mirror of
https://github.com/microsoft/foldingdiff.git
synced 2026-06-04 13:30:33 +08:00
Unused script cleanup
This commit is contained in:
Kevin Wu
@@ -1,15 +0,0 @@
|
||||
# Useful links:
|
||||
# https://github.com/docker/buildx/issues/476
|
||||
# Sometimes need to run sudo service docker restart to build correctly
|
||||
# https://stackoverflow.com/questions/50309605/reading-input-files-with-docker
|
||||
|
||||
# Example command:
|
||||
# nvidia-docker run -it --rm -v ${PWD}:/host_pwd --workdir /host_pwd wukevin:gromacs-latest generated_0_proteinmpnn_residues_0.pdb
|
||||
|
||||
FROM nvcr.io/hpc/gromacs:2022.3
|
||||
|
||||
# Should already come with python3; just copy in files
|
||||
COPY gromacs.py /usr/local/bin/gromacs.py
|
||||
COPY mdp /usr/local/bin/mdp
|
||||
|
||||
ENTRYPOINT [ "python3", "/usr/local/bin/gromacs.py", "--gmxbin", "/usr/local/gromacs/avx2_256/bin/gmx", "--mdp", "/usr/local/bin/mdp/"]
|
||||
@@ -1,206 +0,0 @@
|
||||
"""
|
||||
Script to run GROMACS on an input file
|
||||
|
||||
Take the 20 amino acids, build a skeleton of each side chain
|
||||
Map the coordinates into the glycine
|
||||
|
||||
Don't even need a great "starting structure" - can be in the general proximity
|
||||
GROMACS can do no hydrogen
|
||||
pdb2gmx ignore h to add them in
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import socket
|
||||
import argparse
|
||||
import tempfile
|
||||
import logging
|
||||
import shlex
|
||||
import subprocess
|
||||
import shutil
|
||||
|
||||
GRO_FILE_DIR = os.path.join(os.path.dirname(__file__), "mdp")
|
||||
# Up the prod.mdp nsteps to 50000000 to run a longer simulation
|
||||
# 6nm x 6nm x 6nm (or 7) box (currently gives you 1nm padding around the protein)
|
||||
# gmx insert-molecules -f <grofile.gro> -ci <spc216.gro> -box <x y z> -nmol <# of waters>
|
||||
|
||||
# Run the biggest thing, use box volume and the same number of waters for other things
|
||||
# Run a bunch of 128 residues and see how many water get added
|
||||
|
||||
def run_gromacs(
|
||||
pdb_file: str,
|
||||
outdir: str = os.getcwd(),
|
||||
gmx: str = "gmx",
|
||||
gro_file_dir: str = GRO_FILE_DIR,
|
||||
n_threads: int = 8,
|
||||
) -> float:
|
||||
"""
|
||||
Run GROMACS on a PDB file
|
||||
"""
|
||||
logging.info(f"Running gromacs in outdir {outdir}")
|
||||
assert os.path.isfile(pdb_file), f"File {pdb_file} not found! (pwd: {os.getcwd()})"
|
||||
gro_file = os.path.join(outdir, os.path.basename(pdb_file).replace(".pdb", ".gro"))
|
||||
# pdb2gmx = f"gmx pdb2gmx -f {pdb_file} -o {gro_file} -ff 6 -water tip3p"
|
||||
# Puts it in a GMX format, add water and force field
|
||||
# AMBER/CHARM most common for protein and protein folding.
|
||||
# A force field defines all forces/energies interacting on
|
||||
# a given atom.
|
||||
pdb2gmx = f"{gmx} pdb2gmx -f {pdb_file} -o {gro_file} -water tip3p"
|
||||
logging.debug(f"pdb2gmx cmd: {pdb2gmx}")
|
||||
p = subprocess.Popen(shlex.split(pdb2gmx), stdin=subprocess.PIPE)
|
||||
p.communicate(input="6".encode())
|
||||
|
||||
# gen box - put this in a water solvent 'in a box' - 1nm around the system
|
||||
# box_file = os.path.join(outdir, "box.gro")
|
||||
# box_cmd = f"{gmx} editconf -f {gro_file} -o {box_file} -c -d 1"
|
||||
# subprocess.call(shlex.split(box_cmd))
|
||||
|
||||
# solvate - add water
|
||||
# solvate_cmd = (
|
||||
# f"{gmx} solvate -cp {box_file} -o solv.gro -cs spc216.gro -p topol.top"
|
||||
# )
|
||||
# logging.debug(f"solvate cmd: {solvate_cmd}")
|
||||
# subprocess.call(shlex.split(solvate_cmd))
|
||||
|
||||
# Rather than automatically adding a box and solvating, add an explicit constnat number of
|
||||
# water atoms. This is becasue the energy of the system is dependent on the number of atoms,
|
||||
# so we hold this constant.
|
||||
sol_add = 'echo "SOL 12000" >> topol.top'
|
||||
subprocess.call(sol_add, shell=True)
|
||||
|
||||
addwater_cmd = f"{gmx} insert-molecules -f {gro_file} -ci {gro_file_dir}water2.gro -box 12 12 12 -nmol 12000 -o solv.gro"
|
||||
subprocess.call(shlex.split(addwater_cmd))
|
||||
|
||||
|
||||
# add ions - add counter postive and negative ions to make
|
||||
# the box "neutral"
|
||||
ions_cmd = (
|
||||
f"{gmx} grompp -f {gro_file_dir}ions.mdp -c solv.gro -o ions.tpr -p topol.top"
|
||||
)
|
||||
logging.debug(f"ions cmd: {ions_cmd}")
|
||||
subprocess.call(shlex.split(ions_cmd))
|
||||
|
||||
genion_cmd = f"{gmx} genion -s ions.tpr -o ions.gro -p topol.top -pname NA -nname CL -neutral"
|
||||
logging.debug(f"genion cmd: {genion_cmd}")
|
||||
p = subprocess.Popen(shlex.split(genion_cmd), stdin=subprocess.PIPE)
|
||||
p.communicate(input="13".encode())
|
||||
|
||||
# Energy minimization - remove unfavorable contacts
|
||||
# like making sure nothing is overlapping; nothing should
|
||||
# change too much
|
||||
em_cmd = (
|
||||
f"{gmx} grompp -f {gro_file_dir}minim.mdp -c ions.gro -o em.tpr -p topol.top"
|
||||
)
|
||||
logging.debug(f"EM cmd: {em_cmd}")
|
||||
subprocess.call(shlex.split(em_cmd))
|
||||
|
||||
mdrun_cmd = f"{gmx} mdrun -ntmpi 1 -ntomp {n_threads-1} -deffnm em"
|
||||
logging.debug(f"mdrun cmd: {mdrun_cmd}")
|
||||
subprocess.call(shlex.split(mdrun_cmd))
|
||||
|
||||
# NVT - equilibrate the system at constant volume and temperature
|
||||
# come to "room temperature"
|
||||
grompp_cmd = f"{gmx} grompp -f {gro_file_dir}nvt.mdp -c em.gro -r em.gro -p topol.top -o nvt.tpr"
|
||||
subprocess.call(shlex.split(grompp_cmd))
|
||||
nvt_cmd = f"{gmx} mdrun -ntmpi 1 -ntomp {n_threads - 1} -nb gpu -pin on -deffnm nvt"
|
||||
subprocess.call(shlex.split(nvt_cmd))
|
||||
|
||||
# NPT
|
||||
grompp_cmd = (
|
||||
f"{gmx} grompp -f {gro_file_dir}npt.mdp -c nvt.gro -o npt.tpr -p topol.top"
|
||||
)
|
||||
subprocess.call(shlex.split(grompp_cmd))
|
||||
npt_cmd = f"{gmx} mdrun -ntmpi 1 -ntomp {n_threads - 1} -nb gpu -pin on -deffnm npt"
|
||||
subprocess.call(shlex.split(npt_cmd))
|
||||
|
||||
# Production run
|
||||
grompp_cmd = f"{gmx} grompp -f {gro_file_dir}md.mdp -c npt.gro -t npt.cpt -p topol.top -o prod.tpr"
|
||||
subprocess.call(shlex.split(grompp_cmd))
|
||||
prod_cmd = (
|
||||
f"{gmx} mdrun -ntmpi 1 -ntomp {n_threads - 1} -nb gpu -pin on -deffnm prod"
|
||||
)
|
||||
subprocess.call(shlex.split(prod_cmd))
|
||||
|
||||
# Produce a PDB of final structure
|
||||
pdb_cmd = f"{gmx} editconf -f prod.gro -o prod.pdb"
|
||||
subprocess.call(shlex.split(pdb_cmd))
|
||||
|
||||
# Read energy and return
|
||||
return read_energy("prod.edr", gmx=gmx)
|
||||
|
||||
|
||||
def read_energy(
|
||||
energy_edr_file: str,
|
||||
gmx: str = "gmx",
|
||||
) -> float:
|
||||
"""
|
||||
Read energy from GROMACS energy file
|
||||
"""
|
||||
assert os.path.isfile(energy_edr_file), f"File {energy_edr_file} not found"
|
||||
cmd = f"{gmx} energy -f {energy_edr_file} -o energy.xvg"
|
||||
p = subprocess.Popen(
|
||||
shlex.split(cmd), stdin=subprocess.PIPE, stdout=subprocess.PIPE
|
||||
)
|
||||
stdout = p.communicate(input="11\n\n".encode())[0].decode().split("\n")
|
||||
potential_lines = [l for l in stdout if l.startswith("Potential")]
|
||||
assert len(potential_lines) == 1, "Unexpected number of potential lines"
|
||||
energy = float(potential_lines[0].split()[1])
|
||||
return energy
|
||||
|
||||
|
||||
def build_parser():
|
||||
"""Build basic CLI parser"""
|
||||
parser = argparse.ArgumentParser(
|
||||
usage=__doc__, formatter_class=argparse.ArgumentDefaultsHelpFormatter
|
||||
)
|
||||
parser.add_argument("pdb_file", help="PDB file to run GROMACS on")
|
||||
parser.add_argument(
|
||||
"-o",
|
||||
"--outdir",
|
||||
type=str,
|
||||
default=os.getcwd(),
|
||||
help="Directory to write output",
|
||||
)
|
||||
parser.add_argument("--copyall", action="store_true", help="Copy all GROMACS files")
|
||||
parser.add_argument(
|
||||
"--gmxbin", type=str, default=shutil.which("gmx"), help="GROMACS binary"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--mdp", type=str, default=GRO_FILE_DIR, help="MDP file directory"
|
||||
)
|
||||
parser.add_argument("--threads", type=int, default=32, help="Threads (minimum 2)")
|
||||
return parser
|
||||
|
||||
|
||||
def main():
|
||||
"""Run script"""
|
||||
args = build_parser().parse_args()
|
||||
logging.info(
|
||||
f"Running {args.pdb_file} under Python {sys.version} in {socket.gethostname()}"
|
||||
)
|
||||
assert os.path.isdir(args.outdir), f"Directory {args.outdir} not found"
|
||||
assert args.gmxbin is not None
|
||||
args.pdb_file = os.path.abspath(args.pdb_file)
|
||||
# Run in temporary directory
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
os.chdir(tmpdir)
|
||||
energy = run_gromacs(
|
||||
args.pdb_file,
|
||||
tmpdir,
|
||||
gmx=args.gmxbin,
|
||||
gro_file_dir=args.mdp,
|
||||
n_threads=args.threads,
|
||||
)
|
||||
for file in os.listdir(tmpdir):
|
||||
logging.debug(f"GROMACS file: {file}")
|
||||
if args.copyall:
|
||||
shutil.copy(os.path.join(tmpdir, file), args.outdir)
|
||||
elif file.startswith("prod"):
|
||||
logging.info(f"Copy {file} to {args.outdir}")
|
||||
shutil.copy(os.path.join(tmpdir, file), args.outdir)
|
||||
logging.info(f"{args.pdb_file} energy: {energy:.2f}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
main()
|
||||
@@ -1,73 +0,0 @@
|
||||
"""
|
||||
Simple script to wrap the gromacs.py file in an easy to run docker container
|
||||
to avoid all the messiness of trying to do mounting and stuff.
|
||||
|
||||
Usage: python gromacs_docker.py <input_file> <output_dir>
|
||||
"""
|
||||
import os
|
||||
import logging
|
||||
import shutil
|
||||
import tempfile
|
||||
import subprocess
|
||||
import argparse
|
||||
|
||||
|
||||
def build_parser():
|
||||
"""Build a basic CLI parser"""
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("input_file", nargs="+", help="Input file to run GROMACS on")
|
||||
parser.add_argument("output_dir", help="Output dir to write output files to")
|
||||
parser.add_argument("--gpu", type=int, default=0, help="GPU to use")
|
||||
return parser
|
||||
|
||||
|
||||
def run_gromacs_in_docker(fname: str, out_dir: str, gpu: int = 0):
|
||||
"""
|
||||
Run gromacs in docker
|
||||
"""
|
||||
assert os.path.isfile(fname), f"Input file {fname} not found"
|
||||
assert shutil.which("nvidia-docker")
|
||||
out_dir = os.path.abspath(out_dir)
|
||||
fname = os.path.abspath(fname)
|
||||
bname = os.path.splitext(os.path.basename(fname))[0]
|
||||
|
||||
orig_dir = os.getcwd()
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
logging.info(f"Running {fname} via docker in temporary directory {tmpdir}")
|
||||
assert not os.listdir(tmpdir)
|
||||
os.chdir(tmpdir)
|
||||
# Copy the file into the directory
|
||||
shutil.copy(fname, tmpdir)
|
||||
# Build and run the command
|
||||
# https://github.com/NVIDIA/nvidia-docker/wiki/Frequently-Asked-Questions#i-have-multiple-gpu-devices-how-can-i-isolate-them-between-my-containers
|
||||
cmd = f"nvidia-docker run -it --rm -e NVIDIA_VISIBLE_DEVICES={gpu} -v {tmpdir}:/host_pwd --workdir /host_pwd wukevin:gromacs-latest {os.path.basename(fname)}"
|
||||
logging.info(f"Running command: {cmd}")
|
||||
with open(os.path.join(out_dir, f"{bname}.gromacs.stdout"), "wb") as stdout:
|
||||
with open(os.path.join(out_dir, f"{bname}.gromacs.stderr"), "wb") as stderr:
|
||||
subprocess.call(cmd, shell=True, stdout=stdout, stderr=stderr)
|
||||
|
||||
for src_fname in os.listdir(tmpdir):
|
||||
dest_fname = (
|
||||
src_fname
|
||||
if src_fname.startswith(bname)
|
||||
else ".".join([bname, src_fname])
|
||||
)
|
||||
logging.info(f"Copying {src_fname} to {dest_fname} in {out_dir}")
|
||||
shutil.copy(
|
||||
os.path.join(tmpdir, src_fname), os.path.join(out_dir, dest_fname)
|
||||
)
|
||||
os.chdir(orig_dir) # Restore directory
|
||||
|
||||
|
||||
def main():
|
||||
"""Run script"""
|
||||
args = build_parser().parse_args()
|
||||
if not os.path.isdir(args.output_dir):
|
||||
os.makedirs(args.output_dir)
|
||||
for fname in [os.path.abspath(f) for f in args.input_file]:
|
||||
run_gromacs_in_docker(fname, args.output_dir, gpu=args.gpu)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
main()
|
||||
@@ -1,15 +0,0 @@
|
||||
; ions.mdp - used as input into grompp to generate ions.tpr
|
||||
; Parameters describing what to do, when to stop and what to save
|
||||
integrator = steep ; Algorithm (steep = steepest descent minimization)
|
||||
emtol = 1000.0 ; Stop minimization when the maximum force < 1000.0 kJ/mol/nm
|
||||
emstep = 0.01 ; Minimization step size
|
||||
nsteps = 50000 ; Maximum number of (minimization) steps to perform
|
||||
|
||||
; Parameters describing how to find the neighbors of each atom and how to calculate the interactions
|
||||
nstlist = 1 ; Frequency to update the neighbor list and long range forces
|
||||
cutoff-scheme = Verlet ; Buffered neighbor searching
|
||||
ns_type = grid ; Method to determine neighbor list (simple, grid)
|
||||
coulombtype = cutoff ; Treatment of long range electrostatic interactions
|
||||
rcoulomb = 1.0 ; Short-range electrostatic cut-off
|
||||
rvdw = 1.0 ; Short-range Van der Waals cut-off
|
||||
pbc = xyz ; Periodic Boundary Conditions in all 3 dimensions
|
||||
@@ -1,46 +0,0 @@
|
||||
title = OPLS Lysozyme NPT equilibration
|
||||
; Run parameters
|
||||
integrator = md ; leap-frog integrator
|
||||
nsteps = 500000 ; 2 * 500000 = 1000 ps (1 ns)
|
||||
dt = 0.002 ; 2 fs
|
||||
; Output control
|
||||
nstxout = 0 ; suppress bulky .trr file by specifying
|
||||
nstvout = 0 ; 0 for output frequency of nstxout,
|
||||
nstfout = 0 ; nstvout, and nstfout
|
||||
nstenergy = 5000 ; save energies every 10.0 ps
|
||||
nstlog = 5000 ; update log file every 10.0 ps
|
||||
nstxout-compressed = 5000 ; save compressed coordinates every 10.0 ps
|
||||
compressed-x-grps = System ; save the whole system
|
||||
; Bond parameters
|
||||
continuation = yes ; Restarting after NPT
|
||||
constraint_algorithm = lincs ; holonomic constraints
|
||||
constraints = h-bonds ; bonds involving H are constrained
|
||||
lincs_iter = 1 ; accuracy of LINCS
|
||||
lincs_order = 4 ; also related to accuracy
|
||||
; Neighborsearching
|
||||
cutoff-scheme = Verlet ; Buffered neighbor searching
|
||||
ns_type = grid ; search neighboring grid cells
|
||||
nstlist = 10 ; 20 fs, largely irrelevant with Verlet scheme
|
||||
rcoulomb = 1.0 ; short-range electrostatic cutoff (in nm)
|
||||
rvdw = 1.0 ; short-range van der Waals cutoff (in nm)
|
||||
; Electrostatics
|
||||
coulombtype = PME ; Particle Mesh Ewald for long-range electrostatics
|
||||
pme_order = 4 ; cubic interpolation
|
||||
fourierspacing = 0.16 ; grid spacing for FFT
|
||||
; Temperature coupling is on
|
||||
tcoupl = V-rescale ; modified Berendsen thermostat
|
||||
tc-grps = Protein Non-Protein ; two coupling groups - more accurate
|
||||
tau_t = 0.1 0.1 ; time constant, in ps
|
||||
ref_t = 300 300 ; reference temperature, one for each group, in K
|
||||
; Pressure coupling is on
|
||||
pcoupl = Parrinello-Rahman ; Pressure coupling on in NPT
|
||||
pcoupltype = isotropic ; uniform scaling of box vectors
|
||||
tau_p = 2.0 ; time constant, in ps
|
||||
ref_p = 1.0 ; reference pressure, in bar
|
||||
compressibility = 4.5e-5 ; isothermal compressibility of water, bar^-1
|
||||
; Periodic boundary conditions
|
||||
pbc = xyz ; 3-D PBC
|
||||
; Dispersion correction
|
||||
DispCorr = EnerPres ; account for cut-off vdW scheme
|
||||
; Velocity generation
|
||||
gen_vel = no ; Velocity generation is off
|
||||
@@ -1,15 +0,0 @@
|
||||
; minim.mdp - used as input into grompp to generate em.tpr
|
||||
; Parameters describing what to do, when to stop and what to save
|
||||
integrator = steep ; Algorithm (steep = steepest descent minimization)
|
||||
emtol = 1000.0 ; Stop minimization when the maximum force < 1000.0 kJ/mol/nm
|
||||
emstep = 0.01 ; Minimization step size
|
||||
nsteps = 50000 ; Maximum number of (minimization) steps to perform
|
||||
|
||||
; Parameters describing how to find the neighbors of each atom and how to calculate the interactions
|
||||
nstlist = 1 ; Frequency to update the neighbor list and long range forces
|
||||
cutoff-scheme = Verlet ; Buffered neighbor searching
|
||||
ns_type = grid ; Method to determine neighbor list (simple, grid)
|
||||
coulombtype = PME ; Treatment of long range electrostatic interactions
|
||||
rcoulomb = 1.0 ; Short-range electrostatic cut-off
|
||||
rvdw = 1.0 ; Short-range Van der Waals cut-off
|
||||
pbc = xyz ; Periodic Boundary Conditions in all 3 dimensions
|
||||
@@ -1,44 +0,0 @@
|
||||
title = OPLS Lysozyme NPT equilibration
|
||||
; define = -DPOSRES ; position restrain the protein
|
||||
; Run parameters
|
||||
integrator = md ; leap-frog integrator
|
||||
nsteps = 50000 ; 2 * 50000 = 100 ps
|
||||
dt = 0.002 ; 2 fs
|
||||
; Output control
|
||||
nstxout = 500 ; save coordinates every 1.0 ps
|
||||
nstvout = 500 ; save velocities every 1.0 ps
|
||||
nstenergy = 500 ; save energies every 1.0 ps
|
||||
nstlog = 500 ; update log file every 1.0 ps
|
||||
; Bond parameters
|
||||
continuation = yes ; Restarting after NVT
|
||||
constraint_algorithm = lincs ; holonomic constraints
|
||||
constraints = h-bonds ; bonds involving H are constrained
|
||||
lincs_iter = 1 ; accuracy of LINCS
|
||||
lincs_order = 4 ; also related to accuracy
|
||||
; Nonbonded settings
|
||||
cutoff-scheme = Verlet ; Buffered neighbor searching
|
||||
ns_type = grid ; search neighboring grid cells
|
||||
nstlist = 10 ; 20 fs, largely irrelevant with Verlet scheme
|
||||
rcoulomb = 1.0 ; short-range electrostatic cutoff (in nm)
|
||||
rvdw = 1.0 ; short-range van der Waals cutoff (in nm)
|
||||
DispCorr = EnerPres ; account for cut-off vdW scheme
|
||||
; Electrostatics
|
||||
coulombtype = PME ; Particle Mesh Ewald for long-range electrostatics
|
||||
pme_order = 4 ; cubic interpolation
|
||||
fourierspacing = 0.16 ; grid spacing for FFT
|
||||
; Temperature coupling is on
|
||||
tcoupl = V-rescale ; modified Berendsen thermostat
|
||||
tc-grps = Protein Non-Protein ; two coupling groups - more accurate
|
||||
tau_t = 0.1 0.1 ; time constant, in ps
|
||||
ref_t = 300 300 ; reference temperature, one for each group, in K
|
||||
; Pressure coupling is on
|
||||
pcoupl = Parrinello-Rahman ; Pressure coupling on in NPT
|
||||
pcoupltype = isotropic ; uniform scaling of box vectors
|
||||
tau_p = 2.0 ; time constant, in ps
|
||||
ref_p = 1.0 ; reference pressure, in bar
|
||||
compressibility = 4.5e-5 ; isothermal compressibility of water, bar^-1
|
||||
refcoord_scaling = com
|
||||
; Periodic boundary conditions
|
||||
pbc = xyz ; 3-D PBC
|
||||
; Velocity generation
|
||||
gen_vel = no ; Velocity generation is off
|
||||
@@ -1,41 +0,0 @@
|
||||
title = OPLS Lysozyme NVT equilibration
|
||||
;define = -DPOSRES ; position restrain the protein
|
||||
; Run parameters
|
||||
integrator = md ; leap-frog integrator
|
||||
nsteps = 50000 ; 2 * 50000 = 100 ps
|
||||
dt = 0.002 ; 2 fs
|
||||
; Output control
|
||||
nstxout = 500 ; save coordinates every 1.0 ps
|
||||
nstvout = 500 ; save velocities every 1.0 ps
|
||||
nstenergy = 500 ; save energies every 1.0 ps
|
||||
nstlog = 500 ; update log file every 1.0 ps
|
||||
; Bond parameters
|
||||
continuation = no ; first dynamics run
|
||||
constraint_algorithm = lincs ; holonomic constraints
|
||||
constraints = h-bonds ; bonds involving H are constrained
|
||||
lincs_iter = 1 ; accuracy of LINCS
|
||||
lincs_order = 4 ; also related to accuracy
|
||||
; Nonbonded settings
|
||||
cutoff-scheme = Verlet ; Buffered neighbor searching
|
||||
ns_type = grid ; search neighboring grid cells
|
||||
nstlist = 10 ; 20 fs, largely irrelevant with Verlet
|
||||
rcoulomb = 1.0 ; short-range electrostatic cutoff (in nm)
|
||||
rvdw = 1.0 ; short-range van der Waals cutoff (in nm)
|
||||
DispCorr = EnerPres ; account for cut-off vdW scheme
|
||||
; Electrostatics
|
||||
coulombtype = PME ; Particle Mesh Ewald for long-range electrostatics
|
||||
pme_order = 4 ; cubic interpolation
|
||||
fourierspacing = 0.16 ; grid spacing for FFT
|
||||
; Temperature coupling is on
|
||||
tcoupl = V-rescale ; modified Berendsen thermostat
|
||||
tc-grps = Protein Non-Protein ; two coupling groups - more accurate
|
||||
tau_t = 0.1 0.1 ; time constant, in ps
|
||||
ref_t = 300 300 ; reference temperature, one for each group, in K
|
||||
; Pressure coupling is off
|
||||
pcoupl = no ; no pressure coupling in NVT
|
||||
; Periodic boundary conditions
|
||||
pbc = xyz ; 3-D PBC
|
||||
; Velocity generation
|
||||
gen_vel = yes ; assign velocities from Maxwell distribution
|
||||
gen_temp = 300 ; temperature for Maxwell distribution
|
||||
gen_seed = -1 ; generate a random seed
|
||||
@@ -1,41 +0,0 @@
|
||||
title = OPLS Lysozyme NVT equilibration
|
||||
;define = -DPOSRES ; position restrain the protein
|
||||
; Run parameters
|
||||
integrator = md ; leap-frog integrator
|
||||
nsteps = 2500000 ; 2fs * 125000000 steps = 250 ns
|
||||
dt = 0.002 ; 2 fs
|
||||
; Output control
|
||||
nstxout = 10000 ; save coordinates every 1.0 ps
|
||||
nstvout = 10000 ; save velocities every 1.0 ps
|
||||
nstenergy = 10000 ; save energies every 1.0 ps
|
||||
nstlog = 10000 ; update log file every 1.0 ps
|
||||
; Bond parameters
|
||||
continuation = yes ; first dynamics run
|
||||
constraint_algorithm = lincs ; holonomic constraints
|
||||
constraints = h-bonds ; bonds involving H are constrained
|
||||
lincs_iter = 1 ; accuracy of LINCS
|
||||
lincs_order = 4 ; also related to accuracy
|
||||
; Nonbonded settings
|
||||
cutoff-scheme = Verlet ; Buffered neighbor searching
|
||||
ns_type = grid ; search neighboring grid cells
|
||||
nstlist = 10 ; 20 fs, largely irrelevant with Verlet
|
||||
rcoulomb = 1.0 ; short-range electrostatic cutoff (in nm)
|
||||
rvdw = 1.0 ; short-range van der Waals cutoff (in nm)
|
||||
DispCorr = EnerPres ; account for cut-off vdW scheme
|
||||
; Electrostatics
|
||||
coulombtype = PME ; Particle Mesh Ewald for long-range electrostatics
|
||||
pme_order = 4 ; cubic interpolation
|
||||
fourierspacing = 0.16 ; grid spacing for FFT
|
||||
; Temperature coupling is on
|
||||
tcoupl = V-rescale ; modified Berendsen thermostat
|
||||
tc-grps = Protein Non-Protein ; two coupling groups - more accurate
|
||||
tau_t = 0.1 0.1 ; time constant, in ps
|
||||
ref_t = 300.00 300.00 ; reference temperature, one for each group, in K
|
||||
; Pressure coupling is off
|
||||
pcoupl = no ; no pressure coupling in NVT
|
||||
; Periodic boundary conditions
|
||||
pbc = xyz ; 3-D PBC
|
||||
; Velocity generation
|
||||
;gen_vel = yes ; assign velocities from Maxwell distribution
|
||||
;gen_temp = 300.00 ; temperature for Maxwell distribution
|
||||
;gen_seed = -1 ; generate a random seed
|
||||
@@ -1,21 +0,0 @@
|
||||
#!/bin/bash
|
||||
#SBATCH --partition=jamesz
|
||||
#SBATCH --job-name=alphafold # Job name
|
||||
#SBATCH --mail-type=ALL # Mail events (NONE, BEGIN, END, FAIL, ALL)
|
||||
#SBATCH --mail-user=wukevin@stanford.edu # Where to send mail
|
||||
#SBATCH --nodes=1 # Run all processes on a single node
|
||||
#SBATCH --ntasks=4 # Number of processes
|
||||
#SBATCH --mem=16gb # Job memory request
|
||||
#SBATCH -G 1
|
||||
#SBATCH -C GPU_SKU:RTX_2080Ti
|
||||
#SBATCH --time=6-23:59:59 # Time limit
|
||||
#SBATCH --output=alphafold_%j.log # Standard output and error log
|
||||
|
||||
ml gcc/6.3.0
|
||||
ml cuda/11.7.1
|
||||
. /home/groups/jamesz/miniconda3/etc/profile.d/conda.sh
|
||||
. ~/.bashrc
|
||||
|
||||
# Expects a3m files under "input" directory, outputs to "out" direcotry
|
||||
# Auto handles environment
|
||||
/scratch/users/wukevin/software/localcolabfold/colabfold_batch/bin/colabfold_batch inputs out --num-recycle 15 --num-models 1 --model-order 1 --sort-queries-by random
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/bin/bash
|
||||
#SBATCH --partition=jamesz
|
||||
#SBATCH --job-name=omegafold # Job name
|
||||
#SBATCH --mail-type=ALL # Mail events (NONE, BEGIN, END, FAIL, ALL)
|
||||
#SBATCH --mail-user=wukevin@stanford.edu # Where to send mail
|
||||
#SBATCH --nodes=1 # Run all processes on a single node
|
||||
#SBATCH --ntasks=10 # Number of processes
|
||||
#SBATCH --mem=40gb # Job memory request
|
||||
#SBATCH -G 2
|
||||
#SBATCH -C GPU_SKU:RTX_2080Ti
|
||||
#SBATCH --time=6-23:59:59 # Time limit
|
||||
#SBATCH --output=omegafold_%j.log # Standard output and error log
|
||||
. /home/groups/jamesz/miniconda3/etc/profile.d/conda.sh
|
||||
. ~/.bashrc
|
||||
# Activate the appropriate conda environment
|
||||
conda activate /home/groups/jamesz/wukevin/envs/omegafold
|
||||
python /home/groups/jamesz/wukevin/projects/protdiff/bin/omegafold_across_gpus.py proteinmpnn_residues/*.fasta -o omegafold_predictions_proteinmpnn --weights /home/groups/jamesz/wukevin/software/omegafold/release1.pt
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/bin/bash
|
||||
#SBATCH --partition=jamesz
|
||||
#SBATCH --job-name=training # Job name
|
||||
#SBATCH --mail-type=FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
|
||||
#SBATCH --mail-user=wukevin@stanford.edu # Where to send mail
|
||||
#SBATCH --nodes=1 # Run all processes on a single node
|
||||
#SBATCH --ntasks=20 # Number of processes
|
||||
#SBATCH --mem=40gb # Job memory request
|
||||
#SBATCH -G 2
|
||||
#SBATCH -C GPU_SKU:RTX_2080Ti
|
||||
#SBATCH --time=6-23:59:59 # Time limit
|
||||
#SBATCH --output=training_%j.log # Standard output and error log
|
||||
. /home/groups/jamesz/miniconda3/etc/profile.d/conda.sh
|
||||
. ~/.bashrc
|
||||
# Activate the appropriate conda environment
|
||||
conda activate /home/groups/jamesz/wukevin/envs/protdiff
|
||||
python /home/groups/jamesz/wukevin/projects/protdiff/bin/train_autoregressive.py
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/bin/bash
|
||||
#SBATCH --partition=jamesz
|
||||
#SBATCH --job-name=training # Job name
|
||||
#SBATCH --mail-type=FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
|
||||
#SBATCH --mail-user=wukevin@stanford.edu # Where to send mail
|
||||
#SBATCH --nodes=1 # Run all processes on a single node
|
||||
#SBATCH --ntasks=20 # Number of processes
|
||||
#SBATCH --mem=40gb # Job memory request
|
||||
#SBATCH -G 2
|
||||
#SBATCH -C GPU_SKU:RTX_2080Ti
|
||||
#SBATCH --time=6-23:59:59 # Time limit
|
||||
#SBATCH --output=training_%j.log # Standard output and error log
|
||||
. /home/groups/jamesz/miniconda3/etc/profile.d/conda.sh
|
||||
. ~/.bashrc
|
||||
# Activate the appropriate conda environment
|
||||
conda activate /home/groups/jamesz/wukevin/envs/protdiff
|
||||
python /home/groups/jamesz/wukevin/projects/protdiff/bin/train.py /home/groups/jamesz/wukevin/projects/protdiff/config_jsons/cath_full_angles_cosine_discard_long.json --dryrun
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/bin/bash
|
||||
#SBATCH --partition=jamesz
|
||||
#SBATCH --job-name=training # Job name
|
||||
#SBATCH --mail-type=FAIL # Mail events (NONE, BEGIN, END, FAIL, ALL)
|
||||
#SBATCH --mail-user=wukevin@stanford.edu # Where to send mail
|
||||
#SBATCH --nodes=1 # Run all processes on a single node
|
||||
#SBATCH --ntasks=20 # Number of processes
|
||||
#SBATCH --mem=40gb # Job memory request
|
||||
#SBATCH -G 2
|
||||
#SBATCH -C GPU_SKU:RTX_2080Ti
|
||||
#SBATCH --time=6-23:59:59 # Time limit
|
||||
#SBATCH --output=training_%j.log # Standard output and error log
|
||||
. /home/groups/jamesz/miniconda3/etc/profile.d/conda.sh
|
||||
. ~/.bashrc
|
||||
# Activate the appropriate conda environment
|
||||
conda activate /home/groups/jamesz/wukevin/envs/protdiff
|
||||
python /home/groups/jamesz/wukevin/projects/protdiff/bin/train.py /home/groups/jamesz/wukevin/projects/protdiff/config_jsons/cath_full_angles_discard_long.json --dryrun
|
||||
Reference in New Issue
Block a user