pcantalupo’s gists

pcantalupo / docker_run_abyss_test.sh

Last active March 10, 2020 13:12

	#!/bin/bash

	# To run this script do the folowing: docker_run_abyss_test.sh ABYSS_DOCKER_TAG

	# ABYSS_DOCKER_TAG is optional.
	# Possible values are found here https://hub.docker.com/r/pegi3s/abyss/tags.
	# For example, use '2.0.2-3' to run Abyss version 2.0.2.

	set -euox pipefail

pcantalupo / 12bars_salsa

Created March 10, 2020 01:45

	library(openxlsx)
	library(readr)
	library(dplyr)

	mappings = read.xlsx("mappings.tsv.xlsx") %>% tbl_df()

	registration = read.xlsx("Final Registration List.xlsx")
	cols = gsub(" ", ".", mappings$FinalRegistrationColumnname)
	registration = registration[,!grepl("^What", colnames(registration))] %>%
	select(cols) %>% distinct() %>% arrange(Last.Name) %>% tbl_df()

pcantalupo / Dockerfile_Rocker_Rstudio_Seurat2

Created March 8, 2020 15:35

	$ cat Dockerfile
	FROM rocker/rstudio

	RUN apt-get update && apt-get install -y libpng* libjpeg* libhdf5-dev libxml2-dev

	RUN install2.r R.utils
	RUN R -e "install.packages('https://cran.rstudio.com//src/contrib/Archive/SDMTools/SDMTools_1.1-221.2.tar.gz', repos = NULL)"

	RUN install2.r BiocManager
	RUN R -e "BiocManager::install('multtest')"

pcantalupo / rocker-rstudio_install_Seurat2

Last active March 7, 2020 17:31

	install.packages('R.utils');
	install.packages("https://cran.rstudio.com//src/contrib/Archive/SDMTools/SDMTools_1.1-221.2.tar.gz", repos = NULL)

	install.packages('BiocManager'); BiocManager::install('multtest')

	install.packages('remotes')
	remotes::install_version('Seurat', '2.3.4') # <- this is flaky. Sometimes it finds the older version and sometimes not

	# my sct package installation
	install.packages(c('roxygen2','rversions','devtools'))

pcantalupo / symbol2ensemblid

Last active June 13, 2021 15:55

mapIds gene annotation symbol ensembl

	library(org.Hs.eg.db)

	(fields = columns(org.Hs.eg.db)) # show annotations available


	symbols = c("MYC", "CCNE1", "TP53")

	# get full gene annotation for MYC (takes 1 or 2 minutes to run)
	geneinfo = lapply (fields, function (f) {
	message (f)

pcantalupo / dockerfile_bioconductor_salmon

Created February 23, 2020 13:22

	FROM bioconductor/bioconductor_docker

	RUN wget https://github.com/COMBINE-lab/salmon/releases/download/v1.1.0/salmon-1.1.0_linux_x86_64.tar.gz && \
	tar -xvzf salmon-1.1.0_linux_x86_64.tar.gz

	ENV PATH "$PATH:/salmon-latest_linux_x86_64/bin"

	RUN curl ftp://ftp.ensemblgenomes.org/pub/plants/release-28/fasta/arabidopsis_thaliana/cdna/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa.gz -o athal.fa.gz

	# RUN salmon index -t athal.fa.gz -i athal_index

pcantalupo / twitter

Created February 20, 2020 13:26

	library(rtweet)
	library(dplyr)
	library(tidyr)
	library(reactable)
	library(glue)

	#https://youtu.be/O0gTv9VGRig?t=24
	# bonus video for Shiny : https://www.infoworld.com/video/100759/how-to-code-an-interactive-shiny-app-to-search-twitter-do-more-with-r-bonus-video

	tweet_df = search_tweets("VirusStalker", n=500, include_rts = T)

pcantalupo / gist:8fbb5983574bc3f1967bedc41c8af1eb

Created February 6, 2020 11:49

	Here I'm aligning 10,000 stranded paired end reads. It is a Truseq stranded RNA-seq library generated by GPCL. Below is the code showing that mapping 10K paired reads with either RF or FR results in the exact same alignments.


	pgc92 at supernova in ~/projects/ngs/bkv_rpte_vs_hvec/mappingtoBKV/HVEC2-BK-24/new
	$ hisat2 -x ../../NC_001538.1 -1 foo_1k_1.fq -2 foo_1k_2.fq --rna-strandness FR > FR.sam
	10000 reads; of these:
	10000 (100.00%) were paired; of these:
	3 (0.03%) aligned concordantly 0 times
	8898 (88.98%) aligned concordantly exactly 1 time
	1099 (10.99%) aligned concordantly >1 times

pcantalupo / GSECAdocker_output

Created January 10, 2020 12:16

pcantalupo / clinical rnaseq

Last active January 10, 2020 12:01

Paul Cantalupo pcantalupo