Python readFASTA 예제들

예제 #1

 def test_readFASTA(self):
     self.assertDictEqual(bioio.readFASTA(example_fasta_files),
                          expected_fasta_input)
     with self.assertRaises(SystemExit):
         bioio.readFASTA(['sample1.fasta', 'path/sample2.fasta'])
     with self.assertRaises(SystemExit):
         bioio.readFASTA(['sample1.fasta', 'sample2.txt'])

예제 #2

파일: unittests.py 프로젝트: WatzekDigitalInitiatives/informatix

 def test_writeFASTA(self):
     read_fasta_data = bioio.readFASTA(['sample1.fasta'])['sample1']
     read_fasta_data_seqids = bioio.splitFASTA(read_fasta_data)['output_seq_ids']
     read_fasta_data_seqs = bioio.splitFASTA(read_fasta_data)['output_seqs']
     bioio.writeFASTA('rewritten_sample1.fasta',read_fasta_data_seqids,read_fasta_data_seqs)
     self.assertEqual(bioio.readFASTA(['rewritten_sample1.fasta'])['rewritten_sample1'],read_fasta_data)
     os.remove('rewritten_sample1.fasta')

예제 #3

 def test_writeFASTA(self):
     read_fasta_data = bioio.readFASTA(['sample1.fasta'])['sample1']
     read_fasta_data_seqids = bioio.splitFASTA(
         read_fasta_data)['output_seq_ids']
     read_fasta_data_seqs = bioio.splitFASTA(read_fasta_data)['output_seqs']
     bioio.writeFASTA('rewritten_sample1.fasta', read_fasta_data_seqids,
                      read_fasta_data_seqs)
     self.assertEqual(
         bioio.readFASTA(['rewritten_sample1.fasta'])['rewritten_sample1'],
         read_fasta_data)
     os.remove('rewritten_sample1.fasta')

예제 #4

파일: splitOnIDPrefix.py 프로젝트: WatzekDigitalInitiatives/informatix

import sys
import os
sys.path.append(os.path.join(sys.path[0],'lib'))
sys.path.append(os.path.join(sys.path[0],'test'))
import bioio
import biomath

read_fasta = bioio.readFASTA([sys.argv[-1]])
input_fasta_name = sys.argv[-1][:-6]
input_fasta_data = read_fasta[input_fasta_name]

prefixList = ["ARC", "DRY", "LRE", "PER", "LRU", "PHO", "SIC", "LSP", "PLE", "SCY", "LAZ"]
for prefix in prefixList:
    bioio.splitOnIDPrefix(input_fasta_data, prefix)

예제 #5

파일: reduceNames.py 프로젝트: sophiahorigan/thesis

# -*- coding: utf-8 -*-
"""
@author: thatbudakguy
"""

import sys
import os
sys.path.append(os.path.join(sys.path[0],'lib'))
sys.path.append(os.path.join(sys.path[0],'test'))
import bioio
import biomath

# strip file extensions,'>' and read files
read_fasta = bioio.readFASTA([sys.argv[-2]])
input_fasta_name = sys.argv[-2][:-6]
input_fasta_data = read_fasta[input_fasta_name]
input_fasta_splitdata = bioio.splitFASTA(input_fasta_data)
input_fasta_seq_ids = input_fasta_splitdata['output_seq_ids']
input_fasta_seqs = input_fasta_splitdata['output_seqs']
read_txt = bioio.readTXT([sys.argv[-1]])
input_txt_name = sys.argv[-1][:-4]
input_txt_data = read_txt[input_txt_name]

# find seqs from database using seqids list
output_fasta_data = biomath.reduceNames(input_txt_data,input_fasta_seq_ids,input_fasta_seqs)
output_seq_ids = output_fasta_data['output_seq_ids']
output_seqs = output_fasta_data['output_seqs']

# write the seqs to the file
output_fasta_name = input_fasta_name+"_concatenated.fasta"
bioio.writeFASTA(output_fasta_name,output_seq_ids,output_seqs)

예제 #6

# -*- coding: utf-8 -*-
"""
@author: thatbudakguy
"""

import sys
import os
sys.path.append(os.path.join(sys.path[0],'lib'))
sys.path.append(os.path.join(sys.path[0],'test'))
import bioio
import biomath

# strip file extensions and read files
read_fasta = bioio.readFASTA(sys.argv[1])
input_fasta_name = sys.argv[1][:-6]
input_fasta_data = read_fasta[input_fasta_name]
input_fasta_splitdata = bioio.splitFASTA(input_fasta_data)
input_fasta_seq_ids = input_fasta_splitdata['output_seq_ids']
input_fasta_seqs = input_fasta_splitdata['output_seqs']
read_txt = bioio.readTXT(sys.argv[2:])
output_combined_data = []

# reformat and combine seqid lists
for filename,data in read_txt.iteritems():

	# split on greaterthans
	output_data = bioio.splitLinearSeqids(data)

	# add venom codes based on filename
	output_data = bioio.addVenomCodes(output_data,filename)

예제 #7

파일: compareHomologsProteomes.py 프로젝트: sophiahorigan/thesis

# -*- coding: utf-8 -*-
"""
@author: thatbudakguy
"""

import sys
import os
sys.path.append(os.path.join(sys.path[0], 'lib'))
sys.path.append(os.path.join(sys.path[0], 'test'))
import bioio
import biomath

# strip file extensions and read files
input_1 = sys.argv[-2]
input_2 = sys.argv[-1]
read_fasta_homologs = bioio.readFASTA([input_2])
input_homologs_fasta_name = input_2[:-6]
input_homologs_fasta_data = read_fasta_homologs[input_homologs_fasta_name]
input_homologs_fasta_seq_ids = bioio.splitFASTA(
    input_homologs_fasta_data)['output_seq_ids']
read_fasta_proteomes = bioio.readFASTA([input_1])
input_proteomes_fasta_name = input_1[:-6]
input_proteomes_fasta_data = read_fasta_proteomes[input_proteomes_fasta_name]
input_proteomes_fasta_seq_ids = bioio.splitFASTA(
    input_proteomes_fasta_data)['output_seq_ids']

# strip venom codes from proteomes
input_proteomes_fasta_seq_ids = bioio.trimVenomCodes(
    input_proteomes_fasta_seq_ids)
print input_homologs_fasta_seq_ids

예제 #8

파일: compareHomologsProteomes.py 프로젝트: WatzekDigitalInitiatives/informatix

# -*- coding: utf-8 -*-
"""
@author: thatbudakguy
"""

import sys
import os
sys.path.append(os.path.join(sys.path[0],'lib'))
sys.path.append(os.path.join(sys.path[0],'test'))
import bioio
import biomath

# strip file extensions and read files
input_1 = sys.argv[-2]
input_2 = sys.argv[-1]
read_fasta_homologs = bioio.readFASTA([input_2])
input_homologs_fasta_name = input_2[:-6]
input_homologs_fasta_data = read_fasta_homologs[input_homologs_fasta_name]
input_homologs_fasta_seq_ids = bioio.splitFASTA(input_homologs_fasta_data)['output_seq_ids']
read_fasta_proteomes = bioio.readFASTA([input_1])
input_proteomes_fasta_name = input_1[:-6]
input_proteomes_fasta_data = read_fasta_proteomes[input_proteomes_fasta_name]
input_proteomes_fasta_seq_ids = bioio.splitFASTA(input_proteomes_fasta_data)['output_seq_ids']

# strip venom codes from proteomes
input_proteomes_fasta_seq_ids = bioio.trimVenomCodes(input_proteomes_fasta_seq_ids)
print input_homologs_fasta_seq_ids

# compare input files to find missing and matching lines
output_seq_ids_match = biomath.findMatchingSeqs(input_homologs_fasta_seq_ids,input_proteomes_fasta_seq_ids)
output_seq_ids_miss = biomath.findMissingSeqs(input_homologs_fasta_seq_ids,input_proteomes_fasta_seq_ids)

예제 #9

 def test_splitFASTA(self):
     example_input_fasta = bioio.readFASTA(['sample1.fasta'])
     example_input_fasta = bioio.splitFASTA(example_input_fasta['sample1'])
     self.assertDictEqual(example_input_fasta, expected_split_data)

예제 #10

파일: unittests.py 프로젝트: WatzekDigitalInitiatives/informatix

 def test_splitFASTA(self):
     example_input_fasta = bioio.readFASTA(['sample1.fasta'])
     example_input_fasta = bioio.splitFASTA(example_input_fasta['sample1'])
     self.assertDictEqual(example_input_fasta,expected_split_data)

예제 #11

파일: unittests.py 프로젝트: WatzekDigitalInitiatives/informatix

 def test_readFASTA(self):
     self.assertDictEqual(bioio.readFASTA(example_fasta_files),expected_fasta_input)
     with self.assertRaises(SystemExit):
         bioio.readFASTA(['sample1.fasta','path/sample2.fasta'])
     with self.assertRaises(SystemExit):
         bioio.readFASTA(['sample1.fasta','sample2.txt'])