Protein Structure Prediction Research Articles

Integrating Large-Scale Protein Structure Prediction into Human Genetics Research.

The last five years have seen impressive progress in deep learning models applied to protein research. Most notably, sequence-based structure predictions have seen transformative gains in the form of AlphaFold2 and related approaches. Millions of missense protein variants in the human population lack annotations, and these computational methods are a valuable means to prioritize variants for further analysis. Here, we review the recent progress in deep learning models applied to the prediction of protein structure and protein variants, with particular emphasis on their implications for human genetics and health. Improved prediction of protein structures facilitates annotations of the impact of variants on protein stability, protein-protein interaction interfaces, and small-molecule binding pockets. Moreover, it contributes to the study of host-pathogen interactions and the characterization of protein function. As genome sequencing in large cohorts becomes increasingly prevalent, we believe that better integration of state-of-the-art protein informatics technologies into human genetics research is of paramount importance.

Structure-Based Protein Assembly Simulations Including Various Binding Sites and Conformations.

Many biological functions are mediated by large complexes formed by multiple proteins and other cellular macromolecules. Recent progress in experimental structure determination, as well as in integrative modeling and protein structure prediction using deep learning approaches, has resulted in a rapid increase in the number of solved multiprotein assemblies. However, the assembly process of large complexes from their components is much less well-studied. We introduce a rapid computational structure-based (SB) model, GoCa, that allows to follow the assembly process of large multiprotein complexes based on a known native structure. Beyond existing SB Go̅-type models, it distinguishes between intra- and intersubunit interactions, allowing us to include coupled folding and binding. It accounts automatically for the permutation of identical subunits in a complex and allows the definition of multiple minima (native) structures in the case of proteins that undergo global transitions during assembly. The model is successfully tested on several multiprotein complexes. The source code of the GoCa program including a tutorial is publicly available on Github: https://github.com/ZachariasLab/GoCa. We also provide a web source that allows users to quickly generate the necessary input files for a GoCa simulation: https://goca.t38webservices.nat.tum.de.

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.

Predicting the effect of chemicals on fruit using graph neural networks

The neural network method is a type of machine learning that has made significant advances over the past few years in a variety of fields, particularly text, speech, images, videos, etc. In areas where data is unstructured, traditional machine learning has not been able to surpass the ’glass ceiling’; therefore, researchers have turned to neural networks as auxiliary tools to achieve significant breakthroughs or develop new research methods. An array of computational chemistry challenges can be addressed using neural networks, including virtual screening, quantitative structure-activity relationships, protein structure prediction, materials design, quantum chemistry, and property prediction, among others. This paper proposes a strategy for predicting the chemical properties of fruits by using graph neural networks, and it aims to provide some guidance to researchers and streamline the identification process.

3D Convolutional Neural Networks for Predicting Protein Structure for Improved Drug Recommendation

INTRODUCTION: Protein structure prediction is critical for recommendation personalized medicine and drug discovery. This paper introduces a robust approach using 3D Convolution Neural Networks (3D CNN’s) to improve the accuracy of the structure of protein structure thus contributing for the drug recommendation system.
 OBJECTIVES: In contrast to conventional techniques, 3D CNNs are able to identify complicated folding patterns and comprehend the subtle interactions between amino acids because they are able to capture spatial dependencies inside protein structures.
 METHODS: Data sets are collected from Protein Data Bank, including experimental protein structures and the drugs that interact with them, are used to train the model. With the efficient processing of three-dimensional data, the 3D CNNs exhibit enhanced capability in identifying minute structural details that are crucial for drug binding. This drug recommendation system novel method makes it easier to find potential drugs that interact well with particular protein structures.
 RESULTS: The performance of the proposed classifier is compared with the existing baseline methods with various parameters accuracy, precision, recall, F1 score, mean squared error (MSE)  and area under the receiver operating characteristic curve (AUC-ROC).
 CONCLUSION: Deep learning and 3D structural insights work together to create a new generation of tailored and focused therapeutic interventions by speeding up the drug development process and improving the accuracy of pharmacological recommendations.

Inferring molecular inhibition potency with AlphaFold predicted structures

Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.

Frustraevo: a web server to localize and quantify the conservation of local energetic frustration in protein families.

According to the Principle of Minimal Frustration, folded proteins canonly have a minimal number of strong energetic conflicts in their native states. However, not all interactions are energetically optimized for folding but some remain in energetic conflict, i.e. they are highly frustrated. This remaining local energetic frustration has been shown to be statistically correlated with distinct functional aspects such as protein-protein interaction sites, allosterism and catalysis. Fuelled by the recent breakthroughs in efficient protein structure prediction that have made available good quality models for most proteins, we have developed a strategy to calculate local energetic frustration within large protein families and quantify its conservation over evolutionary time. Based on this evolutionary information we can identify how stability and functional constraints have appeared at the common ancestor of the family and have been maintained over the course of evolution. Here, we present FrustraEvo, a web server tool to calculate and quantify the conservation of local energetic frustration in protein families.

Advancing Ligand Docking through Deep Learning: Challenges and Prospects in Virtual Screening.

ConspectusMolecular docking, also termed ligand docking (LD), is a pivotal element of structure-based virtual screening (SBVS) used to predict the binding conformations and affinities of protein-ligand complexes. Traditional LD methodologies rely on a search and scoring framework, utilizing heuristic algorithms to explore binding conformations and scoring functions to evaluate binding strengths. However, to meet the efficiency demands of SBVS, these algorithms and functions are often simplified, prioritizing speed over accuracy.The emergence of deep learning (DL) has exerted a profound impact on diverse fields, ranging from natural language processing to computer vision and drug discovery. DeepMind's AlphaFold2 has impressively exhibited its ability to accurately predict protein structures solely from amino acid sequences, highlighting the remarkable potential of DL in conformation prediction. This groundbreaking advancement circumvents the traditional search-scoring frameworks in LD, enhancing both accuracy and processing speed and thereby catalyzing a broader adoption of DL algorithms in binding pose prediction. Nevertheless, a consensus on certain aspects remains elusive.In this Account, we delineate the current status of employing DL to augment LD within the VS paradigm, highlighting our contributions to this domain. Furthermore, we discuss the challenges and future prospects, drawing insights from our scholarly investigations. Initially, we present an overview of VS and LD, followed by an introduction to DL paradigms, which deviate significantly from traditional search-scoring frameworks. Subsequently, we delve into the challenges associated with the development of DL-based LD (DLLD), encompassing evaluation metrics, application scenarios, and physical plausibility of the predicted conformations. In the evaluation of LD algorithms, it is essential to recognize the multifaceted nature of the metrics. While the accuracy of binding pose prediction, often measured by the success rate, is a pivotal aspect, the scoring/screening power and computational speed of these algorithms are equally important given the pivotal role of LD tools in VS. Regarding application scenarios, early methods focused on blind docking, where the binding site is unknown. However, recent studies suggest a shift toward identifying binding sites rather than solely predicting binding poses within these models. In contrast, LD with a known pocket in VS has been shown to be more practical. Physical plausibility poses another significant challenge. Although DLLD models often achieve higher success rates compared to traditional methods, they may generate poses with implausible local structures, such as incorrect bond angles or lengths, which are disadvantageous for postprocessing tasks like visualization. Finally, we discuss the future perspectives for DLLD, emphasizing the need to improve generalization ability, strike a balance between speed and accuracy, account for protein conformation flexibility, and enhance physical plausibility. Additionally, we delve into the comparison between generative and regression algorithms in this context, exploring their respective strengths and potential.

Statistically derived proxy potentials accelerate geometry optimization of crystal structures.

The crystal structures of known materials contain the information about the interatomic interactions that produced these stable compounds. Similar to the use of reported protein structures to extract effective interactions between amino acids, that has been a useful tool in protein structure prediction, we demonstrate how to use this statistical paradigm to learn the effective inter-atomic interactions in crystalline inorganic solids. By analyzing the reported crystallographic data for inorganic materials, we have constructed statistically derived proxy potentials (SPPs) that can be used to assess how realistic or unusual a computer-generated structure is compared to the reported experimental structures. The SPPs can be directly used for structure optimization to improve this similarity metric, that we refer to as the SPP score. We apply such optimization step to markedly improve the quality of the input crystal structures for DFT calculations and demonstrate that the SPPs accelerate geometry optimization for three systems relevant to battery materials. As this approach is chemistry-agnostic and can be used at scale, we produced a database of all possible pair potentials in a tabulated form ready to use.

Cross-prediction-powered inference

While reliable data-driven decision-making hinges on high-quality labeled data, the acquisition of quality labels often involves laborious human annotations or slow and expensive scientific measurements. Machine learning is becoming an appealing alternative as sophisticated predictive techniques are being used to quickly and cheaply produce large amounts of predicted labels; e.g., predicted protein structures are used to supplement experimentally derived structures, predictions of socioeconomic indicators from satellite imagery are used to supplement accurate survey data, and so on. Since predictions are imperfect and potentially biased, this practice brings into question the validity of downstream inferences. We introduce cross-prediction: a method for valid inference powered by machine learning. With a small labeled dataset and a large unlabeled dataset, cross-prediction imputes the missing labels via machine learning and applies a form of debiasing to remedy the prediction inaccuracies. The resulting inferences achieve the desired error probability and are more powerful than those that only leverage the labeled data. Closely related is the recent proposal of prediction-powered inference [A. N. Angelopoulos, S. Bates, C. Fannjiang, M. I. Jordan, T. Zrnic, Science 382, 669-674 (2023)], which assumes that a good pretrained model is already available. We show that cross-prediction is consistently more powerful than an adaptation of prediction-powered inference in which a fraction of the labeled data is split off and used to train the model. Finally, we observe that cross-prediction gives more stable conclusions than its competitors; its CIs typically have significantly lower variability.

Can Protein Structure Prediction Methods Capture Alternative Conformations of Membrane Transporters?

Understanding the conformational dynamics of proteins, such as the inward-facing (IF) and outward-facing (OF) transition observed in transporters, is vital for elucidating their functional mechanisms. Despite significant advances in protein structure prediction (PSP) over the past three decades, most efforts have been focused on single-state prediction, leaving multistate or alternative conformation prediction (ACP) relatively unexplored. This discrepancy has led to the development of highly accurate PSP methods such as AlphaFold, yet their capabilities for ACP remain limited. To investigate the performance of current PSP methods in ACP, we curated a data set, named IOMemP, consisting of 32 experimentally determined high-resolution IF and OF structures of 16 membrane proteins with substantial conformational changes. We benchmarked 12 representative PSP methods, along with two recent multistate methods based on AlphaFold, against this data set. Our findings reveal a remarkably consistent preference for specific states across various PSP methods. We elucidated how coevolution information in MSAs influences state preference. Moreover, we showed that AlphaFold, when excluding coevolution information, estimated similar energies between the experimental IF and OF conformations, indicating that the energy model learned by AlphaFold is not biased toward any particular state. Our IOMemP data set and benchmark results are anticipated to advance the development of robust ACP methods.

Fast, accurate ranking of engineered proteins by target-binding propensity using structure modeling

Deep learning-based methods for protein structure prediction have achieved unprecedented accuracy. Yet, their utility in the engineering of protein-based binders remains constrained due to a gap between the ability to predict the structures of candidate proteins and the ability to assess which of those proteins are more probable to bind to a target. To bridge this gap, we introduce Automated Pairwise Peptide-Receptor AnalysIs for Screening Engineered proteins (APPRAISE), a method for predicting the target binding propensity of engineered proteins. After generating models of engineered proteins competing for binding to a target using an established structure-prediction tool such as AlphaFold-Multimer or ESMFold, APPRAISE performs a rapid (under 1 CPU second per model) scoring analysis that takes into account biophysical and geometrical constraints. As proof-of-concept cases, we demonstrate that APPRAISE can accurately classify receptor-dependent vs. receptor-independent adeno-associated viral vectors and diverse classes of engineered proteins such as miniproteins targeting the SARS-CoV-2 spike, nanobodies targeting a G-protein-coupled receptor, and peptides that specifically bind to transferrin receptor or PD-L1. APPRAISE is accessible through a web-based notebook interface using Google Colaboratory (https://tiny.cc/APPRAISE). With its accuracy, interpretability, and generalizability, APPRAISE promises to expand the utility of protein structure prediction and accelerate protein engineering for biomedical applications.

ProNet DB: a proteome-wise database for protein surface property representations and RNA-binding profiles.

The rapid growth in the number of experimental and predicted protein structures and more complicated protein structures poses a significant challenge for computational biology in leveraging structural information and accurate representation of protein surface properties. Recently, AlphaFold2 released the comprehensive proteomes of various species, and protein surface property representation plays a crucial role in protein-molecule interaction predictions, including those involving proteins, nucleic acids and compounds. Here, we proposed the first extensive database, namely ProNet DB, that integrates multiple protein surface representations and RNA-binding landscape for 326 175 protein structures. This collection encompasses the 16 model organism proteomes from the AlphaFold Protein Structure Database and experimentally validated structures from the Protein Data Bank. For each protein, ProNet DB provides access to the original protein structures along with the detailed surface property representations encompassing hydrophobicity, charge distribution and hydrogen bonding potential as well as interactive features such as the interacting face and RNA-binding sites and preferences. To facilitate an intuitive interpretation of these properties and the RNA-binding landscape, ProNet DB incorporates visualization tools like Mol* and an Online 3D Viewer, allowing for the direct observation and analysis of these representations on protein surfaces. The availability of pre-computed features enables instantaneous access for users, significantly advancing computational biology research in areas such as molecular mechanism elucidation, geometry-based drug discovery and the development of novel therapeutic approaches. Database URL: https://proj.cse.cuhk.edu.hk/aihlab/pronet/.

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

Isolation, Characterization, and Expression Analysis of NAC Transcription Factor from Andrographis paniculata (Burm. f.) Nees and Their Role in Andrographolide Production

Andrographis paniculata (Burm. f.) Nees is an important medicinal plant known for its bioactive compound andrographolide. NAC transcription factors (NAM, ATAF1/2, and CUC2) play a crucial role in secondary metabolite production, stress responses, and plant development through hormonal signaling. In this study, a putative partial transcript of three NAC family genes (ApNAC83, ApNAC21 22 and ApNAC02) was used to isolate full length genes using RACE. Bioinformatics analyses such as protein structure prediction, cis-acting regulatory elements, and gene ontology analysis were performed. Based on in silico predictions, the diterpenoid profiling of the plant’s leaves (five-week-old) and the real-time PCR-based expression analysis of isolated NAC genes under abscisic acid (ABA) treatment were performed. Additionally, the expression analysis of isolated NAC genes under MeJA treatment and transient expression in Nicotiana tabacum was performed. Full-length sequences of three members of the NAC transcription factor family, ApNAC83 (1102 bp), ApNAC21 22 (996 bp), and ApNAC02 (1011 bp), were isolated and subjected to the promoter and gene ontology analysis, which indicated their role in transcriptional regulation, DNA binding, ABA-activated signaling, and stress management. It was observed that ABA treatment leads to a higher accumulation of andrographolide and 14-deoxyandrographolide content, along with the upregulation of ApNAC02 (9.6-fold) and the downregulation of ApNAC83 and ApNAC21 22 in the leaves. With methyl jasmonate treatment, ApNAC21 22 expression decreased, while ApNAC02 increased (1.9-fold), with no significant change being observed in ApNAC83. The transient expression of the isolated NAC genes in a heterologous system (Nicotiana benthamiana) demonstrated their functional transcriptional activity, leading to the upregulation of the NtHMGR gene, which is related to the terpene pathway in tobacco. The expression analysis and heterologous expression of ApNAC21 22 and ApNAC02 indicated their role in andrographolide biosynthesis.

SPDesign: protein sequence designer based on structural sequence profile using ultrafast shape recognition.

Protein sequence design can provide valuable insights into biopharmaceuticals and disease treatments. Currently, most protein sequence design methods based on deep learning focus on network architecture optimization, while ignoring protein-specific physicochemical features. Inspired by the successful application of structure templates and pre-trained models in the protein structure prediction, we explored whether the representation of structural sequence profile can be used for protein sequence design. In this work, we propose SPDesign, a method for protein sequence design based on structural sequence profile using ultrafast shape recognition. Given an input backbone structure, SPDesign utilizes ultrafast shape recognition vectors to accelerate the search for similar protein structures in our in-house PAcluster80 structure database and then extracts the sequence profile through structure alignment. Combined with structural pre-trained knowledge and geometric features, they are further fed into an enhanced graph neural network for sequence prediction. The results show that SPDesign significantly outperforms the state-of-the-art methods, such as ProteinMPNN, Pifold and LM-Design, leading to 21.89%, 15.54% and 11.4% accuracy gains in sequence recovery rate on CATH 4.2 benchmark, respectively. Encouraging results also have been achieved on orphan and de novo (designed) benchmarks with few homologous sequences. Furthermore, analysis conducted by the PDBench tool suggests that SPDesign performs well in subdivided structures. More interestingly, we found that SPDesign can well reconstruct the sequences of some proteins that have similar structures but different sequences. Finally, the structural modeling verification experiment indicates that the sequences designed by SPDesign can fold into the native structures more accurately.

BDM: An Assessment Metric for Protein Complex Structure Models Based on Distance Difference Matrix.

Protein complex structure prediction is an important problem in computational biology. While significant progress has been made for protein monomers, accurate evaluation of protein complexes remains challenging. Existing assessment methods in CASP, lack dedicated metrics for evaluating complexes. DockQ, a widely used metric, has some limitations. In this study, we propose a novel metric called BDM (Based on Distance difference Matrix) for assessing protein complex prediction structures. Our approach utilizes a distance difference matrix derived from comparing real and predicted protein structures, establishing a linear correlation with Root Mean Square Deviation (RMSD). BDM overcomes limitations associated with receptor-ligand differentiation and eliminates the requirement for structure alignment, making it a more effective and efficient metric. Evaluation of BDM using CASP14 and CASP15 test sets demonstrates superior performance compared to the official CASP scoring. BDM provides accurate and reasonable assessments of predicted protein complexes, wide adoption of BDM has the potential to advance protein complex structure prediction and facilitate related researches across scientific domains. Code is available at http://mialab.ruc.edu.cn/BDMServer/ .

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.

Enhancing cryo-EM structure prediction with DeepTracer and AlphaFold2 integration.

Understanding the protein structures is invaluable in various biomedical applications, such as vaccine development. Protein structure model building from experimental electron density maps is a time-consuming and labor-intensive task. To address the challenge, machine learning approaches have been proposed to automate this process. Currently, the majority of the experimental maps in the database lack atomic resolution features, making it challenging for machine learning-based methods to precisely determine protein structures from cryogenic electron microscopy density maps. On the other hand, protein structure prediction methods, such as AlphaFold2, leverage evolutionary information from protein sequences and have recently achieved groundbreaking accuracy. However, these methods often require manual refinement, which is labor intensive and time consuming. In this study, we present DeepTracer-Refine, an automated method that refines AlphaFold predicted structures by aligning them to DeepTracers modeled structure. Our method was evaluated on 39 multi-domain proteins and we improved the average residue coverage from 78.2 to 90.0% and average local Distance Difference Test score from 0.67 to 0.71. We also compared DeepTracer-Refine with Phenixs AlphaFold refinement and demonstrated that our method not only performs better when the initial AlphaFold model is less precise but also surpasses Phenix in run-time performance.

Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction

Protein structure-based property prediction has emerged as a promising approach for various biological tasks, such as protein function prediction and sub-cellular location estimation. The existing methods highly rely on experimental protein structure data and fail in scenarios where these data are unavailable. Predicted protein structures from AI tools (e.g., AlphaFold2) were utilized as alternatives. However, we observed that current practices, which simply employ accurately predicted structures during inference, suffer from notable degradation in prediction accuracy. While similar phenomena have been extensively studied in general fields (e.g., Computer Vision) as model robustness, their impact on protein property prediction remains unexplored. In this paper, we first investigate the reason behind the performance decrease when utilizing predicted structures, attributing it to the structure embedding bias from the perspective of structure representation learning. To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures. Extensive experiments have shown that our framework is model-agnostic and effective in improving the property prediction of both predicted structures and experimental structures.