def calculate_rmsf(trajfiles,
topfile,
plot=True,
ref=0,
mask='@CA',
name='default'):
'''
This function returns a numpy.ndarray object that contains rmsf information of the atoms in the mask.
Arguments:
- trajfiles: trajectory file or list of trajecrory files(see formats in the bottom part).
- topfile: topology file used to read the trajectories(see formats in the bottom part).
- ref: frame used as a reference while the RMSF is calculated(integer).
- mask: string that indicates with cpptraj format the mask for the calculation (default: "@Ca").
- plot: if True, plots a RMSF plot(default: True).
- name: Name of the dataset provided. Will apear in the title in the plot.
Returns: numpy.ndarray
Formats that accept:
Amber Trajectory .crd
Amber NetCDF .nc
Amber Restart .rst7
Amber NetCDF .ncrst
Charmm DCD .dcd
PDB .pdb
Mol2 .mol2
Scripps .binpos
Gromacs .trr
SQM Input .sqm
'''
if name == 'default':
if type(trajfiles) == list:
name = trajfiles[0].split('/')[-1]
else:
name = trajfiles.split('/')[-1]
MD = pt.iterload(trajfiles, topfile).superpose(trajfiles, ref=ref)
rmsf = pt.rmsf(MD, mask)
if plot:
mpl.rcParams['font.size'] = 15
plt.figure(figsize=(12, 5))
plt.plot(rmsf.T[1])
plt.xlabel('{} number'.format(mask), fontsize=20)
plt.ylabel('RMSF ($\AA$)', fontsize=20)
plt.xlim((0, len(rmsf)))
plt.title('{} RMSF'.format(name), fontsize=25)
return rmsf.T[1]
def test_RMSF_with_options(self):
traj = pt.iterload(fn('tz2.nc'), fn('tz2.parm7'))
state = pt.load_batch(
traj, '''
atomicfluct @CA byres out fluct.agr''')
state.run()
data = pt.rmsf(traj, '@CA', options='byres')
aa_eq(data, state.data[-1].values)
def get_rms(traj_path):
traj = load_traj(traj_path)
rmsd = pt.rmsd(traj, ref=0, mask='@CA,C,N')
df_rmsd = pd.DataFrame(rmsd, columns=['RMSD'])
rmsf = pt.rmsf(traj)
df_rmsf = pd.DataFrame(rmsf, columns=['ATOM', 'RMSF'])
return df_rmsd, df_rmsf
def test_RMSF(self):
traj = pt.iterload(fn('tz2.nc'), fn('tz2.parm7'))
state = pt.load_batch(traj, '''
rms first
average crdset MyAvg
run
rms ref MyAvg
atomicfluct out fluct.agr''')
state.run()
t0 = traj[:]
pt.superpose(t0, ref=0)
avg = pt.mean_structure(t0)
pt.superpose(t0, ref=avg)
data = pt.rmsf(t0)
aa_eq(data, state.data[-1].values)
def test_RMSF(self):
traj = pt.iterload("./data/tz2.nc", "./data/tz2.parm7")
state = pt.load_batch(traj, '''
rms first
average crdset MyAvg
run
rms ref MyAvg
atomicfluct out fluct.agr''')
state.run()
t0 = traj[:]
pt.superpose(t0, ref=0)
avg = pt.mean_structure(t0)
pt.superpose(t0, ref=avg)
data = pt.rmsf(t0)
aa_eq(data, state.data[-1].values)
def main(traj, pdb):
'''
计算RMSD/RMSF
Parameters
----------
traj: MD轨迹 Pytraj对象
pdb: PDB ID字符串
'''
print('\nStart RMSD/RMSF Analysis...')
data_rmsd_first = pt.rmsd(traj, ref=0,
mask="@CA") # 计算αC原子RMSD Ref=0以第一帧为参考
command = "awk '$4 ~ /MOL/ {print $5}' ./" + pdb + 'comsolvate.pdb' # 提取位于残基后的配体分子序号
temp = os.popen(command)
mol_resnum = str(temp.readlines()[-1]).strip()
res_mask = ':1-' + mol_resnum + '@CA'
data_rmsf = pt.rmsf(traj, mask=res_mask, options='byres') # 计算RMSF 所有非水分子
# 保存数据
print('RMSD Data:')
print(data_rmsd_first)
with open('./pynalysis/rmsd_rmsf/rmsd.dat', 'w') as rmsdfile:
for rmsd in data_rmsd_first[:]:
rmsdfile.write(str(rmsd) + '\n')
rmsdfile.close()
print('rmsd.dat saved.', end='\n')
print('RMSF Data:')
print(data_rmsf)
with open('./pynalysis/rmsd_rmsf/rmsf.dat', 'w') as rmsffile:
for rmsfdata in data_rmsf[:]:
rmsffile.write(str(rmsfdata[1]) + '\n')
rmsffile.close()
print('rmsf.dat saved.', end='\n')
print('\n\nRMSD/RMSF Analysis Complete.')
print(''.center(80, '*'))