def classifRefProtein(pr_dataset,
l_lig,
thresold_identity=30.0,
thresold_similarity=30.0):
pr_out = pathManage.result("clasifRef")
# case fasta file
pr_align_seq = pathManage.generatePath(pr_out + "alignSeq/")
l_p_fasta = []
for lig in l_lig:
pr_dataset = pathManage.dataset(lig)
l_file_by_lig = listdir(pr_dataset)
l_pr_ref_by_lig = [pr_dataset + x for x in l_file_by_lig]
for pr_ref_by_lig in l_pr_ref_by_lig:
PDB_folder = pr_ref_by_lig.split("/")[-1]
try:
l_file = listdir(pr_ref_by_lig)
except:
continue
for file_ref in l_file:
if search("^" + PDB_folder, file_ref):
PDB_ID = file_ref[0:-4]
PDB_ID = PDB_ID[0:4].lower() + PDB_ID[4:]
# PDB ID with chain associated
p_fasta = downloadFile.importFasta(
PDB_ID,
pr_align_seq,
dir_by_PDB=0,
debug=1,
fastaGlobal="/home/borrel/Yue_project/pdb_seqres.txt")
l_p_fasta.append(p_fasta)
break
d_outNeedle = applyNeedleList(l_p_fasta, pr_align_seq)
# writeMatrix
writeMatrixFromDico(d_outNeedle, pr_out + "matrixSimilarSeq", "similarity")
writeMatrixFromDico(d_outNeedle, pr_out + "matrixIDSeq", "identity")
#Group reference -> l 209
p_group_id = GroupRef(
d_outNeedle, "identity",
pr_out + "groupIdentity" + "_" + str(thresold_identity) + ".txt",
thresold_identity, l_lig)
p_group_sim = GroupRef(
d_outNeedle, "similarity",
pr_out + "groupSimilarity" + "_" + str(thresold_similarity) + ".txt",
thresold_similarity, l_lig)
# merge not alone prot
MergeGroup(p_group_id)
MergeGroup(p_group_sim)
def extractReference(p_list_ligand, p_dir_dataset, p_dir_result, substruct):
# struct reference
d_dataset = {}
# retrieve list of ligand in PDB
d_ligand = tool.parseLigandPDBList(p_list_ligand)
# download PDB and fasta associated
l_p_PDB = []
l_p_fasta = []
for PDB_ID in d_ligand[substruct]:
PDB_ID = PDB_ID.upper()
p_pdb = downloadFile.importPDB(PDB_ID,
p_dir_dataset,
dir_by_PDB=1,
debug=1,
dbPDB="/home/borrel/PDB/")
p_fasta = downloadFile.importFasta(
PDB_ID,
p_dir_dataset,
dir_by_PDB=1,
debug=1,
fastaGlobal="/home/borrel/Yue_project/pdb_seqres.txt")
if p_pdb != 0 and p_fasta != 0:
l_p_pdb_chain = separeByChain(p_pdb)
l_p_fasta_chain = separeChainFasta(p_fasta)
d_dataset[PDB_ID] = {}
d_dataset[PDB_ID]["p_pdb"] = p_pdb
d_dataset[PDB_ID]["p_fasta"] = p_fasta
d_dataset[PDB_ID]["p_pdb_chain"] = l_p_pdb_chain
d_dataset[PDB_ID]["p_fasta_chain"] = l_p_fasta_chain
d_dataset[PDB_ID]["conserve"] = 1
# plot resolution
p_file_RX = p_dir_result + "resolution_ref.txt"
file_RX = open(p_file_RX, "w")
for PDB_ID in d_dataset.keys():
RX = parsePDB.resolution(d_dataset[PDB_ID]["p_pdb"])
try:
d_dataset[PDB_ID]["RX"] = float(RX)
except:
d_dataset[PDB_ID]["RX"] = 100.0
file_RX.write(PDB_ID + "\t" + str(RX) + "\n")
file_RX.close()
runOtherSoft.Rhistogram(p_file_RX, "RX_ref_no_filter")
return d_dataset
def classifRefProtein (pr_dataset, l_lig, thresold_identity = 30.0, thresold_similarity = 30.0):
pr_out = pathManage.result("clasifRef")
# case fasta file
pr_align_seq = pathManage.generatePath(pr_out + "alignSeq/")
l_p_fasta = []
for lig in l_lig :
pr_dataset = pathManage.dataset(lig)
l_file_by_lig = listdir(pr_dataset)
l_pr_ref_by_lig =[pr_dataset + x for x in l_file_by_lig]
for pr_ref_by_lig in l_pr_ref_by_lig :
PDB_folder = pr_ref_by_lig.split ("/")[-1]
try : l_file = listdir(pr_ref_by_lig)
except : continue
for file_ref in l_file :
if search("^" + PDB_folder, file_ref) :
PDB_ID = file_ref[0:-4]
PDB_ID = PDB_ID[0:4].lower () + PDB_ID[4:]
# PDB ID with chain associated
p_fasta = downloadFile.importFasta(PDB_ID, pr_align_seq, dir_by_PDB = 0, debug = 1, fastaGlobal = "/home/borrel/Yue_project/pdb_seqres.txt")
l_p_fasta.append (p_fasta)
break
d_outNeedle = applyNeedleList (l_p_fasta, pr_align_seq)
# writeMatrix
writeMatrixFromDico (d_outNeedle, pr_out + "matrixSimilarSeq", "similarity" )
writeMatrixFromDico (d_outNeedle, pr_out + "matrixIDSeq", "identity" )
#Group reference -> l 209
p_group_id = GroupRef (d_outNeedle, "identity", pr_out + "groupIdentity" +"_" + str (thresold_identity) + ".txt", thresold_identity, l_lig)
p_group_sim = GroupRef (d_outNeedle, "similarity", pr_out + "groupSimilarity" +"_" + str (thresold_similarity) + ".txt", thresold_similarity, l_lig)
# merge not alone prot
MergeGroup (p_group_id)
MergeGroup (p_group_sim)
def extractReference (p_list_ligand, p_dir_dataset, p_dir_result, substruct):
# struct reference
d_dataset = {}
# retrieve list of ligand in PDB
d_ligand = tool.parseLigandPDBList (p_list_ligand)
# download PDB and fasta associated
l_p_PDB = []
l_p_fasta = []
for PDB_ID in d_ligand[substruct] :
PDB_ID = PDB_ID.upper()
p_pdb = downloadFile.importPDB(PDB_ID, p_dir_dataset, dir_by_PDB = 1, debug = 1, dbPDB = "/home/borrel/PDB/" )
p_fasta = downloadFile.importFasta(PDB_ID, p_dir_dataset, dir_by_PDB = 1, debug = 1, fastaGlobal = "/home/borrel/Yue_project/pdb_seqres.txt")
if p_pdb != 0 and p_fasta != 0 :
l_p_pdb_chain = separeByChain (p_pdb)
l_p_fasta_chain = separeChainFasta(p_fasta)
d_dataset[PDB_ID] = {}
d_dataset[PDB_ID] ["p_pdb"] = p_pdb
d_dataset[PDB_ID] ["p_fasta"] = p_fasta
d_dataset[PDB_ID] ["p_pdb_chain"] = l_p_pdb_chain
d_dataset[PDB_ID] ["p_fasta_chain"] = l_p_fasta_chain
d_dataset[PDB_ID] ["conserve"] = 1
# plot resolution
p_file_RX = p_dir_result + "resolution_ref.txt"
file_RX = open (p_file_RX, "w")
for PDB_ID in d_dataset.keys () :
RX = parsePDB.resolution(d_dataset[PDB_ID]["p_pdb"])
try : d_dataset[PDB_ID] ["RX"] = float(RX)
except : d_dataset[PDB_ID] ["RX"] = 100.0
file_RX.write (PDB_ID + "\t" + str (RX) + "\n")
file_RX.close ()
runOtherSoft.Rhistogram (p_file_RX, "RX_ref_no_filter")
return d_dataset
