wenjie1991

# Alignemnt
```
## input file
inputFastq1=../data/fastq/input_R1.fastq.gz    ## input file name
inputFastq2=../data/fastq/input_R2.fastq.gz    ## input file name

## Output 
mkdir -p ../tmp/bam   ## Output fold
mappedBam=../tmp/bam/output.mapped.bam

wenjie1991

source("https://github.com/wenjie1991/bioinfo/blob/master/R/scatterBar.R")
source("https://github.com/wenjie1991/bioinfo/blob/master/R/ucscCancer_extractor.R")

#=================================================
# read data 
#=================================================
# read_csv
suppressMessages(dat.CNV <- read.ucscCancer.dir("../../../UCSC_cancer/COADREAD/TCGA_COADREAD_gistic2-2015-02-24/"))
suppressMessages(dat.mRNA <- read.ucscCancer.dir("../../../UCSC_cancer/COADREAD/TCGA_COADREAD_exp_HiSeqV2-2015-02-24"))

wenjie1991

#################################################
# Input:
input = "./pubmed_result.xml"

#################################################
# Output:
output = "./abstract.xls"


# install.packages("pubmed.mineR")

wenjie1991

## download and install package
# source("http://bioconductor.org/biocLite.R")
# biocLite("oligo")

library(oligo)
## read cel files
dir <- tcltk::tk_choose.dir(caption = "Please choose input fold contain cel")
raw <- list.celfiles(dir, full.names=TRUE)
affyGeneFS <- read.celfiles(raw)

wenjie1991

## Variant call

## Input files
gatk_jar=gatk3.jar # https://console.cloud.google.com/storage/browser/gatk-software/package-archive/gatk/?pli=1
refseq=genome.fa
rmdupN=normal.bam  ## aligned & duplication removed bam file
rmdupP1=primary1.bam
rmdupP2=primary2.bam
rmdupM1=metastasis1.bam
rmdupM2=metastasis2.bam

wenjie1991

f1 = "../data/graph_pixel/ROI_170220-40x-tumorR2-405DAPI-488pLgr5-561mTomato-642pThbs1.20_MERGED.tif_Z#44C#1_Simple Segmentation.tif.txt"
f2 = "../data/graph_pixel/ROI_170220-40x-tumorR2-405DAPI-488pLgr5-561mTomato-642pThbs1.20_MERGED.tif_Z#44C#2_Simple Segmentation.tif.txt"
d1 = fread(f1)
d2 = fread(f2)
d1[, channel := "channel1"]
d2[, channel := "channel2"]
d = rbind(d1, d2)
ggplot(d, aes(x = V1, y = V2) ) + geom_point(aes(fill = channel, col = channel), alpha = 0.4) + theme_bw()
ggplot(d, aes(x = V1, y = V2) ) + geom_point(aes(fill = channel, col = channel), alpha = 0.1, size = 5) + theme_bw()
ggplot(d, aes(x = V1, y = V2) ) + geom_point(aes(fill = channel, col = channel), alpha = 0.1, size = 15) + theme_bw()

wenjie1991

```{r}
library(reticulate)
# You can set the conda environment
use_condaenv("scrublet", required = T)
```

```{python}
import scrublet as scr
import scipy.io
import matplotlib.pyplot as plt

wenjie1991

This script is used for cancer gene expression analysis of paper: Paracrine signalling between intestinal epithelial and tumour cells induces a regenerative programme eLife2022;11:e76541 DOI: https://doi.org/10.7554/eLife.76541

Licence

TCGA_expression.Rmd - TCGA gene expression analysis Written in 2022 by Wenjie SUN sunwjie@gmail.com

To the extent possible under law, the author(s) have dedicated all copyright and related and neighboring rights to this software to the public domain worldwide. This software is distributed without any warranty.

wenjie1991

This script is used for pathway enrichment analysis of paper: Paracrine signalling between intestinal epithelial and tumour cells induces a regenerative programme eLife2022;11:e76541 DOI: https://doi.org/10.7554/eLife.76541

Licence

pathway_enrichment.R - Pathway enrichment analysis Written in 2019 by Wenjie SUN sunwjie@gmail.com

To the extent possible under law, the author(s) have dedicated all copyright and related and neighboring rights to this software to the public domain worldwide. This software is distributed without any warranty.

wenjie1991

library(data.table)
library(readr)
library(magrittr)
library(dplyr)
library(plotly)
library(lambda.tools)

read_model_data = function(model_file) {
    # @params model_file the Igor model files