slavailn

library(GEOquery)

# Download existing RA datasets

# Study 1
# Teixeira VH, Olaso R, Martin-Magniette ML, Lasbleiz S et al. Transcriptome 
# analysis describing new immunity and defense genes in peripheral blood 
# mononuclear cells of rheumatoid arthritis patients. 
# PLoS One 2009 Aug 27;4(8):e6803. PMID: 19710928
# Reference: 	GSE15573

slavailn

# Get SNP records based on rs ids from VCF file
# Kevin Blighe recipe from https://www.biostars.org/p/373852/

# Create a file with snp ids of interest, one id per line
# We can give the newly created file any name, for example snp.txt

bcftools view --include ID==@snp.txt target.bcf

slavailn

# Taken from https://www.biostars.org/p/111040/
# Examine and save metadata 
esearch -db sra -query PRJNA484081  | efetch -format runinfo > bioproj.csv

# The first column of comma separated runinfo file are run ids
cat bioproj.csv | cut -d ',' -f 1 | head

# Download first 4 files as an example
cat bioproj.csv | cut -d ',' -f 1 | grep 'SRR' # Check of we are selecting right files

slavailn

#! /bin/bash

# Taken from https://github.com/stephenturner/mergelanes/issues/1
# Exercise caution, does not work accurately in every case:
# Not working accurately for sample IDs like "A11_Barcodexxx_S11_L001_R1_001". 
# It cat together all L001 pertaining to sample ID A11 with different barcodes also

ls *R1* | cut -d _ -f 1 | sort | uniq \
    | while read id; do \
        cat $id*R1*.fastq.gz > $id.R1.fastq.gz;

slavailn

# Get paralogs for the list of genes

library(biomaRt)
human <- useMart("ensembl", dataset = "hsapiens_gene_ensembl")
gene_id <- c("TPM1", "BOD1", "ADAP1")
results <- getBM(attributes = c("ensembl_gene_id", 
                                "external_gene_name",
                                "hsapiens_paralog_ensembl_gene", 
                                "hsapiens_paralog_associated_gene_name"),
                 filters = "external_gene_name",

slavailn

library(GenomicFeatures)
library(TxDb.Mmusculus.UCSC.mm10.knownGene)
library(BSgenome.Mmusculus.UCSC.mm10)
library(Biostrings)
# Fetch promoter sequences to detect enriched transcription factor
# motifs in the promoters of differentially expressed genes

setwd("/path/to/dir")
list.files()

slavailn

library("ChIPpeakAnno")
library("GenomicRanges")
library("org.At.tair.db")
library("TxDb.Athaliana.BioMart.plantsmart28")
library("biomaRt")

# Annotate genomic intervals in bed format using ChIPpeakAnno 
# This script was designed for Arabidopsis, but can be easily changed for
# any other organism available through biomaRt

slavailn

library(KEGGREST)
library(org.Rn.eg.db)

# Download entrez ids and corresponding KEGG pathways followed
# by creation of a table where one column is entrez id and another 
# column is a comma separated list of KEGG pathways

# Download pathway to entrez id relationship
rno_path_eg  <- keggLink("pathway", "rno")
names(rno_path_eg) <- gsub("rno:", "", names(rno_path_eg))

slavailn

library(dplyr)
library(ggplot2)
library(reshape2)
library(topGO)
library(plyr)

# Read in some table with gene ids, for example expressions
coreGenes <- read.table(<some_table_gene_ids>)

# Get gene mappings to GO terms

slavailn

library(RColorBrewer)
library(ggplot2)
library(ggrepel)

setwd("<path/to/dir>")

# Load DESeq2 object
load("expression_data/DESeqOBJ.RData")
dds