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

#! /bin/bash

 sed -i 's/\r//g' file.txt

slavailn

#! /bin/bash

# Kegg enrichment 
~/programs/geneSCF-master-source-v1.1-p2/geneSCF -m='update' -i='sig_ids.txt' -t='gid' -db='KEGG' -org='mmu' -p='yes' -bg=20000 -o='.'

# Prepare GO database
~/programs/geneSCF-master-source-v1.1-p2/prepare_database -db=GO_all -org=mgi

# Run encrichment against cellular component (CC), biological process (BP), molecular function (MF)
~/programs/geneSCF-master-source-v1.1-p2/geneSCF -m=normal -i=sig_ids.txt -o=. -t=gid -db=GO_CC -bg=20000 --plot=yes -org=mgi

slavailn

library("wiggleplotr")
library("dplyr")
library("GenomicRanges")
library("GenomicFeatures")
library("EnsDb.Mmusculus.v79")
library("ensembldb")

setwd(<working_dir>)
list.files()

slavailn

library(pheatmap)

# We need to use cutree inside pheatmap()
# functio, capture the returned object into a variable,
# and than extract the tree, cut it again to the same
# number of clusters and reorder.
# Resulting vector is converted to factor and used in the annotation data frame 
# to create cluster labels

x <- some_matrix # matrix to cluster and show as a heatmap 

slavailn

library(gage)
library(org.Hs.eg.db)
library(pathview)
library(rWikiPathways)
library(DESeq2)

## Get annotation from csv file (obtained via biomaRt)
annot <- read.table("../annotation/annotation.csv", sep = ",", header = T,
                    quote = "\"", fill = T, stringsAsFactors = F)

slavailn

library(GEOquery)

# Get GSE
gse <- getGEO("GSE147507",GSEMatrix=FALSE)
head(Meta(gse))

# names of all the GSM objects contained in the GSE
names(GSMList(gse))

# and get the first GSM object on the list

slavailn

library("GenomicFeatures")
library("DESeq2")
library("TxDb.Hsapiens.UCSC.hg19.knownGene")
library("BSgenome.Hsapiens.UCSC.hg19")
library("biomaRt")

setwd("<working_dir>")

# Assuming we are working with DESeq2 projects
# get all genes expressed in the project

slavailn

resFile <- "DESeq2_result_name" # has to have entrez ids as annotations
compName <- "comparison" # Name of the comparison

calcSPIA <- function(resFile, compName) 
{
  res <- read.table(resFile, header = T, sep = "\t", fill=T, quote = "\"", stringsAsFactors = F)
  
  # Select differentially expressed genes (adjusted p-value < 0.05)
  # This is a named vector, where names are entrez ids, and values are log2 fold changes
  ids <- res[res$padj < 0.05,]$entrezgene_id

slavailn

#! /bin/bash

# 22498713 reads; of these:
#   22498713 (100.00%) were unpaired; of these:
#     1754404 (7.80%) aligned 0 times
#     17667104 (78.52%) aligned exactly 1 time
#     3077205 (13.68%) aligned >1 times
# 92.20% overall alignment rate

echo -e "sampleID\ttotal_reads\tunmapped\taligned_one_time\taligned_multiple\talignment_rate"