scholarly journals Molecular free energy optimization on a computational graph

RSC Advances ◽  
2021 ◽  
Vol 11 (21) ◽  
pp. 12929-12937
Author(s):  
Xiaoyong Cao ◽  
Pu Tian
Keyword(s):  
Neural Network ◽  
Free Energy ◽  
Energy Optimization ◽  
Refinement Method ◽  
Coordinates Transformation

GSFE-refinement is a super efficient protein refinement method that integrates the GSFE theory, coordinates transformation, neural network and auto differentiation, and maps molecular free energy optimization onto a computational graph.

scholarly journals Prospects for recurrent neural network models to learn RNA biophysics from high-throughput data

2017 ◽  
Author(s):  
Michelle J Wu ◽  
Johan OL Andreasson ◽  
Wipapat Kladwang ◽  
William J Greenleaf ◽  
Rhiju Das ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Free Energy ◽  
Recurrent Neural Network ◽  
Neural Network Model ◽  
Data Augmentation ◽  
Rna Folding ◽  
Large Datasets ◽  
Turner Model ◽  
Rna Complexes

AbstractRNA is a functionally versatile molecule that plays key roles in genetic regulation and in emerging technologies to control biological processes. Computational models of RNA secondary structure are well-developed but often fall short in making quantitative predictions of the behavior of multi-RNA complexes. Recently, large datasets characterizing hundreds of thousands of individual RNA complexes have emerged as rich sources of information about RNA energetics. Meanwhile, advances in machine learning have enabled the training of complex neural networks from large datasets. Here, we assess whether a recurrent neural network model, Ribonet, can learn from high-throughput binding data, using simulation and experimental studies to test model accuracy but also determine if they learned meaningful information about the biophysics of RNA folding. We began by evaluating the model on energetic values predicted by the Turner model to assess whether the neural network could learn a representation that recovered known biophysical principles. First, we trained Ribonet to predict the simulated free energy of an RNA in complex with multiple input RNAs. Our model accurately predicts free energies of new sequences but also shows evidence of having learned base pairing information, as assessed by in silico double mutant analysis. Next, we extended this model to predict the simulated affinity between an arbitrary RNA sequence and a reporter RNA. While these more indirect measurements precluded the learning of basic principles of RNA biophysics, the resulting model achieved sub-kcal/mol accuracy and enabled design of simple RNA input responsive riboswitches with high activation ratios predicted by the Turner model from which the training data were generated. Finally, we compiled and trained on an experimental dataset comprising over 600,000 experimental affinity measurements published on the Eterna open laboratory. Though our tests revealed that the model likely did not learn a physically realistic representation of RNA interactions, it nevertheless achieved good performance of 0.76 kcal/mol on test sets with the application of transfer learning and novel sequence-specific data augmentation strategies. These results suggest that recurrent neural network architectures, despite being naïve to the physics of RNA folding, have the potential to capture complex biophysical information. However, more diverse datasets, ideally involving more direct free energy measurements, may be necessary to train de novo predictive models that are consistent with the fundamentals of RNA biophysics.Author SummaryThe precise design of RNA interactions is essential to gaining greater control over RNA-based biotechnology tools, including designer riboswitches and CRISPR-Cas9 gene editing. However, the classic model for energetics governing these interactions fails to quantitatively predict the behavior of RNA molecules. We developed a recurrent neural network model, Ribonet, to quantitatively predict these values from sequence alone. Using simulated data, we show that this model is able to learn simple base pairing rules, despite having no a priori knowledge about RNA folding encoded in the network architecture. This model also enables design of new switching RNAs that are predicted to be effective by the “ground truth” simulated model. We applied transfer learning to retrain Ribonet using hundreds of thousands of RNA-RNA affinity measurements and demonstrate simple data augmentation techniques that improve model performance. At the same time, data diversity currently available set limits on Ribonet’s accuracy. Recurrent neural networks are a promising tool for modeling nucleic acid biophysics and may enable design of complex RNAs for novel applications.

scholarly journals Iterative free-energy optimization for recurrent neural networks (INFERNO)

PLoS ONE ◽  
2017 ◽  
Vol 12 (3) ◽  
pp. e0173684 ◽  
Author(s):  
Alexandre Pitti ◽  
Philippe Gaussier ◽  
Mathias Quoy
Keyword(s):  
Neural Networks ◽  
Free Energy ◽  
Recurrent Neural Networks ◽  
Energy Optimization

scholarly journals Water Dipole and Quadrupole Moment Contributions to the Ion Hydration Free Energy by the Deep Neural Network Trained with Ab Initio Molecular Dynamics Data

2020 ◽  
Author(s):  
YU SHI ◽  
Carrie C. Doyle ◽  
Thomas L. Beck
Keyword(s):  
Neural Network ◽  
Molecular Dynamics ◽  
Free Energy ◽  
Ab Initio ◽  
Deep Neural Network ◽  
Ab Initio Molecular Dynamics ◽  
Quadrupole Moments ◽  
Hydration Free Energy ◽  
Ion Hydration ◽  
Water Dipole

<div>We report a calculation scheme on water molecular dipole and quadrupole moments in the liquid phase through a Deep Neural Network (DNN) model. Employing the the Maximally Localized Wannier Functions (MLWF) for the valence electrons, we obtain the water moments through a post-process on trajectories from \textit{ab-initio} molecular dynamics (AIMD) simulations at the density functional theory (DFT) level. In the framework of the deep potential molecular dynamics (DPMD), we develop a scheme to train a DNN with the AIMD moments data. Applying the model, we calculate the contributions from water dipole and quadrupole moments to the electrostatic potential at the center of a cavity of radius 4.1 \AA\ as -3.87 V, referenced to the average potential in the bulk-like liquid region.</div><div>To unravel the ion-independent water effective local potential contribution to the ion hydration free energy, we estimate the 3rd cumulant term as -0.22 V from simulations totally over 6 ns, a time-scale inaccessible for AIMD calculations. </div>

scholarly journals Molecular free energy optimization on a computational graph

2020 ◽  
Author(s):  
Xiaoyong Cao ◽  
Pu Tian
Keyword(s):  
Free Energy ◽  
Dimensional Space ◽  
Structure Refinement ◽  
Energy Optimization ◽  
Efficient Estimation ◽  
Scoring Functions ◽  
Seamless Integration ◽  
Molecular Systems ◽  
Specific Implementation ◽  
Local Sampling

AbstractFree energy is arguably the most important property of molecular systems. Despite great progress in both its efficient estimation by scoring functions/potentials and more rigorous computation based on extensive sampling, we remain far from accurately predicting and manipulating biomolecular structures and their interactions. There are fundamental limitations, including accuracy of interaction description and difficulty of sampling in high dimensional space, to be tackled. Computational graph underlies major artificial intelligence platforms and is proven to facilitate training, optimization and learning. Combining autodifferentiation, coordinates transformation and generalized solvation free energy theory, we construct a computational graph infrastructure to realize seamless integration of fully trainable local free energy landscape with end to end differentiable iterative free energy optimization. This new framework greatly improves efficiency by replacing local sampling with differentiation. Its specific implementation in protein structure refinement achieves superb efficiency and competitive accuracy when compared with state of the art all-atom mainstream methods.

An antisymmetric neural network to predict free energy changes in protein variants

2021 ◽  
Author(s):  
Silvia Benevenuta ◽  
Corrado Pancotti ◽  
Piero Fariselli ◽  
Giovanni Birolo ◽  
Tiziana Sanavia
Keyword(s):  
Neural Network ◽  
Free Energy ◽  
Protein Variants
Sign in / Sign up

Export Citation Format

Share Document