def test_set_value(self):
import operator
from IMP.pmi.io.crosslink import FilterOperator as FO
cldb1=self.setup_cldb("xl_dataset_test.dat")
cldb2=self.setup_cldb("xl_dataset_test.dat")
cldb1.set_value(cldb1.protein1_key,'FFF',FO(cldb1.protein1_key,operator.eq,"AAA"))
cldb1.set_value(cldb1.protein2_key,'HHH',FO(cldb1.protein2_key,operator.eq,"AAA"))
protein_names_1=[]
for xl in cldb1:
protein_names_1.append((xl[cldb1.protein1_key],xl[cldb1.protein2_key]))
protein_names_2=[]
for xl in cldb2:
protein_names_2.append((xl[cldb1.protein1_key],xl[cldb1.protein2_key]))
new_protein_names=[]
for n,p in enumerate(protein_names_2):
p1=p[0]
p2=p[1]
if p1 == 'AAA':
p1 = 'FFF'
if p2 == 'AAA':
p2 = 'HHH'
new_protein_names.append((p1,p2))
self.assertEqual(protein_names_1,new_protein_names)
def test_FilterOperator(self):
import operator
from IMP.pmi.io.crosslink import FilterOperator as FO
cldb=self.setup_cldb("xl_dataset_test.dat")
fo=FO(cldb.protein1_key,operator.eq,"AAA")
for xl in cldb:
self.assertEqual(fo.evaluate(xl),xl[cldb.protein1_key]=="AAA")
fo=FO(cldb.protein1_key,operator.eq,"AAA")|FO(cldb.protein2_key,operator.eq,"BBB")
for xl in cldb:
self.assertEqual(fo.evaluate(xl),((xl[cldb.protein1_key]=="AAA")|(xl[cldb.protein2_key]=="BBB") ))
fo=(FO(cldb.protein1_key,operator.eq,"AAA")|FO(cldb.protein2_key,operator.eq,"BBB"))&FO("sample",operator.eq,"human")
for xl in cldb:
self.assertEqual(fo.evaluate(xl),((xl[cldb.protein1_key]=="AAA")|(xl[cldb.protein2_key]=="BBB") )&(xl["sample"]=="human"))
fo=(FO(cldb.residue1_key,operator.gt,30)|FO(cldb.protein2_key,operator.eq,"BBB"))
for xl in cldb:
self.assertEqual(fo.evaluate(xl),((xl[cldb.residue1_key]>30)|(xl[cldb.protein2_key]=="BBB") ))
fo=~(FO(cldb.residue1_key,operator.gt,30)|FO(cldb.protein2_key,operator.eq,"BBB"))
for xl in cldb:
self.assertEqual(fo.evaluate(xl),((xl[cldb.residue1_key]<=30)&(xl[cldb.protein2_key]!="BBB") ))
def test_filter_cldbkc(self):
import operator
from IMP.pmi.io.crosslink import FilterOperator as FO
cldb=self.setup_cldb("xl_dataset_test.dat")
fo=FO(cldb.protein1_key,operator.eq,"AAA")
cldb1=cldb.filter(fo)
nentry=len([xl for xl in cldb if (xl[cldb.protein1_key]=="AAA")])
self.assertEqual(len(cldb1),nentry)
"../../../crosslinks/Exp3-KFG-081016-3.csv",
"../../../crosslinks/Exp1-BP-CXMS-12aout16-KFGVE.csv",
"../../../crosslinks/Exp3-KFGE-081016-3.csv",
"../../../crosslinks/Vgrg-Tle1.csv",
"../../../crosslinks/Vgrg-Tle1-2-1008.csv"
]:
cldb_tmp = IMP.pmi.io.crosslink.CrossLinkDataBase(cldbkc)
cldb_tmp.create_set_from_file(csv)
cldb_tmp.rename_proteins({"TssKHis6": "TssK"})
cldb_tmp.set_name(csv)
cldb.append_database(cldb_tmp)
fo = FO("Decision", operator.eq, "Accepted")
fcldb = cldb.filter(fo)
prots = ["TssK"]
protx = prots
proty = prots
suffix = "TssK"
conversion_fastanames_name = {"TssKHis6": "TssK"}
inv_conversion_fastanames_name = {
v: k
for k, v in conversion_fastanames_name.items()
cldb_tmp.create_set_from_file(csv)
cldb_tmp.rename_proteins({"TssKHis6":"TssK","StrepTssF":"TssF","TssGFlag":"TssG"})
cldb_tmp.set_name(csv)
cldb.append_database(cldb_tmp)
for xl in cldb:
xl[cldb.id_score_key]=-math.log(xl[cldb.id_score_key])
cldb.create_new_keyword(cldb.sigma1_key)
cldb.create_new_keyword(cldb.sigma2_key)
cldb.set_value(cldb.sigma1_key,'SIGMA')
cldb.set_value(cldb.sigma2_key,'SIGMA')
cldb.set_value(cldb.sigma1_key,'FLEXIBLE-1',FO(cldb.residue1_links_number_key,operator.gt,5))
cldb.set_value(cldb.sigma2_key,'FLEXIBLE-1',FO(cldb.residue2_links_number_key,operator.gt,5))
cldb.set_value(cldb.sigma1_key,'FLEXIBLE-2',FO(cldb.residue1_links_number_key,operator.gt,30))
cldb.set_value(cldb.sigma2_key,'FLEXIBLE-2',FO(cldb.residue2_links_number_key,operator.gt,30))
#for xl in cldb:
# print xl[cldb.sigma1_key],xl[cldb.residue1_links_number_key],xl[cldb.sigma2_key],xl[cldb.residue2_links_number_key]
fo=FO("Decision",operator.eq,"Accepted")
fcldb=cldb.filter(fo)
data=IMP.crosslinkms.DataFixedLength("/Bis/home/rpellari/imp-projects/imp-050517/imp/modules/crosslinkms/data/data.21.10000.gaussian.1.rmf")
xlmovers=[]
]:
cldb_tmp.offset_residue_index("VgrG-II", -8)
cldb_tmp.clone_protein("VgrG-II", "VgrG.2")
cldb_tmp.clone_protein("VgrG-II", "VgrG.3")
cldb_tmp.rename_proteins({"VgrG-II": "VgrG.1"})
cldb_tmp.set_name(csv)
cldb.append_database(cldb_tmp)
else:
cldb_tmp.clone_protein("VgrGHA", "VgrG.2")
cldb_tmp.clone_protein("VgrGHA", "VgrG.3")
cldb_tmp.rename_proteins({"VgrGHA": "VgrG.1"})
cldb_tmp.set_name(csv)
cldb.append_database(cldb_tmp)
fo = FO("Decision", operator.eq, "Accepted") & FO(cldb.redundancy_key,
operator.gt, 2)
fcldb = cldb.filter(fo)
prots = ["VgrG.1", "VgrG.2", "VgrG.3"]
protx = prots
proty = prots
suffix = "VgrG"
conversion_fastanames_name = {
"VgrGHA.1": "VgrG.1",
"VgrGHA.2": "VgrG.2",
"VgrGHA.3": "VgrG.3"
for csv in [
"../../crosslinks/Vgrg-Tle1.csv",
"../../crosslinks/Vgrg-Tle1-2-1008.csv"
]:
cldb_tmp = IMP.pmi.io.crosslink.CrossLinkDataBase(cldbkc)
cldb_tmp.create_set_from_file(csv)
cldb_tmp.clone_protein("VgrG-II", "VgrGB")
cldb_tmp.clone_protein("VgrG-II", "VgrGC")
cldb_tmp.rename_proteins({"VgrG-II": "VgrGA"})
cldb_tmp.rename_proteins({"Tle1-His": "Tle1"})
cldb_tmp.set_name(csv)
cldb.append_database(cldb_tmp)
cldb.create_new_keyword("Redundancy_for_filter",
values_from_keyword="Redundancy")
fo = FO("Decision", operator.eq, "Accepted") & FO("Redundancy_for_filter",
operator.gt, 2)
fcldb = cldb.filter(fo)
xl = IMP.pmi.restraints.crosslinking.CrossLinkingMassSpectrometryRestraint(
root_hier=hier,
CrossLinkDataBase=fcldb,
length=21.0,
slope=0.01,
resolution=1.0,
label="XL")
xl.add_to_model()
sigma = xl.sigma_dictionary["SIGMA"][0]
psi = xl.psi_dictionary["PSI"][0]
sigma.set_scale(11.0)
psi.set_scale(0.05)
"../data/crosslinks/old/Vgrg-Tle1-2-1008.csv"
]:
cldb_tmp = IMP.pmi.io.crosslink.CrossLinkDataBase(cldbkc)
cldb_tmp.create_set_from_file(csv)
cldb_tmp.rename_proteins({
"TssKHis6": "TssK",
"StrepTssF": "TssF",
"TssGFlag": "TssG"
})
cldb_tmp.set_name(csv)
cldb.append_database(cldb_tmp)
fo = FO("Decision", operator.eq, "Accepted")
fcldb = cldb.filter(fo)
for xl in fcldb:
xl[cldbkc.id_score_key] = -math.log(xl[cldbkc.id_score_key])
prots = ["TssK"]
protx = prots
proty = prots
suffix = "TssK"
conversion_fastanames_name = {"TssKHis6": "TssK"}