Shixiang Wang (王诗翔) ShixiangWang

## tcga_replicateFilter.R
#---------------------------------------------------
# Filter TCGA Replicate Samples
# Author: ShixiangWang <w_shixiang@163.com>
# ooooooo
# The filter rule following broad institute says:
#
# In many instances there is more than one aliquot for a given combination of individual, platform, and data type. However, only one aliquot may be ingested into Firehose. Therefore, a set of precedence rules are applied to select the most scientifically advantageous one among them. Two filters are applied to achieve this aim: an Analyte Replicate Filter and a Sort Replicate Filter.
#
# Analyte Replicate Filter
# The following precedence rules are applied when the aliquots have differing analytes. For RNA aliquots, T analytes are dropped in preference to H and R analytes, since T is the inferior extraction protocol. If H and R are encountered, H is the chosen analyte. This is somewhat arbitrary and subject to change, since it is not clear at present whether H or R is the better protocol. If there are multiple aliquots as

## Genome_Informatics_2017_software.csv

          
            url
            name
            user
            type

            
              https://bioconductor.org/packages/regioneR
              regioneR
              NA
              Bioconductor

            
              https://bioconductor.org/packages/karyoploteR
              karyoploteR
              NA
              Bioconductor

            
              https://bioconductor.org/packages/metavizr
              metavizr
              NA
              Bioconductor

            
              https://bioconductor.org/packages/IsoformSwitchAnalyzeR
              IsoformSwitchAnalyzeR
              NA
              Bioconductor

            
              https://cran.rstudio.com/packages/UpSetR
              UpSetR
              NA
              CRAN

            
              https://github.com/pachterlab/sleuth
              sleuth
              pachterlab
              github

            
              https://github.com/nekrut/lab_site
              lab_site
              nekrut
              github

            
              https://github.com/bernatgel/karyoploter_tutorial
              karyoploter_tutorial
              bernatgel
              github

            
              https://bitbucket.org/biobakery/metaphlan2
              metaphlan2
              biobakery
              github

## clean.sh
#!/usr/bin/env bash
# identify and remove broke images
# with imageMagick

for i in $(ls -d train/cat/* train/fish/* val/cat/* val/fish/* test/cat/* test/fish/*); do
    identify $i > /dev/null 2>&1
    if [ $? -ne 0 ]; then
      echo "file $i is broken, removing it"
      rm $i
    fi

## platformMap.txt
"title"	"gpl"	"bioc_package"	"manufacturer"	"organism"	"data_row_count"
"Illumina Sentrix Array Matrix (SAM) - GoldenGate Methylation Cancer Panel I"	"GPL15380"	"GGHumanMethCancerPanelv1"	"Illumina"	"Homo sapiens"	1536
"Illumina HumanMethylation27 BeadChip (HumanMethylation27_270596_v.1.2)"	"GPL8490"	"IlluminaHumanMethylation27k"	"Illumina, Inc."	"Homo sapiens"	27578
"Illumina HumanMethylation450 BeadChip (HumanMethylation450_15017482)"	"GPL13534"	"IlluminaHumanMethylation450k"	"Illumina, Inc."	"Homo sapiens"	485577
"GE Healthcare/Amersham Biosciences CodeLink™   ADME Rat 16-Assay Bioarray"	"GPL2898"	"adme16cod"	"GE Healthcare"	"Rattus norvegicus"	1280
"[AG] Affymetrix Arabidopsis Genome Array"	"GPL71"	"ag"	"Affymetrix"	"Arabidopsis thaliana"	8297
"[ATH1-121501] Affymetrix Arabidopsis ATH1 Genome Array"	"GPL198"	"ath1121501"	"Affymetrix"	"Arabidopsis thaliana"	22810
"[Bovine] Affymetrix Bovine Genome Array"	"GPL2112"	"bovine"	"Affymetrix"	"Bos taurus"	24128
"[Canine] Affymetrix Canine Genome 1.0 Array"	"GPL39

## groupSurvival.R
library(survival)
library(survminer)

groupSurvival <- function(df, event="OS_IND", time="OS", var=NULL, time.limit=NULL, interval=c("open","close"),
                          method=c("quartile", "mean", "median", "percent", "custom"), percent=NULL,
                          step=20, custom_fun=NULL, group1="High", group2="Low"){
    #'@param df a data.frame at leaset including three column which refer to survival info and variable used to
    #'                       set group.
    #'@param event The status indicator, normally 0=alive, 1=dead. Other choices are TRUE/FALSE (TRUE = death) or 1/2 (2=death).
    #'For interval censored data, the status indicator is 0=right censored, 1=event at time, 2=left censored, 3=interval censored.

## new_post.R
################
## 用rmd写博客 ##
################

# 作者：王诗翔
# 更新日期：2018-02-12


#>>>>>> new_rmd_post 函数 <<<<<<<<<<
# 写好模板文档后，你可以用这个函数来创建Rmarkdown文档

## extract.sh
#!/bin/bash
# function Extract for common file formats

function extract {
 if [ -z "$1" ]; then
    # display usage if no parameters given
    echo "Usage: extract <path/file_name>.<zip|rar|bz2|gz|tar|tbz2|tgz|Z|7z|xz|ex|tar.bz2|tar.gz|tar.xz>"
 else
    if [ -f "$1" ] ; then
        NAME=${1%.*}

## product-info.csv

          
            id
            name
            type
            class
            released

            
              T01
              SupCar
              toy
              vehicle
              yes

            
              T02
              SupPlane
              toy
              vehicle
              no

            
              M01
              JeepX
              model
              vehicle
              yes

            
              M02
              AircraftX
              model
              vehicle
              yes

            
              M03
              Runner
              model
              people
              yes

            
              M04
              Dancer
              model
              people
              no

## init.coffee
# Your init script
#
# Atom will evaluate this file each time a new window is opened. It is run
# after packages are loaded/activated and after the previous editor state
# has been restored.
#
# An example hack to log to the console when each text editor is saved.
#
# atom.workspace.observeTextEditors (editor) ->
#   editor.onDidSave ->

## Bioc2017.R
# ---------------------------
# Accessing the material
# https://tinyurl.com/bioc2017-ELMER
# ---------------------------
library("Bioc2017.TCGAbiolinks.ELMER")
Biobase::openVignette("Bioc2017.TCGAbiolinks.ELMER")

# ---------------------------
# Section 1:
# Aims:
	#---------------------------------------------------
	# Filter TCGA Replicate Samples
	# Author: ShixiangWang <w_shixiang@163.com>
	# ooooooo
	# The filter rule following broad institute says:
	#
	# In many instances there is more than one aliquot for a given combination of individual, platform, and data type. However, only one aliquot may be ingested into Firehose. Therefore, a set of precedence rules are applied to select the most scientifically advantageous one among them. Two filters are applied to achieve this aim: an Analyte Replicate Filter and a Sort Replicate Filter.
	#
	# Analyte Replicate Filter
	# The following precedence rules are applied when the aliquots have differing analytes. For RNA aliquots, T analytes are dropped in preference to H and R analytes, since T is the inferior extraction protocol. If H and R are encountered, H is the chosen analyte. This is somewhat arbitrary and subject to change, since it is not clear at present whether H or R is the better protocol. If there are multiple aliquots as
url	name	user	type
https://bioconductor.org/packages/regioneR	regioneR	NA	Bioconductor
https://bioconductor.org/packages/karyoploteR	karyoploteR	NA	Bioconductor
https://bioconductor.org/packages/metavizr	metavizr	NA	Bioconductor
https://bioconductor.org/packages/IsoformSwitchAnalyzeR	IsoformSwitchAnalyzeR	NA	Bioconductor
https://cran.rstudio.com/packages/UpSetR	UpSetR	NA	CRAN
https://github.com/pachterlab/sleuth	sleuth	pachterlab	github
https://github.com/nekrut/lab_site	lab_site	nekrut	github
https://github.com/bernatgel/karyoploter_tutorial	karyoploter_tutorial	bernatgel	github
https://bitbucket.org/biobakery/metaphlan2	metaphlan2	biobakery	github
	#!/usr/bin/env bash
	# identify and remove broke images
	# with imageMagick

	for i in $(ls -d train/cat/* train/fish/* val/cat/* val/fish/* test/cat/* test/fish/*); do
	identify $i > /dev/null 2>&1
	if [ $? -ne 0 ]; then
	echo "file $i is broken, removing it"
	rm $i
	fi
	"title" "gpl" "bioc_package" "manufacturer" "organism" "data_row_count"
	"Illumina Sentrix Array Matrix (SAM) - GoldenGate Methylation Cancer Panel I" "GPL15380" "GGHumanMethCancerPanelv1" "Illumina" "Homo sapiens" 1536
	"Illumina HumanMethylation27 BeadChip (HumanMethylation27_270596_v.1.2)" "GPL8490" "IlluminaHumanMethylation27k" "Illumina, Inc." "Homo sapiens" 27578
	"Illumina HumanMethylation450 BeadChip (HumanMethylation450_15017482)" "GPL13534" "IlluminaHumanMethylation450k" "Illumina, Inc." "Homo sapiens" 485577
	"GE Healthcare/Amersham Biosciences CodeLink™ ADME Rat 16-Assay Bioarray" "GPL2898" "adme16cod" "GE Healthcare" "Rattus norvegicus" 1280
	"[AG] Affymetrix Arabidopsis Genome Array" "GPL71" "ag" "Affymetrix" "Arabidopsis thaliana" 8297
	"[ATH1-121501] Affymetrix Arabidopsis ATH1 Genome Array" "GPL198" "ath1121501" "Affymetrix" "Arabidopsis thaliana" 22810
	"[Bovine] Affymetrix Bovine Genome Array" "GPL2112" "bovine" "Affymetrix" "Bos taurus" 24128
	"[Canine] Affymetrix Canine Genome 1.0 Array" "GPL39
	library(survival)
	library(survminer)

	groupSurvival <- function(df, event="OS_IND", time="OS", var=NULL, time.limit=NULL, interval=c("open","close"),
	method=c("quartile", "mean", "median", "percent", "custom"), percent=NULL,
	step=20, custom_fun=NULL, group1="High", group2="Low"){
	#'@param df a data.frame at leaset including three column which refer to survival info and variable used to
	#' set group.
	#'@param event The status indicator, normally 0=alive, 1=dead. Other choices are TRUE/FALSE (TRUE = death) or 1/2 (2=death).
	#'For interval censored data, the status indicator is 0=right censored, 1=event at time, 2=left censored, 3=interval censored.
	################
	## 用rmd写博客 ##
	################

	# 作者：王诗翔
	# 更新日期：2018-02-12


	#>>>>>> new_rmd_post 函数 <<<<<<<<<<
	# 写好模板文档后，你可以用这个函数来创建Rmarkdown文档
	#!/bin/bash
	# function Extract for common file formats

	function extract {
	if [ -z "$1" ]; then
	# display usage if no parameters given
	echo "Usage: extract <path/file_name>.<zip\|rar\|bz2\|gz\|tar\|tbz2\|tgz\|Z\|7z\|xz\|ex\|tar.bz2\|tar.gz\|tar.xz>"
	else
	if [ -f "$1" ] ; then
	NAME=${1%.*}
id	name	type	class	released
T01	SupCar	toy	vehicle	yes
T02	SupPlane	toy	vehicle	no
M01	JeepX	model	vehicle	yes
M02	AircraftX	model	vehicle	yes
M03	Runner	model	people	yes
M04	Dancer	model	people	no
	# Your init script
	#
	# Atom will evaluate this file each time a new window is opened. It is run
	# after packages are loaded/activated and after the previous editor state
	# has been restored.
	#
	# An example hack to log to the console when each text editor is saved.
	#
	# atom.workspace.observeTextEditors (editor) ->
	# editor.onDidSave ->
	# ---------------------------
	# Accessing the material
	# https://tinyurl.com/bioc2017-ELMER
	# ---------------------------
	library("Bioc2017.TCGAbiolinks.ELMER")
	Biobase::openVignette("Bioc2017.TCGAbiolinks.ELMER")

	# ---------------------------
	# Section 1:
	# Aims: