def import_3Ds(db_host = 'localhost', db_port = 27017, rna3dhub = False, canonical_only = True, annotate = False, limit = 5000):
client = MongoClient(db_host, db_port)
db_name = ""
if rna3dhub:
db_name = "RNA3DHub"
else:
rna3dHub = None
db_name = "PDB"
db = client[db_name]
rnaview = Rnaview()
if not rna3dhub:
pdb = PDB()
query ="""<orgPdbQuery>
<version>head</version>
<queryType>org.pdb.query.simple.ChainTypeQuery</queryType>
<description>Chain Type: there is a Protein and a RNA chain but not any DNA or Hybrid</description>
<containsProtein>N</containsProtein>
<containsDna>N</containsDna>
<containsRna>Y</containsRna>
<containsHybrid>N</containsHybrid>
</orgPdbQuery>"""
pdb_ids = pdb.query(query)
print "%i 3Ds to process"%len(pdb_ids)
for pdb_id in pdb_ids:
if db['tertiaryStructures'].find_one({'source':"db:pdb:%s"%pdb_id}):
continue
print "Recover %s"%pdb_id
for ts in parsers.parse_pdb(pdb.get_entry(pdb_id)):
try:
ss = None
if annotate:
ss, ts = rnaview.annotate(ts, canonical_only = canonical_only)
save(db, ss, ts, pdb_id, limit)
except Exception, e:
print e
print "No annotation for %s"%pdb_id
save(db, None, ts, pdb_id, limit)
def test():
print "Recovering entry 1EHZ from Protein Databank...\n"
pdb = PDB()
tertiary_structures = parse_pdb(pdb.get_entry('1EHZ'))
print "## 3D annotation ##\n"
print "List of base-pairs computed with RNAVIEW:\n"
for ts in tertiary_structures:
secondary_structure, tertiary_structure = Rnaview().annotate(ts)
print secondary_structure_to_base_pairs(secondary_structure, keep_tertiaries = True)
print "\n## 2D prediction ##\n"
for ts in tertiary_structures:
print "RNA sequence from 1EHZ:\n"
print ts.rna.sequence
print "\nList of base-pairs computed with RNAfold (RNA Vienna Package):\n"
print Rnafold().fold(molecule=ts.rna)
save(db, ss, ts, pdb_id, limit)
except Exception, e:
print e
print "No annotation for %s"%pdb_id
else:
pdb = PDB()
rna3dHub = RNA3DHub()
clusters = rna3dHub.get_clusters()
print "%i 3Ds to process"%len(clusters)
for cluster in clusters['pdb-ids']:
if db['tertiaryStructures'].find_one({'source':"db:pdb:%s"%cluster[0]}):
continue
print "Recover %s"%cluster[0] #we use the first pdb_id in the list of ids making a cluster
for ts in parsers.parse_pdb(pdb.get_entry(cluster[0])):
try:
ss = None
if annotate:
ss, ts = rnaview.annotate(ts, canonical_only = canonical_only)
save(db, ss, ts, cluster[0], limit)
except Exception, e:
print e
print "No annotation for %s"%cluster[0]
def save(db, secondary_structure, tertiary_structure, pdbId, limit):
if db['junctions'].count() >= limit:
print "Limit of %i junctions reached"%limit
sys.exit()
except Exception, e:
print e
print "No annotation for %s"%pdb_id
save(db, None, ts, pdb_id, limit)
else:
pdb = PDB()
rna3dHub = RNA3DHub()
clusters = rna3dHub.get_clusters()
print "%i 3Ds to process"%len(clusters)
for cluster in clusters['pdb-ids']:
pdb_id = cluster[0].split('|')[0]
if db['tertiaryStructures'].find_one({'source':"db:pdb:%s"%pdb_id}):
continue
print "Recover %s"%pdb_id #we use the first pdb_id in the list of ids making a cluster
for ts in parsers.parse_pdb(pdb.get_entry(pdb_id)):
try:
ss = None
if annotate:
ss, ts = rnaview.annotate(ts, canonical_only = canonical_only)
save(db, ss, ts, pdb_id, limit)
except Exception, e:
print e
print "No annotation for %s"%pdb_id
save(db, None, ts, pdb_id, limit)
def save(db, secondary_structure, tertiary_structure, pdbId, limit):
if db['junctions'].count() >= limit:
print "Limit of %i junctions reached"%limit
sys.exit()
from pyrna.computations import Cmalign, Rnaview
from bson.objectid import ObjectId
import os
pdb = PDB()
cmalign = Cmalign()
rnaview = Rnaview()
rfam = Rfam(cache_dir = "/home/fjossinet/tmp/Rfam")
families_with_structures = rfam.get_families_with_structures()
for index, row in families_with_structures.iterrows():
rfam_id = row['rfam_id']
tertiary_structures = parse_pdb(pdb.get_entry(row['pdb_id']))
reference_rna = None
ts = None
for tertiary_structure in tertiary_structures:
if tertiary_structure.rna.name == row['chain_name']:
ts = tertiary_structure
reference_rna = ts.rna
break
if ts:
secondary_structure, tertiary_structure = rnaview.annotate(tertiary_structure = ts)
rnas, orgs, consensus_2d = cmalign.align([reference_rna], rfam_id = rfam_id, rfam = rfam)
os.mkdir("/home/fjossinet/tmp/%s"%rfam_id)
os.mkdir("/home/fjossinet/tmp/%s/Molecules"%rfam_id)
from pyrna.computations import Cmalign, Rnaview
from bson.objectid import ObjectId
import os
pdb = PDB()
cmalign = Cmalign()
rnaview = Rnaview()
rfam = Rfam(cache_dir="/home/fjossinet/tmp/Rfam")
families_with_structures = rfam.get_families_with_structures()
for index, row in families_with_structures.iterrows():
rfam_id = row['rfam_id']
tertiary_structures = parse_pdb(pdb.get_entry(row['pdb_id']))
reference_rna = None
ts = None
for tertiary_structure in tertiary_structures:
if tertiary_structure.rna.name == row['chain_name']:
ts = tertiary_structure
reference_rna = ts.rna
break
if ts:
secondary_structure, tertiary_structure = rnaview.annotate(
tertiary_structure=ts)
rnas, orgs, consensus_2d = cmalign.align([reference_rna],
rfam_id=rfam_id,