info <- read.csv("Traits.csv")
ts<-info[,c(1,3)]
print(ts)
##                                  Trait Sample.Size
## 1                         Intelligence     269,867
## 2                 Rheumatoid arthritis      41,282
## 3                    Smoking cessation     547,219
## 4                 Education attainment     766,345
## 5                             Vitiligo      44,266
## 6                   Smoking initiation   1,232,091
## 7            Major depressive disorder     101,498
## 8                  Alcohol consumption     941,280
## 9                   Ulcerative Colitis      27,432
## 10               Subjective well-being     298,420
## 11     Total body bone mineral density      66,628
## 12                              Stroke     446,696
## 13                     Type 2 diabetes     158,186
## 14                    Bipolar disorder      41,653
## 15                       Schizophrenia      65,967
## 16                 Parkinson's disease     308,518
## 17          Inflammatory bowel disease      34,652
## 18                       Breast cancer     228,951
## 19                   Cigarette per day     262,014
## 20                    Allergic disease      59,832
## 21                      Ovarian cancer      66,450
## 22                     Prostate cancer     140,254
## 23                              Asthma     452,272
## 24                              Height     344,664
## 25                      Disease status     452,272
## 26                             Obesity     258,442
## 27             Iron deficiency anemias     452,272
## 28                              Cancer     452,272
## 29 Varicose veins of lower extremities     452,272
## 30                     Body mass index     344,306
## 31                      Osteoarthritis     452,272
## 32                Hypertensive disease     452,272
## 33                       Coffee intake     421,947
## 34                     Type 2 diabetes     452,272
## 35            Irritable bowel syndrome     452,272
## 36        Hernia abdominopelvic cavity     452,272
## 37                      Severe obesity     157,142
## 38              Cardiovascular disease     452,272
## 39                        Dyslipidemia     452,272
## 40                          Tea intake     440,094
## 41                       Peptic ulcers     452,272
## 42                   Allergic rhinitis     452,272
## 43                Psychiatric disorder     452,272
## 44         Peripheral vascular disease     452,272
## 45                        Osteoporosis     452,272
## 46                         Hemorrhoids     452,272

There are 46 traits with the different sample sizes.

To find distribution of each trait is

library(stringr)
fileName <- "TCGA_HM3_Allergic_disease.profile"
AD <- file(fileName,open="r")
ADPRS <-word(readLines(AD),-1)
ADPRS<- as.numeric(ADPRS[2:length(ADPRS)])
#summary(ADPRS)
AllergicDisease_Histo<-hist(ADPRS,main=fileName, xlab="PRS")

library(stringr)
fileName <- "TCGA_HM3_Breast_Cancer.profile"
BC <- file(fileName,open="r")
BCPRS <-word(readLines(BC),-1)
BCPRS<- as.numeric(BCPRS[2:length(BCPRS)])
#summary(BCPRS)
BreastCancer_Histo<-hist(BCPRS, main=fileName, xlab="PRS")

To make multiple histogram by using ‘for loops’,

library(stringr)
file_names <- info[,5]
#file_names
for (filename in file_names){
  PRS <- word(readLines(file(filename,open="r")),-1)
  PRS <- as.numeric(PRS[2:length(PRS)])
  hist(PRS, main=filename)
}

I saved this file as jihyun_PRShist.R (to run this code in terminal)>>> Rscript jihyun_PRShisto.R (histogram files will be made separately in the folder that the script was in)