I recently used BioEmu for some testing. This could be a complement for a regular MD simulations pipeline but don’t believe it will replace MDS entirely. BioEmu’s model pipeline is quite powerful. It combines one pretraining step with two finetuning steps, drawing on experimentally determined structures, over 200 milliseconds of MD simulation data, and protein stability measurements from in vitro testing. That last piece is super important. Incorporating wet lab data significantly improves...
about 1 month ago • 1 min read
I get asked all the time why MD simulations need an NPT step before production.NPT stands for constant Number of particles, Pressure, and Temperature. And this is one of the most widely used isothermal-isobaric ensembles for MD equilibration. Here is what it does:1-NPT allows the box volume to fluctuate while maintaining constant pressure 2-NPT prevents artificial compression or expansion that would distort the outcome of downstream processes (e.g., binding energy)Please I would highly...
about 1 month ago • 1 min read
I get asked if AI can design a new protein from scratch. The answer used to be sort of, now it's yes.The most widely used approach is via diffusion modelsThe same underlying approach behind image generators, have been adapted to generate protein backbones from scratch. Tools like RFdiffusion take a structure prediction network and repurpose it as a generative model.Starting from noise, iteratively denoise, and you end up with a novel, physically plausible protein backbone. Then a separate...
about 1 month ago • 1 min read
When I started in MDS, one of the first things I had to learn was what force fields were!! Understanding what they do and how to apply them to a specific project can determine the success or failure of the entire study! Here I breakdown for you how FFs work and provide some examples about specific ones you can apply in your own project! My rule of thumb whenever working with a new protein is the following:1- Find similar proteins that exist in the literature. See what FFs were used in the...
about 1 month ago • 1 min read
Here I put together a general workflow that you can use to guide your Molecular dynamics simulation pipelines. In 5 steps you can go from having a steady snapshot to a dynamic protein system that you can use to understand how your protein works: 1) Input: you need a PDB or CIF file for your protein-ligand of interest. This can be obtained from a crystal structure or a deep learning prediction.2)System Preparation: in this step you determine the topology of your system and assign specific...
about 1 month ago • 1 min read
In my opinion the next innovation will be predicting how a protein in either apo or holo configuration moves… And this will be done with the same speed that now we currently can predict any protein structure! Protein dynamics prediction will be the next discovery that will shape the next stage in protein modeling!! Thank you, Best, Omar. © ProteinReach|2026 SciLearningWorkshops LLC Unsubscribe · Preferences
about 1 month ago • 1 min read
I never rely on docking data alone to understand the behavior of my protein-ligand complex. The rationale is simple:Docking = a single snapshot of your ligand in the pocket of your protein. This is unrealistic; proteins and ligands move all the time. Molecular dynamics simulations (MDS) = an ensemble of configurations/poses. This gives you the full breadth of your complex behavior. Not perfect by any means, but better than using a single pose to drive your conclusions. If you have the...
about 2 months ago • 1 min read
I can’t wait to implement machine learning powered force fields! Here’s why: With quantum mechanics one can understand the transitional states. So called in between steps of the reaction. You can imagine with this approach we can now study bound and unbound states in the same analysis. This can increase by several fold how we understand the interactions between a ligand and a protein. This is NOT possible with traditional force fields (e.g., AMBER). A few machine learning based-FFs that I...
about 2 months ago • 1 min read
I always use MMGBSA and MMPBSA as initial binding energy methods. Then use free energy perturbation (FEP) method to assess how accurate my two initial measurements were. So, the sequence of usage goes like this: 1) MMGBSA2) MMPBSA3) FEP The only downside of using FEP is that is computationally expensive. And not many groups have the possibility of using that one. But if you do, please go ahead and use it. Thank you, Best, Omar. © ProteinReach|2026 SciLearningWorkshops LLC Unsubscribe ·...
about 2 months ago • 1 min read