예제 #1
0
def question_07():
	sequences, qualities = dnaseq.read_fastq("ERR037900_1.first1000.fastq")
	stats = {}
	for i in range(len(sequences)):
		for j in range(len(sequences[i])):
			stats[j] = stats.get(j, 0) + qualities[i][j]
	r = min(stats.iterkeys(), key=(lambda x: stats[x]))
	print "question_07: %i" % r
예제 #2
0
#!/usr/bin/python

import dnaseq
import bm_preproc
import kmer_index

human_chromosome = dnaseq.read_genome("chr1.GRCh38.excerpt.fasta")
phix_reads, _ = dnaseq.read_fastq("ERR266411_1.for_asm.fastq")

def question_01():
	p = "GCTGATCGATCGTACG"
	d = dnaseq.approximate_match_distance(human_chromosome, p)
	print "question_01: %i" % d

def question_02():
	p = "GATTTACCAGATTGAG"
	d = dnaseq.approximate_match_distance(human_chromosome, p)
	print "question_02: %i" % d

def question_03():
	d, _ = dnaseq.overlap_graph(phix_reads, 30)
	print "question_03: %i" % len(d)

def question_04():
	_, n = dnaseq.overlap_graph(phix_reads, 30)
	print "question_04: %i" % n


if __name__ == '__main__':
	question_01()
	question_02()
예제 #3
0
#!/usr/bin/python

import dnaseq
import bm_preproc
import kmer_index

mystery_virus_reads, _ = dnaseq.read_fastq("ads1_week4_reads.fq")
mystery_virus_genom = dnaseq.assemble(mystery_virus_reads, 30)

def question_01():
	ss = ["CCT", "CTT", "TGC", "TGG", "GAT", "ATT"]
	s, _ = dnaseq.scs(ss)
	print "question_01: %i" % len(s)

def question_02():
	ss = ["CCT", "CTT", "TGC", "TGG", "GAT", "ATT"]
	_, options = dnaseq.scs(ss)
	print "question_02: %i" % len(options)

def question_03():
	print "question_03: %i" % mystery_virus_genom.count("A")

def question_04():
	print "question_04: %i" % mystery_virus_genom.count("T")

def question_05():
	print "question_04:"
	print "--------- GENOM BEGIN ---------"
	print mystery_virus_genom
	print "--------- GENOM END ---------"