def load_expt(self):
parsed = nmrpystar.parse(open(self.data_filename).read())
print(parsed.status)
q = ChemicalShiftAnalyzer.find_assigned_shifts(parsed)
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[[
"Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID",
"Atom_chem_shift.Val"
]]
x.rename(columns={
"Atom_chem_shift.Seq_ID": "resSeq",
"Atom_chem_shift.Atom_ID": "name",
"Atom_chem_shift.Val": "value"
},
inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
x["expt"] = "CS"
x["system"] = self.identifier
expt = x.set_index(["system", "expt", "resSeq", "name"]).value
expt = pd.Series(expt.values,
multi_index_to_str(expt.index),
name="value")
return expt
def parseSTR(STR_file):
"""Parse BMRB file into a python object"""
my_STR_hash = hashlib.md5(open(STR_file, 'rb').read()).hexdigest()
try:
prev_STR_hash = open(".prevSTRhash").read().strip()
if my_STR_hash == prev_STR_hash:
print("STR file is the same as in the previous run")
print("Skip parsing STR...")
parsed = pickle.load(open(".prevSTR.pickle", 'rb'))
return parsed
except FileNotFoundError:
pass
with open(".prevSTRhash", "w") as prev_HASH:
prev_HASH.write(my_STR_hash)
star_file = open(STR_file) # open STR file
myString = ""
for line in star_file: # rean STR file into a string
myString += line
star_file.close()
parsed = nmrpystar.parse(myString) # parsing -> parsed.value
if parsed.status != 'success': # check if parsing was successful
print('Error during STR parsing: ', parsed)
raise SystemExit
else:
pickle.dump(parsed, open(".prevSTR.pickle", "wb"))
return parsed
def load_expt(self):
parsed = nmrpystar.parse(open(self.data_filename).read())
print(parsed.status)
q = parsed.value.saves["coupling_constant_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[[
"Coupling_constant.Seq_ID_1", "Coupling_constant.Val",
"Coupling_constant.Val_err"
]]
x.rename(columns={
"Coupling_constant.Seq_ID_1": "resSeq",
"Coupling_constant.Val": "value",
"Coupling_constant.Val_err": "err"
},
inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
x["expt"] = "3JHNHA"
x["system"] = self.identifier
expt = x.set_index(["system", "expt", "resSeq"]).value
expt = pd.Series(expt.values, multi_index_to_str(expt.index))
return expt
def load_expt(self):
parsed = nmrpystar.parse(open(self.data_filename).read())
print(parsed.status)
q = parsed.value.saves["coupling_constant_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Coupling_constant.Seq_ID_1", "Coupling_constant.Val", "Coupling_constant.Val_err"]]
x.rename(columns={"Coupling_constant.Seq_ID_1":"resSeq", "Coupling_constant.Val":"value", "Coupling_constant.Val_err":"err"}, inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
x["expt"] = "3JHNHA"
x["system"] = self.identifier
expt = x.set_index(["system", "expt", "resSeq"]).value
expt = pd.Series(expt.values, multi_index_to_str(expt.index))
return expt
def load_expt(self):
parsed = nmrpystar.parse(open(self.data_filename).read())
print(parsed.status)
q = ChemicalShiftAnalyzer.find_assigned_shifts(parsed)
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"]]
x.rename(columns={"Atom_chem_shift.Seq_ID":"resSeq", "Atom_chem_shift.Atom_ID":"name", "Atom_chem_shift.Val":"value"}, inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
x["expt"] = "CS"
x["system"] = self.identifier
expt = x.set_index(["system", "expt", "resSeq", "name"]).value
expt = pd.Series(expt.values, multi_index_to_str(expt.index), name="value")
return expt
import pandas as pd
import nmrpystar
import mdtraj as md
t = md.load("./1am7.dcd", top="./1am7_fixed.pdb")
prediction = md.nmr.chemical_shifts_shiftx2(t).mean(
1) # Average over time dimensions
parsed = nmrpystar.parse(open("./16664.str").read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[[
"Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"
]]
x.rename(columns={
"Atom_chem_shift.Seq_ID": "resSeq",
"Atom_chem_shift.Atom_ID": "name",
"Atom_chem_shift.Val": "value"
},
inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
expt = x.set_index(["resSeq", "name"]).value
delta = (expt - prediction).dropna()
import pandas as pd
import nmrpystar
bmrb_filename = "/home/kyleb/src/choderalab/ForcefieldData/nmr/2EVN/6338.str"
parsed = nmrpystar.parse(open(bmrb_filename).read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"]]
x.rename(columns={"Atom_chem_shift.Seq_ID":"resSeq", "Atom_chem_shift.Atom_ID":"name", "Atom_chem_shift.Val":"value"}, inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
x["expt"] = "CS"
x["system"] = self.identifier
expt = x.set_index(["system", "expt", "resSeq", "name"]).value
expt = pd.Series(expt.values, multi_index_to_str(expt.index))
parser = argparse.ArgumentParser()
parser.add_argument(
'-max',
type=int,
default=-1,
help='Go up to a maximum frame (default is whole trajectory)')
args, sys.argv = parser.parse_known_args(sys.argv)
# Run compare_shifts.py [PDB] [XTC] [12345.str]
t = md.load(sys.argv[2], top=sys.argv[1])
outfnm = sys.argv[4]
# if os.path.exists(outfnm): sys.exit()
parsed = nmrpystar.parse(open(sys.argv[3]).read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[[
"Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"
]]
x.rename(columns={
"Atom_chem_shift.Seq_ID": "resSeq",
"Atom_chem_shift.Atom_ID": "name",
"Atom_chem_shift.Val": "value"
},
inplace=True)
# Need to make dtypes match to do eventual comparison.
import pandas as pd
import nmrpystar
bmrb_filename = "/home/kyleb/src/choderalab/ForcefieldData/nmr/2EVN/6338.str"
parsed = nmrpystar.parse(open(bmrb_filename).read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[[
"Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"
]]
x.rename(columns={
"Atom_chem_shift.Seq_ID": "resSeq",
"Atom_chem_shift.Atom_ID": "name",
"Atom_chem_shift.Val": "value"
},
inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
x["expt"] = "CS"
x["system"] = self.identifier
expt = x.set_index(["system", "expt", "resSeq", "name"]).value
expt = pd.Series(expt.values, multi_index_to_str(expt.index))
import pandas as pd
import nmrpystar
import mdtraj as md
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('-max', type=int, default=-1, help='Go up to a maximum frame (default is whole trajectory)')
args, sys.argv = parser.parse_known_args(sys.argv)
# Run compare_shifts.py [PDB] [XTC] [12345.str]
t = md.load(sys.argv[2], top=sys.argv[1])
outfnm = sys.argv[4]
# if os.path.exists(outfnm): sys.exit()
parsed = nmrpystar.parse(open(sys.argv[3]).read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"]]
x.rename(columns={"Atom_chem_shift.Seq_ID":"resSeq", "Atom_chem_shift.Atom_ID":"name", "Atom_chem_shift.Val":"value"}, inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
expn = x.set_index(["resSeq", "name"])
expt = x.set_index(["resSeq", "name"]).value
print "Doing ShiftX2 prediction."
import pandas as pd
import nmrpystar
import mdtraj as md
t = md.load("/home/kyleb/dat/tmp/pro_0.xtc", top="/home/kyleb/dat/tmp/pro.pdb")
parsed = nmrpystar.parse(open("./19127.str").read())
print(parsed.status)
q = parsed.value.saves["coupling_constant_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[[
"Coupling_constant.Seq_ID_1", "Coupling_constant.Val",
"Coupling_constant.Val_err"
]]
x.rename(columns={
"Coupling_constant.Seq_ID_1": "resSeq",
"Coupling_constant.Val": "value",
"Coupling_constant.Val_err": "err"
},
inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
expt = x.set_index(["resSeq"]).value
top, bonds = t.top.to_dataframe()
ind, values = md.compute_J3_HN_HA(t)
prediction = pd.Series(values.mean(0), top.ix[ind[:, -1]].resSeq)
t0 = md.load(["./Trajectories_ff99sbnmr/1am7_%d.dcd" % i for i in range(10)], top="./1am7_fixed.pdb")[::stride]
t1 = md.load(["./Trajectories/1am7_%d.dcd" % i for i in range(15)], top="./1am7_fixed.pdb")[::stride]
#full_prediction0 = md.nmr.chemical_shifts_shiftx2(t0)
#full_prediction1 = md.nmr.chemical_shifts_shiftx2(t1)
#full_prediction0 = md.nmr.chemical_shifts_spartaplus(t0)
#full_prediction1 = md.nmr.chemical_shifts_spartaplus(t1)
full_prediction0 = md.nmr.chemical_shifts_ppm(t0)
full_prediction1 = md.nmr.chemical_shifts_ppm(t1)
parsed = nmrpystar.parse(open("./16664.str").read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"]]
x.rename(columns={"Atom_chem_shift.Seq_ID":"resSeq", "Atom_chem_shift.Atom_ID":"name", "Atom_chem_shift.Val":"value"}, inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
expt = x.set_index(["resSeq", "name"]).value
prediction0 = full_prediction0.mean(1) # Average over time dimensions
import pandas as pd
import nmrpystar
import mdtraj as md
t = md.load("/home/kyleb/dat/tmp/pro_0.xtc", top="/home/kyleb/dat/tmp/pro.pdb")
parsed = nmrpystar.parse(open("./19127.str").read())
print(parsed.status)
q = parsed.value.saves["coupling_constant_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Coupling_constant.Seq_ID_1", "Coupling_constant.Val", "Coupling_constant.Val_err"]]
x.rename(
columns={
"Coupling_constant.Seq_ID_1": "resSeq",
"Coupling_constant.Val": "value",
"Coupling_constant.Val_err": "err",
},
inplace=True,
)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype("int")
x["value"] = x["value"].astype("float")
expt = x.set_index(["resSeq"]).value
top, bonds = t.top.to_dataframe()
ind, values = md.compute_J3_HN_HA(t)
prediction = pd.Series(values.mean(0), top.ix[ind[:, -1]].resSeq)
import pandas as pd
import nmrpystar
import mdtraj as md
t = md.load("./1d3z.dcd", top="./1d3z_frame0.pdb")
prediction = md.nmr.chemical_shifts_shiftx2(t).mean(1) # Average over time dimensions
parsed = nmrpystar.parse(open("./bmrb17439_v3.str").read())
print(parsed.status)
q = parsed.value.saves["assigned_chem_shift_list_1"].loops[1]
x = pd.DataFrame(q.rows, columns=q.keys)
x = x[["Atom_chem_shift.Seq_ID", "Atom_chem_shift.Atom_ID", "Atom_chem_shift.Val"]]
x.rename(columns={"Atom_chem_shift.Seq_ID":"resSeq", "Atom_chem_shift.Atom_ID":"name", "Atom_chem_shift.Val":"value"}, inplace=True)
# Need to make dtypes match to do eventual comparison.
x["resSeq"] = x["resSeq"].astype('int')
x["value"] = x["value"].astype('float')
expt = x.set_index(["resSeq", "name"]).value
delta = (expt - prediction).dropna()
delta.name = "value"
rms = (delta ** 2.).reset_index().groupby("name").value.mean() ** 0.5
