Kevin Lee cyklee

## count_fastq.sh
for i in *.fastq; do
  echo $(cat $i| wc -l)/4 | bc >> count.txt # can use zcat for gzipped files
done

calc `paste -sd+ count.txt`

## find.replace.sh
paste Short.name.txt Proper.name.txt | while read n k; do sed -i "s/$n/$k/g" tree.nwk; done

## sequencial.grep.sh
# https://stackoverflow.com/questions/21908809/grep-f-file-to-print-in-order-as-a-file
# You can pipe patt.grep (pattern) to xargs, which will pass the patterns to grep one at a time.
# By default xargs appends arguments at the end of the command. But in this case, grep needs myfile.log to be the last argument. So use the -I{} option to tell xargs to replace {} with the arguments.
# foobar here is the placeholder

# This is useful as grep
cat patt.grep | xargs -Ifoobar grep foobar myfile.log

## count.fastq.nucleotides
# If, for some crazy reason, you want to know how many individual bases you have in your dataset.
for i in *.fastq; do
cat $i | paste - - - - | cut -f 2 | tr -d '\n' | wc -c >> char.txt
done
R -e 'sum(read.csv("char.txt"))'

# You can replace *.fastq with *.fastq.gz and cat with zcat if your data is compressed

## extract_fasta_awk.sh
awk -v seq="header_id" -v RS='>' '$1 == seq {print RS $0}' file

## prokkagff2gtf.sh
#!/bin/bash

infile=$1

if [ "$infile" == "" ] ; then
    echo "Usage: prokkagff2gtf.sh <PROKKA gff file>"
    exit 0
fi

grep -v "#" $infile | grep "ID=" | cut -f1 -d ';' | sed 's/ID=//g' | cut -f1,4,5,7,9 |  awk -v OFS='\t' '{print $1,"PROKKA","CDS",$2,$3,".",$4,".","gene_id " $5}'

## import_biom2.R
import_biom2 <- function(x,
                         treefilename=NULL, refseqfilename=NULL, refseqFunction=readDNAStringSet, refseqArgs=NULL,
                         parseFunction=parse_taxonomy_default, parallel=FALSE, version=1.0, ...){

  # initialize the argument-list for phyloseq. Start empty.
  argumentlist <- list()

  x = read_biom(x)
  b_data = biom_data(x)
  b_data_mat = as(b_data, "matrix")

## port_forwarding.sh
# Port forwarding using miniUPNP client
# Use crontab to automate upon reboot
# https://superuser.com/questions/634628/is-there-a-script-to-add-port-forwarding-rule-in-home-router

upnpc -a `ifconfig wlan0 | grep "inet addr" | cut -d : -f 2 | cut -d " " -f 1` 22 22 TCP
upnpc -a `ifconfig wlan0 | grep "inet addr" | cut -d : -f 2 | cut -d " " -f 1` 5900 5900 TCP
upnpc -a `ifconfig wlan0 | grep "inet addr" | cut -d : -f 2 | cut -d " " -f 1` 9091 9091 TCP

## Subset_FASTA.sh
# https://www.biostars.org/p/49820/
# https://github.com/mdshw5/pyfaidx can be used as a drop-in replacement
xargs samtools faidx test.fa < names.txt

## manjaro_vboxsf.sh
su
systemctl enable vboxservice
systemctl start vboxservice
groupadd vboxsf
gpasswd -a $USER vboxsf
exit

sudo usermod -aG vboxsf $(whoami)
# Log off & log back in
	for i in *.fastq; do
	echo $(cat $i\| wc -l)/4 \| bc >> count.txt # can use zcat for gzipped files
	done

	calc `paste -sd+ count.txt`
	# https://stackoverflow.com/questions/21908809/grep-f-file-to-print-in-order-as-a-file
	# You can pipe patt.grep (pattern) to xargs, which will pass the patterns to grep one at a time.
	# By default xargs appends arguments at the end of the command. But in this case, grep needs myfile.log to be the last argument. So use the -I{} option to tell xargs to replace {} with the arguments.
	# foobar here is the placeholder

	# This is useful as grep
	cat patt.grep \| xargs -Ifoobar grep foobar myfile.log
	# If, for some crazy reason, you want to know how many individual bases you have in your dataset.
	for i in *.fastq; do
	cat $i \| paste - - - - \| cut -f 2 \| tr -d '\n' \| wc -c >> char.txt
	done
	R -e 'sum(read.csv("char.txt"))'

	# You can replace .fastq with .fastq.gz and cat with zcat if your data is compressed
	#!/bin/bash

	infile=$1

	if [ "$infile" == "" ] ; then
	echo "Usage: prokkagff2gtf.sh <PROKKA gff file>"
	exit 0
	fi

	grep -v "#" $infile \| grep "ID=" \| cut -f1 -d ';' \| sed 's/ID=//g' \| cut -f1,4,5,7,9 \| awk -v OFS='\t' '{print $1,"PROKKA","CDS",$2,$3,".",$4,".","gene_id " $5}'
	import_biom2 <- function(x,
	treefilename=NULL, refseqfilename=NULL, refseqFunction=readDNAStringSet, refseqArgs=NULL,
	parseFunction=parse_taxonomy_default, parallel=FALSE, version=1.0, ...){

	# initialize the argument-list for phyloseq. Start empty.
	argumentlist <- list()

	x = read_biom(x)
	b_data = biom_data(x)
	b_data_mat = as(b_data, "matrix")
	# Port forwarding using miniUPNP client
	# Use crontab to automate upon reboot
	# https://superuser.com/questions/634628/is-there-a-script-to-add-port-forwarding-rule-in-home-router

	upnpc -a `ifconfig wlan0 \| grep "inet addr" \| cut -d : -f 2 \| cut -d " " -f 1` 22 22 TCP
	upnpc -a `ifconfig wlan0 \| grep "inet addr" \| cut -d : -f 2 \| cut -d " " -f 1` 5900 5900 TCP
	upnpc -a `ifconfig wlan0 \| grep "inet addr" \| cut -d : -f 2 \| cut -d " " -f 1` 9091 9091 TCP
	# https://www.biostars.org/p/49820/
	# https://github.com/mdshw5/pyfaidx can be used as a drop-in replacement
	xargs samtools faidx test.fa < names.txt
	su
	systemctl enable vboxservice
	systemctl start vboxservice
	groupadd vboxsf
	gpasswd -a $USER vboxsf
	exit

	sudo usermod -aG vboxsf $(whoami)
	# Log off & log back in