baseModel
2023-05-08
library(omicade4)## Loading required package: ade4library(mogsa)
library(RSpectra)
# library(lubridate)
library(glmnet)## Loading required package: Matrix## Loaded glmnet 4.1-7library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:mogsa':
##
## combine## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(cowplot)
library(ggplot2)setwd("/Users/rnili/Desktop/repo/gitLab/cmi-pb-multiomics-main/results/main/cmi_pb_datasets/processed/harmonized")
# Read in metadata
meta.2020<-read.table('clinical_metadata.2020.tsv',sep='\t',header=TRUE,stringsAsFactors=TRUE,row.names=1)
meta.2021<-read.table('clinical_metadata.2021.tsv',sep='\t',header=TRUE,stringsAsFactors=TRUE,row.names=1)files from imputed data is already normalised so we don’t need to normalise them
# imputed_dir is path to local drive where data is saved
setwd("/Users/rnili/Desktop/repo/gitLab/cmi-pb-multiomics-main/results/main/cmi_pb_datasets/processed/imputed")
# Import imputed datasets
rnaseq_baseline_mat_imputed_20 <- read.csv('rnaseq_baseline_mat_imputed_20_051022.csv',row.names=1)
cytof_baseline_mat_imputed_20 <- read.csv('cytof_baseline_mat_imputed_20_051022.csv',row.names=1)
olink_baseline_mat_imputed_20 <- read.csv('olink_baseline_mat_imputed_20_051022.csv',row.names=1)
abtiters_baseline_mat_imputed_20 <- read.csv('abtiters_baseline_mat_imputed_20_051022.csv',row.names=1)
rnaseq_baseline_mat_imputed_21 <- read.csv('rnaseq_baseline_mat_imputed_21_051022.csv',row.names=1)
cytof_baseline_mat_imputed_21 <- read.csv('cytof_baseline_mat_imputed_21_051022.csv',row.names=1)
olink_baseline_mat_imputed_21 <- read.csv('olink_baseline_mat_imputed_21_051022.csv',row.names=1)
abtiters_baseline_mat_imputed_21 <- read.csv('abtiters_baseline_mat_imputed_21_051022.csv',row.names=1)tasks_seq<-c('ENSG00000277632','ENSG00000136244','ENSG00000100906','ENSG00000229807')
names(rnaseq_baseline_mat_imputed_20[tasks_seq])## [1] "ENSG00000277632" "ENSG00000136244" "ENSG00000100906" "ENSG00000229807"distPlot <- function(col, df){
p <-
ggplot(df) +
aes_string(col)
if(is.numeric(df[[col]])) {
p <- p + geom_density()
} else {
p <- p + geom_bar()
}
}
distPlots <- lapply(tasks_seq, distPlot, df=rnaseq_baseline_mat_imputed_20)## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.plot_grid(plotlist = distPlots)
# Get age at boost
library(lubridate)##
## Attaching package: 'lubridate'## The following object is masked from 'package:cowplot':
##
## stamp## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionmeta.2020$date_of_boost<-parse_date_time(meta.2020$date_of_boost,"ymd")
meta.2020$year_of_birth<-parse_date_time(meta.2020$year_of_birth,"ymd")
meta.2020$age_at_boost<- as.numeric(round(difftime(meta.2020$date_of_boost,
meta.2020$year_of_birth,units="weeks")/52,2))
meta.2021$date_of_boost<-parse_date_time(meta.2021$date_of_boost,"ymd")
meta.2021$year_of_birth<-parse_date_time(meta.2021$year_of_birth,"ymd")
meta.2021$age_at_boost<- as.numeric(round(difftime(meta.2021$date_of_boost,
meta.2021$year_of_birth,units="weeks")/52,2))
meta <- rbind(meta.2020[c("age_at_boost", "infancy_vac", "biological_sex")], meta.2021[c("age_at_boost", "infancy_vac", "biological_sex")])
meta$infancy_vac <- as.numeric(meta$infancy_vac)
meta$biological_sex <- as.numeric(meta$biological_sex)
colnames(meta)## [1] "age_at_boost" "infancy_vac" "biological_sex"add exposure table
library(DBI)
library(RPostgreSQL)
library(tidyr)##
## Attaching package: 'tidyr'## The following objects are masked from 'package:Matrix':
##
## expand, pack, unpacklibrary(dplyr)
library(readr)
dsn_database = "cmipb_v4_0"
dsn_hostname = "cmi-pb.lji.org"
dsn_port = "5432"
dsn_uid = "cmipb"
dsn_pwd = "b5mq62vW7JE2YUwq"
tryCatch({
drv <- dbDriver("PostgreSQL")
print("Connecting to Database…")
connec <- dbConnect(drv,
dbname = dsn_database,
host = dsn_hostname,
port = dsn_port,
user = dsn_uid,
password = dsn_pwd)
print("Database Connected!")
},
error=function(cond) {
print("Unable to connect to Database.")
})## [1] "Connecting to Database…"
## [1] "Database Connected!"# dbListTables(connec)library(tibble)
library(tidyverse)## ── Attaching core tidyverse packages ─────────────────── tidyverse 2.0.0.9000 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::combine() masks mogsa::combine()
## ✖ tidyr::expand() masks Matrix::expand()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ tidyr::pack() masks Matrix::pack()
## ✖ lubridate::stamp() masks cowplot::stamp()
## ✖ tidyr::unpack() masks Matrix::unpack()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors# library(lubridate)
exposDf <- dbGetQuery(connec, "SELECT * FROM immune_exposure")
ifelse(exposDf$event_start==exposDf$event_end,"Yes","No")## [1] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [13] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [25] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [37] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [49] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [61] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [73] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [85] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [97] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [109] "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes" "Yes"
## [121] "Yes"exposDf %>% count(event_type)## event_type n
## 1 bronchitis 1
## 2 covid 36
## 3 dtap 1
## 4 hib 2
## 5 hpv 11
## 6 influenza 32
## 7 japanese encephalitis 1
## 8 meningococcal 8
## 9 mononucleosis 1
## 10 pneumococcal 1
## 11 pneumonia 3
## 12 polio 10
## 13 strep throat 4
## 14 tick-borne encephalitis 1
## 15 typhoid 1
## 16 varicella 7
## 17 whooping cough 1exposDf$exposure_material_type <- as.character(as.numeric(as.factor(exposDf$exposure_material_type)))
exposDf$event_start <- as.character(as.numeric(as.factor(exposDf$event_start)))
#
exposDf <- dplyr::filter(exposDf, event_type %in% c('covid', 'influenza'))
exposDf1 <- exposDf[, c('subject_id', 'event_type','exposure_material_type', 'event_start')] %>%
pivot_wider( names_from = event_type,
values_from = c(event_start, exposure_material_type),
values_fn= max,
values_fill='Not known'
)
colnames(exposDf1)## [1] "subject_id" "event_start_influenza"
## [3] "event_start_covid" "exposure_material_type_influenza"
## [5] "exposure_material_type_covid"typeof(exposDf1)## [1] "list"exposDf2 <- as.data.frame(exposDf1)
for (col in colnames(exposDf1)[2:length(colnames(exposDf1))]){
exposDf2 <- exposDf1[!grepl(',', exposDf1[[col]]), ]
}
exposDf2 <- exposDf2%>% mutate(across(colnames(exposDf2), as.factor))
exposDf2 <- exposDf2%>% mutate(across(colnames(exposDf2), as.numeric))
exposDf2 ## # A tibble: 56 × 5
## subject_id event_start_influenza event_start_covid exposure_material_type_i…¹
## <dbl> <dbl> <dbl> <dbl>
## 1 3 1 1 1
## 2 40 1 1 1
## 3 43 3 1 1
## 4 35 1 1 1
## 5 49 2 1 1
## 6 47 2 1 1
## 7 2 1 3 1
## 8 4 2 3 1
## 9 5 1 3 1
## 10 6 1 3 1
## # ℹ 46 more rows
## # ℹ abbreviated name: ¹​exposure_material_type_influenza
## # ℹ 1 more variable: exposure_material_type_covid <dbl># nullToNA <- function(x) {
# x[sapply(x, is.null)] <- 'Not known'
# return(x)
# }
# z=exposDf3[2][1]
# exposDf3 <- lapply(exposDf2, nullToNA)
# exposDf3.df <- t(do.call(rbind,lapply(exposDf3, rbind)))
#
# # z= dim(exposDf3.df)[1]
# # print(dim(exposDf3.df))
# # print(exposDf3.df[[2]][2])
# # exposDf4 <- as.data.frame(matrix(unlist(exposDf3.df),nrow=dim(exposDf3.df)[1],byrow=TRUE)
# exposDf4 <- as.data.frame(matrix(unlist(exposDf3.df),nrow=dim(exposDf3.df)[1],byrow=FALSE))
# # z= typeof(exposDf4)
# colnames(exposDf4) <- names(exposDf3)
# #
# # z=exposDf3.df$subject_id
# #All data from abtiter been log2 transformed. Why? to make them normally distributed since our glm uses gaussian as the distribution kernel?
# Get the y data
dataY = read.table('/Users/rnili/Desktop/repo/gitLab/cmi-pb-multiomics-main/results/yData_task_matrix.common_names.mfi_raw.tsv',sep='\t',header=TRUE,stringsAsFactors=TRUE,row.names=1)
dataY <- dataY[c("IgG.PT.day14", "ENSG00000277632.day3", "Monocytes.day1")]
colnames(dataY) <- c("IgG.PT.day14", "CCL3.day3", "Monocytes.day1")
dataY$IgG.PT.day14 <- log2(dataY[,'IgG.PT.day14']+1)
dataY$CCL3.day3 <- log2(dataY[,'CCL3.day3']+1)
dataY$subject_id <- rownames(dataY)
colnames(dataY)## [1] "IgG.PT.day14" "CCL3.day3" "Monocytes.day1" "subject_id"distPlot <- function(col, df){
p <-
ggplot(df) +
aes_string(col)
if(is.numeric(df[[col]])) {
p <- p + geom_density()
} else {
p <- p + geom_bar()
}
}
typeof(dataY)## [1] "list"#
distPlots <- lapply(c("IgG.PT.day14", "CCL3.day3", "Monocytes.day1"), distPlot, df=dataY)
plot_grid(plotlist = distPlots)## Warning: Removed 4 rows containing non-finite values (`stat_density()`).## Warning: Removed 22 rows containing non-finite values (`stat_density()`).## Warning: Removed 41 rows containing non-finite values (`stat_density()`).
colnames(rnaseq_baseline_mat_imputed_20)[which(names(rnaseq_baseline_mat_imputed_20) == "ENSG00000277632")] <- "CCL3"
colnames(rnaseq_baseline_mat_imputed_21)[which(names(rnaseq_baseline_mat_imputed_21) == "ENSG00000277632")] <- "CCL3"
rnaDf <- rbind(rnaseq_baseline_mat_imputed_20["CCL3"], rnaseq_baseline_mat_imputed_21["CCL3"])
abtiterDf <- rbind(abtiters_baseline_mat_imputed_20["IgG.PT"], abtiters_baseline_mat_imputed_21["IgG.PT"])
cytofDf <- rbind(cytof_baseline_mat_imputed_20["Monocytes"], cytof_baseline_mat_imputed_21["Monocytes"])
dataDf1 <- merge(rnaDf, abtiterDf, by='row.names', all=T)
colnames(dataDf1)[1] <- "subject_id"
dataDf2 <- merge(cytofDf, meta, by='row.names', all=T)
colnames(dataDf2)[1] <- "subject_id"
dataX1 <- merge(dataDf1, dataDf2, by='subject_id', all=T)
# colnames(dataX1)[1] <- "subject_id"
dataX <- merge(dataX1, exposDf2, by='subject_id', all=T)
#
dataDf <- merge(dataX, dataY, by='subject_id', all=T)
rownames(dataDf) <- dataDf$subject_id
dataDf## subject_id CCL3 IgG.PT Monocytes age_at_boost infancy_vac
## 1 1 5.333531 2.24397113 7.5260062 30.80 2
## 10 10 4.101398 0.04154169 13.4642547 34.68 2
## 11 11 4.542939 1.77698271 10.7905171 30.76 2
## 12 12 NA NA NA 34.68 2
## 13 13 3.399718 1.36806068 5.0304685 19.63 1
## 14 14 NA NA NA 23.70 2
## 15 15 4.835874 0.38100554 15.6373679 27.71 2
## 16 16 NA NA NA 29.66 2
## 17 17 4.512669 3.45553366 14.4574172 36.82 2
## 18 18 4.083384 1.68734290 0.9568001 19.73 1
## 19 19 4.459300 2.16297720 13.5202756 22.81 2
## 2 2 NA NA NA 51.25 2
## 20 20 3.963474 2.55022450 21.3991621 35.78 2
## 21 21 3.823138 2.77448207 15.2266453 33.77 2
## 22 22 4.462314 2.16393744 11.9355890 31.77 2
## 23 23 4.421223 0.40194862 11.7041207 25.82 2
## 24 24 3.106516 0.26992483 11.5201600 24.79 2
## 25 25 4.042732 0.74967184 13.4709985 28.80 2
## 26 26 4.735685 0.72685734 5.5320667 33.85 2
## 27 27 3.782618 0.77080873 13.8965682 19.80 1
## 28 28 NA NA NA 34.85 2
## 29 29 4.447249 0.99688351 16.0947648 19.80 1
## 3 3 4.599972 1.06789053 13.0245725 33.89 2
## 30 30 NA NA NA 28.84 2
## 31 31 4.693487 0.16545091 4.8790233 27.83 2
## 32 32 5.779549 1.40368966 13.5492381 19.88 1
## 33 33 5.311794 0.63824158 7.6518328 26.87 2
## 34 34 NA NA NA 33.93 2
## 35 35 5.434762 1.19302502 13.5420630 25.86 2
## 36 36 3.016496 1.04080942 11.2437986 19.88 1
## 37 37 NA NA NA 18.91 1
## 38 38 3.017922 0.77149215 13.7721006 19.88 1
## 39 39 NA NA NA 31.92 2
## 4 4 4.094574 1.60723380 5.4908380 28.76 2
## 40 40 NA NA NA 22.89 2
## 41 41 NA NA NA 31.96 2
## 42 42 5.230280 1.11654738 10.6095832 19.92 1
## 43 43 3.871351 1.00310977 13.6337391 18.91 1
## 44 44 4.518409 0.92865661 23.1032762 18.91 1
## 45 45 NA NA NA 19.98 1
## 46 46 NA NA NA 18.91 1
## 47 47 6.900831 2.65845646 10.1292397 20.98 1
## 48 48 6.731536 0.04154169 14.9597507 19.11 1
## 49 49 NA NA NA 20.11 1
## 5 5 4.916572 2.26243525 13.1258248 25.75 2
## 50 50 8.091139 0.50769248 9.3613078 19.98 1
## 51 51 NA NA NA 19.98 1
## 52 52 7.288949 1.97201547 28.5490352 19.07 1
## 53 53 9.867189 4.17711376 12.8294284 19.07 1
## 54 54 NA NA NA 20.11 1
## 55 55 NA NA NA 20.11 1
## 56 56 NA NA NA 20.15 1
## 57 57 NA NA NA 21.15 1
## 58 58 NA NA NA 20.15 1
## 59 59 NA NA NA 20.15 1
## 6 6 4.575554 0.27896948 22.7930283 28.87 2
## 60 60 NA NA NA 20.15 1
## 61 61 12.042340 1.00000000 12.8005992 32.38 2
## 62 62 6.937333 1.07602222 13.5692650 25.99 2
## 63 63 6.691953 1.79570532 15.3000000 23.98 2
## 64 64 6.760926 2.04705167 12.9000000 25.99 2
## 65 65 7.605079 0.80140188 15.8000000 29.02 2
## 66 66 5.042425 1.32512343 15.8000000 43.07 2
## 67 67 5.889230 0.70618673 34.6000000 47.24 2
## 68 68 5.853946 1.05459788 13.5000000 47.24 2
## 69 69 5.528321 1.07297696 13.1000000 29.17 2
## 7 7 NA NA NA 35.97 2
## 70 70 5.815166 0.47027882 32.3000000 21.15 1
## 71 71 5.987707 2.90659418 12.2000000 21.15 1
## 72 72 5.880881 2.08840338 19.9000000 28.25 2
## 73 73 4.529196 1.88327381 15.7000000 24.23 2
## 74 74 3.871745 0.52016941 36.3000000 24.23 2
## 75 75 5.678804 0.17736981 14.4559889 21.22 1
## 76 76 4.663800 3.53643892 18.0000000 21.22 1
## 77 77 8.217396 0.69081102 28.8000000 31.32 2
## 78 78 7.151839 0.99519368 29.0000000 26.30 2
## 79 79 6.969300 2.32256773 41.5000000 32.32 2
## 8 8 NA NA NA 34.27 2
## 80 80 7.178107 0.46841860 21.9000000 27.30 2
## 81 81 10.726589 1.81601157 34.9000000 26.30 2
## 82 82 9.413611 0.76723104 22.5000000 21.28 1
## 83 83 8.588209 1.26356779 32.4000000 20.34 1
## 84 84 7.593122 0.28053529 18.9000000 22.34 1
## 85 85 4.937862 0.33276350 19.7000000 19.39 1
## 86 86 5.362224 0.30403242 23.5000000 21.40 1
## 87 87 5.295650 1.07997538 22.9000000 19.39 1
## 88 88 5.567850 1.04544297 17.6000000 19.39 1
## 89 89 5.130601 0.06807137 15.7000000 22.49 1
## 9 9 4.238481 0.28783862 5.7229578 20.63 1
## 90 90 4.837136 0.33985853 20.6000000 20.49 1
## 91 91 4.140370 0.92749667 25.4000000 21.49 1
## 92 92 4.623047 0.23829881 40.6000000 19.54 1
## 93 93 4.616769 1.57747907 16.3000000 23.56 1
## 94 94 4.785446 2.65824315 26.2000000 20.55 1
## 95 95 4.878235 2.29792327 17.3000000 21.55 1
## 96 96 4.356355 0.76421696 34.2000000 19.54 1
## biological_sex event_start_influenza event_start_covid
## 1 1 4 1
## 10 1 3 3
## 11 1 2 3
## 12 2 4 1
## 13 2 1 3
## 14 2 3 3
## 15 2 3 3
## 16 1 4 1
## 17 1 3 3
## 18 1 3 3
## 19 2 3 3
## 2 1 1 3
## 20 1 3 3
## 21 2 3 3
## 22 1 4 1
## 23 1 4 1
## 24 1 2 3
## 25 1 3 3
## 26 1 4 1
## 27 1 3 3
## 28 2 2 3
## 29 2 1 3
## 3 1 1 1
## 30 1 2 3
## 31 1 3 3
## 32 2 4 1
## 33 2 3 3
## 34 1 4 1
## 35 2 1 1
## 36 1 4 1
## 37 1 4 1
## 38 1 4 2
## 39 1 2 2
## 4 2 2 3
## 40 1 1 1
## 41 2 4 1
## 42 1 4 1
## 43 1 3 1
## 44 1 4 1
## 45 1 4 1
## 46 1 4 1
## 47 1 2 1
## 48 1 4 1
## 49 1 2 1
## 5 2 1 3
## 50 1 4 1
## 51 2 4 2
## 52 2 4 1
## 53 1 4 1
## 54 1 4 1
## 55 1 4 1
## 56 1 4 1
## 57 1 NA NA
## 58 1 NA NA
## 59 1 NA NA
## 6 1 1 3
## 60 2 NA NA
## 61 1 NA NA
## 62 1 NA NA
## 63 1 NA NA
## 64 2 NA NA
## 65 2 NA NA
## 66 1 NA NA
## 67 1 NA NA
## 68 2 NA NA
## 69 1 NA NA
## 7 1 3 3
## 70 2 NA NA
## 71 1 NA NA
## 72 1 NA NA
## 73 1 NA NA
## 74 1 NA NA
## 75 1 NA NA
## 76 1 NA NA
## 77 2 NA NA
## 78 1 NA NA
## 79 2 NA NA
## 8 1 3 3
## 80 1 NA NA
## 81 2 NA NA
## 82 1 NA NA
## 83 1 NA NA
## 84 1 NA NA
## 85 1 NA NA
## 86 1 NA NA
## 87 2 NA NA
## 88 2 NA NA
## 89 1 NA NA
## 9 2 1 3
## 90 1 NA NA
## 91 2 NA NA
## 92 1 NA NA
## 93 1 NA NA
## 94 2 NA NA
## 95 1 NA NA
## 96 2 NA NA
## exposure_material_type_influenza exposure_material_type_covid IgG.PT.day14
## 1 3 1 7.6475855
## 10 1 2 2.2695086
## 11 1 2 8.6987531
## 12 3 1 6.6128578
## 13 1 2 5.8841566
## 14 1 2 8.0768224
## 15 1 2 6.6651860
## 16 3 1 6.4541001
## 17 1 2 7.4085495
## 18 1 2 7.5228254
## 19 1 2 7.4194018
## 2 1 2 NA
## 20 1 2 7.0689888
## 21 1 2 5.1846314
## 22 3 1 6.5076306
## 23 3 1 7.0576625
## 24 1 2 4.6224481
## 25 1 2 4.5909272
## 26 3 1 5.5468623
## 27 1 2 5.4905601
## 28 1 2 6.8762502
## 29 1 2 6.2496495
## 3 1 1 7.0245630
## 30 1 2 5.9932153
## 31 1 2 5.0875933
## 32 3 1 8.0965425
## 33 1 2 3.8450834
## 34 3 1 7.4372481
## 35 1 1 6.2916862
## 36 3 1 5.4060017
## 37 3 1 NA
## 38 3 1 6.9326678
## 39 2 1 6.1874734
## 4 1 2 7.1886911
## 40 1 1 7.1901774
## 41 3 1 7.6409027
## 42 3 1 7.3543048
## 43 1 1 4.7818220
## 44 3 1 8.2039885
## 45 3 1 5.3037468
## 46 3 1 7.6599183
## 47 1 1 8.1390023
## 48 3 1 0.6191782
## 49 1 1 7.1395468
## 5 1 2 6.6256103
## 50 3 1 5.7517331
## 51 3 1 6.2205920
## 52 3 1 6.7943897
## 53 3 1 7.7831903
## 54 3 1 7.4376533
## 55 3 1 6.9266194
## 56 3 1 7.6690347
## 57 NA NA 6.3923743
## 58 NA NA 7.8093466
## 59 NA NA 8.4674371
## 6 1 2 7.3965736
## 60 NA NA 4.4714296
## 61 NA NA 8.2526654
## 62 NA NA 10.5975417
## 63 NA NA 10.9051623
## 64 NA NA 9.1278687
## 65 NA NA 10.8445096
## 66 NA NA 11.0087787
## 67 NA NA 11.0562652
## 68 NA NA 10.6132806
## 69 NA NA 10.1689229
## 7 1 2 6.5497867
## 70 NA NA 7.6596483
## 71 NA NA 9.8422738
## 72 NA NA 10.7625897
## 73 NA NA 10.3994888
## 74 NA NA 8.5950614
## 75 NA NA 7.1006623
## 76 NA NA 10.2854022
## 77 NA NA 8.9872640
## 78 NA NA 9.7013065
## 79 NA NA 9.9947070
## 8 1 2 NA
## 80 NA NA 7.9628960
## 81 NA NA 9.0161118
## 82 NA NA NA
## 83 NA NA 8.7729745
## 84 NA NA 8.8946701
## 85 NA NA 7.4072678
## 86 NA NA 9.2672550
## 87 NA NA NA
## 88 NA NA NA
## 89 NA NA 7.0762538
## 9 1 2 4.2023938
## 90 NA NA 7.8005768
## 91 NA NA 8.9320595
## 92 NA NA 8.5651021
## 93 NA NA 9.3359486
## 94 NA NA 9.9581902
## 95 NA NA 10.0764114
## 96 NA NA 8.5961898
## CCL3.day3 Monocytes.day1
## 1 8.531381 NA
## 10 7.491853 NA
## 11 7.179909 7.257095
## 12 NA NA
## 13 9.832890 NA
## 14 NA NA
## 15 8.118941 10.585489
## 16 NA NA
## 17 8.209453 16.401488
## 18 6.643856 NA
## 19 7.066089 NA
## 2 NA NA
## 20 8.909893 26.605583
## 21 7.900867 34.812168
## 22 6.375039 NA
## 23 7.066089 NA
## 24 7.238405 NA
## 25 7.562242 NA
## 26 7.219169 16.108508
## 27 7.592457 NA
## 28 NA NA
## 29 8.154818 25.083209
## 3 7.888743 NA
## 30 NA NA
## 31 8.897845 8.545243
## 32 9.353147 NA
## 33 9.550747 17.703064
## 34 NA NA
## 35 7.774787 NA
## 36 7.584963 17.446750
## 37 NA NA
## 38 5.977280 NA
## 39 NA NA
## 4 7.066089 7.211965
## 40 NA NA
## 41 NA NA
## 42 8.980140 NA
## 43 8.317413 NA
## 44 7.209453 35.241054
## 45 NA 13.545087
## 46 NA 30.018793
## 47 13.173521 8.663056
## 48 11.965063 18.252658
## 49 NA 10.347126
## 5 7.554589 NA
## 50 13.075145 NA
## 51 NA NA
## 52 13.313733 23.512649
## 53 12.686938 NA
## 54 NA NA
## 55 NA 15.334381
## 56 NA NA
## 57 NA NA
## 58 NA NA
## 59 NA NA
## 6 7.761551 41.380502
## 60 NA NA
## 61 8.717676 NA
## 62 10.582142 NA
## 63 9.266787 18.700000
## 64 9.333155 13.800000
## 65 11.200899 20.400000
## 66 9.951285 13.900000
## 67 8.826548 31.100000
## 68 8.344296 15.500000
## 69 9.631177 18.900000
## 7 NA NA
## 70 8.495855 46.100000
## 71 9.881114 18.200000
## 72 8.243174 27.500000
## 73 8.717676 23.400000
## 74 7.700440 50.000000
## 75 7.924813 NA
## 76 7.686501 22.300000
## 77 10.913637 31.000000
## 78 8.290019 35.700000
## 79 11.197831 52.600000
## 8 NA NA
## 80 11.810973 26.400000
## 81 11.244958 35.600000
## 82 12.988152 20.500000
## 83 7.033423 27.700000
## 84 9.219169 25.100000
## 85 8.479780 18.700000
## 86 9.159871 25.200000
## 87 10.062046 22.500000
## 88 12.066426 20.200000
## 89 9.377211 16.600000
## 9 8.388017 NA
## 90 8.781360 21.600000
## 91 7.459432 40.400000
## 92 8.108524 33.000000
## 93 8.189825 15.000000
## 94 7.139551 39.500000
## 95 7.721099 23.500000
## 96 7.475733 35.000000###Distination plot
distPlot <- function(col, df){
p <-
ggplot(df) +
aes_string(col)
if(is.numeric(df[[col]])) {
p <- p + geom_density()
} else {
p <- p + geom_bar()
}
}
names(dataDf)[2:length(dataDf)]## [1] "CCL3" "IgG.PT"
## [3] "Monocytes" "age_at_boost"
## [5] "infancy_vac" "biological_sex"
## [7] "event_start_influenza" "event_start_covid"
## [9] "exposure_material_type_influenza" "exposure_material_type_covid"
## [11] "IgG.PT.day14" "CCL3.day3"
## [13] "Monocytes.day1"distPlots <- lapply(names(dataDf)[2:length(dataDf)], distPlot, df=dataDf)
plot_grid(plotlist = distPlots)## Warning: Removed 24 rows containing non-finite values (`stat_density()`).
## Removed 24 rows containing non-finite values (`stat_density()`).
## Removed 24 rows containing non-finite values (`stat_density()`).## Warning: Removed 40 rows containing non-finite values (`stat_density()`).
## Removed 40 rows containing non-finite values (`stat_density()`).
## Removed 40 rows containing non-finite values (`stat_density()`).
## Removed 40 rows containing non-finite values (`stat_density()`).## Warning: Removed 6 rows containing non-finite values (`stat_density()`).## Warning: Removed 24 rows containing non-finite values (`stat_density()`).## Warning: Removed 43 rows containing non-finite values (`stat_density()`).
Test model quality
options(warn=-1)
xCols = c("CCL3", "IgG.PT", "Monocytes", "age_at_boost", "infancy_vac", "biological_sex", "event_start_influenza", "event_start_covid", "exposure_material_type_influenza", "exposure_material_type_covid")
yCols = c("IgG.PT.day14", "CCL3.day3", "Monocytes.day1")
pred_cor <- data.frame(matrix(nrow=length(yCols), ncol=3))
rownames(pred_cor) <- yCols
colnames(pred_cor) <- c('pearson.cor.pred.true', 'spearman.cor.pred.true', 'ranked.spearman.cor.pred.true')
rownames(dataDf) <- attr(dataDf, "row.names")
print(typeof(row.names(dataDf)))## [1] "character"#
for (i in 1:length(yCols)){
all_preds <- c()
all_true <- c()
set.seed(1)
filteredY <- na.omit(dataDf[yCols[i]])
filteredX <- na.omit(dataDf[xCols])
row_int <- intersect(rownames(filteredY), rownames(filteredX))
for (j in 1:length(row_int)){
train <- row_int[-c(j)]
xData <- filteredX[train, xCols]
yData <- filteredY[train,]
a1= nrow(xData[train,])
a2= nrow(xData[train,]-1)
allidx = row_int
predidx = setdiff(allidx, train)
# create lasso model
cvfit_out <- cv.glmnet(x=as.matrix(xData), yData, family='gaussian',
alpha=1, nfolds=nrow(xData[train,]))
preds <- predict(cvfit_out, newx = as.matrix(data.frame(filteredX[predidx,])), s='lambda.min')
all_preds <- c(all_preds, preds)
all_true<- c(all_true, filteredY[predidx, yCols[i]])
}
b = data_frame(all_preds, rank(all_preds,na.last="keep",ties.method="min"), all_true, rank(all_true,na.last="keep",ties.method="min"))
pred_cor[yCols[i],'pearson.cor.pred.true'] <- cor(all_preds,all_true)
pred_cor[yCols[i],'spearman.cor.pred.true'] <- cor(all_preds,all_true, method="spearman")
pred_cor[yCols[i],'ranked.spearman.cor.pred.true'] <- cor(rank(all_preds,na.last="keep",ties.method="min"),rank(all_true,na.last="keep",ties.method="min"), method="spearman")
}
pred_cor## pearson.cor.pred.true spearman.cor.pred.true
## IgG.PT.day14 0.3965526 0.4630631
## CCL3.day3 0.7906531 0.5311535
## Monocytes.day1 0.5462973 0.6205882
## ranked.spearman.cor.pred.true
## IgG.PT.day14 0.4630631
## CCL3.day3 0.5311535
## Monocytes.day1 0.6205882typeof(pred_cor)## [1] "list"For each model, can assess which features contribute to non-zero coefficients
Consider only choosing models for follow-on analysis that show good correlation scores
size <- length(yCols)
all_models_coef<-vector(mode='list',length=size)
all_models_names<-vector(mode='list',length=size)
all_models<-vector(mode='list',length=size)
for (i in 1:length(yCols)){
set.seed(1)
filteredY <- na.omit(dataDf[yCols[i]])
filteredX <- na.omit(dataDf[xCols])
row_int <- intersect(rownames(filteredY), rownames(filteredX))
# create lasso model
suppressWarnings(cvfit_out <- cv.glmnet(x=as.matrix(filteredX[row_int,]), as.matrix(filteredY[row_int,]), family='gaussian', alpha=1, nfolds=nrow(filteredX[row_int,])))
plot(cvfit_out)
all_models_coef[i]=list(coef(cvfit_out, s = 'lambda.min')[coef(cvfit_out, s = 'lambda.min')[,1]!= 0])
all_models_names[i]=list(rownames(coef(cvfit_out, s = 'lambda.min'))[coef(cvfit_out, s = 'lambda.min')[,1]!= 0])
}## <sparse>[ <logic> ]: .M.sub.i.logical() maybe inefficient
## <sparse>[ <logic> ]: .M.sub.i.logical() maybe inefficient
## <sparse>[ <logic> ]: .M.sub.i.logical() maybe inefficient
names(all_models_coef) <- yCols
names(all_models_names) <- yColsfor (i in 1:size){
all_models[[i]] = data.frame(cbind(all_models_names[[i]],all_models_coef[[i]]))
colnames(all_models[[i]])<-c("Variable","Coefficient")
all_models[[i]]$Coefficient<-as.numeric(all_models[[i]]$Coefficient)
all_models[[i]]$Coefficient=round(all_models[[i]]$Coefficient,3)
all_models[[i]]<-all_models[[i]] %>% arrange(desc(abs(Coefficient)))
}
names(all_models)<-yCols
all_models## $IgG.PT.day14
## Variable Coefficient
## 1 (Intercept) 5.345
## 2 IgG.PT 0.650
##
## $CCL3.day3
## Variable Coefficient
## 1 (Intercept) 5.030
## 2 CCL3 0.926
## 3 infancy_vac -0.623
##
## $Monocytes.day1
## Variable Coefficient
## 1 (Intercept) 13.213
## 2 CCL3 -1.238
## 3 Monocytes 0.877# library(capture)
# setwd("/Users/rnili/Desktop/repo/gitLab/cmi-pb-multiomics-main/rasteh/models")
a= append(list(pred_cor),all_models)
# names(a)[1] <- 'pred_cor'
# sink("allModels_predCor_baseExposure_normalized.txt")
print(a)## [[1]]
## pearson.cor.pred.true spearman.cor.pred.true
## IgG.PT.day14 0.3965526 0.4630631
## CCL3.day3 0.7906531 0.5311535
## Monocytes.day1 0.5462973 0.6205882
## ranked.spearman.cor.pred.true
## IgG.PT.day14 0.4630631
## CCL3.day3 0.5311535
## Monocytes.day1 0.6205882
##
## $IgG.PT.day14
## Variable Coefficient
## 1 (Intercept) 5.345
## 2 IgG.PT 0.650
##
## $CCL3.day3
## Variable Coefficient
## 1 (Intercept) 5.030
## 2 CCL3 0.926
## 3 infancy_vac -0.623
##
## $Monocytes.day1
## Variable Coefficient
## 1 (Intercept) 13.213
## 2 CCL3 -1.238
## 3 Monocytes 0.877# sink()Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.