Protein sequence-to-structure learning: Is this the end(-to-end revolution)?

AutoRNC: An automated modeling program for building atomic models of ribosome-nascent chain complexes

The interpretation of experimental studies of co-translational protein folding often benefits from the use of computational methods that seek to model or simulate the nascent chain and its interactions with the ribosome. Building realistic 3D models of ribosome-nascent chain (RNC) constructs often requires expert knowledge, so to circumvent this issue, we describe here AutoRNC, an automated modeling program capable of constructing large numbers of plausible atomic models of RNCs within minutes. AutoRNC takes input from the user specifying any regions of the nascent chain that contain secondary or tertiary structure and attempts to build conformations compatible with those specifications-and with the constraints imposed by the ribosome-by sampling and progressively piecing together dipeptide conformations extracted from the Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB). Despite using only modest computational resources, we show here that AutoRNC can build plausible conformations for a wide range of RNC constructs for which experimental data have already been reported.

Can AlphaFold's breakthrough in protein structure help decode the fundamental principles of adaptive cellular immunity?

T cells are essential immune cells responsible for identifying and eliminating pathogens. Through interactions between their T-cell antigen receptors (TCRs) and antigens presented by major histocompatibility complex molecules (MHCs) or MHC-like molecules, T cells discriminate foreign and self peptides. Determining the fundamental principles that govern these interactions has important implications in numerous medical contexts. However, reconstructing a map between T cells and their antagonist antigens remains an open challenge for the field of immunology, and success of in silico reconstructions of this relationship has remained incremental. In this Perspective, we discuss the role that new state-of-the-art deep-learning models for predicting protein structure may play in resolving some of the unanswered questions the field faces linking TCR and peptide-MHC properties to T-cell specificity. We provide a comprehensive overview of structural databases and the evolution of predictive models, and highlight the breakthrough AlphaFold provided the field.

Enhancing coevolutionary signals in protein-protein interaction prediction through clade-wise alignment integration

Protein-protein interactions (PPIs) play essential roles in most biological processes. The binding interfaces between interacting proteins impose evolutionary constraints that have successfully been employed to predict PPIs from multiple sequence alignments (MSAs). To construct MSAs, critical choices have to be made: how to ensure the reliable identification of orthologs, and how to optimally balance the need for large alignments versus sufficient alignment quality. Here, we propose a divide-and-conquer strategy for MSA generation: instead of building a single, large alignment for each protein, multiple distinct alignments are constructed under distinct clades in the tree of life. Coevolutionary signals are searched separately within these clades, and are only subsequently integrated using machine learning techniques. We find that this strategy markedly improves overall prediction performance, concomitant with better alignment quality. Using the popular DCA algorithm to systematically search pairs of such alignments, a genome-wide all-against-all interaction scan in a bacterial genome is demonstrated. Given the recent successes of AlphaFold in predicting direct PPIs at atomic detail, a discover-and-refine approach is proposed: our method could provide a fast and accurate strategy for pre-screening the entire genome, submitting to AlphaFold only promising interaction candidates-thus reducing false positives as well as computation time.

Deep learning for protein structure prediction and design-progress and applications

Proteins are the key molecular machines that orchestrate all biological processes of the cell. Most proteins fold into three-dimensional shapes that are critical for their function. Studying the 3D shape of proteins can inform us of the mechanisms that underlie biological processes in living cells and can have practical applications in the study of disease mutations or the discovery of novel drug treatments. Here, we review the progress made in sequence-based prediction of protein structures with a focus on applications that go beyond the prediction of single monomer structures. This includes the application of deep learning methods for the prediction of structures of protein complexes, different conformations, the evolution of protein structures and the application of these methods to protein design. These developments create new opportunities for research that will have impact across many areas of biomedical research.

Accurate prediction of protein assembly structure by combining AlphaFold and symmetrical docking

AlphaFold can predict the structures of monomeric and multimeric proteins with high accuracy but has a limit on the number of chains and residues it can fold. Here we show that a combination of AlphaFold and all-atom symmetric docking simulations enables highly accurate prediction of the structure of complex symmetrical assemblies. We present a method to predict the structure of complexes with cubic - tetrahedral, octahedral and icosahedral - symmetry from sequence. Focusing on proteins where AlphaFold can make confident predictions on the subunit structure, 27 cubic systems were assembled with a median TM-score of 0.99 and a DockQ score of 0.72. 21 had TM-scores of above 0.9 and were categorized as acceptable- to high-quality according to DockQ. The resulting models are energetically optimized and can be used for detailed studies of intermolecular interactions in higher-order symmetrical assemblies. The results demonstrate how explicit treatment of structural symmetry can significantly expand the size and complexity of AlphaFold predictions.

A STRP-ed definition of Structured Tandem Repeats in Proteins

Tandem Repeat Proteins (TRPs) are a class of proteins with repetitive amino acid sequences that have been studied extensively for over two decades. Different features at the level of sequence, structure, function and evolution have been attributed to them by various authors. And yet many of its salient features appear only when looking at specific subclasses of protein tandem repeats. Here, we attempt to rationalize the existing knowledge on Tandem Repeat Proteins (TRPs) by pointing out several dichotomies. The emerging picture is more nuanced than generally assumed and allows us to draw some boundaries of what is not a "proper" TRP. We conclude with an operational definition of a specific subset, which we have denominated STRPs (Structural Tandem Repeat Proteins), which separates a subclass of tandem repeats with distinctive features from several other less well-defined types of repeats. We believe that this definition will help researchers in the field to better characterize the biological meaning of this large yet largely understudied group of proteins.

Alignment-based Protein Mutational Landscape Prediction: Doing More with Less

The wealth of genomic data has boosted the development of computational methods predicting the phenotypic outcomes of missense variants. The most accurate ones exploit multiple sequence alignments, which can be costly to generate. Recent efforts for democratizing protein structure prediction have overcome this bottleneck by leveraging the fast homology search of MMseqs2. Here, we show the usefulness of this strategy for mutational outcome prediction through a large-scale assessment of 1.5M missense variants across 72 protein families. Our study demonstrates the feasibility of producing alignment-based mutational landscape predictions that are both high-quality and compute-efficient for entire proteomes. We provide the community with the whole human proteome mutational landscape and simplified access to our predictive pipeline.

Improving Inter-Helix Contact Prediction With Local 2D Topological Information

Inter-helix contact prediction is to identify residue contact across different helices in α-helical integral membrane proteins. Despite the progress made by various computational methods, contact prediction remains as a challenging task, and there is no method to our knowledge that directly tap into the contact map in an alignment free manner. We build 2D contact models from an independent dataset to capture the topological patterns in the neighborhood of a residue pair depending it is a contact or not, and apply the models to the state-of-art method's predictions to extract the features reflecting 2D inter-helix contact patterns. A secondary classifier is trained on such features. Realizing that the achievable improvement is intrinsically hinged on the quality of original predictions, we devise a mechanism to deal with the issue by introducing, 1) partial discretization of original prediction scores to more effectively leverage useful information 2) fuzzy score to assess the quality of the original prediction to help with selecting the residue pairs where improvement is more achievable. The cross-validation results show that the prediction from our method outperforms other methods including the state-of-the-art method (DeepHelicon) by a notable degree even without using the refinement selection scheme. By applying the refinement selection scheme, our method outperforms the state-of-the-art method significantly in these selected sequences.

Solvent Accessibility Promotes Rotamer Errors during Protein Modeling with Major Side-Chain Prediction Programs

Side-chain rotamer prediction is one of the most critical late stages in protein 3D structure building. Highly advanced and specialized algorithms (e.g., FASPR, RASP, SCWRL4, and SCWRL4v) optimize this process by use of rotamer libraries, combinatorial searches, and scoring functions. We seek to identify the sources of key rotamer errors as a basis for correcting and improving the accuracy of protein modeling going forward. In order to evaluate the aforementioned programs, we process 2496 high-quality single-chained all-atom filtered 30% homology protein 3D structures and use discretized rotamer analysis to compare original with calculated structures. Among 513,024 filtered residue records, increased amino acid residue-dependent rotamer errors─associated in particular with polar and charged amino acid residues (ARG, LYS, and GLN)─clearly correlate with increased amino acid residue solvent accessibility and an increased residue tendency toward the adoption of non-canonical off rotamers which modeling programs struggle to predict accurately. Understanding the impact of solvent accessibility now appears key to improved side-chain prediction accuracies.

AutoRNC: an automated modeling program for building atomic models of ribosome-nascent chain complexes

The interpretation of experimental studies of co-translational protein folding often benefits from the use of computational methods that seek to model the nascent chain and its interactions with the ribosome. Ribosome-nascent chain (RNC) constructs studied experimentally can vary significantly in size and the extent to which they contain secondary and tertiary structure, and building realistic 3D models of them therefore often requires expert knowledge. To circumvent this issue, we describe here AutoRNC, an automated modeling program capable of constructing large numbers of plausible atomic models of RNCs within minutes. AutoRNC takes input from the user specifying any regions of the nascent chain that contain secondary or tertiary structure and attempts to build conformations compatible with those specifications - and with the constraints imposed by the ribosome - by sampling and progressively piecing together dipeptide conformations extracted from the RCSB. We first show that conformations of completely unfolded proteins built by AutoRNC in the absence of the ribosome have radii of gyration that match well with the corresponding experimental data. We then show that AutoRNC can build plausible conformations for a wide range of RNC constructs for which experimental data have already been reported. Since AutoRNC requires only modest computational resources, we anticipate that it will prove to be a useful hypothesis generator for experimental studies, for example, in providing indications of whether designed constructs are likely to be capable of folding, as well as providing useful starting points for downstream atomic or coarse-grained simulations of the conformational dynamics of RNCs.

PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces

Proteins are essential molecular building blocks of life, responsible for most biological functions as a result of their specific molecular interactions. However, predicting their  binding  interfaces remains a challenge. In this study, we present a geometric transformer that acts directly on atomic coordinates labeled only with element names. The resulting model-the Protein Structure Transformer, PeSTo-surpasses the current state of the art in predicting protein-protein interfaces and can also predict and differentiate between interfaces involving nucleic acids, lipids, ions, and small molecules with high confidence. Its low computational cost enables processing high volumes of structural data, such as molecular dynamics ensembles allowing for the discovery of interfaces that remain otherwise inconspicuous in static experimentally solved structures. Moreover, the growing foldome provided by de novo structural predictions can be easily analyzed, providing new opportunities to uncover unexplored biology.

Progress at protein structure prediction, as seen in CASP15

In Dec 2020, the results of AlphaFold version 2 were presented at CASP14, sparking a revolution in the field of protein structure predictions. For the first time, a purely computational method could challenge experimental accuracy for structure prediction of single protein domains. The code of AlphaFold v2 was released in the summer of 2021, and since then, it has been shown that it can be used to accurately predict the structure of most ordered proteins and many protein-protein interactions. It has also sparked an explosion of development in the field, improving AI-based methods to predict protein complexes, disordered regions, and protein design. Here I will review some of the inventions sparked by the release of AlphaFold.

Machine learning in computational modelling of membrane protein sequences and structures: From methodologies to applications

Membrane proteins mediate a wide spectrum of biological processes, such as signal transduction and cell communication. Due to the arduous and costly nature inherent to the experimental process, membrane proteins have long been devoid of well-resolved atomic-level tertiary structures and, consequently, the understanding of their functional roles underlying a multitude of life activities has been hampered. Currently, computational tools dedicated to furthering the structure-function understanding are primarily focused on utilizing intelligent algorithms to address a variety of site-wise prediction problems (e.g., topology and interaction sites), but are scattered across different computing sources. Moreover, the recent advent of deep learning techniques has immensely expedited the development of computational tools for membrane protein-related prediction problems. Given the growing number of applications optimized particularly by manifold deep neural networks, we herein provide a review on the current status of computational strategies mainly in membrane protein type classification, topology identification, interaction site detection, and pathogenic effect prediction. Meanwhile, we provide an overview of how the entire prediction process proceeds, including database collection, data pre-processing, feature extraction, and method selection. This review is expected to be useful for developing more extendable computational tools specific to membrane proteins.

Metal-induced structural variability of mononuclear metal-binding sites from a database perspective

Metalloproteins are ubiquitous in all kingdoms of life. Their role and function are tightly related to the local structure of the metal-binding site. In this regard, the MetalPDB database is an invaluable tool since it stores the 3D structure of metal-binding sites and of their corresponding apo forms. In this work, we exploited MetalPDB to compute extensive statistics over >3000 clusters of mononuclear sites about the rearrangements occurring upon change in metalation state. For each cluster, we matched the holo and apo sites so that it was possible to average the distances between all possible pairs of Cα and donor atoms and thus quantitatively assess structural variations by computing the Δ values (mean apo distance - mean holo distance). For most of the structures the backbone is rigid with little to no rearrangement, while donor atoms experience significant changes of their relative position when the metal is removed. Sodium and potassium sites are an exception to this general observation. This is most likely caused by their preference for coordination by the main-chain oxygen atoms, making the rearrangement of donor atoms superimposable to that of the backbone. Magnesium and calcium show a different behavior, despite their chemical similarity: calcium sites undergo a larger reorganization upon metalation although both metals have similar percentage of backbone oxygen as donor atoms. We ascribe this observation to the structural and energetic factors regulating the selectivity for calcium over magnesium.

Protein Design: From the Aspect of Water Solubility and Stability

Water solubility and structural stability are key merits for proteins defined by the primary sequence and 3D-conformation. Their manipulation represents important aspects of the protein design field that relies on the accurate placement of amino acids and molecular interactions, guided by underlying physiochemical principles. Emulated designer proteins with well-defined properties both fuel the knowledge-base for more precise computational design models and are used in various biomedical and nanotechnological applications. The continuous developments in protein science, increasing computing power, new algorithms, and characterization techniques provide sophisticated toolkits for solubility design beyond guess work. In this review, we summarize recent advances in the protein design field with respect to water solubility and structural stability. After introducing fundamental design rules, we discuss the transmembrane protein solubilization and de novo transmembrane protein design. Traditional strategies to enhance protein solubility and structural stability are introduced. The designs of stable protein complexes and high-order assemblies are covered. Computational methodologies behind these endeavors, including structure prediction programs, machine learning algorithms, and specialty software dedicated to the evaluation of protein solubility and aggregation, are discussed. The findings and opportunities for Cryo-EM are presented. This review provides an overview of significant progress and prospects in accurate protein design for solubility and stability.

Structural Bioinformatics and Deep Learning of Metalloproteins: Recent Advances and Applications

All living organisms require metal ions for their energy production and metabolic and biosynthetic processes. Within cells, the metal ions involved in the formation of adducts interact with metabolites and macromolecules (proteins and nucleic acids). The proteins that require binding to one or more metal ions in order to be able to carry out their physiological function are called metalloproteins. About one third of all protein structures in the Protein Data Bank involve metalloproteins. Over the past few years there has been tremendous progress in the number of computational tools and techniques making use of 3D structural information to support the investigation of metalloproteins. This trend has been boosted by the successful applications of neural networks and machine/deep learning approaches in molecular and structural biology at large. In this review, we discuss recent advances in the development and availability of resources dealing with metalloproteins from a structure-based perspective. We start by addressing tools for the prediction of metal-binding sites (MBSs) using structural information on apo-proteins. Then, we provide an overview of the methods for and lessons learned from the structural comparison of MBSs in a fold-independent manner. We then move to describing databases of metalloprotein/MBS structures. Finally, we summarizing recent ML/DL applications enhancing the functional interpretation of metalloprotein structures.

Cryptic Oxidative Transamination of Hydroxynaphthoquinone in Natural Product Biosynthesis

Pyridoxal 5'-phosphate (PLP)-dependent enzymes are a group of versatile enzymes that catalyze various reactions, but only a small number of them react with O₂. Here, we report an unprecedented PLP-dependent enzyme, NphE, that catalyzes both transamination and two-electron oxidation using O₂ as an oxidant. Our intensive analysis reveals that NphE transfers the l-glutamate-derived amine to 1,3,6,8-tetrahydroxynaphthalene-derived mompain to form 8-amino-flaviolin (8-AF) via a highly conjugated quinonoid intermediate that is reactive with O₂. During the NphE reaction, O₂ is reduced to yield H₂O₂. An integrated technique involving NphE structure prediction by AlphaFold v2.0 and molecular dynamics simulation suggested the O₂-accessible cavity. Our in vivo results demonstrated that 8-AF is a genuine biosynthetic intermediate for the 1,3,6,8-tetrahydroxynaphthalene-derived meroterpenoid naphterpin without an amino group, which was supported by site-directed mutagenesis. This study clearly establishes the NphE reaction product 8-AF as a common intermediate with a cryptic amino group for the biosynthesis of terpenoid-polyketide hybrid natural products.

How much metagenome data is needed for protein structure prediction: The advantages of targeted approach from the ecological and evolutionary perspectives

It has been proven that three-dimensional protein structures could be modeled by supplementing homologous sequences with metagenome sequences. Even though a large volume of metagenome data is utilized for such purposes, a significant proportion of proteins remain unsolved. In this review, we focus on identifying ecological and evolutionary patterns in metagenome data, decoding the complicated relationships of these patterns with protein structures, and investigating how these patterns can be effectively used to improve protein structure prediction. First, we proposed the metagenome utilization efficiency and marginal effect model to quantify the divergent distribution of homologous sequences for the protein family. Second, we proposed that the targeted approach effectively identifies homologous sequences from specified biomes compared with the untargeted approach's blind search. Finally, we determined the lower bound for metagenome data required for predicting all the protein structures in the Pfam database and showed that the present metagenome data is insufficient for this purpose. In summary, we discovered ecological and evolutionary patterns in the metagenome data that may be used to predict protein structures effectively. The targeted approach is promising in terms of effectively extracting homologous sequences and predicting protein structures using these patterns.

Using metagenomic data to boost protein structure prediction and discovery

Over the past decade, metagenomic sequencing approaches have been providing an ever-increasing amount of protein sequence data at an astonishing rate. These constitute an invaluable source of information which has been exploited in various research fields such as the study of the role of the gut microbiota in human diseases and aging. However, only a small fraction of all metagenomic sequences collected have been functionally or structurally characterized, leaving much of them completely unexplored. Here, we review how this information has been used in protein structure prediction and protein discovery. We begin by presenting some widely used metagenomic databases and analyze in detail how metagenomic data has contributed to the impressive improvement in the accuracy of structure prediction methods in recent years. We then examine how metagenomic information can be exploited to annotate protein sequences. More specifically, we focus on the role of metagenomes in the discovery of enzymes and new CRISPR-Cas systems, and in the identification of antibiotic resistance genes. With this review, we provide an overview of how metagenomic data is currently revolutionizing our understanding of protein science.

Critical assessment of methods of protein structure prediction (CASP)-Round XIV

Critical assessment of structure prediction (CASP) is a community experiment to advance methods of computing three-dimensional protein structure from amino acid sequence. Core components are rigorous blind testing of methods and evaluation of the results by independent assessors. In the most recent experiment (CASP14), deep-learning methods from one research group consistently delivered computed structures rivaling the corresponding experimental ones in accuracy. In this sense, the results represent a solution to the classical protein-folding problem, at least for single proteins. The models have already been shown to be capable of providing solutions for problematic crystal structures, and there are broad implications for the rest of structural biology. Other research groups also substantially improved performance. Here, we describe these results and outline some of the many implications. Other related areas of CASP, including modeling of protein complexes, structure refinement, estimation of model accuracy, and prediction of inter-residue contacts and distances, are also described.

Protein Design with Deep Learning

Computational Protein Design (CPD) has produced impressive results for engineering new proteins, resulting in a wide variety of applications. In the past few years, various efforts have aimed at replacing or improving existing design methods using Deep Learning technology to leverage the amount of publicly available protein data. Deep Learning (DL) is a very powerful tool to extract patterns from raw data, provided that data are formatted as mathematical objects and the architecture processing them is well suited to the targeted problem. In the case of protein data, specific representations are needed for both the amino acid sequence and the protein structure in order to capture respectively 1D and 3D information. As no consensus has been reached about the most suitable representations, this review describes the representations used so far, discusses their strengths and weaknesses, and details their associated DL architecture for design and related tasks.