Browse
Submit Data
Databases
API
Help

Dataset Information

16 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Neural Upscaling from Residue-Level Protein Structure Networks to Atomistic Structures.

ABSTRACT: Coarse-graining is a powerful tool for extending the reach of dynamic models of proteins and other biological macromolecules. Topological coarse-graining, in which biomolecules or sets thereof are represented via graph structures, is a particularly useful way of obtaining highly compressed representations of molecular structures, and simulations operating via such representations can achieve substantial computational savings. A drawback of coarse-graining, however, is the loss of atomistic detail-an effect that is especially acute for topological representations such as protein structure networks (PSNs). Here, we introduce an approach based on a combination of machine learning and physically-guided refinement for inferring atomic coordinates from PSNs. This "neural upscaling" procedure exploits the constraints implied by PSNs on possible configurations, as well as differences in the likelihood of observing different configurations with the same PSN. Using a 1 μs atomistic molecular dynamics trajectory of Aβ1-40, we show that neural upscaling is able to effectively recapitulate detailed structural information for intrinsically disordered proteins, being particularly successful in recovering features such as transient secondary structure. These results suggest that scalable network-based models for protein structure and dynamics may be used in settings where atomistic detail is desired, with upscaling employed to impute atomic coordinates from PSNs.

SUBMITTER: Duong VT

PROVIDER: S-EPMC8698800 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Structure-Based Neural Network Protein-Carbohydrate Interaction Predictions at the Residue Level.

Project description:Carbohydrates dynamically and transiently interact with proteins for cell-cell recognition, cellular differentiation, immune response, and many other cellular processes. Despite the molecular importance of these interactions, there are currently few reliable computational tools to predict potential carbohydrate binding sites on any given protein. Here, we present two deep learning models named CArbohydrate-Protein interaction Site IdentiFier (CAPSIF) that predict carbohydrate binding sites on proteins: (1) a 3D-UNet voxel-based neural network model (CAPSIF:V) and (2) an equivariant graph neural network model (CAPSIF:G). While both models outperform previous surrogate methods used for carbohydrate binding site prediction, CAPSIF:V performs better than CAPSIF:G, achieving test Dice scores of 0.597 and 0.543 and test set Matthews correlation coefficients (MCCs) of 0.599 and 0.538, respectively. We further tested CAPSIF:V on AlphaFold2-predicted protein structures. CAPSIF:V performed equivalently on both experimentally determined structures and AlphaFold2 predicted structures. Finally, we demonstrate how CAPSIF models can be used in conjunction with local glycan-docking protocols, such as GlycanDock, to predict bound protein-carbohydrate structures.

| S-EPMC10054975 | biostudies-literature

Structure-based neural network protein-carbohydrate interaction predictions at the residue level.

Project description:Carbohydrates dynamically and transiently interact with proteins for cell-cell recognition, cellular differentiation, immune response, and many other cellular processes. Despite the molecular importance of these interactions, there are currently few reliable computational tools to predict potential carbohydrate-binding sites on any given protein. Here, we present two deep learning (DL) models named CArbohydrate-Protein interaction Site IdentiFier (CAPSIF) that predicts non-covalent carbohydrate-binding sites on proteins: (1) a 3D-UNet voxel-based neural network model (CAPSIF:V) and (2) an equivariant graph neural network model (CAPSIF:G). While both models outperform previous surrogate methods used for carbohydrate-binding site prediction, CAPSIF:V performs better than CAPSIF:G, achieving test Dice scores of 0.597 and 0.543 and test set Matthews correlation coefficients (MCCs) of 0.599 and 0.538, respectively. We further tested CAPSIF:V on AlphaFold2-predicted protein structures. CAPSIF:V performed equivalently on both experimentally determined structures and AlphaFold2-predicted structures. Finally, we demonstrate how CAPSIF models can be used in conjunction with local glycan-docking protocols, such as GlycanDock, to predict bound protein-carbohydrate structures.

| S-EPMC10318439 | biostudies-literature

QDeep: distance-based protein model quality estimation by residue-level ensemble error classifications using stacked deep residual neural networks.

Project description:MotivationProtein model quality estimation, in many ways, informs protein structure prediction. Despite their tight coupling, existing model quality estimation methods do not leverage inter-residue distance information or the latest technological breakthrough in deep learning that has recently revolutionized protein structure prediction.ResultsWe present a new distance-based single-model quality estimation method called QDeep by harnessing the power of stacked deep residual neural networks (ResNets). Our method first employs stacked deep ResNets to perform residue-level ensemble error classifications at multiple predefined error thresholds, and then combines the predictions from the individual error classifiers for estimating the quality of a protein structural model. Experimental results show that our method consistently outperforms existing state-of-the-art methods including ProQ2, ProQ3, ProQ3D, ProQ4, 3DCNN, MESHI, and VoroMQA in multiple independent test datasets across a wide-range of accuracy measures; and that predicted distance information significantly contributes to the improved performance of QDeep.Availability and implementationhttps://github.com/Bhattacharya-Lab/QDeep.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC7355297 | biostudies-literature

Uncertainty quantification for predictions of atomistic neural networks.

Project description:The value of uncertainty quantification on predictions for trained neural networks (NNs) on quantum chemical reference data is quantitatively explored. For this, the architecture of the PhysNet NN was suitably modified and the resulting model (PhysNet-DER) was evaluated with different metrics to quantify its calibration, the quality of its predictions, and whether prediction error and the predicted uncertainty can be correlated. Training on the QM9 database and evaluating data in the test set within and outside the distribution indicate that error and uncertainty are not linearly related. However, the observed variance provides insight into the quality of the data used for training. Additionally, the influence of the chemical space covered by the training data set was studied by using a biased database. The results clarify that noise and redundancy complicate property prediction for molecules even in cases for which changes - such as double bond migration in two otherwise identical molecules - are small. The model was also applied to a real database of tautomerization reactions. Analysis of the distance between members in feature space in combination with other parameters shows that redundant information in the training dataset can lead to large variances and small errors whereas the presence of similar but unspecific information returns large errors but small variances. This was, e.g., observed for nitro-containing aliphatic chains for which predictions were difficult although the training set contained several examples for nitro groups bound to aromatic molecules. The finding underlines the importance of the composition of the training data and provides chemical insight into how this affects the prediction capabilities of a ML model. Finally, the presented method can be used for information-based improvement of chemical databases for target applications through active learning optimization.

| S-EPMC9667919 | biostudies-literature

Progress Toward Proteome-Wide Photo-Crosslinking to Enable Residue-Level Visualization of Protein Structure and Networks in vivo

Project description:Crosslinking mass spectrometry (XL-MS) is emerging as a method at the crossroads of structural and cellular biology, uniquely capable of identifying protein-protein interactions with residue-level resolution and on the proteome-wide scale. With the development of crosslinkers that can form linkages inside cells and easily cleave during fragmentation on the mass spectrometer (MS-cleavable crosslinks), it has become increasingly facile to identify contacts between any two proteins in complex samples, including in live cells or tissues. Photo-crosslinkers possess the advantages of high temporal resolution and high reactivity, thereby engaging all residue-types (rather than just lysine); nevertheless, photo-crosslinkers have not enjoyed widespread use, and have yet to be employed for proteome-wide studies, because their products are challenging to identify. Here, we demonstrate the synthesis and application of two heterobifunctional photo-crosslinkers that feature diazirines and N-hydroxy-succinimidyl carbamate groups, the latter of which unveil symmetrical MS-cleavable linkages upon acyl transfer to protein targets. Moreover, these crosslinkers demonstrate high water-solubility and cell-permeability. Using these compounds, we demonstrate the feasibility of proteome-wide photo-crosslinking in cellulo. These studies elucidate a small portion of E. coli’s interaction network, albeit with residue-level resolution. With further optimization, these methods will enable the detection of protein quinary interaction networks in their native environment at residue-level resolution, and we expect they will prove useful toward the effort to explore the molecular sociology of the cell.

2023-06-27 | PXD041148 | Pride

Physically informed artificial neural networks for atomistic modeling of materials.

Project description:Large-scale atomistic computer simulations of materials heavily rely on interatomic potentials predicting the energy and Newtonian forces on atoms. Traditional interatomic potentials are based on physical intuition but contain few adjustable parameters and are usually not accurate. The emerging machine-learning (ML) potentials achieve highly accurate interpolation within a large DFT database but, being purely mathematical constructions, suffer from poor transferability to unknown structures. We propose a new approach that can drastically improve the transferability of ML potentials by informing them of the physical nature of interatomic bonding. This is achieved by combining a rather general physics-based model (analytical bond-order potential) with a neural-network regression. This approach, called the physically informed neural network (PINN) potential, is demonstrated by developing a general-purpose PINN potential for Al. We suggest that the development of physics-based ML potentials is the most effective way forward in the field of atomistic simulations.

| S-EPMC6538760 | biostudies-literature

Learning the local landscape of protein structures with convolutional neural networks.

Project description:One fundamental problem of protein biochemistry is to predict protein structure from amino acid sequence. The inverse problem, predicting either entire sequences or individual mutations that are consistent with a given protein structure, has received much less attention even though it has important applications in both protein engineering and evolutionary biology. Here, we ask whether 3D convolutional neural networks (3D CNNs) can learn the local fitness landscape of protein structure to reliably predict either the wild-type amino acid or the consensus in a multiple sequence alignment from the local structural context surrounding site of interest. We find that the network can predict wild type with good accuracy, and that network confidence is a reliable measure of whether a given prediction is likely going to be correct or not. Predictions of consensus are less accurate and are primarily driven by whether or not the consensus matches the wild type. Our work suggests that high-confidence mis-predictions of the wild type may identify sites that are primed for mutation and likely targets for protein engineering.

| S-EPMC8603988 | biostudies-literature

Universality in protein residue networks.

Project description:Residue networks representing 595 nonhomologous proteins are studied. These networks exhibit universal topological characteristics as they belong to the topological class of modular networks formed by several highly interconnected clusters separated by topological cavities. There are some networks that tend to deviate from this universality. These networks represent small-size proteins having <200 residues. This article explains such differences in terms of the domain structure of these proteins. On the other hand, the topological cavities characterizing proteins residue networks match very well with protein binding sites. This study investigates the effect of the cutoff value used in building the residue network. For small cutoff values, <5 A, the cavities found are very large corresponding almost to the whole protein surface. On the contrary, for large cutoff value, >10.0 A, only very large cavities are detected and the networks look very homogeneous. These findings are useful for practical purposes as well as for identifying protein-like complex networks. Finally, this article shows that the main topological class of residue networks is not reproduced by random networks growing according to Erdös-Rényi model or the preferential attachment method of Barabási-Albert. However, the Watts-Strogatz model reproduces very well the topological class as well as other topological properties of residue network. A more biologically appealing modification of the Watts-Strogatz model to describe residue networks is proposed.

| S-EPMC2830435 | biostudies-literature

Complementarity of the residue-level protein function and structure predictions in human proteins

Project description:Graphical abstract Sequence-based predictors of the residue-level protein function and structure cover a broad spectrum of characteristics including intrinsic disorder, secondary structure, solvent accessibility and binding to nucleic acids. They were catalogued and evaluated in numerous surveys and assessments. However, methods focusing on a given characteristic are studied separately from predictors of other characteristics, while they are typically used on the same proteins. We fill this void by studying complementarity of a representative collection of methods that target different predictions using a large, taxonomically consistent, and low similarity dataset of human proteins. First, we bridge the gap between the communities that develop structure-trained vs. disorder-trained predictors of binding residues. Motivated by a recent study of the protein-binding residue predictions, we empirically find that combining the structure-trained and disorder-trained predictors of the DNA-binding and RNA-binding residues leads to substantial improvements in predictive quality. Second, we investigate whether diverse predictors generate results that accurately reproduce relations between secondary structure, solvent accessibility, interaction sites, and intrinsic disorder that are present in the experimental data. Our empirical analysis concludes that predictions accurately reflect all combinations of these relations. Altogether, this study provides unique insights that support combining results produced by diverse residue-level predictors of protein function and structure.

| S-EPMC9118482 | biostudies-literature

Predicting protein residue-residue contacts using deep networks and boosting.

Project description:MotivationProtein residue-residue contacts continue to play a larger and larger role in protein tertiary structure modeling and evaluation. Yet, while the importance of contact information increases, the performance of sequence-based contact predictors has improved slowly. New approaches and methods are needed to spur further development and progress in the field.ResultsHere we present DNCON, a new sequence-based residue-residue contact predictor using deep networks and boosting techniques. Making use of graphical processing units and CUDA parallel computing technology, we are able to train large boosted ensembles of residue-residue contact predictors achieving state-of-the-art performance.AvailabilityThe web server of the prediction method (DNCON) is available at http://iris.rnet.missouri.edu/dncon/.Contactchengji@missouri.eduSupplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC3509494 | 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