Browse
Submit Data
Databases
API
Help

Dataset Information

22 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting.

ABSTRACT: In molecular dynamics (MD), neural network (NN) potentials trained bottom-up on quantum mechanical data have seen tremendous success recently. Top-down approaches that learn NN potentials directly from experimental data have received less attention, typically facing numerical and computational challenges when backpropagating through MD simulations. We present the Differentiable Trajectory Reweighting (DiffTRe) method, which bypasses differentiation through the MD simulation for time-independent observables. Leveraging thermodynamic perturbation theory, we avoid exploding gradients and achieve around 2 orders of magnitude speed-up in gradient computation for top-down learning. We show effectiveness of DiffTRe in learning NN potentials for an atomistic model of diamond and a coarse-grained model of water based on diverse experimental observables including thermodynamic, structural and mechanical properties. Importantly, DiffTRe also generalizes bottom-up structural coarse-graining methods such as iterative Boltzmann inversion to arbitrary potentials. The presented method constitutes an important milestone towards enriching NN potentials with experimental data, particularly when accurate bottom-up data is unavailable.

SUBMITTER: Thaler S

PROVIDER: S-EPMC8617111 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

A Differentiable Neural-Network Force Field for Ionic Liquids.

Project description:We present NeuralIL, a model for the potential energy of an ionic liquid that accurately reproduces first-principles results with orders-of-magnitude savings in computational cost. Built on the basis of a multilayer perceptron and spherical Bessel descriptors of the atomic environments, NeuralIL is implemented in such a way as to be fully automatically differentiable. It can thus be trained on ab initio forces instead of just energies, to make the most out of the available data, and can efficiently predict arbitrary derivatives of the potential energy. Using ethylammonium nitrate as the test system, we obtain out-of-sample accuracies better than 2 meV atom-1 (<0.05 kcal mol-1) in the energies and 70 meV Å-1 in the forces. We show that encoding the element-specific density in the spherical Bessel descriptors is key to achieving this. Harnessing the information provided by the forces drastically reduces the amount of atomic configurations required to train a neural network force field based on atom-centered descriptors. We choose the Swish-1 activation function and discuss the role of this choice in keeping the neural network differentiable. Furthermore, the possibility of training on small data sets allows for an ensemble-learning approach to the detection of extrapolation. Finally, we find that a separate treatment of long-range interactions is not required to achieve a high-quality representation of the potential energy surface of these dense ionic systems.

| S-EPMC8757435 | biostudies-literature

Vessel trajectory classification via transfer learning with Deep Convolutional Neural Networks

Project description: Not available

| S-EPMC11346933 | biostudies-literature

Fitting quantum machine learning potentials to experimental free energy data: predicting tautomer ratios in solution.

Project description:The computation of tautomer ratios of druglike molecules is enormously important in computer-aided drug discovery, as over a quarter of all approved drugs can populate multiple tautomeric species in solution. Unfortunately, accurate calculations of aqueous tautomer ratios-the degree to which these species must be penalized in order to correctly account for tautomers in modeling binding for computer-aided drug discovery-is surprisingly difficult. While quantum chemical approaches to computing aqueous tautomer ratios using continuum solvent models and rigid-rotor harmonic-oscillator thermochemistry are currently state of the art, these methods are still surprisingly inaccurate despite their enormous computational expense. Here, we show that a major source of this inaccuracy lies in the breakdown of the standard approach to accounting for quantum chemical thermochemistry using rigid rotor harmonic oscillator (RRHO) approximations, which are frustrated by the complex conformational landscape introduced by the migration of double bonds, creation of stereocenters, and introduction of multiple conformations separated by low energetic barriers induced by migration of a single proton. Using quantum machine learning (QML) methods that allow us to compute potential energies with quantum chemical accuracy at a fraction of the cost, we show how rigorous relative alchemical free energy calculations can be used to compute tautomer ratios in vacuum free from the limitations introduced by RRHO approximations. Furthermore, since the parameters of QML methods are tunable, we show how we can train these models to correct limitations in the underlying learned quantum chemical potential energy surface using free energies, enabling these methods to learn to generalize tautomer free energies across a broader range of predictions.

| S-EPMC8409483 | biostudies-literature

SpikePropamine: Differentiable Plasticity in Spiking Neural Networks.

Project description:The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications using Spiking Neural Networks (SNNs) retain static synaptic connections, preventing additional learning after the initial training period. Here, we introduce a framework for simultaneously learning the underlying fixed-weights and the rules governing the dynamics of synaptic plasticity and neuromodulated synaptic plasticity in SNNs through gradient descent. We further demonstrate the capabilities of this framework on a series of challenging benchmarks, learning the parameters of several plasticity rules including BCM, Oja's, and their respective set of neuromodulatory variants. The experimental results display that SNNs augmented with differentiable plasticity are sufficient for solving a set of challenging temporal learning tasks that a traditional SNN fails to solve, even in the presence of significant noise. These networks are also shown to be capable of producing locomotion on a high-dimensional robotic learning task, where near-minimal degradation in performance is observed in the presence of novel conditions not seen during the initial training period.

| S-EPMC8493296 | biostudies-literature

Simulating protein-ligand binding with neural network potentials.

Project description:Drug molecules adopt a range of conformations both in solution and in their protein-bound state. The strain and reduced flexibility of bound drugs can partially counter the intermolecular interactions that drive protein-ligand binding. To make accurate computational predictions of drug binding affinities, computational chemists have attempted to develop efficient empirical models of these interactions, although these methods are not always reliable. Machine learning has allowed the development of highly-accurate neural-network potentials (NNPs), which are capable of predicting the stability of molecular conformations with accuracy comparable to state-of-the-art quantum chemical calculations but at a billionth of the computational cost. Here, we demonstrate that these methods can be used to represent the intramolecular forces of protein-bound drugs within molecular dynamics simulations. These simulations are shown to be capable of predicting the protein-ligand binding pose and conformational component of the absolute Gibbs energy of binding for a set of drug molecules. Notably, the conformational energy for anti-cancer drug erlotinib binding to its target was found to be considerably overestimated by a molecular mechanical model, while the NNP predicts a more moderate value. Although the ANI-1ccX NNP was not trained to describe ionic molecules, reasonable binding poses are predicted for charged ligands, but this method is not suitable for modeling charged ligands in solution.

| S-EPMC8157423 | biostudies-literature

An integrated reweighting theory of perceptual learning.

Project description:Improvements in performance on visual tasks due to practice are often specific to a retinal position or stimulus feature. Many researchers suggest that specific perceptual learning alters selective retinotopic representations in early visual analysis. However, transfer is almost always practically advantageous, and it does occur. If perceptual learning alters location-specific representations, how does it transfer to new locations? An integrated reweighting theory explains transfer over retinal locations by incorporating higher level location-independent representations into a multilevel learning system. Location transfer is mediated through location-independent representations, whereas stimulus feature transfer is determined by stimulus similarity at both location-specific and location-independent levels. Transfer to new locations/positions differs fundamentally from transfer to new stimuli. After substantial initial training on an orientation discrimination task, switches to a new location or position are compared with switches to new orientations in the same position, or switches of both. Position switches led to the highest degree of transfer, whereas orientation switches led to the highest levels of specificity. A computational model of integrated reweighting is developed and tested that incorporates the details of the stimuli and the experiment. Transfer to an identical orientation task in a new position is mediated via more broadly tuned location-invariant representations, whereas changing orientation in the same position invokes interference or independent learning of the new orientations at both levels, reflecting stimulus dissimilarity. Consistent with single-cell recording studies, perceptual learning alters the weighting of both early and midlevel representations of the visual system.

| S-EPMC3746919 | biostudies-literature

End-to-End Differentiable Learning of Protein Structure.

Project description:Predicting protein structure from sequence is a central challenge of biochemistry. Co-evolution methods show promise, but an explicit sequence-to-structure map remains elusive. Advances in deep learning that replace complex, human-designed pipelines with differentiable models optimized end to end suggest the potential benefits of similarly reformulating structure prediction. Here, we introduce an end-to-end differentiable model for protein structure learning. The model couples local and global protein structure via geometric units that optimize global geometry without violating local covalent chemistry. We test our model using two challenging tasks: predicting novel folds without co-evolutionary data and predicting known folds without structural templates. In the first task, the model achieves state-of-the-art accuracy, and in the second, it comes within 1-2 Å; competing methods using co-evolution and experimental templates have been refined over many years, and it is likely that the differentiable approach has substantial room for further improvement, with applications ranging from drug discovery to protein design.

| S-EPMC6513320 | biostudies-literature

Augmenting the anisotropic network model with torsional potentials improves PATH performance, enabling detailed comparison with experimental rate data.

Project description:PATH algorithms for identifying conformational transition states provide computational parameters-time to the transition state, conformational free energy differences, and transition state activation energies-for comparison to experimental data and can be carried out sufficiently rapidly to use in the "high throughput" mode. These advantages are especially useful for interpreting results from combinatorial mutagenesis experiments. This report updates the previously published algorithm with enhancements that improve correlations between PATH convergence parameters derived from virtual variant structures generated by RosettaBackrub and previously published kinetic data for a complete, four-way combinatorial mutagenesis of a conformational switch in Tryptophanyl-tRNA synthetase.

| S-EPMC5315668 | biostudies-literature

Deep neural network learning of complex binary sorption equilibria from molecular simulation data.

Project description:We employed deep neural networks (NNs) as an efficient and intelligent surrogate of molecular simulations for complex sorption equilibria using probabilistic modeling. Canonical (N 1 N 2 VT) Gibbs ensemble Monte Carlo simulations were performed to model a single-stage equilibrium desorptive drying process for (1,4-butanediol or 1,5-pentanediol)/water and 1,5-pentanediol/ethanol from all-silica MFI zeolite and 1,5-pentanediol/water from all-silica LTA zeolite. A multi-task deep NN was trained on the simulation data to predict equilibrium loadings as a function of thermodynamic state variables. The NN accurately reproduces simulation results and is able to obtain a continuous isotherm function. Its predictions can be therefore utilized to facilitate optimization of desorption conditions, which requires a laborious iterative search if undertaken by simulation alone. Furthermore, it learns information about the binary sorption equilibria as hidden layer representations. This allows for application of transfer learning with limited data by fine-tuning a pretrained NN for a different alkanediol/solvent/zeolite system.

| S-EPMC6482883 | biostudies-literature

Cumulative learning enables convolutional neural network representations for small mass spectrometry data classification.

Project description:Rapid and accurate clinical diagnosis remains challenging. A component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some Machine Learning approaches have been investigated but these models require time-consuming preprocessing steps to remove artifacts, making them unsuitable for rapid analysis. Convolutional Neural Networks (CNNs) have been found to perform well under such circumstances since they can learn representations from raw data. However, their effectiveness decreases when the number of available training samples is small, which is a common situation in medicine. In this work, we investigate transfer learning on 1D-CNNs, then we develop a cumulative learning method when transfer learning is not powerful enough. We propose to train the same model through several classification tasks over various small datasets to accumulate knowledge in the resulting representation. By using rat brain as the initial training dataset, a cumulative learning approach can have a classification accuracy exceeding 98% for 1D clinical MS-data. We show the use of cumulative learning using datasets generated in different biological contexts, on different organisms, and acquired by different instruments. Here we show a promising strategy for improving MS data classification accuracy when only small numbers of samples are available.

| S-EPMC7644674 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data