michaelbarton

import System.Environment
import Data.List.Split
import Data.List
import qualified Data.Map.Strict as Map

main = do
  [f]      <- getArgs
  contents <- readFile f
  putStr . unlines . map unwords . map (kmers 6) . getSequences $ contents

michaelbarton

Continuous, reproducible genome assembler benchmarking

New bioinformatics software is always being produced and published. The constant stream of new developments makes it difficult to keep track of the software available for common bioinformatics tasks. An example of this is the domain of genome assembly where there is already a large number of existing software.

If you are researching which bioinformatics software to use, it can be difficult understanding how effective the software is. For example given a new

michaelbarton

DATA = SRR013437

# Allowed errors for primers and barcodes
# Even reads containing errors in these may still be usuable.
BCDE_ERS = 2
PRMR_ERS = 3

# Nucleotides differences to cluster sequences
DIFF = 4

michaelbarton

*.png
*.tab

michaelbarton

functions = [ [:map,    lambda{|x|   x * 3}],
              [:select, lambda{|x|   x % 2 == 0 }],
              [:reduce, lambda{|x,y| x + y}] ]

values = [1, 2, 3, 4]

p functions.inject(values){|x,(f,args)| x.send(f,&args) }
#=> 18

michaelbarton

#!/usr/bin/env clj
(use 'clojure.java.io)
(require ['clojure.contrib.string :as 'string])

(def pairs (first *command-line-args*))

(defn reciprocal-edge? [edges]
  (let [a (nth edges 0)
        b (nth edges 1)]
  (= (take 2 a) (take 2 b))))

michaelbarton

vimux
  - https://github.com/benmills/vimux
  - https://www.braintreepayments.com/braintrust/vimux-simple-vim-and-tmux-integration

vimrx-ruby-test
  - https://github.com/pgr0ss/vimux-ruby-test

tslime
  - https://github.com/kikijump/tslime.vim
  - try using with clojure repl

michaelbarton

#!/usr/bin/env ruby

require 'bio'

trnas = Bio::FlatFile.auto('genes.fna').
  map(&:definition).
  grep(/tRNA_..._.../).
  map{|i| /^(?<id>\d+).+tRNA_(?<amino_acid>...)_(?<codon>...)/.match(i)}.
  inject(Hash.new){|h,i| h[i[:id]] = {:amino_acid => i[:amino_acid], :codon => i[:codon]}; h}

michaelbarton

#!/usr/bin/env clj

(ns format
  (:require [clojure.string         :as str1])
  (:require [clojure.contrib.string :as str2]))

(def csv
  (map #(str2/split #"," %)
    (str2/split-lines
      (slurp (first *command-line-args*)))))

michaelbarton

#!/usr/bin/env Rscript

library(lubridate)
library(plyr)
library(ggplot2)

split.out <- function(string,split.at,position){
  sort(unlist(strsplit(string,split.at)))[[position]]
}