3 rs7412         19 44908822   Glenn Allen Nolen   19           7             CC
#> 4 rs7412         19 44908822        Angel Harris  495         223             CC
#> 5 rs7412         19 44908822           Mom to AG  387         173             CC
#> 6 rs7412         19 44908822            kevinmcc  285         118             CC

All Phenotypes

Get all phenotypes, their variations, and how many users have data available for a given phenotype

Get all data

x <- allphenotypes(df = TRUE)
head(x)
#>   id characteristic known_variations number_of_users
#> 1  1      Eye color            Brown            1665
#> 2  1      Eye color      Brown-green            1665
#> 3  1      Eye color       Blue-green            1665
#> 4  1      Eye color        Blue-grey            1665
#> 5  1      Eye color            Green            1665
#> 6  1      Eye color             Blue            1665

Output a list, then call the characteristic of interest by 'id' or 'characteristic'

datalist <- allphenotypes()

Get a list of all characteristics you can call

names(datalist)[1:10]
#>  [1] "Eye color"                        "Lactose intolerance"              "Handedness"                      
#>  [4] "white skin"                       "Ability to find a bug in openSNP" "Beard Color"                     
#>  [7] "Hair Color"                       "Ability to Tan"                   "Height"                          
#> [10] "Hair Type"

Get data.frame for ADHD

datalist[["ADHD"]]
#>    id characteristic                                                                                             known_variations
#> 1  29           ADHD                                                                                                        False
#> 2  29           ADHD                                                                                                         True
#> 3  29           ADHD                                                                               Undiagnosed, but probably true
#> 4  29           ADHD                                                                                                           No
#> 5  29           ADHD                                                                                                          Yes
#> 6  29           ADHD                                                                                                Not diagnosed
#> 7  29           ADHD                                                                  Diagnosed as not having but with some signs
#> 8  29           ADHD                                                                                                  Mthfr c677t
#> 9  29           ADHD                                                                                                    Rs1801260
#> 10 29           ADHD                                                                                                  Adult onset
#> 11 29           ADHD                                                                   Diagnosed as "other hyperkinetic disorder"
#> 12 29           ADHD                                                                                 Blonde, european, green eyes
#> 13 29           ADHD                                                                                                      Extreme
#> 14 29           ADHD Diagnosed as hyperactive type, though it is my belief that adhd is simply a normal trait such as eye color. 
#>    number_of_users
#> 1              325
#> 2              325
#> 3              325
#> 4              325
#> 5              325
#> 6              325
#> 7              325
#> 8              325
#> 9              325
#> 10             325
#> 11             325
#> 12             325
#> 13             325
#> 14             325

Get data.frame for mouth size and SAT Writing

datalist[c("mouth size","SAT Writing")]
#> $`mouth size`
#>    id characteristic     known_variations number_of_users
#> 1 120     mouth size               Medium             202
#> 2 120     mouth size                Small             202
#> 3 120     mouth size                Large             202
#> 4 120     mouth size Slightly wide mouth              202
#> 
#> $`SAT Writing`
#>    id characteristic                                        known_variations number_of_users
#> 1  41    SAT Writing                                                     750             110
#> 2  41    SAT Writing                                      Tested before 2005             110
#> 3  41    SAT Writing                                                     800             110
#> 4  41    SAT Writing                                     Country with no sat             110
#> 5  41    SAT Writing                                                     N/a             110
#> 6  41    SAT Writing                                 Never & have ba & above             110
#> 7  41    SAT Writing                                                     720             110
#> 8  41    SAT Writing                         Did well - don't remember score             110
#> 9  41    SAT Writing                                                     511             110
#> 10 41    SAT Writing                                                     760             110
#> 11 41    SAT Writing                                                     780             110
#> 12 41    SAT Writing                                                     700             110
#> 13 41    SAT Writing Not part of sat when i took test in august 1967 at uiuc             110
#> 14 41    SAT Writing                                 Not part of sat in 1961             110
#> 15 41    SAT Writing                                                     620             110
#> 16 41    SAT Writing                                                     560             110

Annotations

Get just the metadata

annotations(snp = 'rs7903146', output = 'metadata')
#>          .id        V1
#> 1       name rs7903146
#> 2 chromosome        10
#> 3   position 112998590

Just from PLOS journals

annotations(snp = 'rs7903146', output = 'plos')[c(1:2),]
#>                   author
#> 1        Maggie C. Y. Ng
#> 2 André Gustavo P. Sousa
#>                                                                                                                                      title
#> 1 Meta-Analysis of Genome-Wide Association Studies in African Americans Provides Insights into the Genetic Architecture of Type 2 Diabetes
#> 2                                  Genetic Variants of Diabetes Risk and Incident Cardiovascular Events in Chronic Coronary Artery Disease
#>           publication_date number_of_readers                                          url                          doi
#> 1 2014-08-07T00:00:00.000Z             11650 https://doi.org/10.1371/journal.pgen.1004517 10.1371/journal.pgen.1004517
#> 2 2011-01-20T00:00:00.000Z              2482 https://doi.org/10.1371/journal.pone.0016341 10.1371/journal.pone.0016341

Just from SNPedia

annotations(snp = 'rs7903146', output = 'snpedia')
#>                                               url                                                          summary
#> 1 http://www.snpedia.com/index.php/Rs7903146(C;C) Normal (lower) risk of Type 2 Diabetes and Gestational Diabetes.
#> 2 http://www.snpedia.com/index.php/Rs7903146(C;T)     1.4x increased risk for diabetes (and perhaps colon cancer).
#> 3 http://www.snpedia.com/index.php/Rs7903146(T;T)                            2x increased risk for Type-2 diabetes

Get all annotations

annotations(snp = 'rs7903146', output = 'all')[1:5,]
#>        .id              author
#> 1 mendeley           T E Meyer
#> 2 mendeley      Camilla Cervin
#> 3 mendeley Nicholette D Palmer
#> 4 mendeley      Ashis K Mondal
#> 5 mendeley        Julian Munoz
#>                                                                                                                                title
#> 1                                                Diabetes genes and prostate cancer in the Atherosclerosis Risk in Communities study
#> 2                                                        Diabetes in Adults , Type 1 Diabetes , and Type 2 Diabetes GENETICS OF LADA
#> 3                                Association of TCF7L2 gene polymorphisms with reduced acute insulin response in Hispanic Americans.
#> 4                  Genotype and tissue-specific effects on alternative splicing of the transcription factor 7-like 2 gene in humans.
#> 5 Polymorphism in the transcription factor 7-like 2 (TCF7L2) gene is associated with reduced insulin secretion in nondiabetic women.
#>   publication_year number_of_readers open_access
#> 1             2010                 3        TRUE
#> 2             2008                 2       FALSE
#> 3             2008                 8       FALSE
#> 4             2010                13        TRUE
#> 5             2006                10        TRUE
#>                                                                                                                                      url
#> 1                              http://www.mendeley.com/research/diabetes-genes-prostate-cancer-atherosclerosis-risk-communities-study-4/
#> 2                                        http://www.mendeley.com/research/diabetes-adults-type-1-diabetes-type-2-diabetes-genetics-lada/
#> 3              http://www.mendeley.com/research/association-tcf7l2-gene-polymorphisms-reduced-acute-insulin-response-hispanic-americans/
#> 4        http://www.mendeley.com/research/genotype-tissuespecific-effects-alternative-splicing-transcription-factor-7like-2-gene-humans/
#> 5 http://www.mendeley.com/research/polymorphism-transcription-factor-7like-2-tcf7l2-gene-associated-reduced-insulin-secretion-nondiabet/
#>                                              doi publication_date summary first_author pubmed_link journal trait pvalue
#> 1 19/2/558 [pii]\\r10.1158/1055-9965.EPI-09-0902             <NA>    <NA>         <NA>        <NA>    <NA>  <NA>     NA
#> 2                         10.2337/db07-0299.Leif             <NA>    <NA>         <NA>        <NA>    <NA>  <NA>     NA
#> 3                           10.1210/jc.2007-1225             <NA>    <NA>         <NA>        <NA>    <NA>  <NA>     NA
#> 4                           10.1210/jc.2009-2064             <NA>    <NA>         <NA>        <NA>    <NA>  <NA>     NA
#> 5                              10.2337/db06-0574             <NA>    <NA>         <NA>        <NA>    <NA>  <NA>     NA
#>   pvalue_description confidence_interval
#> 1               <NA>                <NA>
#> 2               <NA>                <NA>
#> 3               <NA>                <NA>
#> 4               <NA>                <NA>
#> 5               <NA>                <NA>

Download

Download genotype data for a user from 23andme or other repo. (not evaluated in this example)

data <- users(df=TRUE)
head(data[[1]])
fetch_genotypes(url = data[[1]][1,"genotypes.download_url"], rows=15)

Genotype user data

Genotype data for one or multiple users

genotypes(snp='rs9939609', userid=1)
#> $snp
#> $snp$name
#> [1] "rs9939609"
#> 
#> $snp$chromosome
#> [1] "16"
#> 
#> $snp$position
#> [1] "53786615"
#> 
#> 
#> $user
#> $user$name
#> [1] "Bastian Greshake Tzovaras"
#> 
#> $user$id
#> [1] 1
#> 
#> $user$genotypes
#> $user$genotypes[[1]]
#> $user$genotypes[[1]]$genotype_id
#> [1] 9
#> 
#> $user$genotypes[[1]]$local_genotype
#> [1] "AT"
genotypes('rs9939609', userid='1,6,8', df=TRUE)
#>    snp_name snp_chromosome snp_position                 user_name user_id genotype_id genotype
#> 1 rs9939609             16     53786615 Bastian Greshake Tzovaras       1           9       AT
#> 2 rs9939609             16     53786615              Nash Parovoz       6           5       AT
#> 3 rs9939609             16     53786615         Samantha B. Clark       8           2       TT
genotypes('rs9939609', userid='1-2', df=FALSE)
#> [[1]]
#> [[1]]$snp
#> [[1]]$snp$name
#> [1] "rs9939609"
#> 
#> [[1]]$snp$chromosome
#> [1] "16"
#> 
#> [[1]]$snp$position
#> [1] "53786615"
#> 
#> 
#> [[1]]$user
#> [[1]]$user$name
#> [1] "Bastian Greshake Tzovaras"
#> 
#> [[1]]$user$id
#> [1] 1
#> 
#> [[1]]$user$genotypes
#> [[1]]$user$genotypes[[1]]
#> [[1]]$user$genotypes[[1]]$genotype_id
#> [1] 9
#> 
#> [[1]]$user$genotypes[[1]]$local_genotype
#> [1] "AT"
#> 
#> 
#> 
#> 
#> 
#> [[2]]
#> [[2]]$snp
#> [[2]]$snp$name
#> [1] "rs9939609"
#> 
#> [[2]]$snp$chromosome
#> [1] "16"
#> 
#> [[2]]$snp$position
#> [1] "53786615"
#> 
#> 
#> [[2]]$user
#> [[2]]$user$name
#> [1] "Senficon"
#> 
#> [[2]]$user$id
#> [1] 2
#> 
#> [[2]]$user$genotypes
#> list()

Phenotype user data

Get phenotype data for one or multiple users

phenotypes(userid=1)$phenotypes[1:3]
#> $`Caffeine dependence`
#> $`Caffeine dependence`$phenotype_id
#> [1] 538
#> 
#> $`Caffeine dependence`$variation
#> [1] "No"
#> 
#> 
#> $`hair on ear`
#> $`hair on ear`$phenotype_id
#> [1] 254
#> 
#> $`hair on ear`$variation
#> [1] "No"
#> 
#> 
#> $`Third Nipple`
#> $`Third Nipple`$phenotype_id
#> [1] 259
#> 
#> $`Third Nipple`$variation
#> [1] "None"
phenotypes(userid='1,6,8', df=TRUE)[[1]][1:10,]
#>                                phenotype phenotypeID                                                           variation
#> 1                    Caffeine dependence         538                                                                  No
#> 2                            hair on ear         254                                                                  No
#> 3                           Third Nipple         259                                                                None
#> 4                             Alcoholism         485                                                                None
#> 5         Alcohol Consumption (per week)         484                                                                   0
#> 6  Allergy to artificial grape flavoring         352                                                                  No
#> 7                       inverted nipples         583                                                                None
#> 8    Do you prefer python, matlab, or R?         585                                                          Python & R
#> 9                      Political Compass         276 Economic Left/Right: -8.88  Social Libertarian/Authoritarian: -9.49
#> 10               Sweat eating spicy food         219                                                                 Yes
out <- phenotypes(userid='1-8', df=TRUE)
lapply(out, head)
#> $`Bastian Greshake Tzovaras`
#>                               phenotype phenotypeID variation
#> 1                   Caffeine dependence         538        No
#> 2                           hair on ear         254        No
#> 3                          Third Nipple         259      None
#> 4                            Alcoholism         485      None
#> 5        Alcohol Consumption (per week)         484         0
#> 6 Allergy to artificial grape flavoring         352        No
#> 
#> $Senficon
#>   phenotype phenotypeID variation
#> 1   no data     no data   no data
#> 
#> $`no info on user_3`
#>   phenotype phenotypeID variation
#> 1   no data     no data   no data
#> 
#> $`no info on user_4`
#>   phenotype phenotypeID variation
#> 1   no data     no data   no data
#> 
#> $`no info on user_5`
#>   phenotype phenotypeID variation
#> 1   no data     no data   no data
#> 
#> $`Nash Parovoz`
#>                          phenotype phenotypeID        variation
#> 1         Y-DNA Haplogroup (ISOGG)         150        J-FGC5206
#> 2  The Dress: Perception of colour         338   White and gold
#> 3           Number of wisdom teeth          57                4
#> 4 Ability to find a bug in openSNP           5   extremely high
#> 5              Lactose intolerance           2 lactose-tolerant
#> 6                       white skin           4        Caucasian
#> 
#> $`no info on user_7`
#>   phenotype phenotypeID variation
#> 1   no data     no data   no data
#> 
#> $`Samantha B. Clark`
#>                             phenotype phenotypeID           variation
#> 1                            Gambling         539                  No
#> 2                 Caffeine dependence         538                  No
#> 3            Dietary supplements used         534                 b12
#> 4                                Diet         533 Vegan / plant-based
#> 5                   Tooth sensitivity         532         Sweet, cold
#> 6 OCD - Obsessive-Compulsive Disorder         555                  No

All known variations

Get all known variations and all users sharing that phenotype for one phenotype(-ID).

phenotypes_byid(phenotypeid=12, return_ = 'desc')
#> $id
#> [1] 12
#> 
#> $characteristic
#> [1] "Beard Color"
#> 
#> $description
#> [1] "coloration of facial hair"
phenotypes_byid(phenotypeid=12, return_ = 'knownvars')
#> $known_variations
#> $known_variations[[1]]
#> [1] "Red"
#> 
#> $known_variations[[2]]
#> [1] "Blonde"
#> 
#> $known_variations[[3]]
#> [1] "Red-brown"
#> 
#> $known_variations[[4]]
#> [1] "Red-blonde-brown-black(in diferent parts i have different color,for example near the lips blond-red"
#> 
#> $known_variations[[5]]
#> [1] "No beard-female"
#> 
#> $known_variations[[6]]
#> [1] "Brown-black"
#> 
#> $known_variations[[7]]
#> [1] "Blonde-brown"
#> 
#> $known_variations[[8]]
#> [1] "Black"
#> 
#> $known_variations[[9]]
#> [1] "Dark brown with minor blondish-red"
#> 
#> $known_variations[[10]]
#> [1] "Brown-grey"
#> 
#> $known_variations[[11]]
#> [1] "Red-blonde-brown-black"
#> 
#> $known_variations[[12]]
#> [1] "Blond-brown"
#> 
#> $known_variations[[13]]
#> [1] "Brown, some red"
#> 
#> $known_variations[[14]]
#> [1] "Brown"
#> 
#> $known_variations[[15]]
#> [1] "Brown-gray"
#> 
#> $known_variations[[16]]
#> [1] "Never had a beard"
#> 
#> $known_variations[[17]]
#> [1] "I'm a woman"
#> 
#> $known_variations[[18]]
#> [1] "Black-brown-blonde"
#> 
#> $known_variations[[19]]
#> [1] "Was red-brown now mixed with gray,"
#> 
#> $known_variations[[20]]
#> [1] "Red-blonde-brown"
#> 
#> $known_variations[[21]]
#> [1] "Dark brown w/few blonde & red hairs"
#> 
#> $known_variations[[22]]
#> [1] "Dark blonde with red and light blonde on goatee area."
#> 
#> $known_variations[[23]]
#> [1] "Black with few red hairs"
#> 
#> $known_variations[[24]]
#> [1] "Black, graying"
#> 
#> $known_variations[[25]]
#> [1] "Red, moustache still is, beard mostly white"
#> 
#> $known_variations[[26]]
#> [1] "Blonde/brown-some black-and red on chin-all starting to gray"
#> 
#> $known_variations[[27]]
#> [1] "Dark brown"
#> 
#> $known_variations[[28]]
#> [1] "Every possible color, most hair shafts have more than one color at different points along the shaft"
#> 
#> $known_variations[[29]]
#> [1] "Black with few white hairs"
#> 
#> $known_variations[[30]]
#> [1] "Brown ginger"
#> 
#> $known_variations[[31]]
#> [1] "Dark blonde"
#> 
#> $known_variations[[32]]
#> [1] "Black - going white due to age"
#> 
#> $known_variations[[33]]
#> [1] "N/a"
phenotypes_byid(phenotypeid=12, return_ = 'users')[1:10,]
#>    user_id                                                                                           variation
#> 1       22                                                                                                 Red
#> 2        1                                                                                              Blonde
#> 3       26                                                                                           red-brown
#> 4       10 Red-Blonde-Brown-Black(in diferent parts i have different color,for example near the lips blond-red
#> 5       14                                                                                     No beard-female
#> 6       42                                                                                         Brown-black
#> 7       45 Red-Blonde-Brown-Black(in diferent parts i have different color,for example near the lips blond-red
#> 8       16                                                                                        blonde-brown
#> 9        8                                                                                     No beard-female
#> 10     661                                                                                         Brown-black

NCBI SNP data

dbSNP

Query NCBI's dbSNP for information on a set of SNPs.

An example with four markers, where one has been merged, and one has been withdrawn from NCBI.

snps <- c("rs332", "rs420358", "rs1837253", "rs1209415715", "rs111068718")
(dbsnp_info <- ncbi_snp_query(snps))
#> # A tibble: 4 × 16
#>   query  chromosome     bp class rsid  gene  alleles ancestral_allele variation_allele seqname hgvs  assembly ref_seq minor    maf
#>   <chr>  <chr>       <dbl> <chr> <chr> <chr> <chr>   <chr>            <chr>            <chr>   <chr> <chr>    <chr>   <chr>  <dbl>
#> 1 rs332  7          1.18e8 del   rs12… "CFT… TTT, d… TTT              delTTT           NC_000… NC_0… GRCh38.… <NA>    <NA>  NA    
#> 2 rs420… 1          4.03e7 snv   rs42… ""    A,C,G,T A                C,G,T            NC_000… NC_0… GRCh38.… <NA>    <NA>  NA    
#> 3 rs183… 5          1.11e8 snv   rs18… ""    T,C     T                C                NC_000… NC_0… GRCh38.… T       C      0.726
#> 4 rs120… 9          4.18e7 snv   rs12… ""    T,A,C   T                A,C              NC_000… NC_0… GRCh38.… <NA>    <NA>  NA    
#> # … with 1 more variable: maf_population <list>

The maf column contains the minor allele frequency from the GnomAD database (if available). All population specific allele frequencies can be accessed through the column maf_population which returns a list.

dbsnp_info$maf_population
#> [[1]]
#>   study ref_seq Minor MAF
#> 1            NA    NA  NA
#> 
#> [[2]]
#>             study ref_seq Minor       MAF
#> 1          ALSPAC       A     C 0.8227815
#> 2        Estonian       A     C 0.7895089
#> 3       GENOME_DK       A     C 0.8750000
#> 4            GoNL       A     C 0.8266533
#> 5          KOREAN       A     C 0.9658703
#> 6  NorthernSweden       A     C 0.8183333
#> 7          Qatari       A     C 0.8379630
#> 8        SGDP_PRJ       A     C 0.9175824
#> 9        Siberian       A     C 0.8333333
#> 10          TOMMO       A     C 0.9589499
#> 11         TOPMED       A     C 0.8765689
#> 12         TOPMED       A     C 0.8767313
#> 13        TWINSUK       A     C 0.8193096
#> 14     Vietnamese       A     C 0.9952830
#> 15  dbGaP_PopFreq       A     C 0.7991653
#> 16         KOREAN       A     G 0.0000000
#> 17         KOREAN       A     T 0.0000000
#> 18  dbGaP_PopFreq       A     T 0.0000000
#> 
#> [[3]]
#>             study ref_seq Minor       MAF
#> 1     1000Genomes       T     C 0.6178115
#> 2          ALSPAC       T     C 0.7477945
#> 3       Daghestan       T     C 0.6856128
#> 4        Estonian       T     C 0.7037946
#> 5       GENOME_DK       T     C 0.7250000
#> 6          GnomAD       T     C 0.7257767
#> 7            GoNL       T     C 0.7274549
#> 8   HGDP_Stanford       T     C 0.6602687
#> 9          HapMap       T     C 0.6054025
#> 10         KOREAN       T     C 0.3969283
#> 11        Korea1K       T     C 0.3733624
#> 12 NorthernSweden       T     C 0.6850000
#> 13     PAGE_STUDY       T     C 0.6673868
#> 14     PRJEB36033       T     C 1.0000000
#> 15     PRJEB37584       T     C 0.4141414
#> 16         Qatari       T     C 0.7824074
#> 17       SGDP_PRJ       T     C 0.7670940
#> 18       Siberian       T     C 0.7826087
#> 19          TOMMO       T     C 0.3405728
#> 20         TOPMED       T     C 0.7110490
#> 21         TOPMED       T     C 0.7196758
#> 22        TWINSUK       T     C 0.7437972
#> 23     Vietnamese       T     C 0.4074074
#> 24  dbGaP_PopFreq       T     C 0.7300999
#> 
#> [[4]]
#>           study ref_seq Minor MAF
#> 1 dbGaP_PopFreq       T     A   0