Insights on AI-powered molecular simulation and drug discovery
An independent structural study of CrGO-897 asks how the engineered enzyme might position peptide-bound CML for FAD-dependent chemistry.
The best-scoring docking pose missed the reaction geometry. A lower-ranked pose placed the reactive carbon near FAD N5 and retained that arrangement during a short molecular dynamics simulation.
Read more →Lessons from rebuilding a 67 nm Martini 3 collagen fibril workflow. Large ECM simulations amplify reproducibility risk — a mismatched pull index, incomplete topology, or unstable equilibration can produce a trajectory that looks normal but measures the wrong experiment.
We walk through the failure modes we encountered and how a layer-by-layer workflow catches them before they become scientific conclusions.
Read more →This benchmark compares HADDOCK3 docking with short all-atom MD rescoring on 47 experimentally validated protein-peptide complexes.
We measured early true-binder enrichment and show how MD rescoring improves top-hit prioritization while keeping compute cost low.
Read more →One of the most rewarding parts of building SimAtomic is seeing it used in real research—especially when the workflow ends up in a peer-reviewed paper. Recently, I collaborated with a team at Florida State University on a study published in ACS Omega: "Desensitization of the Cardiac Troponin Complex by TnI Phosphorylation and Epigallocatechin-3-Gallate."
The paper combines in vitro motility assays with modern computational modeling—AlphaFold 3, docking, and MD—to connect experimental effects to a structural mechanism.
Read more →Eight independent GaMD simulations yielded open-like Switch II pocket candidates. Variability among replicas, sensitivity to the opening threshold, and unstable reweighting prevented a reliable estimate of their equilibrium population.
Read more →Molecular dynamics (MD) simulations are notoriously computationally intensive, especially when run with explicit solvent. GPUs have become essential for accelerating MD engines like OpenMM, offering order-of-magnitude speedups over CPUs [1].
SimAtomic collaborated with Shadeform, a marketplace providing access to GPU instances across 20+ cloud providers, to benchmark a range of GPU instance types. Here are the results...
Read more →Adding a short molecular-dynamics (MD) step after docking in virtual drug screening can cut wet-lab costs by > 50 %. Savings that matter especially for startups and small biotechs needing to stretch their runway, yet few are using it.
Read more →Advanced computational tools for drug discovery have traditionally been accessible only to large pharmaceutical companies with significant resources. This has created a barrier for smaller biotech companies and academic researchers who could benefit from these technologies.
Here we present how our open-source package streamlines MD simulation setup and execution.
Coming soon →