High-accuracy protein structures by combining machine-learning with physics-based refinement.
Ontology highlight
ABSTRACT:
SUBMITTER: Heo L
PROVIDER: S-EPMC7125014 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.
| S-EPMC7910447 | biostudies-literature
Project description:Samples of primary tumors collected from 23 ovarian cancer patients
2018-04-07 | GSE112798 | GEO
Project description:IntroductionPhosphoinositide 3-kinase gamma (PI3Kγ) has been regarded as a promising drug target for the treatment of various diseases, and the diverse physiological roles of class I PI3K isoforms (α, β, δ, and γ) highlight the importance of isoform selectivity in the development of PI3Kγ inhibitors. However, the high structural conservation among the PI3K family makes it a big challenge to develop selective PI3Kγ inhibitors.ObjectivesA novel machine learning-based virtual screening with multiple PI3Kγ protein structures was developed to discover novel PI3Kγ inhibitors.MethodsA large chemical database was screened using the virtual screening model, the top-ranked compounds were then subjected to a series of bio-evaluations, which led to the discovery of JN-KI3. The selective inhibition mechanism of JN-KI3 against PI3Kγ was uncovered by a theoretical study.Results49 hits were identified through virtual screening, and the cell-free enzymatic studies found that JN-KI3 selectively inhibited PI3Kγ at a concentration as low as 3,873 nM but had no inhibitory effect on Class IA PI3Ks, leading to the selective cytotoxicity on hematologic cancer cells. Meanwhile, JN-KI3 potently blocked the PI3K signaling, finally led to distinct apoptosis of hematologic cell lines at a low concentration. Lastly, the key residues of PI3Kγ and the structural characteristics of JN-KI3, which both would influence γ isoform-selective inhibition, were highlighted by systematic theoretical studies.ConclusionThe developed virtual screening model strongly manifests the robustness to find novel PI3Kγ inhibitors. JN-KI3 displays a specific cytotoxicity on hematologic tumor cells, and significantly promotes apoptosis associated with the inhibition of the PI3K signaling, which depicts PI3Kγ as a potential target for the hematologic tumor therapy. The theoretical results reveal that those key residues interacting with JN-KI3 are less common compared to most of the reported PI3Kγ inhibitors, indicating that JN-KI3 has novel structural characteristics as a selective PIK3γ inhibitor.
| S-EPMC8800018 | biostudies-literature
Project description:The accuracy of computational models of water is key to atomistic simulations of biomolecules. We propose a computationally efficient way to improve the accuracy of the prediction of hydration-free energies (HFEs) of small molecules: the remaining errors of the physics-based models relative to the experiment are predicted and mitigated by machine learning (ML) as a postprocessing step. Specifically, the trained graph convolutional neural network attempts to identify the "blind spots" in the physics-based model predictions, where the complex physics of aqueous solvation is poorly accounted for, and partially corrects for them. The strategy is explored for five classical solvent models representing various accuracy/speed trade-offs, from the fast analytical generalized Born (GB) to the popular TIP3P explicit solvent model; experimental HFEs of small neutral molecules from the FreeSolv set are used for the training and testing. For all of the models, the ML correction reduces the resulting root-mean-square error relative to the experiment for HFEs of small molecules, without significant overfitting and with negligible computational overhead. For example, on the test set, the relative accuracy improvement is 47% for the fast analytical GB, making it, after the ML correction, almost as accurate as uncorrected TIP3P. For the TIP3P model, the accuracy improvement is about 39%, bringing the ML-corrected model's accuracy below the 1 kcal/mol threshold. In general, the relative benefit of the ML corrections is smaller for more accurate physics-based models, reaching the lower limit of about 20% relative accuracy gain compared with that of the physics-based treatment alone. The proposed strategy of using ML to learn the remaining error of physics-based models offers a distinct advantage over training ML alone directly on reference HFEs: it preserves the correct overall trend, even well outside of the training set.
| S-EPMC10950260 | biostudies-literature
Project description:Scoring functions are essential for modern in silico drug discovery. However, the accurate prediction of binding affinity by scoring functions remains a challenging task. The performance of scoring functions is very heterogeneous across different target classes. Scoring functions based on precise physics-based descriptors better representing protein-ligand recognition process are strongly needed. We developed a set of new empirical scoring functions, named DockTScore, by explicitly accounting for physics-based terms combined with machine learning. Target-specific scoring functions were developed for two important drug targets, proteases and protein-protein interactions, representing an original class of molecules for drug discovery. Multiple linear regression (MLR), support vector machine and random forest algorithms were employed to derive general and target-specific scoring functions involving optimized MMFF94S force-field terms, solvation and lipophilic interactions terms, and an improved term accounting for ligand torsional entropy contribution to ligand binding. DockTScore scoring functions demonstrated to be competitive with the current best-evaluated scoring functions in terms of binding energy prediction and ranking on four DUD-E datasets and will be useful for in silico drug design for diverse proteins as well as for specific targets such as proteases and protein-protein interactions. Currently, the MLR DockTScore is available at www.dockthor.lncc.br .
| S-EPMC7862620 | biostudies-literature
Project description:Chemical stability is a major concern in the development of protein therapeutics due to its impact on both efficacy and safety. Protein "hotspots" are amino acid residues that are subject to various chemical modifications, including deamidation, isomerization, glycosylation, oxidation etc. A more accurate prediction method for potential hotspot residues would allow their elimination or reduction as early as possible in the drug discovery process. In this work, we focus on prediction models for asparagine (Asn) deamidation. Sequence-based prediction method simply identifies the NG motif (amino acid asparagine followed by a glycine) to be liable to deamidation. It still dominates deamidation evaluation process in most pharmaceutical setup due to its convenience. However, the simple sequence-based method is less accurate and often causes over-engineering a protein. We introduce structure-based prediction models by mining available experimental and structural data of deamidated proteins. Our training set contains 194 Asn residues from 25 proteins that all have available high-resolution crystal structures. Experimentally measured deamidation half-life of Asn in penta-peptides as well as 3D structure-based properties, such as solvent exposure, crystallographic B-factors, local secondary structure and dihedral angles etc., were used to train prediction models with several machine learning algorithms. The prediction tools were cross-validated as well as tested with an external test data set. The random forest model had high enrichment in ranking deamidated residues higher than non-deamidated residues while effectively eliminated false positive predictions. It is possible that such quantitative protein structure-function relationship tools can also be applied to other protein hotspot predictions. In addition, we extensively discussed metrics being used to evaluate the performance of predicting unbalanced data sets such as the deamidation case.
| S-EPMC5521779 | biostudies-literature
Project description:The DeepRefiner webserver, freely available at http://watson.cse.eng.auburn.edu/DeepRefiner/, is an interactive and fully configurable online system for high-accuracy protein structure refinement. Fuelled by deep learning, DeepRefiner offers the ability to leverage cutting-edge deep neural network architectures which can be calibrated for on-demand selection of adventurous or conservative refinement modes targeted at degree or consistency of refinement. The method has been extensively tested in the Critical Assessment of Techniques for Protein Structure Prediction (CASP) experiments under the group name 'Bhattacharya-Server' and was officially ranked as the No. 2 refinement server in CASP13 (second only to 'Seok-server' and outperforming all other refinement servers) and No. 2 refinement server in CASP14 (second only to 'FEIG-S' and outperforming all other refinement servers including 'Seok-server'). The DeepRefiner web interface offers a number of convenient features, including (i) fully customizable refinement job submission and validation; (ii) automated job status update, tracking, and notifications; (ii) interactive and interpretable web-based results retrieval with quantitative and visual analysis and (iv) extensive help information on job submission and results interpretation via web-based tutorial and help tooltips.
| S-EPMC8262753 | biostudies-literature
Project description:One of the greatest challenges in protein structure prediction is the refinement of low-resolution predicted models to high-resolution structures that are close to the native state. Although contemporary structure prediction methods can assemble the correct topology for a large fraction of protein domains, such approximate models are often not of the resolution required for many important applications, including studies of reaction mechanisms and virtual ligand screening. Thus, the development of a method that could bring those structures closer to the native state is of great importance. We recently optimized the relative weights of the components of the Amber ff03 potential on a large set of decoy structures to create a funnel-shaped energy landscape with the native structure at the global minimum. Such an energy function might be able to drive proteins toward their native structure. In this work, for a test set of 47 proteins, with 100 decoy structures per protein that have a range of structural similarities to the native state, we demonstrate that our optimized potential can drive protein models closer to their native structure. Comparing the lowest-energy structure from each trajectory with the starting decoy, structural improvement is seen for 70% of the models on average. The ability to do such systematic structural refinements by using a physics-based all-atom potential represents a promising approach to high-resolution structure prediction.
| S-EPMC2448826 | biostudies-other
Project description:Machine learning (ML) has been widely applied to chemical property prediction, most prominently for the energies and forces in molecules and materials. The strong interest in predicting energies in particular has led to a 'local energy'-based paradigm for modern atomistic ML models, which ensures size-extensivity and a linear scaling of computational cost with system size. However, many electronic properties (such as excitation energies or ionization energies) do not necessarily scale linearly with system size and may even be spatially localized. Using size-extensive models in these cases can lead to large errors. In this work, we explore different strategies for learning intensive and localized properties, using HOMO energies in organic molecules as a representative test case. In particular, we analyze the pooling functions that atomistic neural networks use to predict molecular properties, and suggest an orbital weighted average (OWA) approach that enables the accurate prediction of orbital energies and locations.
| S-EPMC10171074 | biostudies-literature
Project description:The minimal requirements of a physics-based potential that can refine protein structures are the existence of a correlation between the energy with native similarity and the scoring of the native structure as the lowest in energy. To develop such a force field, the relative weights of the Amber ff03 all-atom potential supplemented by an explicit hydrogen-bond potential were adjusted by global optimization of energetic and structural criteria for a large set of protein decoys generated for a set of 58 nonhomologous proteins. The average correlation coefficient of the energy with TM-score significantly improved from 0.25 for the original ff03 potential to 0.65 for the optimized force field. The fraction of proteins for which the native structure had lowest energy increased from 0.22 to 0.90. Moreover, use of an explicit hydrogen-bond potential improves scoring performance of the force field. Promising preliminary results were obtained in applying the optimized potentials to refine protein decoys using only an energy criterion to choose the best decoy among sampled structures. For a set of seven proteins, 63% of the decoys improve, 18% get worse, and 19% are not changed.
| S-EPMC2275715 | biostudies-literature