crazyhottommy

chmod a+x vcfsort.sh
vcfsort.sh trio.trim.vep.vcf.gz

crazyhottommy

## devtools::install_github("stephenturner/msigdf")
library(msigdf)
library(dplyr)
library(clusterProfiler)

c2 <- msigdf.human %>% 
    filter(collection == "c2") %>% select(geneset, entrez) %>% as.data.frame

data(geneList)
de <- names(geneList)[1:100]

crazyhottommy

query.maf.hg19 <- GDCquery(project = "TCGA-COAD", 
                           data.category = "Simple nucleotide variation", 
                           data.type = "Simple somatic mutation",
                           access = "open", 
                           legacy = TRUE)
# Check maf availables
knitr::kable(getResults(query.maf.hg19)[,c("created_datetime","file_name")]) 

query.maf.hg19 <- GDCquery(project = "TCGA-COAD", 
                           data.category = "Simple nucleotide variation", 

crazyhottommy

# This code will get all clinical indexed data from TCGA
library(TCGAbiolinks)
library(data.table)
clinical <- TCGAbiolinks:::getGDCprojects()$project_id %>% 
            regexPipes::grep("TCGA",value=T) %>% 
            sort %>% 
            plyr::alply(1,GDCquery_clinic, .progress = "text") %>% 
            rbindlist
readr::write_csv(clinical,path = paste0("all_clin_indexed.csv"))

crazyhottommy

#!/bin/bash

printf "\n *** BIS BATCH PRIMER version 2.0 ***"
printf "\n\n !!! 'Primer3 & fastx-toolkit' must be installed on the system.\n\n !!! Edit parameters (e.g. sizes, Tm, and etc) before start\n\n "
printf "\n\n  Usage : \n    ./mp_primer.sh FASTA PARAMETER \n\n"
printf "   >>>  input FASTA = "$1
printf " \n   >>>  parameters  = "$2
printf "\n\n\n  ()()() Running... \n\n"

if [ -f $1 -a -f $2 ]; then

crazyhottommy

#API created by @apfejes (Anthony Fejes) on top of my half-cooked script
#python ebi_url_from_srr.py --file srr_list.txt | xargs -I {} wget {}

import argparse
def prepareURL(srr_name, prefix="ftp://ftp.sra.ebi.ac.uk/vol1/fastq/"):
    dir_1=srr_name[:6]
    dir_2=""
    url=""
    num_digits=sum(s.isdigit() for s in srr_name)
    if(num_digits == 6):

crazyhottommy

# somewhat hackish solution to:
# https://twitter.com/EamonCaddigan/status/646759751242620928
# based mostly on copy/pasting from ggplot2 geom_violin source:
# https://github.com/hadley/ggplot2/blob/master/R/geom-violin.r

library(ggplot2)
library(dplyr)


"%||%" <- function(a, b) {

crazyhottommy

# somewhat hackish solution to:
# https://twitter.com/EamonCaddigan/status/646759751242620928
# based mostly on copy/pasting from ggplot2 geom_violin source:
# https://github.com/hadley/ggplot2/blob/master/R/geom-violin.r

library(ggplot2)
library(dplyr)


"%||%" <- function(a, b) {

crazyhottommy

#install UMAP from https://github.com/lmcinnes/umap
#install.packages("rPython")

umap <- function(x,n_neighbors=10,min_dist=0.1,metric="euclidean"){
  x <- as.matrix(x)
  colnames(x) <- NULL
  rPython::python.exec( c( "def umap(data,n,mdist,metric):",
                  "\timport umap" ,
                  "\timport numpy",
                  "\tembedding = umap.UMAP(n_neighbors=n,min_dist=mdist,metric=metric).fit_transform(data)",

crazyhottommy

#' When plotting multiple data series that share a common x axis but different y axes,
#' we can just plot each graph separately. This suffers from the drawback that the shared axis will typically
#' not align across graphs due to different plot margins.
#' One easy solution is to reshape2::melt() the data and use ggplot2's facet_grid() mapping. However, there is
#' no way to label individual y axes.
#' facet_grid() and facet_wrap() were designed to plot small multiples, where both x- and y-axis ranges are
#' shared acros all plots in the facetting. While the facet_ calls allow us to use different scales with
#' the \code{scales = "free"} argument, they should not be used this way.
#' A more robust approach is to the grid package grid.draw(), rbind() and ggplotGrob() to create a grid of 
#' individual plots where the plot axes are properly aligned within the grid.