stephenturner

################################################################################
# GCP/AWS setup script for general bioinformatics
# Base image: Ubuntu 22.04 LTS x86/64
################################################################################

# Make a directory in which to build stuff
sudo mkdir -p ${HOME}/build && sudo chmod 777 ${HOME}/build && cd ${HOME}/build

# Install system libs
sudo apt-get update

stephenturner

library(tidyverse)
library(rvest)
library(tidytext)

## Function to get full text given a DOI
get_full_text <- function(doi) {
  paste0("https://www.biorxiv.org/content/", doi, ".full") |>
    rvest::read_html() |>
    rvest::html_nodes("div.section") |>
    rvest::html_text() |>

stephenturner

library(tidyverse)
library(httr2)

# Set URL path variables
url <- "https://api.biorxiv.org/"
what <- "details"
server <- "biorxiv"
date1 <- "2014-01-01"
date2 <- "2023-12-31"

stephenturner

# Get / clean data ----
library(tidyverse)
library(httr2)

# Set URL path variables
url <- "https://api.biorxiv.org/"
what <- "details"
server <- "biorxiv"
date1 <- "2014-01-01"
date2 <- "2023-12-31"

stephenturner

// Place your key bindings in this file to overwrite the defaults
[
    // RStudio: Copy lines up/down with alt+cmd+up/down
    {
        "key": "alt+cmd+down",
        "command": "editor.action.copyLinesDownAction",
        "when": "editorTextFocus && !editorReadonly"
    },
    {
        "key": "shift+alt+down",

stephenturner

# R session 1: model training and deployment ------------------------------

library(tidymodels)
library(vetiver)
library(plumber)

# Not the way you'd actually split data - for demo only
cars_train <- mtcars[1:24,]
cars_test <- mtcars[25:32,]

stephenturner

#!/usr/bin/env python 

# Adds allelic depth (AD)=2 to a VCF.
# Usage: bcftools view my.vcf.gz | addad.py | bcftools sort -Oz -o my.ad.vcf.gz && tabix my.ad.vcf.gz
 
import pysam

vcf_in=pysam.VariantFile("-","r")

vcf_in.header.formats.add("AD",".","Integer","Allelic depth, hard-coded as 2")

stephenturner

# Start window and pane indices at 1 instead of 0
set -g base-index 1
set -g pane-base-index 1

# Shift arrow keys to move around panes
bind -n S-Up    select-pane -U
bind -n S-Down  select-pane -D
bind -n S-Left  select-pane -L
bind -n S-Right select-pane -R

stephenturner

n <- 1e7
x <- sample(n, size=n, replace=TRUE)
length(unique(x))/n
# [1] 0.6321897
1-exp(-1)
# [1] 0.6321206

stephenturner

# Compile and install htslib, bcftools, samtools 1.9 to home directory

# Set up dirs where stuff will be installed
mkdir -p ${HOME}/bin/htslib
mkdir -p ${HOME}/bin/bcftools
mkdir -p ${HOME}/bin/samtools

# Make a dir to build
mkdir -p ${HOME}/tmp