Students cannot be initially expected to understand the “bigger picture” of what is involved with setting up and running a simulation or to interpret complex output from a program like CHARMM. While documentation exists, a novice user may not be able to clearly relate their own outputs to it and to results reported in the literature. Therefore, the lessons system must clearly show each step in a calculation and whether or not it has been performed successfully.

Since molecular modeling is a broad field, the infrastructure should limit the lesson implementer as little as possible. Reasonable default values are given along with step-by-step instructions for performing various tasks.

Anyone with some knowledge of the Python programming language should be able to implement their own lesson without having to learn the entirety of the CHARMMing source code. CHARMMing accomplishes this by providing “hooks” at various points in the workflow. The only requirement, then, is to write the particular logic needed for each step and the accompanying user-facing instructions.

A lesson in CHARMMing is a list of tasks that a user must perform, beginning with creating a structure. Each lesson is independent and has an HTML page within CHARMMing that updates the user's progress as they complete tasks. Initially, the page for a particular lesson will contain instructions for submitting the structure that is to be used. Once each step is done, new text is added to the lesson page describing the next step that is to be performed. Once all steps are completed, the user is informed that the lesson is over. If a task is performed incorrectly at any time, an error message is displayed on the lesson page, and the step must be repeated until it is done correctly. All of the lesson pages are accessed under the “Lessons” subheader of CHARMMing's main menu. A drop down box was also added to the Submit Structure page that lets the user select with which, if any, lesson the structure is associated (see Figure 1). This allows users to start multiple lessons and even multiple copies of the same lesson. When a lesson is started, an additional status window is shown on the left-hand sidebar following the user's progress (Figure 2).

On structure upload and submission of a calculation (e.g., minimization or dynamics), CHARMMing checks to see if a lesson is in progress. If it is, then it calls a routine specific to that lesson to see if the calculation was set up correctly. Likewise, when a calculation is finished, CHARMMing sends its exit status and, depending on the type of calculation, results to another lesson-specific routine. Based on this information, the lesson logic can decide whether or not the submission or calculation was performed as intended. If it was sucessful, the user is allowed to move onto the next step of the lesson. If not, an error message is generated, which is displayed on the lesson HTML page, and the lesson status box also displays the fact that an error was detected.

The objective of this lesson is to provide an introduction to the most basic features of CHARMMing. The student is instructed to create a periodic water box and run a short MD simulation. To accomplish this, the user uploads structure files describing a single water molecule and then uses the solvation functionality to create a rhombic dodecahedral unit cell. The user must then run minimization to place the structure in a low energy conformation. This step is often a prerequisite to further calculations, a facet that is described more completely in the tutorial. The behavior of the system is then studied via MD simulation. Since minimization puts the molecular system at a low energy state, it is necessary to “reheat” it to physiological temperature. Therefore, the user is instructed to start a heating simulation that increases the temperature from 210.15 K to 310.15 K over the course of 1,000 MD steps. For a publication-quality simulation, somewhat slower heating would likely be employed (e.g., 10,000–100,000 steps). The final outputs from the heating include a dynamics trajectory, and after completion the student should have a very basic understanding of the steps necessary to upload a simple structure into CHARMMing, solvate it, and perform a MD simulation with periodic boundary conditions (PBC).

The major objective of lesson two is the application of simulation techniques to a protein system, the oxysterol binding protein complexed with cholesterol, which was previously studied by Singh et al. [17]. As part of this, additional details about force field parameters are introduced. The user is given a special structure file adapted from the protein data bank (www.pdb.org) [18], code 1ZHY [19], to upload into CHARMMing. CHARMM topology and parameter files containing cholesterol are provided [20], and the user must upload these into CHARMMing. Solvation is used, as in lesson one, but in this case the structure contains a net charge, so neutralization is introduced. This procedure adds counter-ions to the solvent to make the unit cell electrically neutral; important for the particle-mesh Ewald (PME) electrostatic method [21], [22]. Minimization is used as above to prepare the structure for dynamics. For this lesson, both heating and constant temperature (using the NVT ensemble, where number of particles [N], volume [V], and temperature [T] are held constant) dynamics are run, and the user is instructed to “make a movie” from the NVT trajectory. At the conclusion of this lesson, the user should have a better understanding of the techniques introduced in lesson one and be able to apply them to simple protein systems; furthermore, they should be able to use custom parameter files and know how to neutralize a charged system.

The objective of this lesson is to illustrate how molecular simulations can be used to study protein structure and conformation. For example, a critical component of current research efforts is determining how proteins fold [23]. It is intractable to conduct a complete conformational search or sampling study within the computational limits imposed by CHARMMing, and in fact, folding any more than relatively small (70–100 residue) polypeptides is currently beyond the capabilities of even the largest supercomputers; [24]–[26] however, students can still learn some basic principles. In this lesson, the user gives CHARMMing an amino acid sequence, GNNQQNY, which is found in the yeast protein Sup35 and has been crystallized (PDB: 1YJP) [27], and then instructs the software to generate an initial conformation. After minimization, a very short simulation (1 picosecond) is run utilizing an advanced sampling method, (SGLD) [28], which is designed to speed up slow, low frequency motion. The final step presents a simple analysis technique using the root mean squared differences (RMSD) between the starting and ending structures to give a measure of conformational change. Upon finishing this lesson, students should have a basic familiarity with the idea of methods that enhance conformational sampling in proteins. Furthermore, they should know how to simulate arbitrary amino acid sequences using CHARMMing.

So far, all of the lessons in CHARMMing have focused on classical simulation techniques using MM. In recent years, several techniques have been developed to combine MM with more accurate but computationally expensive QM methods. This has led to a hybrid class of methods, i.e., QM/MM [29]–[32], which are important for simulating a wide variety of systems, such as those undergoing reactions where a covalent bond is formed or broken [33]–[36]. The primary objective of CHARMMing's fourth lesson is to introduce QM/MM techniques; a secondary objective is to teach users about CHARMM's RTF format. The RTF describes the chemical topology, but not the interaction parameters, of various subunits (“residues”) such as amino acids, nucleic acids, and small molecules. In CHARMMing, several mechanisms exist for automatically generating a RTF and the associated parameters for many different types of biomolecules using the CHARMM General Force Field (CGenFF) [37]–[39].

To begin this lesson, the user creates a custom RTF for butane and then uploads it with the provided PDB file. Once the structure is uploaded, the user is instructed to calculate its single point classical energy to ensure that the custom RTF was made correctly. Afterwards, the user must calculate the energy again, but this time using QM/MM. Various schemes for managing the interactions between the classical and quantum regions have been devised [34]; however, for this lesson CHARMMing utilizes the additive QM/MM scheme implemented via the Q-Chem/CHARMM interface [40], [41]. The user is asked to use the Hartree-Fock method for the QM region (i.e., no correlation) in conjunction with the STO-3G basis set; the QM charge should be set to zero. The QM region is defined as half of the butane (i.e., one methyl and methylene group and its associated link atom). The final step in this lesson is to perform an energy minimization using QM/MM. At the conclusion of this lesson, the student should be able to perform simple QM/MM calculations in CHARMMing and have gained some insight into how to create and edit topology files for small molecules.

As mentioned previously, one of the major challenges facing the field of molecular modeling is elucidating large scale conformational changes in proteins. In the current lesson, coarse grained (CG) models [42]–[44], where multiple atoms are combined into a single interaction center (“bead”), are illustrated as an effective strategy to overcome many computational limitations. Full details of this are given in part II of this series of manuscripts.

Oxidation and reduction reactions, where one atom involved in the reaction donates an electron to another atom, are an important part of many different biological reactions, such as those found in glycolysis or the Krebs cycle. Recently, CHARMMing has been extended to use the Adaptive Poisson-Boltzmann Solver (APBS) [45] for calculating reduction potentials of iron–sulphur metalloenzymes [46]. To illustrate the utility of these calculations, a lesson has been developed and integrated with new graphical capabilities and generic amino acid mutation functionality. Full details of this of this lesson and reduction potential calculations in CHARMMing are presented in Part III of this series of manuscripts.

CHARMMing's lesson system is designed to allow the easy addition of new lessons, implemented as Django applications (see [4] for further information). Currently, this requires some knowledge of Python; however, we have developed an external Python script that creates the basic lesson infrastructure. From there, additional customization is still required; specifically, the lesson logic needs to be implemented and the user-facing instructions written. In the future, lessons will be created based on a “recorded” set of actions. For example, if the user uploads a stucture, performs a minimization, and identifies the energy; a lesson will then be created based on those actions and results.