1-poissonTC.R

# Mon Oct 29 13:17:55 2018 ------------------------------
## DREAM olfaction prediction challenge
library(caret)
library(rsample)
library(tidyverse)
library(recipes)
library(magrittr)
library(doMC)

# Create directory and download files
dir.create("data/")
ghurl <- "https://github.com/dream-olfaction/olfaction-prediction/raw/master/data/"
download.file(paste0(ghurl, "TrainSet.txt"),
              destfile = "data/trainSet.txt")
download.file(paste0(ghurl, "molecular_descriptors_data.txt"),
              destfile = "data/molFeats.txt")

# Read files with readr, select least diluted compounds            
responses <- read_tsv("data/trainSet.txt") %>%
      rename(CID = `Compound Identifier`)

molFeats <- read_tsv("data/molFeats.txt") # molecular features