Accuracy Of Structure Prediction Research Articles

Computationally efficient dominant load-based local bone microstructure reconstruction method using topology optimization

The bone microstructure of the human proximal femur is clinically crucial for diagnosing skeletal pathologies, such as osteoporosis and bone metastases. The topology optimization-based bone microstructure method obtains these bone microstructures by converting low-resolution (LR) images into high-resolution images. However, this method is inherently computationally inefficient as it requires numerous finite elements, iterative analyses, and parallel computations. Therefore, this study proposes a novel topology optimization-based localised bone microstructure reconstruction method using the dominant load, which highly affects the selected region of interest (ROI), for efficient resolution enhancement. The load dependency of selected ROIs is quantified with a load dependency score. Then, the localised finite element model is constructed based on the local load estimation. Finally, the selected dominant load is applied as an input for the topology optimization-based bone microstructure reconstruction method. The reconstructed bone microstructure was similar to that of the conventional method. The localised finite element model applied by the dominant load effectively and accurately reconstructed the bone morphology and exhibited high computational efficiency. In conclusion, the dominant load-based approach can be used to construct a reasonable trabecular bone structure for ROI with high computational efficiency. The predictive performance of the proposed method was validated and showed promise for accurate trabecular bone structure prediction without additional radiation exposure.

Accurate Structure Prediction for Cyclic Peptides Containing Proline Residues with High-Temperature Molecular Dynamics.

Cyclic peptides (CPs) are emerging as promising drug candidates. Numerous natural CPs and their analogs are effective therapeutics against various diseases. Notably, many of them contain peptidyl cis-prolyl bonds. Due to the high rotational barrier of peptide bonds, conventional molecular dynamics simulations struggle to effectively sample the cis/trans-isomerization of peptide bonds. Previous studies have highlighted the high accuracy of the residue-specific force field (RSFF) and the high sampling efficiency of high-temperature molecular dynamics (high-T MD). Herein, we propose a protocol that combines high-T MD with RSFF2C and a recently developed reweighting method based on probability densities for accurate structure prediction of proline-containing CPs. Our method successfully predicted 19 out of 23 CPs with the backbone rmsd < 1.0 Å compared to X-ray structures. Furthermore, we performed high-T MD and density reweighting on the sunflower trypsin inhibitor (SFTI-1)/trypsin complex to demonstrate its applicability in studying CP-complexes containing cis-prolines. Our results show that the conformation of SFTI-1 in aqueous solution is consistent with its bound conformation, potentially facilitating its binding.

Prediction of protein secondary structure by the improved TCN-BiLSTM-MHA model with knowledge distillation

Secondary structure prediction is a key step in understanding protein function and biological properties and is highly important in the fields of new drug development, disease treatment, bioengineering, etc. Accurately predicting the secondary structure of proteins helps to reveal how proteins are folded and how they function in cells. The application of deep learning models in protein structure prediction is particularly important because of their ability to process complex sequence information and extract meaningful patterns and features, thus significantly improving the accuracy and efficiency of prediction. In this study, a combined model integrating an improved temporal convolutional network (TCN), bidirectional long short-term memory (BiLSTM), and a multi-head attention (MHA) mechanism is proposed to enhance the accuracy of protein prediction in both eight-state and three-state structures. One-hot encoding features and word vector representations of physicochemical properties are incorporated. A significant emphasis is placed on knowledge distillation techniques utilizing the ProtT5 pretrained model, leading to performance improvements. The improved TCN, achieved through multiscale fusion and bidirectional operations, allows for better extraction of amino acid sequence features than traditional TCN models. The model demonstrated excellent prediction performance on multiple datasets. For the TS115, CB513 and PDB (2018–2020) datasets, the prediction accuracy of the eight-state structure of the six datasets in this paper reached 88.2%, 84.9%, and 95.3%, respectively, and the prediction accuracy of the three-state structure reached 91.3%, 90.3%, and 96.8%, respectively. This study not only improves the accuracy of protein secondary structure prediction but also provides an important tool for understanding protein structure and function, which is particularly applicable to resource-constrained contexts and provides a valuable tool for understanding protein structure and function.

Quantum phase transitions in one-dimensional nanostructures: a comparison between DFT and DMRG methodologies.

In the realm of quantum chemistry, the accurate prediction of electronic structure and properties of nanostructures remains a formidable challenge. Density functional theory (DFT) and density matrix renormalization group (DMRG) have emerged as two powerful computational methods for addressing electronic correlation effects in diverse molecular systems. We compare ground-state energies ( ), density profiles ( ), and average entanglement entropies ( ) in metals, insulators and at the transition from metal to insulator, in homogeneous, superlattices, and harmonically confined chains described by the fermionic one-dimensional Hubbard model. While for the homogeneous systems, there is a clear hierarchy between the deviations, , and all the deviations decrease with the chain size; for superlattices and harmonic confinement, the relation among the deviations is less trivial and strongly dependent on the superlattice structure and the confinement strength considered. For the superlattices, in general, increasing the number of impurities in the unit cell represents lower precision in the DFT calculations. For the confined chains, DFT performs better for metallic phases, while the highest deviations appear for the Mott and band-insulator phases. This work provides a comprehensive comparative analysis of these methodologies, shedding light on their respective strengths, limitations, and applications. The DFT calculations were performed using the standard Kohn-Sham scheme within the BALDA approach. It integrated the numerical Bethe-Ansatz (BA) solution of the Hubbard model as the homogeneous density functional within a local-density approximation (LDA) for the exchange-correlation energy. The DMRG algorithms were implemented using the ITensor library, which is based on the matrix product states (MPS) ansatz. The calculations were performed until the energy reaches convergence of at least .

A database of high-pressure crystal structures from hydrogen to lanthanum

This paper introduces the HEX (High-pressure Elemental Xstals) database, a complete database of the ground-state crystal structures of the first 57 elements of the periodic table, from H to La, at 0, 100, 200 and 300 GPa. HEX aims to provide a unified reference for high-pressure research, by compiling all available experimental information on elements at high pressure, and complementing it with the results of accurate evolutionary crystal structure prediction runs based on Density Functional Theory. Besides offering a much-needed reference, our work also serves as a benchmark of the accuracy of current ab-initio methods for crystal structure prediction. We find that, in 98% of the cases in which experimental information is available, ab-initio crystal structure prediction yields structures which either coincide or are degenerate in enthalpy to within 300 K with experimental ones. The main manuscript contains synthetic tables and figures, while the Crystallographic Information File (cif) for all structures can be downloaded from the related figshare online repository.

Review and Comparative Analysis of Methods and Advancements in Predicting Protein Complex Structure.

Protein complexes perform diverse biological functions, and obtaining their three-dimensional structure is critical to understanding and grasping their functions. In many cases, it's not just two proteins interacting to form a dimer; instead, multiple proteins interact to form a multimer. Experimentally resolving protein complex structures can be quite challenging. Recently, there have been efforts and methods that build upon prior predictions of dimer structures to attempt to predict multimer structures. However, in comparison to monomeric protein structure prediction, the accuracy of protein complex structure prediction remains relatively low. This paper provides an overview of recent advancements in efficient computational models for predicting protein complex structures. We introduce protein-protein docking methods in detail and summarize their main ideas, applicable modes, and related information. To enhance prediction accuracy, other critical protein-related information is also integrated, such as predicting interchain residue contact, utilizing experimental data like cryo-EM experiments, and considering protein interactions and non-interactions. In addition, we comprehensively reviewcomputational approaches for end-to-end prediction ofprotein complex structuresbased on artificial intelligence (AI) technologyand describe commonly used datasets and representative evaluation metrics in protein complexes. Finally, we analyze the formidable challenges faced in current protein complex structure prediction tasks, including the structure prediction of heteromeric complex, disordered regions in complex, antibody-antigen complex, and RNA-related complex, as well as the evaluation metrics for complex assessment. We hope that this work will provide comprehensive knowledge of complex structure predictions to contribute to future advanced predictions.

Accurate prediction of CDR-H3 loop structures of antibodies with deep learning.

Accurate prediction of the structurally diverse complementarity determining region heavy chain 3 (CDR-H3) loop structure remains a primary and long-standing challenge for antibody modeling. Here, we present the H3-OPT toolkit for predicting the 3D structures of monoclonal antibodies and nanobodies. H3-OPT combines the strengths of AlphaFold2 with a pre-trained protein language model and provides a 2.24 Å average RMSDCα between predicted and experimentally determined CDR-H3 loops, thus outperforming other current computational methods in our non-redundant high-quality dataset. The model was validated by experimentally solving three structures of anti-VEGF nanobodies predicted by H3-OPT. We examined the potential applications of H3-OPT through analyzing antibody surface properties and antibody-antigen interactions. This structural prediction tool can be used to optimize antibody-antigen binding and engineer therapeutic antibodies with biophysical properties for specialized drug administration route.

Multi-Head Attention in Residual Networks to Improve Coral Reef Structure Classification

Residual Networks (ResNet) mark a crucial advancement in convolutional neural network architecture, effectively tackling challenges like vanishing gradients for improved pattern detection in various image classification tasks. This study introduces a novel adaptation of the ResNet50 architecture that integrates a multi-head attention mechanism (MHA), coined MHA-ResNet50, for discerning coral reef structures within images. Strategic modifications are applied to the input of each stage, leading to the development of an MHA block, which is augmented by separable convolution. The deliberate inclusion of the MHA block at various stages in identity-block Resnet50, in adherence to multiscale gate principles, precedes its traversal through fully connected layers. Furthermore, we implemented the Stratified K-fold concept to ensure that each fold has a comparable proportion of each class. We successfully assessed the efficacy of the MHA-Resnet50 model in several MHA-block placement scenarios and saw improvements in the accuracy of coral reef structure predictions. The most optimal results were achieved by incorporating four attention blocks (MHA-ResNet50-4), yielding an accuracy rate of 85.23% in recognition of coral structure images, comprising a mere 409 images. This model showcases adaptability to small datasets while delivering commendable performance. The ResNet50 architecture undergoes enhancement in our proposed model by integrating multi-head attention, separable convolution, and multiscale gate principles. The MHA-ResNet50 model substantially advances accurately predicting coral reef structures, demonstrating adaptability to limited datasets. Future lines of this research involve digging deeper into the model design and using more significant amounts and classes of data to strengthen a more comprehensive range of generalizations.

Accurate prediction of antibody function and structure using bio-inspired antibody language model.

In recent decades, antibodies have emerged as indispensable therapeutics for combating diseases, particularly viral infections. However, their development has been hindered by limited structural information and labor-intensive engineering processes. Fortunately, significant advancements in deep learning methods have facilitated the precise prediction of protein structure and function by leveraging co-evolution information from homologous proteins. Despite these advances, predicting the conformation of antibodies remains challenging due to their unique evolution and the high flexibility of their antigen-binding regions. Here, to address this challenge, we present the Bio-inspired Antibody Language Model (BALM). This model is trained on a vast dataset comprising 336 million 40% nonredundant unlabeled antibody sequences, capturing both unique and conserved properties specific to antibodies. Notably, BALM showcases exceptional performance across four antigen-binding prediction tasks. Moreover, we introduce BALMFold, an end-to-end method derived from BALM, capable of swiftly predicting full atomic antibody structures from individual sequences. Remarkably, BALMFold outperforms those well-established methods like AlphaFold2, IgFold, ESMFold and OmegaFold in the antibody benchmark, demonstrating significant potential to advance innovative engineering and streamline therapeutic antibody development by reducing the need for unnecessary trials. The BALMFold structure prediction server is freely available at https://beamlab-sh.com/models/BALMFold.

Component-based wing structure reconfiguration and analysis on the fly

To facilitate the structural design of an aircraft wing, we propose a simulation technique that can not only readily reshape a wing structure, but also rapidly yet accurately analyze its responses. For swift wing reconfiguration, we express a wing geometry with respect to shape parameters, such as a taper ratio, a half wingspan, and a sweep angle, by geometric parameterization. For rapid yet accurate analysis, we simulate a large-sized wing structure using small-sized common components whose solution spaces are shrunken by port-reduced static condensation reduced basis element (PR-SCRBE) approximation. As a result, we can easily modify both the shape and topology of a wing structure in the context of repetitive analysis. For demonstration, we construct six exemplary wing structures by assembling deformed duplicates of five common wing components. With the six wing structures, we examine the accuracy and efficiency of linear elastostatic PR-SCRBE analyses in predicting displacements and stresses compared with the corresponding finite element (FE) analyses. Regarding accuracy, the six PR-SCRBE analyses yield displacements and stresses with average relative errors of less than 0.01% and 2.79%, respectively. As for efficiency, the six PR-SCRBE analyses evaluate displacements and stresses with average speedups of 12.58 and 11.56, respectively. In conclusion, the proposed approach for wing reconfiguration and analysis may produce rapid yet accurate structural predictions, thereby considerably assisting the structural design of an aircraft wing.

Critical analysis of polycyclic tetramate macrolactam biosynthetic gene cluster phylogeny and functional diversity.

Polycyclic tetramate macrolactams (PTMs) are bioactive natural products commonly associated with certain actinobacterial and proteobacterial lineages. These molecules have been the subject of numerous structure-activity investigations since the 1970s. New members continue to be pursued in wild and engineered bacterial strains, and advances in PTM biosynthesis suggest their outwardly simplistic biosynthetic gene clusters (BGCs) belie unexpected product complexity. To address the origins of this complexity and understand its influence on PTM discovery, we engaged in a combination of bioinformatics to systematically classify PTM BGCs and PTM-targeted metabolomics to compare the products of select BGC types. By comparing groups of producers and BGC mutants, we exposed knowledge gaps that complicate bioinformatics-driven product predictions. In sum, we provide new insights into the evolution of PTM BGCs while systematically accounting for the PTMs discovered thus far. The combined computational and metabologenomic findings presented here should prove useful for guiding future discovery.IMPORTANCEPolycyclic tetramate macrolactam (PTM) pathways are frequently found within the genomes of biotechnologically important bacteria, including Streptomyces and Lysobacter spp. Their molecular products are typically bioactive, having substantial agricultural and therapeutic interest. Leveraging bacterial genomics for the discovery of new related molecules is thus desirable, but drawing accurate structural predictions from bioinformatics alone remains challenging. This difficulty stems from a combination of previously underappreciated biosynthetic complexity and remaining knowledge gaps, compounded by a stream of yet-uncharacterized PTM biosynthetic loci gleaned from recently sequenced bacterial genomes. We engaged in the following study to create a useful framework for cataloging historic PTM clusters, identifying new cluster variations, and tracing evolutionary paths for these molecules. Our data suggest new PTM chemistry remains discoverable in nature. However, our metabolomic and mutational analyses emphasize the practical limitations of genomics-based discovery by exposing hidden complexity.

SimRNAweb v2.0: a web server for RNA folding simulations and 3D structure modeling, with optional restraints and enhanced analysis of folding trajectories.

Research on ribonucleic acid (RNA) structures and functions benefits from easy-to-use tools for computational prediction and analyses of RNA three-dimensional (3D) structure. The SimRNAweb server version 2.0 offers an enhanced, user-friendly platform for RNA 3D structure prediction and analysis of RNA folding trajectories based on the SimRNA method. SimRNA employs a coarse-grained model, Monte Carlo sampling and statistical potentials to explore RNA conformational space, optionally guided by spatial restraints. Recognized for its accuracy in RNA 3D structure prediction in RNA-Puzzles and CASP competitions, SimRNA is particularly useful for incorporating restraints based on experimental data. The new server version introduces performance optimizations and extends user control over simulations and the processing of results. It allows the application of various hard and soft restraints, accommodating alternative structures involving canonical and noncanonical base pairs and unpaired residues, while also integrating data from chemical probing methods. Enhanced features include an improved analysis of folding trajectories, offering advanced clustering options and multiple analyses of the generated trajectories. These updates provide comprehensive tools for detailed RNA structure analysis. SimRNAweb v2.0 significantly broadens the scope of RNA modeling, emphasizing flexibility and user-defined parameter control. The web server is available at https://genesilico.pl/SimRNAweb.

Chainsaw: protein domain segmentation with fully convolutional neural networks.

Protein domains are fundamental units of protein structure and play a pivotal role in understanding folding, function, evolution, and design. The advent of accurate structure prediction techniques has resulted in an influx of new structural data, making the partitioning of these structures into domains essential for inferring evolutionary relationships and functional classification. This article presents Chainsaw, a supervised learning approach to domain parsing that achieves accuracy that surpasses current state-of-the-art methods. Chainsaw uses a fully convolutional neural network which is trained to predict the probability that each pair of residues is in the same domain. Domain predictions are then derived from these pairwise predictions using an algorithm that searches for the most likely assignment of residues to domains given the set of pairwise co-membership probabilities. Chainsaw matches CATH domain annotations in 78% of protein domains versus 72% for the next closest method. When predicting on AlphaFold models, expert human evaluators were twice as likely to prefer Chainsaw's predictions versus the next best method. github.com/JudeWells/Chainsaw.

Accurate structure prediction of biomolecular interactions with AlphaFold 3

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2–6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

The Phenix-AlphaFold webservice: Enabling AlphaFold predictions for use in Phenix.

Advances in machine learning have enabled sufficiently accurate predictions of protein structure to be used in macromolecular structure determination with crystallography and cryo-electron microscopy data. The Phenix software suite has AlphaFold predictions integrated into an automated pipeline that can start with an amino acid sequence and data, and automatically perform model-building and refinement to return a protein model fitted into the data. Due to the steep technical requirements of running AlphaFold efficiently, we have implemented a Phenix-AlphaFold webservice that enables all Phenix users to run AlphaFold predictions remotely from the Phenix GUI starting with the official 1.21 release. This webservice will be improved based on how it is used by the research community and the future research directions for Phenix.

Broadening environmental research in the era of accurate protein structure determination and predictions

Broadening environmental research in the era of accurate protein structure determination and predictions

AlphaFold and Protein Folding: Not Dead Yet! The Frontier Is Conformational Ensembles.

Like the black knight in the classic Monty Python movie, grand scientific challenges such as protein folding are hard to finish off. Notably, AlphaFold is revolutionizing structural biology by bringing highly accurate structure prediction to the masses and opening up innumerable new avenues of research. Despite this enormous success, calling structure prediction, much less protein folding and related problems, "solved" is dangerous, as doing so could stymie further progress. Imagine what the world would be like if we had declared flight solved after the first commercial airlines opened and stopped investing in further research and development. Likewise, there are still important limitations to structure prediction that we would benefit from addressing. Moreover, we are limited in our understanding of the enormous diversity of different structures a single protein can adopt (called a conformational ensemble) and the dynamics by which a protein explores this space. What is clear is that conformational ensembles are critical to protein function, and understanding this aspect of protein dynamics will advance our ability to design new proteins and drugs.

MFTrans: A multi-feature transformer network for protein secondary structure prediction

In the rapidly evolving field of computational biology, accurate prediction of protein secondary structures is crucial for understanding protein functions, facilitating drug discovery, and advancing disease diagnostics. In this paper, we propose MFTrans, a deep learning-based multi-feature fusion network aimed at enhancing the precision and efficiency of Protein Secondary Structure Prediction (PSSP). This model employs a Multiple Sequence Alignment (MSA) Transformer in combination with a multi-view deep learning architecture to effectively capture both global and local features of protein sequences. MFTrans integrates diverse features generated by protein sequences, including MSA, sequence information, evolutionary information, and hidden state information, using a multi-feature fusion strategy. The MSA Transformer is utilized to interleave row and column attention across the input MSA, while a Transformer encoder and decoder are introduced to enhance the extracted high-level features. A hybrid network architecture, combining a convolutional neural network with a bidirectional Gated Recurrent Unit (BiGRU) network, is used to further extract high-level features after feature fusion. In independent tests, our experimental results show that MFTrans has superior generalization ability, outperforming other state-of-the-art PSSP models by 3 % on average on public benchmarks including CASP12, CASP13, CASP14, TEST2016, TEST2018, and CB513. Case studies further highlight its advanced performance in predicting mutation sites. MFTrans contributes significantly to the protein science field, opening new avenues for drug discovery, disease diagnosis, and protein.

The Predicted Structure of a Thermophilic Malate Synthase

This project aims to solve the structure of the crenarchaeal Sulfolobus acidocaldarius enzyme malate synthase. Other known malate synthase enzymes have been found to require a magnesium ion in the active site to carry out catalytic activities, but a study reported that S. acidocaldarius malate synthase does not require magnesium. This suggests a novel mechanism for this enzyme. Additionally, the mature S. acidocaldarius protein is approximately 100 residues larger than any other structurally characterized malate synthase. It has also been reported to form a dimer, while previously solved structures have only displayed monomeric, trimeric, and hexameric arrangements. We plan to determine the structure experimentally. However, major advances in the accuracy of protein structure prediction were made recently by AlphaFold, an artificial intelligence system developed by DeepMind, which has revolutionized the field and has largely solved the protein folding problem. A similar AI system, RoseTTAFold, developed by David Baker’s lab at the University of Washington, has been publicly available. Here, we report our analysis of the structure of this protein, predicted using both of these algorithms and of a predicted structural model for the dimeric form of the enzyme using ClusPro. Our results strongly support a conserved catalytic mechanism requiring magnesium, which is common with all previously solved malate synthase isoforms. KEYWORDS: Glyoxylate Cycle; Malate synthase; Protein Prediction; Thermophile; Sulfolobus acidocaldarius; Magnesium; AlphaFold; RoseTTAFold

High-throughput prediction of protein conformational distributions with subsampled AlphaFold2

This paper presents an innovative approach for predicting the relative populations of protein conformations using AlphaFold 2, an AI-powered method that has revolutionized biology by enabling the accurate prediction of protein structures. While AlphaFold 2 has shown exceptional accuracy and speed, it is designed to predict proteins’ ground state conformations and is limited in its ability to predict conformational landscapes. Here, we demonstrate how AlphaFold 2 can directly predict the relative populations of different protein conformations by subsampling multiple sequence alignments. We tested our method against nuclear magnetic resonance experiments on two proteins with drastically different amounts of available sequence data, Abl1 kinase and the granulocyte-macrophage colony-stimulating factor, and predicted changes in their relative state populations with more than 80% accuracy. Our subsampling approach worked best when used to qualitatively predict the effects of mutations or evolution on the conformational landscape and well-populated states of proteins. It thus offers a fast and cost-effective way to predict the relative populations of protein conformations at even single-point mutation resolution, making it a useful tool for pharmacology, analysis of experimental results, and predicting evolution.