for i in range(len(groups_list)):
group_hits = []
kv.make_id_list_fasta(groups_list[i], 'core')
results = blast_vs_db('tmp.fna', 'blast_databases/other')
hits_collection = kv.get_collection('hits')
if results:
for j in range(len(results)):
group_hits.append(results[j])
hits_collection.insert_one({'group':(i+1), 'group_hits':group_hits})
if __name__ == '__main__':
import sys
kv.mongo_init('pacbio2')
os.chdir('/Users/KBLaptop/computation/kvasir/data/output/pacbio2/')
# kv.mongo_init(sys.argv[1])
# os.chdir('output/{}/'.format(sys.argv[1]))
make_blast_db('core')
make_blast_db('other')
hits_reset()
hgt_blast(perc_identity='90')
hgt_blast(perc_identity='95')
hgt_blast(perc_identity='99')
blast_to_db(perc_identity='90')
blast_to_db(perc_identity='95')
blast_to_db(perc_identity='99')
other_blast()
for i in range(len(ssu_df['strain'])):
print ssu_df['strain'][i], ssu_df['16S'][i]
if not pd.isnull(ssu_df['16S'][i]):
gene_record = {
'species':ssu_df['strain'][i],
'location':{
'contig':None,
'start':None,
'end':None,
'strand':None,
},
'annotation':'Small subunit ribosomal RNA',
'dna_seq':ssu_df['16S'][i],
'kvtag':None,
'type':'16S'
}
print "adding 16S gene!"
kv.get_collection('16S').remove({'species':ssu_df['strain'][i]})
print kv.get_collection('16S').find_one({'species':ssu_df['strain'][i]})
kv.get_collection('16S').insert_one(gene_record)
print kv.get_collection('16S').find_one({'species':ssu_df['strain'][i]})
def get_list_from_tree(newick_file):
pass
if __name__ == '__main__':
os.chdir('/Users/KBLaptop/computation/kvasir/data/output/reorg/')
kv.mongo_init('reorg')
fig = plt.figure()
ypos = 1
for pair in list_of_species_pairs:
if pair[0] == pairs[0][0]:
ax = fig.add_axes([1,ypos,1,1])
output_loc_hist(pair[0], pair[1], ax)
plot_url = py.plot_mpl(fig)
print plot_url
# plt.xlabel("Position")
# plt.ylabel("percent identity")
# plt.savefig('/Users/KBLaptop/Desktop/try.pdf')
if __name__ == '__main__':
kv.mongo_init('more_genomes')
os.chdir('/Users/KBLaptop/computation/kvasir/data/output/more_genomes/')
ls = kv.get_species_collections()
print ls
ls.remove('Arthrobacter_arilaitensis_Re117')
pairs = []
for pair in combinations(ls, 2):
pairs.append((pair[0], pair[1]))
plot_many(pairs)
# if os.path.isfile('{}_{}.pdf'.format(pair[0], pair[1])):
# continue
# try:
# output_loc_hist(pair[0], pair[1])
# except RuntimeError:
#!/usr/bin/env python # by Kevin Bonham, PhD (2015) # for Dutton Lab, Harvard Center for Systems Biology, Cambridge MA # Unless otherwise indicated, licensed under GNU Public License (GPLv3) import sys import KvDataStructures as kv kv.mongo_init(sys.argv[1]) kv.reset_database(kv.db.name)