Science topic

Molecular Simulation - Science topic

Explore the latest questions and answers in Molecular Simulation, and find Molecular Simulation experts.
Questions related to Molecular Simulation
  • asked a question related to Molecular Simulation
Question
5 answers
I am conducting molecular simulations to study the interaction between RNA and a polymer. However, during the simulation process using GROMACS, multiple errors arise, hindering the progress of the simulation. I am seeking guidance to troubleshoot and resolve these issues effectively."
Relevant answer
Answer
To troubleshoot RNA-polymer simulations in GROMACS:
  1. Check topology and parameter compatibility: Ensure proper force fields for RNA and the polymer (e.g., CHARMM for RNA).
  2. Minimize energy: Perform energy minimization to avoid steric clashes.
  3. Review input files: Double-check the PDB, topology, and simulation settings for errors.
  4. Use proper restraints: Apply constraints to stabilize the system (e.g., for the polymer backbone).
  5. Check simulation box: Ensure the box is appropriately sized for both RNA and polymer.
Fix errors step-by-step and review GROMACS logs for specific issues.
all of which can we easily done at mdsim360.com, a new platform that lets you run MD simulations entirely online without local installation.
  • asked a question related to Molecular Simulation
Question
2 answers
Hello everyone, I am currently working on miRNA- mRNA interaction study. Further, I would like to do MD simulations for the miRNA-mRNA models.
For the Simulation, I have modelled this complex using the Alphafold server. But when I try to use AlphaFold models for the Gromacs MD simulations, it gives some error when I apply the force field (Amber - 2010).
The error is "Atom OP3 in residue U 1 was not found in rtp entry RU5 with 28 atoms while sorting atoms."
If I change the atom name, it shows another atom is missing (attached the screen shot with this Q&A)
Is there any updated force field or modelling algorithm?
Kindly help me to solve this issue.
Relevant answer
Answer
I removed all the OP3, P, OP1, and OP2 atoms from the file. Now, The Amber force field is working for the model. Thank you for the suggestion.
  • asked a question related to Molecular Simulation
Question
2 answers
Hi,
I am working on LAMMPS molecular simulation on CO2 mineralization. I have some scripts which require to compile Lammps files using cmake in ubuntu. Is there anyone who has some expertise can help me to solve that problem.
I look forward to hearing from someone. Thank you.
Sincerely,
Akash
Relevant answer
Answer
Hi, I am sorry to make delay in response. Meanwhile, I was working on compiling the LAMMPS files. I think I did it successfully using cmake. However, now I am facing to run simulation in ubuntu using those files. May I request to help what I am doing wrong? I have attached a screenshot of the problem that I am facing. Thank you.
  • asked a question related to Molecular Simulation
Question
8 answers
How to commence simulations in nanoscale? In which part of the code do we introduce the nano dimensions?
Relevant answer
Answer
Dear S
MD simulations are a complex and often computationally expensive technique. It is important to have a good understanding of the underlying principles and be familiar with the chosen software and force field before starting a simulation. Don't hesitate to consult with experts and use available resources to learn more about MD simulations and their applications in nanoscale systems.
Here are some additional resources that you may find helpful:
  • asked a question related to Molecular Simulation
Question
3 answers
I am docking multiple ligands (new designed ligand) against my protein using Autodock Vina in Chimera. The results displayed in this program are somewhat strange, because in some cases the ligands with no hydrogen bond or fewer bonds has the most negative Score than the ligand with more hydrogen bonds!!? Please look at the picture to get my mean(The best model in ligand with 2 hydrogen bonds has a score -8.3, While the best model in ligand with one or zero hydrogen bond has score -8.7 and -10.1 respectively!).
I understand that checking with other software or tools like PyMOL or PDBSUM will better help to analyze the possible interactions, however since I have several ligands with almost similar score and interaction network or equal hydrogen bond numbers, I am curious to now how to pick the best one (based on the in silico analysis) among them. If any body has suggestion for this I will appreciated it.
Relevant answer
Answer
You should choose the pose with the highest score (-10.1) since it has a significant score difference with the second pose.
Docking algorithms like Autodock Vina evaluate multiple factors when calculating the docking score, including van der Waals interactions, electrostatic interactions, and hydrogen bonding. While the number of hydrogen bonds can be an important indicator of ligand binding, it's not the sole determinant of the docking score. Other factors such as the strength and geometry of the hydrogen bonds, as well as non-polar interactions, can also contribute to the overall score.
  • asked a question related to Molecular Simulation
Question
1 answer
Dear all,
I have the cif file of the MOF structure, the atoms and their indexes goes like this:
C1 1.0 0.3521 0.68248 0.49724
Cr2 1.0 0.6727 0.73299 0.90674
C3 1.0 0.9812 0.86236 0.85294
C4 1.0 0.29174 0.5265 0.71863
...
C1185 1.0 0.17108 0.59341 0.61745
C1186 1.0 0.14289 0.58226 0.66194
C1187 1.0 0.1861 0.67126 0.70408
Cr1188 1.0 0.25915 0.66547 0.69122
...
But in the simulation, we divided the atoms to different types,e.g. only 3 types of carbon atom and 2 types of Cr and so on. The force field is made for the type of atoms such as:
C1 lennard-jones 47.8562 3.47299
C2 lennard-jones 47.8562 3.47299
Cr1 lennard-jones 7.54829 2.69319
Cr2 lennard-jones 7.54829 2.69319
So the data need to be like:
C1 1.0 0.3521 0.68248 0.49724
Cr2 1.0 0.6727 0.73299 0.90674
C1 1.0 0.9812 0.86236 0.85294
C2 1.0 0.29174 0.5265 0.71863
...
C1 1.0 0.17108 0.59341 0.61745
C1 1.0 0.14289 0.58226 0.66194
C2 1.0 0.1861 0.67126 0.70408
Cr2 1.0 0.25915 0.66547 0.69122
...
How do I change the atom index? There are too many atoms for me to do it manually. Is there any software that can do this ?
Relevant answer
Answer
Openbabel conversions work to get cifs into a RASPA readable format.
  • asked a question related to Molecular Simulation
Question
3 answers
Molecular simulation of protein ligand complex
Relevant answer
Answer
Dear Dr Gautum
"MD" typically refers to "Molecular Dynamics," a computational simulation method used to study the behavior of atoms and molecules over time. The amount of time required for a molecular dynamics simulation is highly dependent on several factors, including the complexity of the system being studied, the desired level of accuracy, the computational resources available, and the specific simulation parameters being used.
The time step used in a molecular dynamics simulation is usually in the range of femtoseconds (10^-15 seconds) to picoseconds (10^-12 seconds). This time step determines how often the simulation calculates the forces and updates the positions and velocities of the atoms in the system. The total simulation time is then a product of the number of time steps and the time step size.
For example, if you are simulating a system for 1 nanosecond (10^-9 seconds) with a time step of 1 femtosecond, you would need 1,000,000 time steps to cover that time span.
Keep in mind that the length of a simulation doesn't directly correlate with the accuracy of the results. Longer simulations can provide more statistically significant data, but the choice of simulation parameters and the quality of the force field used (if applicable) are also crucial factors in determining the reliability of the results.
Additionally, the computational resources available play a significant role in how quickly a simulation can be performed. More powerful hardware can complete simulations faster. Some simulations might take hours, while others could take days, weeks, or even longer.
In summary, there is no fixed answer to how many nanoseconds are required for a molecular dynamics simulation, as it depends on various factors. Scientists and researchers often perform preliminary tests to determine an appropriate simulation length based on their specific research goals and available resources.
  • asked a question related to Molecular Simulation
Question
1 answer
Hello,
We want to continue one of our previous simulations and add one more molecule into the system. We used 53a6 force field files from ATB server for our previous simulations since we started it many years ago. However, currently, when we submit a molecule to the ATB server, it always outputs the G54A7FF force field files. Could you please tell me how can I get 53a6 files from the ATB server?
Any help would be much appreciated!
Relevant answer
Answer
As of my knowledge cutoff in September 2021, the ATB (Automated Topology Builder) server provided force field files for the Gromacs G54A7FF force field, which is an updated version of the Gromos 53a6 force field. The G54A7FF force field includes improvements and refinements over the original Gromos 53a6 force field.
If you specifically need the Gromos 53a6 force field files for your simulations, you may face challenges obtaining them directly from the ATB server since it primarily provides the G54A7FF force field files.
However, there are a few potential options to consider:
  1. Local Backups: If you have performed simulations using the Gromos 53a6 force field in the past, you should check your local backups or archives for the necessary force field files. If you have saved the required files from your previous simulations, you can use those files for the continuation of your simulations.
  2. Contact ATB Support: If you have a specific reason for using the Gromos 53a6 force field files and cannot find them in your backups, you can reach out to the support team or administrators of the ATB server. They might be able to provide you with more information or assistance in accessing the older Gromos 53a6 force field files.
  3. Use G54A7FF Force Field: Alternatively, you can consider using the G54A7FF force field files provided by the ATB server for your simulations. Although the force field is updated, it may still be suitable for your research needs. Be sure to review the differences between G54A7FF and Gromos 53a6 force fields and evaluate if the updated force field is acceptable for your specific study.
  4. Consult with Experts: If your research or project requires the Gromos 53a6 force field for specific reasons, you may consider consulting with experts in your field or other researchers who have experience with this force field. They might be able to provide insights or guidance on using the Gromos 53a6 force field in your simulations.
Please note that the availability of force field files on the ATB server might change over time, so it's essential to check the latest information and options available on the ATB website or contact their support team for the most up-to-date details.
  • asked a question related to Molecular Simulation
Question
2 answers
I pass the nvt step easily but in the npt step I can't get the pressure to 1 bar .please suggest a solution. It is a protein-peptide complex
Relevant answer
Answer
Make sure you choice appropriate box size if you run with periodic boundary condition. If the periodic box is too small, the preset pressure may be unreachable.
And if your MD simulation procedure raise an error, you have better upload the log file, or it is difficult for others to give you useful advice.
  • asked a question related to Molecular Simulation
Question
4 answers
Could you explain the process by which the RMSD result is created, and provide insight into any noticeable jumps or fluctuations in the data? I'm curious about the underlying reasons behind these patterns.
Relevant answer
Answer
Thank you for providing the answers. I made a modification to the command (gmx trjconv -s md.tpr -f md.xtc -o md_noPBC.xtc -pbc mol -center) by changing it to (gmx trjconv -s md.tpr -f md.xtc -o md_noPBC.xtc -pbc nojump -center). As a result of this modification, the graph displayed a different outcome.
  • asked a question related to Molecular Simulation
Question
4 answers
I am performing an all-atom molecular dynamic simulation in LAMMPS to perform the diffusion and adsorption capacities of gaseous hydrogen in metal alloys. For the simulation, I am using an embedded atom potential to model the interaction between the metal elements and a Lennard-Jones potential to model the H-H and H-metal elements interactions. All the lennard jones interactions follow the Lorentz-Berthelot mixing rules. I have used 0 as both the epsilon and sigma for the H-H interactions and by doing that all the other epsilons between the H-metal element are automatically going down to 0 (as the mixing rule for epsilon follows the geometric mean).
I am concerned about whether I am doing it right by using 0 LJ parameters for the H-H interaction. I have found some literature to support this for the adsorption but not for the case of diffusion analysis. It will be highly appreciated if anyone can give me some thoughts/advice on this.
pair_coeff * * eam/alloy 12_eam.alloy Al Cu NULL
pair_coeff 2 3 lj/cut/coul/cut 0 1.344
pair_coeff 1 3 lj/cut/coul/cut 0 1.1597
pair_coeff 3 3 lj/cut/coul/cut 0 0
Relevant answer
Answer
The interaction of hydrogen with metals at such high temperatures is not in my field of expertise. But I can tell you this: If hydrogen dissolves in the metal as a molecule you need a non-zero sigma. If it dissolves by forming a metal hydride the H atoms will probably lie within the outer orbitals of the metal atoms, and therefore not require additional space. You need to find out first whether hydrogen dissolves in molecular form or undergoes a chemical reaction.
Incidentally, the Berthelot rule for estimating cross pair potentials is good for nonpolar, non-reacting molecules only, e.g., (H2 + CH4). It is not safe to assume its validity for the interaction of a hydrogen atom and a nickel atom.
  • asked a question related to Molecular Simulation
Question
2 answers
hi
What kind of force field is used for the molecular simulation of protein-peptide complex, and what kind of water is used? Is there any file or guideline in this field?
Relevant answer
Chek with the kind people at https://www.schrodinger.com/ and request a demo. Please ask meaningful questions and do your homework!
  • asked a question related to Molecular Simulation
Question
4 answers
A pH of 5.5 would mean 3.16*10^-6 mol/L of H+ concentration. When I convert it into number of molecules per cubic Angstrom, it would be 1.9*10^-9 molecules. It means the box length (assuming cubic) should be around 800A for one H+ molecule. This is too huge simulation box.
In general, how is this problem statement addressed in MD simulations? How do we consider such pH range with feasible simulation parameters?
I want to simulate a solution of organic acids in water system, with different pH ranges.
Relevant answer
Answer
Mohammed Almajidi Thanks for useful insights.
  • asked a question related to Molecular Simulation
Question
2 answers
Hello all,
I'm trying to understand how we can combine the Forward Flux sampling method with LAMMPS to obtain ice nucleation rates using mW potential of water?
I do not understand if this is performed through LAMMPS itself or through a separate application and if so how is it applied in practice.
This method has been described in many publications but how FFS is used and which software is deployed for it is never clearly explained - maybe because it is directly understood but I cannot figure it out !
Any insight is appreciated. Thanks.
Relevant answer
Answer
Thanks Jeet Majumdar !!
  • asked a question related to Molecular Simulation
Question
4 answers
Hi,
I am new to gromacs and using gromacs 4.6.5 and dssp-2.0.4. To study the secondary structure, when I am running these commands:
>export DSSP=/usr/local/bin/dssp
>do_dssp -s md_0_1.tpr -f md_0_1_noPBC.xtc -o dssp.xvg -ver 2
I am getting this error:
dssp cmd='/usr/local/bin/dssp -na dd31ZWbc ddI6at3a > /dev/null 2> /dev/null' Reading frame 0 time 0.000 Back Off! I just backed up dd31ZWbc to ./#dd31ZWbc.1#
-------------------------------------------------------Program do_dssp, VERSION 4.6.5 Source code file: /build/buildd/gromacs-4.6.5/src/tools/gmx_do_dssp.c, line: 669
Fatal error: Failed to execute command: Try specifying your dssp version with the -ver option.
I have already checked many helping sites but couldn't solve it.
I don't know how to fix it. Please help me?
Relevant answer
Answer
  • asked a question related to Molecular Simulation
Question
5 answers
I am trying to run a QM/MM in Amber on a protein-ligand system. I have looked for tutorials but they don't explain a few things such as how to heat your system and equilibrate it before MD.
Then there are errors in output files. I have run the questions in the list and applied the changes, but the errors still remain. I would appreciate if someone could share their experience on running these for protein-ligand systems.
Thank you.
Relevant answer
Answer
Hi,
  I am trying to run QM/MM with the oniom package. My system consists of  protein and DNA. During gaussian run, i am  getting  error like-
Bondstretch undefined between atoms   5618   5619 HO5'-O5' [L,L]
Bondstretch undefined between atoms   5618   5620 HO5'-C5' [L,L]
-------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------
Angle bend  undefined between atoms   6536   6537   6539 N1-C6-C5 [L,L,L]  Angle bend  undefined between atoms   7471   5618   7472 OW-HO5'-HW [L,L,L]  * These undefined terms cancel in the ONIOM expression. MM function not complete
These atoms are mainly from DNA. Can you  please tell me where we have to  incorporate these parameters in gaussian?
Thank you
Vipin
  • asked a question related to Molecular Simulation
Question
3 answers
The adsorption capacity was calculated using molecular simulation. When the adsorbent is MOF or COF, it is often mentioned in the literature that the molecular structure of the adsorbent needs to carry charge data. However, I don't know exactly how the charge affects the adsorption capacity, and how much?
Relevant answer
Answer
Do you mean surface charge of the adsorbent or the adsorbate or both of them?
  • asked a question related to Molecular Simulation
Question
4 answers
Every time I start loading a lammps dump file of more than 4GB in windows, VMD crashes. Are there any certain modifications I need to make?
Relevant answer
Answer
Hey There, The most probable reason is that your machine memory (RAM) < what is required by VMD for visualizing the dump file. VMD uses 12 bytes of memory /atom /frame, so you can calculate the memory required by the formula 12*Number of atoms*Number of frames.
Solutions:
1. Load a subset of your dump file, either by limiting the start/end frame indices or by setting a frame stride greater than 1 when loading the trajectory.
2. Expand your workstation specs.
I hope this helps.
  • asked a question related to Molecular Simulation
Question
3 answers
I did a free energy calculation based on the BAR method (in GROMACS) and now I want to see the entropic and enthalpic contribution of that free energy. How could it be done with molecular simulation?
Thank you in advance!
Relevant answer
Answer
To obtain the enthalpy and entropy contribution, you can calculate the free energy of solvation at several temperatures then draw the curve between dG as y versus temperature as x. If the temperatures range is not too large, the line should be linear. Then, you can get the dS from the -slope and the dH from the extrapolation of dG (y) at x = 0.
You can refer to this publication for more detail. It is actually for the evaporation process, but the ideas will be the same. The method in the publication is quite complex, but I think you can estimate the contribution of enthalpy and entropy from the linear regression of dG = dH - TdS.
  • asked a question related to Molecular Simulation
Question
4 answers
Hi,
I am a new user of ORCA. My initial calculations were successful but at this moment I am facing a problem to run a new calculation on my laptop. However, I can run calculation with the same input file on my older laptop.
Here is an example of my input file for the calculation on nitric oxide:
!RKS BP86 RI SV(P) SV/J TightSCF Opt
*xyz 0 2
N 0 0 0
O 0 0 1.2
*
Here is the error message mentioned at the bottom of the .out file:
ERROR : GSTEP Program returns an error
cannot continue with the optimization
COMMAND : orca_gstep NO.ginp.tmp
RETURN CODE : -1
I would appreciate your help.
Best regards,
Subrata
Relevant answer
Answer
This is due to the difference between the number of cores in the input and sbatch files.
  • asked a question related to Molecular Simulation
Question
6 answers
Dear all,
I have been confused about the use of restraints in the molecular simulation. As far as I understand, the restraints are added in energy minimization so that only the solvent will optimize and it will orient correctly around our protein. The equilibration is considered the relaxation towards equilibrium of the system, but as the large motion of the protein before sampling is unwanted, the restraints are added again.
Yet, I by chance heard from a senior research that for dt=1fs nvt equilibration, we should not add constraints. (only added for 2fs)
I wonder whether 'constraint' here means 'restraint' or not. If it's restraint, then why should we removed it in case of shorter time steps?
Or maybe I have mistaken the definition/ purpose of the processes?
Relevant answer
Answer
Dear Tini Chu
I am not an expert in this, so take my explanation with also because sometimes people use constraint/restraint interchangeably.
What you said about the protein being restrained is correct. Restraints are the general term used when you specify, for example, that you are applying an energy penalty to some type of movement. Then, in the protein sim, you can restrain the heavy atoms of the protein so that most of the position changes are experienced by water atoms/ions/hydrogen atoms, and you don't risk any weird non-physiological unfolding. The utility is basically to go from a starting configuration that can contain high forces weird packing etc to an equilibrated one, and want to go there without losing any geometrical properties while you remove these 'generation' artifacts. The same is done for example with lipid bilayers, where you restrain lipids in their position so that the bilayer does not lose integrity during the equilibrium phases.
In general restraints can also be applied for other reasons, such as energy sampling (umbrella sampling, AWH etc) or to drive some changes such as dragging an ion across a channel. Basically what you do is integrating the equations of motion by considering this additional energy penalty, which for example could take the form of a harmonic potential centered in the position of interest so that the atom is 'trapped' where you want it to be.
Constraints usually do refer to some type of constraint that is put on the bonds, such as setting a bond length or an angle among some atoms in a molecule. You constrain a bond so that it does not oscillate. Oscillation of bonds can be very fast, and therefore would need a small integration time step to be properly picked up and described. If your oscillations have a typical period of, say, 0.1 fs, and your dt is 1fs, then you wouldn't be able to properly describe what is going on in the system. In a way, you can see bond constraints as a way to remove these oscillations, and make larger integration steps achievable. For example
What you heard about NVT constraints could be true, depending on the context, but it is not a general rule. Bond constraints are a serious thing, and strongly depend on the integration time step and the forcefield you are using, and therefore you must follow what is suggested for that forcefield, depending also on what you are trying to achieve and investigate. Differently from restraints, a constraint is usually applied using some specific algorithms (LINCS, SHAKE, etc) that corrects the position of the atoms after the dynamical step has been taken, that is after an unconstrained step. The implementation is quite different from constraints and it could also depend on the specific algorithm and code you are using for MD (LAMMPS, CHARMM, GROMACS, etc).
Hope this helps,
Nicola
  • asked a question related to Molecular Simulation
Question
2 answers
I am working of oxidative stress and found out one target protein form network pharmacology approach. We tried the molecular docking studies with some triazol derivatives. This gave us good result. Now we are planning to do wet work with this system but meanwhile i would like to so some simulation studies on the same. If any body is interested in collaboration pl mail me on
Dr. Manisha Modak
Relevant answer
Answer
Good Idea!!
  • asked a question related to Molecular Simulation
Question
7 answers
I have a 20a x 17a x 20a simulation box filled with bcc tungsten atoms. What lammps command can I write to make 20a x 2.5a x 20a at the bottom of the box "immobile"?
The script below shows how my atoms were created:
# ---------- Create Atoms --------------------------
## define crystal structure and lattice constant a_0
## define direction vectors, i.e., set x=[100], y=[010], z=[001] and origin point.
variable a_0 equal 3.1648
lattice bcc 3.1648 orient x 1 0 0 orient y 0 1 0 orient z 0 0 1 &
origin 0.1 0.1 0.1
region box block 0 20 0 17 0 20 ## define box sizes along x, y, z (in the unit of a_0)
create_box 1 box ## create the simulation box, allowing a max of one specie
create_atoms 1 box ## create type-1 metal atoms in the box
Relevant answer
Answer
Dear Nitin,
Can you share the script where some of the atoms in a slice (group) can be made mobile. This is specifically an interdiffusion of two materials I.e. setting up bonding/Welding etc. Exact problem is to make one body thermostat and another body to heat up say via NVT.
  • asked a question related to Molecular Simulation
Question
7 answers
So, My question is what basis we choose the membrane proteins for docking and molecular simulations, because in PDB there are a lot of structures for membrane proteins Like GPCRs, Ionic linked receptors, and Enzyme-linked receptors.
Above mentioned I have some knowledge about the PDB structures for choosing based on the Resolution 1-3 b/w, this range is good crystal structure.
But, the problem is how nanoparticles interact with membrane proteins? So, what basis we choose the PDB structures for docking.
Relevant answer
Answer
What is your nanoparticles? You can use openmm to build several nanoparticles.
  • asked a question related to Molecular Simulation
Question
3 answers
I use VMD for analysis of NAMD molecular simulation.
I have gotten a RMSF plot using a scrip via VMD.
As it obvious, residue number 1399, attained maximum fluctuation in this plot.
Now I wanna know residue number 1399 belongs to which amino acid in my protein structure.
BTW: I have to use stride=80 because of large dcd file.
I have attached the RMSF script I used and also the RMSF plot.
Help me if you can
Thanks.
Relevant answer
Answer
1. Upload your PSF and DCD files into the VMD.
2. Click on Graphics and select Representations.
3. Type the keyword "resid 1399 and not water" in Selected Atoms
4. Press enter
5. In Coloring Method choose ColorID red in adjacent tab
6. In Drawing Method choose Licorice
7. Now you can see your selected residue number in VMD OpenGL Display
8. Now press 1 in your keyboard and click on that selected residue number
9. Now you can see the residue name of your selected residue number.
Hope you will get the information which you want to know.
Thanks
  • asked a question related to Molecular Simulation
Question
5 answers
Hello Everyone!
I am working on molecular simulations of nanoparticles and for that I have to use LAMMPS. I want to install LAMMPS on Linux and tried several tutorials but couldn't install it anyway. Currently I am watching and trying this tutorial "https://www.youtube.com/watch?v=FMjwSdPAT3k&t=243s" but doesn't get its some of codes as its not working on my side. Can anyone please give me some good tutorial of LAMMPS with complete guideline of its installation?
Your answers are highly appreciated
Regards & Thanks
Misbah
Relevant answer
Answer
Just type these codes one by one
$ sudo add-apt-repository ppa:gladky-anton/lammps $ sudo add-apt-repository ppa:openkim/latest $ sudo apt-get update
$ sudo apt-get install lammps-stable
$ lmp_stable -in in.lj
$ sudo apt-get install lammps-stable-doc
  • asked a question related to Molecular Simulation
Question
8 answers
Dear all,
I have started to study molecular simulation for weeks, and have studied the basic theory of molecular simulation from lectures and videos. I am currently trying to do some hands-on practices, but here comes the question.
I follow the tutorials, yet I don't know how to come up with the protocol of my target. I have been puzzled 'how to study my target' for a while. Also, how to be familiar with my target is another big problem.
Can anyone please give me some suggestions? Study route or any recommendations are appreciated.
Relevant answer
Answer
Dear Tini Chu
To properly get started you need a solid theoretical background of thermodynamics, statistical thermodynamics and molecular dynamics in general. Many good books have been written over the years, such as
Computer simulation of liquids (Allen)
Understanding molecular simulations (Frenkel)
Molecular modelling (Leach)
Thermodynamics and statistical mechanics (Greiner)
When you have the theoretical tools, you need the practical ones. This mainly means finding a software which is able to run simulations of your system of interest, depending also on the hardware available. GROMACS, CHARMM, LAMPS are common examples of MD software. You have to decide what to use and install it if not already available to you.
Next, and arguably most important step, is setting up your starting systems, which roughly reduces to choosing a force field. What system are you interested in? What molecules? What timescales? Is the force field implemented in the MD software you are using?
At this point you will be able to start running simulations about your system of interest.
There is no general answer to these questions. Some software is better than another in certain aspects, or supports a force field that you need while others don't. Similarly, some force fields work better for some properties/molecules/systems than others. Maybe you are looking to be fast, and therefore are looking to coarse grained or united atoms systems.
A 'must do' is looking in the given field and understand what has been done and what is the common procedure to do it. If you are interested into binding properties of some ligand, then read relevant literature about it, maybe something has already been done with your ligand of interest. What software are they using? What force field? What properties do they measure? Once you have an idea, install and get experience with that software. For example, for GROMACS do some of these tutorials (first one always plus other relevant to you)
I use GROMACS as an example because that's what I work with, but CHARMM, LAMPS etc are available and you will for sure find many tutorials online. Once you are familiar with the software, find some fundamental work in the literature that is achievable and try to reproduce it, so that you get experience with a system similar to yours and with the sampling procedures you also will need.
Hope this helps,
Nicola
  • asked a question related to Molecular Simulation
Question
5 answers
I want to simulate polymers. Could you recommend any software to build the molecules? I want to do simulations to evaluate new polymers that were generated in my laboratory, could you recommend key properties that I should measure? I want to do molecular dynamics with gromacs because it is the software that I know how to use, but would there be any better? Could you recommend any guide or tutorial. Only free access software.
I already tried Charmm-gui but it doesn't have the polymers I need to model.
Thanks for your help,
Relevant answer
Answer
It is not difficult to create a new polymer. For example, it can be done by means of Avogadro software. Note that, obtaining proper force field parameters is a challenging task in MD simulations. The structural optimization and determination of partial charges can be performed by DFT calculations. In order to do that you have to parameterize your polymer which needs to represent the correct interaction parameters in hydrophobic and hydrophilic content. Please, find below links for several papers which might be helpful for your case:
  • asked a question related to Molecular Simulation
Question
3 answers
There is some software or tool that allows me to create a molecular simulation in which the pressure in my system is increasing?
I am working with a pressure sensitive membrane protein and I would like to analyze its behavior in molecular dynamics
Thanks!
Relevant answer
Answer
Usually you will either use an NPT or NVT ensemble. NPT is constant pressure that you set in the input file so you won’t be able to change the pressure. NVT allows pressure to fluctuate, but you can’t control the pressure. I may be mistaken, but it seems to me that changing the pressure would require re-equilibration to prevent the system crashing, so I don’t think using restarts at different set pressures would work (I guess you could always try). I think the way to go would be to use separate simulations. I would be to launch multiple replicas of NPT simulation at different pressures (say 25 replicas each) and then use the aggregate data sets to do your analysis. This method lends itself well to Markov modeling and other collective variable analysis as well but requires a lot of computational resources. Perhaps someone else will have a better suggestion, good luck to you.
  • asked a question related to Molecular Simulation
Question
5 answers
Dear All,
I have problem with pressure (virial) calculation. My task is quite different than normal. In my case I have total forces Fk on particle k treated as the sum of all the forces from the other particles j in the system. I have that information from external program (e.g. CP2K), off course I have also atoms positions all k particles. My question is how can I calculate a virial component (pressure) with that?
Thank You!
  • asked a question related to Molecular Simulation
Question
23 answers
Hello All
I am trying to calculate the frequency of a transition state of the molecule, but everytime the running jobs stops after calculating the rotational constant in the output file and shows" Error termination request processed by link 9999."
  I would be very thankful if anyone could help me with the reason of this problem and what can be done?
I already tried increasing the SCF Maxcycle, but it still got struck at the same point mentioned above.
Relevant answer
Answer
Another way is to increase %mem. Please refer to an outstanding report about "How to solve the error message in Gaussian" as follow: https://docs.computecanada.ca/wiki/Gaussian_error_messages
  • asked a question related to Molecular Simulation
Question
17 answers
I am trying to optimize a hexa-coordinated Cu-complex with N2O(N=N=O) as one of the ligand. My input file parameters are define below. Can anyone help me how to solve the problem?
N.B:- When I optimize the same Cu-complex without N2O(N=N=O) i.e- a penta-coordinated Cu-complex, it ends with normal termination .
%mem=2500MB
%chk=cu_complex.chk
# opt=maxcycles=500 b3lyp/3-21g scrf=(solvent=dichloromethane)
geom=connectivity
Relevant answer
Answer
Total agreement with the good colleagues using keyword opt=cartesian and nosymm or symmetry=none. An outstanding summary about "How to solve the error message in Gaussian" as follow: https://docs.computecanada.ca/wiki/Gaussian_error_messages
  • asked a question related to Molecular Simulation
Question
4 answers
For spin isomers such as ortho-parahydrogen, is it possible to study the catalytic addition of their mutual conversion through molecular simulation technology?
As we know that hydrogen has two spin isomers, specifically, they are orthohydrogen and para hydrogen. Now there are some studies that use catalysts to convert it catalytically. With the popularization of first principles, many studies have used molecular simulation methods to study problems at the atomic level, but it is rare to see that this method is applied to parahydrogen conversion. Is this method not working? Or are there other reasons for this phenomenon?Is there a combination of machine learning and molecular simulation technology to quickly screen the most favorable catalyst?
Relevant answer
Answer
Dear Zheng Gao this is a very interesting technical question. Since we are working in synthetic inorganic chemistry I'm certainly not a proven expert in this field. However, I can suggest to you a few potentially useful literature references. For example, please have a look at the following articles:
Para-ortho hydrogen conversion: Solving a 90-year old mystery
and
Hydrogen Conversion in Nanocages
(see attached pdf file)
The first article is freely available as public full text on RG, and the second one has been published Open Access.
Good luck with your research work!
  • asked a question related to Molecular Simulation
Question
6 answers
I have done one NVT molecular simulation for liquid phase propanol and one vacuum simulation for gas phase propanol simulation. However, my calculated heat of vaporization did not match with the experimental value. My liquid phase enthalpy was 21.52 KJ/mol and gas phase enthalpy was 31.6 KJ/mol. So, I got the heat for vaporization is 12.5 KJ/mol whereas, the experimental value is 42.5 KJ/mol. I suspect that the potential energy for liquid phase has having some problem. But, I could not figure that out. My liquid phase potential energy is -13.16 KJ/mol and kinetic energy is 34.68 KJ/mol.
Relevant answer
Answer
First of all, you need an interaction potential that accounts for hydrogen bonding. There are simple Lennard-Jones- or Mie-type effective potentials that can be used, but these are usually optimized for the liquid phase, and therefore are not very good for the vapour phase. Which potential/force field did you use?
Second, you have to ensure that both phases have the same pressure. You need
NpT simulations for this, and then you have to set the pressure to the equilibrium vapour pressure.
If you do not know the vapour pressure for your propanol model, you can either use a simulation technique that involves fluctuations of the particle number (e.g., grand canonical Monte Carlo or Gibbbs ensemble Monte Carlo) or to obtain the chemical potentials (e.g., Widom's insertion method or thermodynamic integration) and vary the pressure until the chemical potentials of the liquid and the vapour become equal.
  • asked a question related to Molecular Simulation
Question
10 answers
Hii,
I want to know if it is a good choice to do model refinement with online server like 3D refine after model generation instead of Molecular dynamics?
I have run the molecule simulations up to 10ns for my structure also but when I was docking the ligand after simulations ithe interactions were totally different?
So, I decided to do the refinement with 3D refine and after docking ligand interactions are somewhat similiar so I want to know if it is okay to use web server for refinement.
Thanks!
Relevant answer
Answer
Mahbubul Himel Rajesh Pal Nancy might be referring to the fact that protein molecules can be minimised/refined using YASARA or Galaxy Refine servers before performing MD simulations. Also, YASARA (and many other minimisation servers) do employ MD simulations to achieve the minimised state of protein molecules. For example, YASARA performs MD simulations (in an implicit solvent and using YASARA2 ff) until the Fmax reaches 0.05 kJ/mol/atom.
  • asked a question related to Molecular Simulation
Question
4 answers
I have been trying to finish the polymer tutorial for MARTINI, I was able to reproduce the bonded distribution, and I was also able to get the density, end to end distance and gyration radius within 5%. But I am not able to reproduce the solvation free energy in case of PEG9 in a solution. According to the tutorial I should get 7kJ/mol, but I am getting a value of 150kJ/mol. 
md.mdp file:
integrator = sd
; start time and timestep in ps =
tinit = 0
dt = 0.01
nsteps = 2500000
cutoff-scheme = group
; We remove center of mass motion. In periodic boundary conditions, the center of mass motion is spurious; the periodic system is the same in all translational directions.
comm-mode = Linear
; number of steps for center of mass motion removal =
nstcomm = 10;5 ; ORIGINALLY 10
ns_type = grid ; USER ADDED NOT IN TUTORIAL
pbc = xyz ; USER ADDED NOT IN TUTORIAL
table-extension = 2
; Output frequency for energies to log file and energy file =
nstxout = 0
nstvout = 0
nstfout = 0
nstlog = 10000
nstenergy = 10000
nstcalcenergy = 10
nstxtcout = 10000
nstlist = 10;10 ;5 ; ORIGINALLY 10
rlist = 1.4
coulombtype = Shift
;rcoulomb_switch = 0.0
;rcoulomb = 1.2
;epsilon_r = 15
vdw_type = Shift
rvdw_switch = 0.9
rvdw = 1.2
tc-grps = System
tcoupl = v-rescale
tau_t = 1.0
ref_t = 300
; Pressure coupling =
Pcoupl = Parrinello-Rahman
tau_p = 12.0 ; PREVIOUSLY 4
compressibility = 3e-4
ref_p = 1.0
;--------------------
; Free energy parameters
free-energy = yes
sc-power = 1
sc-alpha = 0.5sc-r-power = 6
sc-r-power = 6
; Which intermediate state do we start with?
-------
init-lambda-state = sedstate
; What are the values of lambda at the intermediate states?
;-------
vdw-lambdas = 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
; This makes sure we print out the differences in Hamiltonians between all states, and not just the neighboring states
;--------
calc-lambda-neighbors = -1
; the frequency the free energy information is calculated. This
; frequency (every 0.2 ps) is pretty good for small molecule solvation.
;-------
nstdhdl = 10
; not required, but useful if you are doing any temperature reweighting. Without
; temperature reweighting, you don't need the total energy -- differences are enough
dhdl-print-energy = yes
couple-moltype = PEG
; we are changing both the vdw and the charge. In the initial state, both are on
couple-lambda0 = vdw
; in the final state, both are off.
couple-lambda1 = none
; we are keeping the intramolecular interactions ON in all the interactions from state 0 to state 8
couple-intramol = no
Please help, I have been stuck at this tutorial for far too long. 
Relevant answer
Answer
It means that you do not need to multiply the potential energies with an arbitrary factor.
You still can do HREMD, but depending on the method you should think about changing angles/Lennard-Jones parameters instead of dihedrals and electrostatics. In the MARTINI coarse-grained representation, most molecules do not have dihedrals and electrostatic interactions are mostly parameterized within the VdW interactions (with a few exceptions).
  • asked a question related to Molecular Simulation
Question
6 answers
I have a target and a small molecule which is interaction with the enzyme. How do you determine whether the small molecule is a substrate or an competitive inhibitor of the enzyme?
I feel so confused because the substrates and competitive inhibitors of an enzyme are usually structurally similar.
Relevant answer
Answer
Simply, you can carry out an enzyme inhibition assay on your proposed inhibitor if this enzyme is available, otherwise, you can predict if your molecule can bind to the enzyme's active site by conducting docking and molecular dynamic simulation experiments.
  • asked a question related to Molecular Simulation
Question
6 answers
I am currently performing coarse-grained MD simulations in LAMMPS using mW potential for water. I initialize the water model at 273K, equilibrate for 50ns followed by a quenching process from 273K to 200K at a rate of 0.5K/ns for a total of 146ns. At the end I observe what looks like a nucleated structure. But how can I be certain that homogeneous nucleation has indeed taken place?
Can a specific property be extracted from LAMMPS or any visualization technique be used to confirm that the structure has indeed nucleated?
Any insight is appreciated.
Relevant answer
Write a script to calculate the radial distribution function of your system along a predefined reaction coordinate between the interface and the buried atoms. Check the coordination number and the behavior of the RDF to get insights about nucleation.
  • asked a question related to Molecular Simulation
Question
8 answers
I am trying to do a molecular simulation for a single molecule at box dimension 15 A * 15 A * 15 A. But every time I am getting an error saying "1 of the 64 bonded interactions could not be calculated because some atoms involved moved further apart than the multi-body cut-off distance (0.4 nm) or the two-body cut-off distance (0.4 nm), see option -rdd, for pairs and tabulated bonds also see option -ddcheck"
Can anyone share the input command line for this type of simulation?
Relevant answer
Answer
thanks for your important question
  • asked a question related to Molecular Simulation
Question
5 answers
I want to calculate just the distance between two neighbouring monomers using Avogadro but since it doesn't allow to create long chains, I am in this dilemma. Kindly help !!
Relevant answer
Answer
Distance between the monomers barely depends on the chain length but the state of the macromolecule. So you can proceed, hopefully. Thanks.
  • asked a question related to Molecular Simulation
Question
2 answers
I'm working with molecular simulation of systems composed of nonspherical particles and currently interested in calculating the first- and second-order perturbation coefficients and comparing the results with the spherical case. These coefficents are related to the high-temperature power series expansion steming from Zwanzig's perturbation theory. I've come across an article ( ) that relates the ratio of these coefficients with the low-density limit. In other words:
a2/a1 = 0.5
or, in a most general case:
a_i/a_i-1 = 1/i
where a_i represent the perturbation coefficients and i is an integer number greater than or equal to 2. Does anyone know where this "perturbation ratio" comes from?
Relevant answer
Answer
  • asked a question related to Molecular Simulation
Question
1 answer
Hi, I'm trying to do a simulation of my docking results and i got this error
Fatal error:
The residues in the chain MET1--NI602 do not have a consistent type. The first
residue has type 'Protein', while residue KCX219 is of type 'Other'. Either
there is a mistake in your chain, or it includes nonstandard residue names
that have not yet been added to the residuetypes.dat file in the GROMACS
library directory. If there are other molecules such as ligands, they should
not have the same chain ID as the adjacent protein chain since it's a separate
molecule.
I have tried adding residue name to residuetypes.dat and also added the residue to the forcefield at the aminoacids.rtp file based on previous papers but i'm still getting the error. perhaps im doing it wrong. in the residuetypes.dat i put KCX Protein but i still get the error as 'Other'. Where should i change the residue type? or is it because i put the wrong residue type?
anyone know how to solve this?
Relevant answer
Answer
You can use openforcefield to add a residue to a forcefield:
If you want to perfomed a protein-ligand complex simulation follow GROMACS tutorial:
  • asked a question related to Molecular Simulation
Question
2 answers
I am using the HOOMD-blue package, and I was advised to use force-shifted Leanard Jones potential, with a tree neighbor list. I do not know which parameters I should write for those charged molecules (hard spheres) "'N, charge'" The system would also have some counterions, and they have an impact on the system.
classhoomd.md.pair.ForceShiftedLJ(nlist, r_cut=None, r_on=0.0, mode='none')
nlist = hoomd.md.nlist.tree(
r_buff=0.4, check_period=1, d_max=None, dist_check=True, name=None)
Thanks in advance!
Relevant answer
Answer
Mohamed-Mourad Lafifi Thanks, those papers are useful, but they do not help me.
I did build the model, and I am struggling to apply electrostatic field to the model.
  • asked a question related to Molecular Simulation
Question
3 answers
I have created an Ice 1h structure and created an adhesive bond with the substrate in LAMMPS. Now in order to replicate an adhesion test, I need to detach it using a tensile force that pulls it away from the substrate. How can this be achieved? What fixes can be used for replicating this detachment mechanism? Any insight is appreciated.
Relevant answer
Answer
A universal testing machine, calibrated by existing measurements.
  • asked a question related to Molecular Simulation
Question
4 answers
Dear experts,
I am doing molecular dynamics simulation for quadruplex DNA and nickel Schiff base complexes with the workflow in attached picture. However, when I tried to generate the parameter files for Nickel complex using antechamber and tleap with GAFF in Ambertools 13 (step 2 and 3), there were major errors with the following announcements:
1.  For atom[27]:Ni, the best APS is not zero, bonds involved by this atom are frozen. The frozen atom type can only be 1, 2, 3, 7 (aromatic single), 8 (aromatic double) Error: cannot run
 2. Sourcing: ./leap.in
source: Improper number of arguments!
usage:  source <filename>
Could not open file frcmod: not found
Could not open file Ni1.mol2: not found
----------------------------
I used these commands for generating parameters:
 antechamber -i Ni1.pdb -fi pdb -o Ni1.mol2 -fo mol2 -c bcc
 parmchk2 -i Ni1.mol2 -f mol2 -o frcmod
 tleap -f leap.in
* The commands in leap.in file:
source leaprc.gaff
mods = loadAmberParams frcmod
N = loadMol2 Ni1.mol2
saveAmberParm N prmtop inpcrd
quit
----------------
Could you please give me some advices to fix these problems? I have attached the pdb file of nickel complex in case you need further information.
Thank you very much.
Kind regards,
Sean.
Relevant answer
Answer
hi dear
i am facing same problem. How you solved it ???
  • asked a question related to Molecular Simulation
Question
5 answers
I have a pre-equilibrated Ice 1h structure at 250K. I also have an Aluminium substrate which is 10 Angstroms below it within a simulation box. With the potential defined for structures (TIP4P for Ice, EAM for Al, LJ for cross-interactions), how can I bring both structures together to form an adhesive bond at the interface?
In terms of LAMMPS commands, how can this be achieved? Any insight is appreciated.
Relevant answer
Answer
Abhay Vincent in your model the LJ cross-interactions are the only ones between ice and Al, and the adhesion will be a consequence of them. Those are nonbonded pair interactions, so you don't need to create anything in terms of topology.
  • asked a question related to Molecular Simulation
Question
4 answers
Hi,
I am learning steered MD simulation for protein-ligand system. As I am a beginner in this method, I am trying to run the Lysozyme-ligand complex system described in the Bevan lab tutorial (http://bevanlab.biochem.vt.edu/Pages/Personal/justin/gmx-tutorials/umbrella/index.html).
I have run up to constant pulling velocity step for the protein-ligand system. After that I have got a trajectory file which show that the ligand gradually coming out at a distance from the protein's active site due to the application of constant pulling force. After this step, I used the perl script available there in the tutorial which gives .gro files for each of the frames in the trajectory file.
After this step, I have 300 .gro files and protein-ligand distance containing .xvg files for each of the frames (attached).
After that, the tutorial described about the steps of umbrella sampling where individual MD run have to run for a number of .gro file from the frames. In the tutorial it has been mentioned that, the .gro files should be selected from a specific frame interval.
I have following questions at this point:
1. Which .gro files from the frames should I take for the umbrella sampling run and what is the logic behind selecting those frame?
2. Is this selection process vary with different protein-ligand complex? Or there is a specific trend?
3. What should be the total time scale for running each MD simulation of each .gro file during umbrella sampling? (for a protein-ligand system approx 350 residues)
4. What should be the configuration of CPU (How many core needed) for running umbrella sampling of a protein-ligand system?
Please help.
Attachements:
1. conf.gro.zip (all the .gro files for each of the frames)
2. dist_prot_lig.xvg (all the .xvg files corresponding those .gro files describing the distance between protein and ligand).
3. Summary_distance.dat (protein-ligand distance from the xvg files gathered in one document)
4. pullf.xvg (change of pulling force respect with each frame during the MD run)
5. summary_distance.png (plot of the Summary_distance.dat)
6. pullf.png (plot of the pullf.xvg)
Thanks & Regards
Manish.
Relevant answer
Answer
I have same question as asked my Manish
  • asked a question related to Molecular Simulation
Question
1 answer
I want to get a average structure from a pdb file containing multiple models. I used the command below:
gmx cluster -f input.pdb -s topol.tpr -cutoff 20 -method gromos -av
GROMACS Doc states that the ''-av'' option can ''write average structure of each cluster'', but how does it do it. I think there will be atom clash or unphysical residue structure if it is a simple average of atom positions, however, the result above seemed rational.
On the other hand, the GROMACS website also has a suggestion about average structure:
I am confused by the algorithm, and I wish someone can help me!
Thank you!
Relevant answer
Answer
I guess you are correct unless you describe the atom positions in center of mass coordinates, and more importantly, you have a system that has a very rigid conformation with small RMS deviations.
  • asked a question related to Molecular Simulation
Question
2 answers
Is there any way to construct different initial filler shapes like triangle, square, rectangle, pillar, and tube in any simulation software.
Relevant answer
Answer
Thank you @Wojciech Kopec.
  • asked a question related to Molecular Simulation
Question
13 answers
I have created an Ice 1h structure and am equilibrating it 100K in NVT ensemble in LAMMPS for a timestep of 0.25fs in 3000 steps. The potential used is TIP4P/Ice. Although the simulation runs fine without errors, the Ice 1h structure loses it's crystalline shape and atoms become disoriented inside the simulation box. Atoms are not lost but they just don't hold the hexagonal shape they are supposed to.
Is this supposed to happen or does it represent a problem with the geometry/potential?
Relevant answer
Answer
The initial geometry of the system is not related with the interaction force field (let's suppose that you have a good one and you have no mistakes in its implementation), therefore before to start the MD simulations you have to optimize the system geometry first. When you do the equilibration of the system you have to carefully produce the initial velocities (in old school, the initial velocities were zero, but the atoms were slightly displaced from their initial equilibrium position) in order to have no drift or initial tensions inside the system.
It is recommended to start the equilibration with a small systems, get it equilibrated, create a supercell of it (with the size what you are interested) and after that start the your simulation.
  • asked a question related to Molecular Simulation
Question
2 answers
Trying to simulate a ice-PTFE interaction and am unable to find a reference which actually lists out forcefield parameters for PTFE-PTFE interactions using ReaxFF or even other force fields like Dreidig, Tersoff etc. Any help is appreciated.
Relevant answer
Answer
T. P M Goumans Thank you so much for the reply.
  • asked a question related to Molecular Simulation
Question
6 answers
I am searching for tools to construct molecular beacons which shall be complementary to a given sequence. I don't want to design any primers. I found that UNAfold is one such tool which I could use. However, I am unable to download it. The server is consistently down. Please help.
Relevant answer
Answer
I am able to access it through http://www.unafold.org/
There appears to be no access issues currently.
  • asked a question related to Molecular Simulation
Question
5 answers
I am working on molecular simulation of adsorption and I want to design a new molecular simulator software by C++.
The input of this software is some text file. I want to get initial position of each atom in Cartesian coordinate in a text file.
So I want to make this initial position data.
Can I make a structure in Material Studio 2017 and convert/export or extract this data to a text file?
Relevant answer
Answer
You can export the Materials Studio generated structure into .car format. It will give you the coordinates of your structure in txt format.
  • asked a question related to Molecular Simulation
Question
2 answers
Is it possible to transfer heat from one group to another using simulated aneeling technique in the Gromacs software? I would like to transfer heat from a gold nanoparticle (group 1 from 310 to 350 K) into a dppc bilayer (group 2) that is at 310 K. How can I do it using a NPT ensemble in a molecular dynamics?
Relevant answer
Dear Andre Silva Pimentel , This technique allows you to evaluate the variation of free energy from a mechanical event in GROMACS, eg. the adsorption of Ag-nanoparticles on the membrane. I really wouldn't be able to inform you about heat transfer without the event.
Using gmx energy, you can calculate Delta H from the mechanism by Hess's Law.
  • asked a question related to Molecular Simulation
Question
6 answers
I'm studying adsorption of CO2 on faujasite (FAU) and I would like to compare my data with literature. However, most of the published works have been shown the loading of CO2 on FAUs as molecules of CO2 per unit cell of FAU. The following reference supplied the composition of FAU NaY as Na56.Al56.Si136.O384 and it showed the equilibrium data of CO2 on NaY as molecules per unit cell. How can I convert these data to mmol per gram?
Relevant answer
Hello dear Lucas,
If you have molecules per unit cell and you want to convert it into mmol per gram, the procedure that you could apply would be as follow:
x (molecules/unit cell) * (1 mol / 6.02x10^23 molecules)*(1000 mmoles/ 1 mol)= mmol/unit.cell
and to convert Unit cell to gram, you can apply this equation:
Mass of unit cell = Z.M/Na, where Z= Effective number of atoms in unit cell, M molar mass and Na Avogadro's number.
So, the general equation to convert x molecules per unit cell into mmol per gram will be:
x (molecules/unit cell)* (1 mol/Na)*(1000 mmoles/ 1mol)*(Na/Z.M)
Simplifying:
x (molecules/unit cell)*(1000)/(1/Z.M), where Z is the effective number of atoms in unit cell, M is the molar mass.
Best regards,
Julián Sánchez.
  • asked a question related to Molecular Simulation
Question
12 answers
Dear All,
I am good at MD simulations with AMBER, NAMD, Gromacs, Forcite... But not familiar with MC simulation. Could you suggest some MC simulation packages? I have to calculate the binding energy of copper MOFs and small molecules at different temperatures.
Thanks,
Xiaoquan.
Relevant answer
Answer
You may find MC simulator inside LAMMPS package.
There is another simulator developed by the same group, but specifically for MC and Kinetic MC simulations (SPPARKS).
  • asked a question related to Molecular Simulation
Question
6 answers
I have a g-C3N4 sheet and I want to know the probability of bond length and bond angles for this material (something like the attached photo) from its trajectory result. Is there any specific software to do so?
Relevant answer
Answer
Please have a look at this tutorial (http://www.wag.caltech.edu/home/duin/Reax/Reax_training.pdf). This should help you out.
  • asked a question related to Molecular Simulation
Question
20 answers
I am newbie in this simulation, so i would like to see the simulation for Protein-ligand..
can anyone here suggest which software that is easy to use for newbie?
Relevant answer
Answer
These are 5 most commonly used softwares for MD calculations: GROMACS, CHARMM, AMBER, NAMD, and LAMMPS. All these software have some common features along with some unique capabilities. Some are them are open-source (e.g, GROMACS, and LAMMPS) and rest are either proprietary or commercial. For biological applications, GROMACS seems to more suitable, though I have never used it. For other applications, e.g., materials and fluids, LAMMPS is a great tool. I am using is for the past 4 years and found it very robust, fast, and well documented. Although the initial learning curve of LAMMPS is quite steep, I can assure you that its capabilities make it worth going through that learning phase.
  • asked a question related to Molecular Simulation
Question
3 answers
Can someone please simulate and explain these protein-ligand interactions for each of the ligands:
Please help me, it's urgent.
Protein
Ligands
I can be contacted directly at alirazashafqat@gmail.com
Relevant answer
Answer
As you mention, all these are proteins only
  • asked a question related to Molecular Simulation
Question
6 answers
I have a problem. My system is MGDG bilayer and in this system membrane has curves. I want to analyze hydrogen bonds only in small part of the system. I want to check how many hydrogen bonds I have, how many water bridges I have etc.
I try several methods to do that:
1. I delete all lipids and water from my system by my script and I left an only a small fragment in which I want to analyze hydrogen bonds.
a) Then I use gmx hbonds to analyze:
gmx hbonds -f *.gro -s .tpr -num *.xvg
but I use tpr from the whole system and it doesn't work. when I write this command my terminal stuck
b) Another method I created index file by using gmx make_ndx and I use my *.gro file to make index file and this gro file has an only small number of atoms, so I have an index groups (for water and for lipid) from an only small fragment of my system.
Then I use gmx hbonds to analyze:
gmx hbonds -f *.gro -s .tpr -num *.xvg
It works, but I have a very little number of hydrogen bonds and I know why, because the new index file gives inappropriate atom number. For example, if in my old system my atom had 110100 index number, now he have 100, because when I make new index file from my gro file it started count from 1 (and my fragment for example has atoms which have atom numbers from for example 90000 to 100000 and 130000 and 140000
c) I use new .tpr file by using gmx grompp, but it's very boring and you need a lot of work if you want analyze hydrogen bonds from for example 100 .gro files from a different time of trajectory, because I need to change every time my topology, because I have gro files from different times of trajectory and for example one file has 61 lipids and 1512 SOL and another gro file has 58 lipids and 1632 SOL molecules
So maybe someone knows how to do this?
Relevant answer
Answer
Your problem with method B is that you used an index file generated from a reduced atom to index into the full atom set. However, the indeces do not have to match (they wont once you have a gap in your atom selection). You can use your original tpr or gro file (of the whole system) to generate an index file with gmx make_ndx or gmx select and create index groups containing only the part of the system you want to analyze. Then use these small index groups as input for gmx hbonds with the whole system trajectory.
  • asked a question related to Molecular Simulation
Question
3 answers
It is difficult for us to directly observe the digestion process of food in the human gastrointestinal tract. However, molecular simulation is a powerful tool for us to explore the unknown world. We wonder whether molecular simulation can visualize this process?
Relevant answer
Answer
Molecular simulations is a powerfull tool for processes at atomic and molecular level, but you have to bear in mind that the length-scales and time-scales that are accessible for molecular simulations, provided you use supercomputers, are around a few tens of nm and ns-ms (small systems - longer time and viceversa). And then you have to have more precise questions before your set up the simulations (like "how protein A bonds to enzyme B" or something). Just throwing everything in a simulations box to see "what happens" is rarely a good idea.
  • asked a question related to Molecular Simulation
Question
3 answers
I am working with molecular simulation and modelling, and searching some softwares.
The most used software are Materials Studio and LAMMPS for Moleclar for Molecular Dynamics.
Is there a site/document that talks about it?
Relevant answer
Answer
Hi Bianca,
VMD is also a good option for construction of initial topologies and analysis of MD simulation results. I have not used it much, particularly I prefer to use tools in the command mode of linux, but there is much literature about it.
  • asked a question related to Molecular Simulation
Question
18 answers
I recently updated to macOS 10.15 only to realize after the update that Catalina can only run 64-bit apps. VMD software often used in our group for visualization  only exists as 32-bit (https://www.ks.uiuc.edu/Development/Download/download.cgi?PackageName=VMD)
I cannot downgrade my OS version as that required cleaning up the hard disk.
What is the way around this? Has anyone faced this issue? Any suggestions 
#VMD
Relevant answer
Answer
Now there is a tentative build of VMD for Catalina:
Kudos to François-Xavier Coudert!
  • asked a question related to Molecular Simulation
Question
4 answers
I want to generate some random coordinates using Gaussian distribution function in MATLAB and import them into Materials Studio. Is there any tool available for doing this?
Relevant answer
Answer
Yes I already did the same steps but when I imported the new coordinates I found the bonds were broken. Is there any option inside Materials Studio to generate random rough surface using Gaussian distribution function?
  • asked a question related to Molecular Simulation
Question
5 answers
I was trying Oplsaa, which worked fine for me for polyethelene. But in the case of PS I had problems because grompp produced many warnings the same type: "No default Angle types, using zeroes". These errors concern the topology file, the part with 3-body angle. The problem is not connected with all atoms, but only one specific C atom in each styrene monomer: the one that connects the backbone with the phenyl ring. Each styrene part produces 3 warnings like above for C4-C3-C8, C3-C4-H and C3-C8-H interaction. I did not notice any other warnings.
Below I made bold the parts which produced warnings
           C1-C2-
                  |
                 C3
             //        \
      H-C4        C8-H
           |            ||
          C5        C7
            \\         /
                 C6
Can I then use oplsaa for PS in Gromacs?
Relevant answer
Answer
  • asked a question related to Molecular Simulation
Question
10 answers
for example, I have used POPE cell membrane in my research work (molecular dynamics), but according to the paper that I attached below, this membrane is a kind of normal membrane.
if there is somebody who knows how to modify this membrane as a cancerous membrane, please recommend me.
Relevant answer
Answer
I would suggest you to look for a litterature about the lipid composition of cancerous cell membranes. POPE is just a model-membrane which does not need to be a representative for a cancerous cell membrane. Moreover, from the behaviour of compounds with the membrane composed only of POPE lipids you can not draw conclusions of the behaviour of cancerous cell membrane. To do more accurate research you shall also keep in mind what kind of cancer you are dealing with? In what tissue? Depending on tissues you will find the lipid composition which you need.
  • asked a question related to Molecular Simulation
Question
8 answers
The molecular simulation of two 50 amino acid long helical proteins forming heterodimer has ran 100ns then again ran for 50 ns. But the RMSD graph deformed. I have used gromacs 5.0 and saved it nopbc.xtc format . The graph is attached below. Kindly help me!
Relevant answer
Answer
Or you can use gmx trjconv with -pbc mol -center and then compute the rmsd
  • asked a question related to Molecular Simulation
Question
1 answer
I'm a very much beginner in using RASPA. I want to simulate a crystal phase, for which I have .xyz file. Can RASPA read .xyz files?
Relevant answer
Answer
You can use openbabel to convert structure files from one format to almost all possible formats with a simple command such as this:
babel myfile.xyz myfile.cif
  • asked a question related to Molecular Simulation
Question
3 answers
I wrote an MC algorithm that simulates bead-spring models and am in need of verifying the results of my code. Is there any resource in the literature that has energy expectation values (or any other metric) for MC simulation of bead-spring models that I can use for result verification?
Relevant answer
Answer
I appreciate your answer! I wasn't aware that that could be done for anything but the simplest models. I will look into this! Zhaoxi Sun
  • asked a question related to Molecular Simulation