yannickwurm

Keybase proof

I hereby claim:

• I am yannickwurm on github.
• I am yannickwurm (https://keybase.io/yannickwurm) on keybase.
• I have a public key ASAc2uIUfWuRgyD_pL3W24qhH4QIrd41fz8nqpUiuzSzIAo

To claim this, I am signing this object:

yannickwurm

1. Create authentification token on github

2. cd to somewhere with some space.

3. The following

ACCESS_TOKEN=theSetOfLettersAndNumbersInGithubAuthentificationToken
curl -s "https://api.github.com/orgs/wurmlab/repos?page=1&per_page=100&type=private&access_token=$ACCESS_TOKEN" | ruby -rubygems -e 'require "json"; JSON.load(STDIN.read).each { |repo| %x[git clone #{repo["ssh_url"]} ]}'

yannickwurm

ants_fyi <- read.table("https://bit.ly/antsofuk")
colnames(ants_fyi) <- c("genus", "species")
nrow(ants_fyi)
head(ants_fyi)

play_guess_the_genus <- function() {
    ants <- read.table("https://bit.ly/antsofuk")
    colnames(ants) <- c("genus", "species")
    score <- 0
    attempts <- 0

yannickwurm

egrep '^@' in.fq | cut -f 1 -d ' ' | sort | uniq -c > in.fq.counts   

cat in.fq.counts | egrep " 1 " | ruby -pe 'gsub(/ +1 @/, "")' > in.fq.orphan_ids
cat in.fq.counts | egrep " 2 " | ruby -pe 'gsub(/ +2 @/, "")' > in.fq.paired_ids 


then subseq

yannickwurm

  def parse(signalp_hash, open_reading_frames_condensed, motif)
      signalp_with_seq = {}
      signalp_hash.each do |id, h|
          current_orf = open_reading_frames_condensed[id]
          sequence = current_orf.to_s.gsub('["', '').gsub('"]', '')
          sp_clv = h[0][:cut_off].to_i - 1
          signalp = sequence[0,sp_clv]
          seq_end = sequence[sp_clv+1, sequence.length - (sp_clv+1)]
           if seq_end.match(/#{motif}/)
                signalp_with_seq[id + "~- S.P. Cleavage Site: #{sp_clv}:" \

yannickwurm

    def YWSystemTools.number_of_processors
        if RUBY_PLATFORM =~ /linux/
            cpuinfo = IO.readlines("/proc/cpuinfo").delete_if{|x| x.index("processor")==nil}
            return cpuinfo.length
        elsif RUBY_PLATFORM =~ /darwin/
            return `sysctl -n hw.logicalcpu`.to_i
        elsif RUBY_PLATFORM =~ /win32/
            #            this works for windows 2000 or greater
            require 'win32ole'
            wmi = WIN32OLE.connect("winmgmts://")

yannickwurm

        ('proc00001'..'proc00024').each do |processor|
            threads << Thread.new(processor) do |threadid|                                                          
                until commandArray.empty?
                    commandToRun = commandArray.pop
                    $log.info('running:' + commandToRun)
##                    %x[#{commandToRun}] 
                    stdout = %x[#{commandToRun}]
                    print(stdout)
                end
            end

yannickwurm

    def YWSystemTools.runMultithreaded(commandArray)
        # runs commands on N processors at a time - can take more jobs & launches them sequentially.

        if commandArray.length > 1
            $log.info("#{commandArray.length} commands to run")
        elsif commandArray.length == 1
            $log.warn("only one command!")
        else
            raise ArgumentError, 'No commands to run!'
        end

yannickwurm

#!/usr/bin/env ruby
# (copy) Yannick Wurm - google me.
# All right reserved. 

help = "Usage: \n" + 
       "      #{$0} MySequences_R1.fastq MySequences_R2.fastq > MySequences_R1R2pasted.fastq\n" + 
       "Joins two paired reads into a single megaread. Can be helpful for deduplication.\n" +
       "The two fastq files must have reads in the same order. Some error checking is performed.\n"

yannickwurm

# from https://en.wikipedia.org/wiki/List_of_ants_of_Great_Britain - unclear how reliable
Anergates atratulus
Camponotus sp.
Crematogaster scutellaris
Formica aquilonia
Formica cunicularia
Formica exsecta
Formica fusca
Formica lemani
Formica lugubris