Week2

R Markdown

#Example of a search with str_detect for 4.7
data <- read.csv('phenotype_options.csv',header=FALSE)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.2     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

result1<-data[str_detect(data$V1, "10-heptadecenoate"), ]
write.csv(result1,"result.csv") #Turn this is for 4.7

#Example of biomaRt search using phenotype list from 4.7
#Satisfies 4.6 because searching by phenotype
#Added attributes to also satisfy 4.10
library(biomaRt)

## Warning: replacing previous import 'utils::findMatches' by
## 'S4Vectors::findMatches' when loading 'AnnotationDbi'

ensembl=useMart("ENSEMBL_MART_SNP",
                dataset="hsapiens_snp")

att1 <- c('refsnp_id','minor_allele','minor_allele_freq','phenotype_name',
          'phenotype_description','clinical_significance',
          'associated_variant_risk_allele','p_value','validated')

searchResults <-getBM(att1,
                      filters= 'phenotype_description',
                      values= result1, mart=ensembl)
write.csv(searchResults,'search.csv',row.names=FALSE)

myJW <- read.csv('FormattedSNPS.csv',header=TRUE)
myMerge <-  merge(myJW,searchResults,by.x="rsid",by.y="refsnp_id")
countSNPs <-length(unique(myMerge$rsid))
write.csv(myMerge,"merge.csv",row.names = FALSE) #turn in for 4.8