#taxa_file = os.path.expanduser("~/data_analysis/data/genome_assemblies/test_genomes_02062016.tsv")
taxa_file = os.path.expanduser("~/data_analysis/data/genome_assemblies/genome_lists/genomes_euks_Fungi_Protists_02082016.tsv")
#taxa_file = os.path.expanduser("~/data_analysis/data/genome_assemblies/genome_lists/test_genomes_02062016.tsv")
#taxa_file = os.path.expanduser("~/data_analysis/data/genome_assemblies/Sacch_with_headers.tsv")
output_path = os.path.expanduser("~/data_analysis/data/genome_assemblies/assemblies_02152016")
seq_downloader = os.path.expanduser("~/data_analysis/code/bioinformatics-toolbox/src/seq_convert_genbank.pl")
# Parameters
parse_headers = 0
taxa_col = 0
# Load taxa file data
print(tistamp(1)+"\tReading taxa...")
taxa = []
with open(taxa_file) as inputfile:
for line in inputfile:
taxa.append(line.strip().split(','))
validated_taxa = 0
reset_validation = 1
taxa_i = 0
skip_to = 0
end_at = 999
# Parse data
for taxon in taxa[1:]:
taxa_i = taxa_i + 1
# Skip ahead
"~/data_analysis/data/genome_assemblies/genome_lists/genomes_euks_Fungi_Protists_02082016.tsv"
)
#taxa_file = os.path.expanduser("~/data_analysis/data/genome_assemblies/genome_lists/test_genomes_02062016.tsv")
#taxa_file = os.path.expanduser("~/data_analysis/data/genome_assemblies/Sacch_with_headers.tsv")
output_path = os.path.expanduser(
"~/data_analysis/data/genome_assemblies/assemblies_02152016")
seq_downloader = os.path.expanduser(
"~/data_analysis/code/bioinformatics-toolbox/src/seq_convert_genbank.pl")
# Parameters
parse_headers = 0
taxa_col = 0
# Load taxa file data
print(tistamp(1) + "\tReading taxa...")
taxa = []
with open(taxa_file) as inputfile:
for line in inputfile:
taxa.append(line.strip().split(','))
validated_taxa = 0
reset_validation = 1
taxa_i = 0
skip_to = 0
end_at = 999
# Parse data
for taxon in taxa[1:]:
taxa_i = taxa_i + 1
# Skip ahead
print("Cache: " + str(clear_cache))
'''
-word_size <Integer, >=4>
Word size for wordfinder algorithm (length of best perfect match)
-gapopen <Integer>
Cost to open a gap
-gapextend <Integer>
Cost to extend a gap
-penalty <Integer, <=0>
Penalty for a nucleotide mismatch
-reward <Integer, >=0>
Reward for a nucleotide match
'''
# Load query file names
print(tistamp(1) + "\tReading queries...")
queries = []
with open(query_file) as inputfile:
for line in inputfile:
queries.append(line.strip().split(','))
# Load database file names
print(tistamp(1) + "\tReading databases...")
databases = []
with open(db_file) as inputfile:
for line in inputfile:
databases.append(line.strip().split(','))
# Start main loop of query sequence files
for query_file in queries:
query_file = ''.join(query_file[0])
'''
-word_size <Integer, >=4>
Word size for wordfinder algorithm (length of best perfect match)
-gapopen <Integer>
Cost to open a gap
-gapextend <Integer>
Cost to extend a gap
-penalty <Integer, <=0>
Penalty for a nucleotide mismatch
-reward <Integer, >=0>
Reward for a nucleotide match
'''
# Load query file names
print(tistamp(1)+"\tReading queries...")
queries = []
with open(query_file) as inputfile:
for line in inputfile:
queries.append(line.strip().split(','))
# Load database file names
print(tistamp(1)+"\tReading databases...")
databases = []
with open(db_file) as inputfile:
for line in inputfile:
databases.append(line.strip().split(','))
# Start main loop of query sequence files
for query_file in queries:
query_file = ''.join(query_file[0])