Wei Shen shenwei356

Filtering Spades assembly result according to coverage information in sequence header

Sample sequence

$ cat contigs.fasta 
>NODE_1_length_869844_cov_1135.34
ACTGNacgtn 
>NODE_2_length_576386_cov_975.882
acgtn

URL list

$ head choose_ftp.txt
ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/015/405/GCA_000015405.1_ASM1540v1
ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/620/625/GCA_000620625.1_ASM62062v1
ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/972/925/GCA_000972925.1_ASM97292v1
ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/001/021/385/GCA_001021385.1_ASM102138v1
ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/328/565/GCA_000328565.1_ASM32856v1

Target files

	#!/usr/bin/python
	import re
	from itertools import groupby

	s = '11M1D31M1I3M1D48M2I1M1D28M'
	g = re.findall('\d+[A-Z]', s) # ['11M', '1D', '31M', '1I', '3M', '1D', '48M', '2I', '1M', '1D', '28M']
	kv = [[x[-1], int(x[0:-1])] for x in g] # [['M', 11], ['D', 1], ['M', 31], ['I', 1], ['M', 3], ['D', 1], ['M', 48], ['I', 2], ['M', 1], ['D', 1], ['M', 28]]
	kv = sorted(kv, key=lambda e: e[0]) # fuck !! sorting needed!
	stat = { k: sum((g[1] for g in group)) for k, group in groupby(kv, key=lambda e: e[0])}
	print(stat) # {'M': 122, 'I': 3, 'D': 3}

	#!/usr/bin/env python
	# different implemention of nested dict in Python
	from collections import defaultdict


	# from: http://stackoverflow.com/questions/635483/what-is-the-best-way-to-implement-nested-dictionaries-in-python
	class AutoVivification(dict):
	def __getitem__(self, item):
	try:
	return dict.__getitem__(self, item)

	// run:
	//
	// go test -test.bench="." -test.cpuprofile=prof.out
	// go tool pprof ./gist.test prof.out
	package main

	import (
	"bytes"
	"testing"
	)

	#!/usr/bin/env python
	import argparse
	import random

	parser = argparse.ArgumentParser(description="generate test data",
	epilog="https://github.com/shenwei356/")
	parser.add_argument('-n',
	type=int,
	default=700000,
	help='number of query list')

	package main

	import (
	"fmt"
	)

	type IntGenerator struct {
	Chan chan int
	n int
	}

	scaf001 glean mRNA 20 30 0.4 - . somestring
	scaf001 glean CDS 30 50 . + 0 asdfasd
	scaf003 glean CDS 10 25 0.4 - . somestring

	var system = require('system');
	var page = require('webpage').create();

	page.open(system.args[1], function()
	{
	console.log(page.content);
	phantom.exit();
	});

	# Hello, and welcome to makefile basics.
	#
	# You will learn why `make` is so great, and why, despite its "weird" syntax,
	# it is actually a highly expressive, efficient, and powerful way to build
	# programs.
	#
	# Once you're done here, go to
	# http://www.gnu.org/software/make/manual/make.html
	# to learn SOOOO much more.