Protein Structure Prediction Research Articles

Predicting ion mobility collision cross sections using projection approximation with ROSIE-PARCS webserver.

Ion mobility coupled to mass spectrometry informs on the shape and size of protein structures in the form of a collision cross section (CCSIM). Although there are several computational methods for predicting CCSIM based on protein structures, including our previously developed projection approximation using rough circular shapes (PARCS), the process usually requires prior experience with the command-line interface. To overcome this challenge, here we present a web application on the Rosetta Online Server that Includes Everyone (ROSIE) webserver to predict CCSIM from protein structure using projection approximation with PARCS. In this web interface, the user is only required to provide one or more PDB files as input. Results from our case studies suggest that CCSIM predictions (with ROSIE-PARCS) are highly accurate with an average error of 6.12%. Furthermore, the absolute difference between CCSIM and CCSPARCS can help in distinguishing accurate from inaccurate AlphaFold2 protein structure predictions. ROSIE-PARCS is designed with a user-friendly interface, is available publicly and is free to use. The ROSIE-PARCS web interface is supported by all major web browsers and can be accessed via this link (https://rosie.graylab.jhu.edu).

Structural bioinformatics studies of bacterial outer membrane beta-barrel transporters and their AlphaFold2 predicted water-soluble QTY variants.

Beta-barrel outer membrane proteins (OMP) are integral components of Gram-negative bacteria, eukaryotic mitochondria, and chloroplasts. They play essential roles in various cellular processes including nutrient transport, membrane stability, host-pathogen interactions, antibiotic resistance and more. The advent of AlphaFold2 for accurate protein structure predictions transformed structural bioinformatic studies. We previously used a QTY code to convert hydrophobic alpha-helices to hydrophilic alpha-helices in over 50 membrane proteins with all alpha-helices. The QTY code systematically replaces hydrophobic leucine (L), isoleucine (I), valine (V), and phenylalanine (F) with hydrophilic glutamine (Q), threonine (T), and tyrosine (Y). We here present a structural bioinformatic analysis of five outer membrane beta-barrel proteins with known molecular structures, including a) BamA, b) Omp85 (also called Sam50), c) FecA, d) Tsx, and e) OmpC. We superposed the structures of five native beta-barrel outer membrane proteins and their AlphaFold2-predicted corresponding QTY variant structures. The superposed structures of OMPs and their QTY variants exhibit remarkable structural similarity, as evidenced by residue mean square distance (RMSD) values between 0.206Å to 0.414Å despite the replacement of at least 22% (Transmembrane variation) of the amino acids in the transmembrane regions. We also show that native outer membrane proteins and QTY variants have different hydrophobicity patches. Our study provides important insights into the differences between hydrophobic and hydrophilic beta-barrels and validates the QTY code for studying beta-barrel membrane proteins and perhaps other hydrophobic aggregated proteins. Our findings demonstrate that the QTY code can be used as a simple tool for designing hydrophobic proteins in various biological contexts.

Diverse Clinical Phenotypes of CASK-Related Disorders and Multiple Functional Domains of CASK Protein.

CASK-related disorders are a form of rare X-linked neurological diseases and most of the patients are females. They are characterized by several symptoms, including microcephaly with pontine and cerebellar hypoplasia (MICPCH), epilepsy, congenital nystagmus, and neurodevelopmental disorders. Whole-genome sequencing has identified various mutations, including nonsense and missense mutations, from patients with CASK-related disorders, revealing correlations between specific mutations and clinical phenotypes. Notably, missense mutations associated with epilepsy and intellectual disability were found throughout the whole region of the CASK protein, while missense mutations related to microcephaly and MICPCH were restricted in certain domains. To investigate the pathophysiology of CASK-related disorders, research groups have employed diverse methods, including the generation of CASK knockout mice and the supplementation of CASK to rescue the phenotypes. These approaches have yielded valuable insights into the identification of functional domains of the CASK protein associated with a specific phenotype. Additionally, recent advancements in the AI-based prediction of protein structure, such as AlphaFold2, and the application of genome-editing techniques to generate CASK mutant mice carrying missense mutations from patients with CASK-related disorders, allow us to understand the pathophysiology of CASK-related disorders in more depth and to develop novel therapeutic methods for the fundamental treatment of CASK-related disorders.

Enzymes in 3D: Synthesis, remodelling, and hydrolysis of cell wall (1,3;1,4)-β-glucans.

Recent breakthroughs in structural biology have provided valuable new insights into enzymes involved in plant cell wall metabolism. More specifically, the molecular mechanism of synthesis of (1,3;1,4)-β-glucans, which are widespread in cell walls of commercially important cereals and grasses, has been the topic of debate and intense research activity for decades. However, an inability to purify these integral membrane enzymes or apply transgenic approaches without interpretative problems associated with pleiotropic effects has presented barriers to attempts to define their synthetic mechanisms. Following the demonstration that some members of the CslF sub-family of GT2 family enzymes mediate (1,3;1,4)-β-glucan synthesis, the expression of the corresponding genes in a heterologous system that is free of background complications has now been achieved. Biochemical analyses of the (1,3;1,4)-β-glucan synthesized in vitro, combined with 3-dimensional (3D) cryogenic-electron microscopy and AlphaFold protein structure predictions, have demonstrated how a single CslF6 enzyme, without exogenous primers, can incorporate both (1,3)- and (1,4)-β-linkages into the nascent polysaccharide chain. Similarly, 3D structures of xyloglucan endo-transglycosylases and (1,3;1,4)-β-glucan endo- and exohydrolases have allowed the mechanisms of (1,3;1,4)-β-glucan modification and degradation to be defined. X-ray crystallography and multi-scale modeling of a broad specificity GH3 β-glucan exohydrolase recently revealed a previously unknown and remarkable molecular mechanism with reactant trajectories through which a polysaccharide exohydrolase can act with a processive action pattern. The availability of high-quality protein 3D structural predictions should prove invaluable for defining structures, dynamics, and functions of other enzymes involved in plant cell wall metabolism in the immediate future.

Modeling orientational features via geometric algebra for 3D protein coordinates prediction

Protein structure prediction (PSP) is the prediction of the three‐dimensional (3D) folding of a protein (its tertiary structure) starting from its amino acid sequence (its primary structure). The state of the art in PSP is achieved by deep learning pipelines that require several input features extracted from amino acid sequences. It has been demonstrated that features that grasp the relative orientation of amino acids positively impact the prediction accuracy of the 3D coordinates of atoms in the protein backbone. In this paper, we demonstrate the relevance of geometric algebra (GA) in instantiating orientational features for PSP problems. We do so by proposing two novel GA‐based metrics which contain information on relative orientations of amino acid residues. We then employ these metrics as additional input features to a graph transformer (GT) architecture to aid the prediction of the 3D coordinates of a protein, and compare them to classical angle‐based metrics. We show how our GA features yield comparable results to angle maps in terms of accuracy of the predicted coordinates. This is despite being constructed from less initial information about the protein backbone. The features are also fewer and more informative and can be (i) closely associated to protein secondary structures and (ii) more easily predicted compared to angle maps. We hence deduce that GA can be employed as a tool to simplify the modeling of protein structures and pack orientational information in a more natural and meaningful way.

Hidden Glutathione Transferases in the Human Genome.

With the development of accurate protein structure prediction algorithms, artificial intelligence (AI) has emerged as a powerful tool in the field of structural biology. AI-based algorithms have been used to analyze large amounts of protein sequence data including the human proteome, complementing experimental structure data found in resources such as the Protein Data Bank. The EBI AlphaFold Protein Structure Database (for example) contains over 230 million structures. In this study, these data have been analyzed to find all human proteins containing (or predicted to contain) the cytosolic glutathione transferase (cGST) fold. A total of 39 proteins were found, including the alpha-, mu-, pi-, sigma-, zeta- and omega-class GSTs, intracellular chloride channels, metaxins, multisynthetase complex components, elongation factor 1 complex components and others. Three broad themes emerge: cGST domains as enzymes, as chloride ion channels and as protein-protein interaction mediators. As the majority of cGSTs are dimers, the AI-based structure prediction algorithm AlphaFold-multimer was used to predict structures of all pairwise combinations of these cGST domains. Potential homo- and heterodimers are described. Experimental biochemical and structure data is used to highlight the strengths and limitations of AI-predicted structures.

AlphaFold Accurately Predicts the Structure of Ribosomally Synthesized and Post-Translationally Modified Peptide Biosynthetic Enzymes.

Ribosomally synthesized and post-translationally modified peptides (RiPPs) are a growing class of natural products biosynthesized from a genetically encoded precursor peptide. The enzymes that install the post-translational modifications on these peptides have the potential to be useful catalysts in the production of natural-product-like compounds and can install non-proteogenic amino acids in peptides and proteins. However, engineering these enzymes has been somewhat limited, due in part to limited structural information on enzymes in the same families that nonetheless exhibit different substrate selectivities. Despite AlphaFold2's superior performance in single-chain protein structure prediction, its multimer version lacks accuracy and requires high-end GPUs, which are not typically available to most research groups. Additionally, the default parameters of AlphaFold2 may not be optimal for predicting complex structures like RiPP biosynthetic enzymes, due to their dynamic binding and substrate-modifying mechanisms. This study assessed the efficacy of the structure prediction program ColabFold (a variant of AlphaFold2) in modeling RiPP biosynthetic enzymes in both monomeric and dimeric forms. After extensive benchmarking, it was found that there were no statistically significant differences in the accuracy of the predicted structures, regardless of the various possible prediction parameters that were examined, and that with the default parameters, ColabFold was able to produce accurate models. We then generated additional structural predictions for select RiPP biosynthetic enzymes from multiple protein families and biosynthetic pathways. Our findings can serve as a reference for future enzyme engineering complemented by AlphaFold-related tools.

Biomolecular NMR in the AI-assisted structural biology era: Old tricks and new opportunities

Over the last 40 years nuclear magnetic resonance (NMR) spectroscopy has established itself as one of the most versatile techniques for the characterization of biomolecules, especially proteins. Given the molecular size limitations of NMR together with recent advances in cryo-electron microscopy and artificial intelligence-assisted protein structure prediction, the bright future of NMR in structural biology has been put into question. In this mini review we argue the contrary. We discuss the unique opportunities solution NMR offers to the protein chemist that distinguish it from all other experimental or computational methods, and how it can benefit from machine learning.

Improved protein structure prediction with trRosettaX2, AlphaFold2, and optimized MSAs in CASP15.

We present the monomer and multimer structure prediction results of our methods in CASP15. We first designed an elaborate pipeline that leverages complementary sequence databases and advanced database searching algorithms to generate high-quality multiple sequence alignments (MSAs). Top MSAs were then selected for the subsequent step of structure prediction. We utilized trRosettaX2 and AlphaFold2 for monomer structure prediction (group name Yang-Server), and AlphaFold-Multimer for multimer structure prediction (group name Yang-Multimer). Yang-Server and Yang-Multimer are ranked at the top and the fourth, respectively, for monomer and multimer structure prediction. For 94 monomers, the average TM-score of the predicted structure models by Yang-Server is 0.876, compared to 0.798 by the default AlphaFold2 (i.e., the group NBIS-AF2-standard). For 42 multimers, the average DockQ score of the predicted structure models by Yang-Multimer is 0.464, compared to 0.389 by the default AlphaFold-Multimer (i.e., the group NBIS-AF2-multimer). Detailed analysis of the results shows that several factors contribute to the improvement, including improved MSAs, iterated modeling for large targets, interplay between monomer and multimer structure prediction for intertwined structures, etc. However, the structure predictions for orphan proteins and multimers remain challenging, and breakthroughs in this area are anticipated in the future.

Effects of sequence-dependent non-native interactions in equilibrium and kinetic folding properties of knotted proteins.

Determining the role of non-native interactions in folding dynamics, kinetics, and mechanisms is a classic problem in protein folding. More recently, this question has witnessed a renewed interest in light of the hypothesis that knotted proteins require the assistance of non-native interactions to fold efficiently. Here, we conduct extensive equilibrium and kinetic Monte Carlo simulations of a simple off-lattice C-alpha model to explore the role of non-native interactions in the thermodynamics and kinetics of three proteins embedding a trefoil knot in their native structure. We find that equilibrium knotted conformations are stabilized by non-native interactions that are non-local, and proximal to native ones, thus enhancing them. Additionally, non-native interactions increase the knotting frequency at high temperatures, and in partially folded conformations below the transition temperatures. Although non-native interactions clearly enhance the efficiency of transition from an unfolded conformation to a partially folded knotted one, they are not required to efficiently fold a knotted protein. Indeed, a native-centric interaction potential drives the most efficient folding transition, provided that the simulation temperature is well below the transition temperature of the considered model system.

AggBERT: Best in Class Prediction of Hexapeptide Amyloidogenesis with a Semi-Supervised ProtBERT Model.

The prediction of peptide amyloidogenesis is a challenging problem in the field of protein folding. Large language models, such as the ProtBERT model, have recently emerged as powerful tools in analyzing protein sequences for applications, such as predicting protein structure and function. In this article, we describe the use of a semisupervised and fine-tuned ProtBERT model to predict peptide amyloidogenesis from sequences alone. Our approach, which we call AggBERT, achieved state-of-the-art performance, demonstrating the potential for large language models to improve the accuracy and speed of amyloid fibril prediction over simple heuristics or structure-based approaches. This work highlights the transformative potential of machine learning and large language models in the fields of chemical biology and biomedicine.

Estimating protein complex model accuracy based on ultrafast shape recognition and deep learning in CASP15.

This article reports and analyzes the results of protein complex model accuracy estimation by our methods (DeepUMQA3 and GraphGPSM) in the 15th Critical Assessment of techniques for protein Structure Prediction (CASP15). The new deep learning-based multimeric complex model accuracy estimation methods are proposed based on the ensemble of three-level features coupling with deep residual/graph neural networks. For the input multimeric complex model, we describe it from three levels: overall complex features, intra-monomer features, and inter-monomer features. We designed an overall ultrafast shape recognition (USR) to characterize the relationship between local residues and the overall complex topology, and an inter-monomer USR to characterize the relationship between the residues of one monomer and the topology of other monomers. DeepUMQA3 (Group name: GuijunLab-RocketX) ranked first in the interface residue accuracy estimation of CASP15. The Pearson correlation between the interface residue Local Distance Difference Test (lDDT) predicted by DeepUMQA3 and the real lDDT is 0.570, the only method that exceeds 0.5. Among the top 5 methods, DeepUMQA3 achieved the highest Pearson correlation of lDDT on 25 out of 39 targets. GraphGPSM (Group name: GuijunLab-PAthreader) has TM-score Pearson correlations greater than 0.9 on 14 targets, showing a good ability to estimate the overall fold accuracy. The DeepUMQA3 server is available at http://zhanglab-bioinf.com/DeepUMQA/ and the GraphGPSM server is available at http://zhanglab-bioinf.com/GraphGPSM/.

Structure prediction of novel isoforms from uveal melanoma by AlphaFold

Alternative splicing is an important mechanism that enhances protein functional diversity. To date, our understanding of alternative splicing variants has been based on mRNA transcript data, but due to the difficulty in predicting protein structures, protein tertiary structures have been largely unexplored. However, with the release of AlphaFold, which predicts three-dimensional models of proteins, this challenge is rapidly being overcome. Here, we present a dataset of 315 predicted structures of abnormal isoforms in 18 uveal melanoma patients based on second- and third-generation transcriptome-sequencing data. This information comprises a high-quality set of structural data on recurrent aberrant isoforms that can be used in multiple types of studies, from those aimed at revealing potential therapeutic targets to those aimed at recognizing of cancer neoantigens at the atomic level.

Mutated isocitrate dehydrogenase and therapeutic modalities

Isocitrate dehydrogenase (IDH) is crucial in the metabolism pathway that converts isocitrate to -ketoglutarate. When isocitrate dehydrogenase is mutated, IDH produces 2-hydroxyglutarate instead of alpha-ketoglutarate. The newly formed IDH, with the ability to dysregulate the metabolic pathways of cells, can potentially lead to the development of cancer. The mutation leads to malignancies such as acute myeloid leukemia and glioma. Current treatment for IDH-related malignancies includes IDH inhibitors, epigenetic modulators, immunotherapies, and cancer vaccination. The development of a cancer vaccine requires the discovery of a suitable epitope being found. Newly developed deep learning algorithms have the ability to predict protein structures and thus have the potential to help discover suitable epitopes for cancer vaccines. This study discusses the structure of IDH and gives an overview of how mutated IDH can potentially cause malignancies. In addition, this study proposed potential approaches with deep learning to aid the investigation of preventing IDH using cancer vaccines.

Protein structure prediction from the complementary science perspective.

A comparative analysis between two problems-apparently unrelated-which are solved in a period of ~400 years, viz., the accurate prediction of both the planetary orbits and the protein structures, leads to inferred conjectures that go far beyond the existence of a common path in their resolution, i.e., observation → pattern recognition → modeling. The preliminary results from this analysis indicate that complementary science, together with a new perspective on protein folding, may help us discover common features that could contribute to a more in-depth understanding of still-unsolved problems such as protein folding.

The protein folding problem in the “post-AlphaFold era”

The protein folding problem in the “post-AlphaFold era”

Advances in Peptide/Protein Structure Prediction Tools and their Relevance for Structural Biology in the Last Decade

Abstract: Peptides and proteins are involved in several biological processes at a molecular level. In this context, three-dimensional structure characterization and determination of peptides and proteins have helped researchers unravel the chemical and biological role of these macromolecules. Over 50 years, peptide and protein structures have been determined by experimental methods, including nuclear magnetic resonance (NMR), X-ray crystallography, and cryo-electron microscopy (cryo-EM). Therefore, an increasing number of atomic coordinates for peptides and proteins have been deposited in public databases, thus assisting the development of computational tools for predicting unknown 3D structures. In the last decade, a race for innovative methods has arisen in computational sciences, including more complex biological activity and structure prediction algorithms. As a result, peptide/protein theoretical models have achieved a new level of structure prediction accuracy compared with experimentally determined structures. Machine learning and deep learning approaches, for instance, incorporate fundamental aspects of peptide/protein geometry and include physical/biological knowledge about these macromolecules' experimental structures to build more precise computational models. Additionally, computational strategies have helped structural biology, including comparative, threading, and ab initio modeling and, more recently, prediction tools based on machine learning and deep learning. Bearing this in mind, here we provide a retrospective of protein and peptide structure prediction tools, highlighting their advances and obstacles and how they have assisted researchers in answering crucial biological questions.

How can the protein design community best support biologists who want to harness AI tools for protein structure prediction and design?

How can the protein design community best support biologists who want to harness AI tools for protein structure prediction and design?

Local RNA folding revisited.

Most of the functional RNA elements located within large transcripts are local. Local folding therefore serves a practically useful approximation to global structure prediction. Due to the sensitivity of RNA secondary structure prediction to the exact definition of sequence ends, accuracy can be increased by averaging local structure predictions over multiple, overlapping sequence windows. These averages can be computed efficiently by dynamic programming. Here we revisit the local folding problem, present a concise mathematical formalization that generalizes previous approaches and show that correct Boltzmann samples can be obtained by local stochastic backtracing in McCaskill's algorithms but not from local folding recursions. Corresponding new features are implemented in the ViennaRNA package to improve the support of local folding. Applications include the computation of maximum expected accuracy structures from RNAplfold data and a mutual information measure to quantify the sensitivity of individual sequence positions.

Comparative Functional Genomics Studies for Understanding the Hypothetical Proteins in Mycobacterium Tuberculosis Variant Microti 12

Comparative Functional Genomics Studies for Understanding the Hypothetical Proteins in Mycobacterium Tuberculosis Variant Microti 12