Catalog
- Results include
-
Simulating protein folding with full atomistic detail [electronic resource]
Pande, Vijay S.London : Henry Stewart Talks, 2007.Online Henry Stewart Talks
-
Results of Quantum Chemical and Machine Learning Computations for Molecules in the QM9 Database
Sinitskiy, Anton V.2019Two types of approaches to modeling molecular systems have demonstrated high practical efficiency. Density functional theory (DFT), the most widely used quantum chemical method, is a physical approach predicting energies and electron densities of molecules. Recently, numerous papers on machine learning (ML) of molecular properties have also been published. ML models greatly outperform DFT in terms of computational costs, and may even reach comparable accuracy, but they are missing physicality - a direct link to Quantum Physics - which limits their applicability. Here, we propose an approach that combines the strong sides of DFT and ML, namely, physicality and low computational cost. We derive general equations for exact electron densities and energies that can naturally guide applications of ML in Quantum Chemistry. Based on these equations, we build a deep neural network that can compute electron densities and energies of a wide range of organic molecules not only much faster, but also closer to exact physical values than current versions of DFT. In particular, we reached a mean absolute error in energies of molecules with up to eight non-hydrogen atoms as low as 0.9 kcal/mol relative to CCSD(T) values, noticeably lower than those of DFT (approaching ~2 kcal/mol) and ML (~1.5 kcal/mol) methods. A simultaneous improvement in the accuracy of predictions of electron densities and energies suggests that the proposed approach describes the physics of molecules better than DFT functionals developed by "human learning" earlier. Thus, physics-based ML offers exciting opportunities for modeling, with high-theory-level quantum chemical accuracy, of much larger molecular systems than currently possible.
-
Millisecond molecular dynamics simulation of the mu Opioid Receptor
Feinberg, Evan N2015 - 2017The μ Opioid Receptor (μOR) is a G-Protein Coupled Receptor (GPCR) that mediates pain and is a key target for clinically administered analgesics. The current generation of prescribed opiates -- drugs that bind to μOR -- engender dangerous side effects such as respiratory depression and addiction in part by stabilizing off-target conformations of the receptor. To determine both the key conformations of μOR to atomic resolution as well as the transitions between them, long timescale molecular dynamics (MD) simulations were conducted and analyzed. These simulations predict new and potentially druggable metastable states that have not been observed by crystallography. We applied cutting edge algorithms (e.g., tICA and Transfer Entropy) to guide our analysis and distill the key events and conformations from simulation, presenting a transferrable and systematic analysis scheme. Our approach provides a complete, predictive model of the dynamics, structure of states, and structure-ligand relationships of μOR with broad applicability to GPCR biophysics and medicinal chemistry.
Guides
Library website
Exhibits
EarthWorks
More search tools
Tools to help you discover resources at Stanford and beyond.