First we're gonna get an EC2 instance up and running with the training data
# Run on an AWS c4.xlarge EC2
$ sudo apt-get update
$ sudo apt-get install r-base-core docker.io
library(tidyverse) | |
shared_file <- read_tsv("data/mothur/kws_final.an.shared") %>% | |
select(-label, -numOtus) %>% | |
# melt, onvert to relative abundance | |
gather("OTU", "abundance", starts_with("Otu")) %>% | |
group_by(Group) %>% | |
mutate(abundance = abundance / sum(abundance)) %>% ungroup | |
tax_file <- read_tsv("data/mothur/kws_final.an.cons.taxonomy") %>% select(-Size) %>% |
Ubuntu Server 18.04 LTS (HVM), SSD Volume Type - ami-005bdb005fb00e791 (64-bit x86)
t2.medium
Name
= turbo-rstudio
turbo-rstudio
keypair
.pem
file in your ~/Downloads/
dir, already did chmod 0400