AlphaFold2 fails to predict protein fold switching

Pathways to a Shiny Future: Building the Foundation for Computational Physical Chemistry and Biophysics in 2050

In the last quarter-century, the field of molecular dynamics (MD) has undergone a remarkable transformation, propelled by substantial enhancements in software, hardware, and underlying methodologies. In this Perspective, we contemplate the future trajectory of MD simulations and their possible look at the year 2050. We spotlight the pivotal role of artificial intelligence (AI) in shaping the future of MD and the broader field of computational physical chemistry. We outline critical strategies and initiatives that are essential for the seamless integration of such technologies. Our discussion delves into topics like multiscale modeling, adept management of ever-increasing data deluge, the establishment of centralized simulation databases, and the autonomous refinement, cross-validation, and self-expansion of these repositories. The successful implementation of these advancements requires scientific transparency, a cautiously optimistic approach to interpreting AI-driven simulations and their analysis, and a mindset that prioritizes knowledge-motivated research alongside AI-enhanced big data exploration. While history reminds us that the trajectory of technological progress can be unpredictable, this Perspective offers guidance on preparedness and proactive measures, aiming to steer future advancements in the most beneficial and successful direction.

δ-Conotoxin Structure Prediction and Analysis through Large-Scale Comparative and Deep Learning Modeling Approaches

The δ-conotoxins, a class of peptides produced in the venom of cone snails, are of interest due to their ability to inhibit the inactivation of voltage-gated sodium channels causing paralysis and other neurological responses, but difficulties in their isolation and synthesis have made structural characterization challenging. Taking advantage of recent breakthroughs in computational algorithms for structure prediction that have made modeling especially useful when experimental data is sparse, this work uses both the deep-learning-based algorithm AlphaFold and comparative modeling method RosettaCM to model and analyze 18 previously uncharacterized δ-conotoxins derived from piscivorous, vermivorous, and molluscivorous cone snails. The models provide useful insights into the structural aspects of these peptides and suggest features likely to be significant in influencing their binding and different pharmacological activities against their targets, with implications for drug development. Additionally, the described protocol provides a roadmap for the modeling of similar disulfide-rich peptides by these complementary methods.

An ancestral fold reveals the evolutionary link between RNA polymerase and ribosomal proteins

Numerous molecular machines are required to drive the central dogma of molecular biology. However, the means by which these numerous proteins emerged in the early evolutionary stage of life remains enigmatic. Many of them possess small β-barrel folds with different topologies, represented by double-psi β-barrels (DPBBs) conserved in DNA and RNA polymerases, and similar but topologically distinct six-stranded β-barrel RIFT or five-stranded β-barrel folds such as OB and SH3 in ribosomal proteins. Here, we discover that the previously reconstructed ancient DPBB sequence could also adopt a β-barrel fold named Double-Zeta β-barrel (DZBB), as a metamorphic protein. The DZBB fold is not found in any modern protein, although its structure shares similarities with RIFT and OB. Indeed, DZBB could be transformed into them through simple engineering experiments. Furthermore, the OB designs could be further converted into SH3 by circular-permutation as previously predicted. These results indicate that these β-barrels diversified quickly from a common ancestor at the beginning of the central dogma evolution.

Explaining Conformational Diversity in Protein Families through Molecular Motions

Proteins play a central role in biological processes, and understanding their conformational variability is crucial for unraveling their functional mechanisms. Recent advancements in high-throughput technologies have enhanced our knowledge of protein structures, yet predicting their multiple conformational states and motions remains challenging. This study introduces Dimensionality Analysis for protein Conformational Exploration (DANCE) for a systematic and comprehensive description of protein families conformational variability. DANCE accommodates both experimental and predicted structures. It is suitable for analysing anything from single proteins to superfamilies. Employing it, we clustered all experimentally resolved protein structures available in the Protein Data Bank into conformational collections and characterized them as sets of linear motions. The resource facilitates access and exploitation of the multiple states adopted by a protein and its homologs. Beyond descriptive analysis, we assessed classical dimensionality reduction techniques for sampling unseen states on a representative benchmark. This work improves our understanding of how proteins deform to perform their functions and opens ways to a standardised evaluation of methods designed to sample and generate protein conformations.

AggreProt: a web server for predicting and engineering aggregation prone regions in proteins

Recombinant proteins play pivotal roles in numerous applications including industrial biocatalysts or therapeutics. Despite the recent progress in computational protein structure prediction, protein solubility and reduced aggregation propensity remain challenging attributes to design. Identification of aggregation-prone regions is essential for understanding misfolding diseases or designing efficient protein-based technologies, and as such has a great socio-economic impact. Here, we introduce AggreProt, a user-friendly webserver that automatically exploits an ensemble of deep neural networks to predict aggregation-prone regions (APRs) in protein sequences. Trained on experimentally evaluated hexapeptides, AggreProt compares to or outperforms state-of-the-art algorithms on two independent benchmark datasets. The server provides per-residue aggregation profiles along with information on solvent accessibility and transmembrane propensity within an intuitive interface with interactive sequence and structure viewers for comprehensive analysis. We demonstrate AggreProt efficacy in predicting differential aggregation behaviours in proteins on several use cases, which emphasize its potential for guiding protein engineering strategies towards decreased aggregation propensity and improved solubility. The webserver is freely available and accessible at https://loschmidt.chemi.muni.cz/aggreprot/.

Exploring conformational landscapes and binding mechanisms of convergent evolution for the SARS-CoV-2 spike Omicron variant complexes with the ACE2 receptor using AlphaFold2-based structural ensembles and molecular dynamics simulations

In this study, we combined AlphaFold-based approaches for atomistic modeling of multiple protein states and microsecond molecular simulations to accurately characterize conformational ensembles evolution and binding mechanisms of convergent evolution for the SARS-CoV-2 spike Omicron variants BA.1, BA.2, BA.2.75, BA.3, BA.4/BA.5 and BQ.1.1. We employed and validated several different adaptations of the AlphaFold methodology for modeling of conformational ensembles including the introduced randomized full sequence scanning for manipulation of sequence variations to systematically explore conformational dynamics of Omicron spike protein complexes with the ACE2 receptor. Microsecond atomistic molecular dynamics (MD) simulations provide a detailed characterization of the conformational landscapes and thermodynamic stability of the Omicron variant complexes. By integrating the predictions of conformational ensembles from different AlphaFold adaptations and applying statistical confidence metrics we can expand characterization of the conformational ensembles and identify functional protein conformations that determine the equilibrium dynamics for the Omicron spike complexes with the ACE2. Conformational ensembles of the Omicron RBD-ACE2 complexes obtained using AlphaFold-based approaches for modeling protein states and MD simulations are employed for accurate comparative prediction of the binding energetics revealing an excellent agreement with the experimental data. In particular, the results demonstrated that AlphaFold-generated extended conformational ensembles can produce accurate binding energies for the Omicron RBD-ACE2 complexes. The results of this study suggested complementarities and potential synergies between AlphaFold predictions of protein conformational ensembles and MD simulations showing that integrating information from both methods can potentially yield a more adequate characterization of the conformational landscapes for the Omicron RBD-ACE2 complexes. This study provides insights in the interplay between conformational dynamics and binding, showing that evolution of Omicron variants through acquisition of convergent mutational sites may leverage conformational adaptability and dynamic couplings between key binding energy hotspots to optimize ACE2 binding affinity and enable immune evasion.

Integration of a Randomized Sequence Scanning Approach in AlphaFold2 and Local Frustration Profiling of Conformational States Enable Interpretable Atomistic Characterization of Conformational Ensembles and Detection of Hidden Allosteric States in the ABL1 Protein Kinase

Despite the success of AlphaFold methods in predicting single protein structures, these methods showed intrinsic limitations in the characterization of multiple functional conformations of allosteric proteins. The recent NMR-based structural determination of the unbound ABL kinase in the active state and discovery of the inactive low-populated functional conformations that are unique for ABL kinase present an ideal challenge for the AlphaFold2 approaches. In the current study, we employ several adaptations of the AlphaFold2 methodology to predict protein conformational ensembles and allosteric states of the ABL kinase including randomized alanine sequence scanning combined with the multiple sequence alignment subsampling proposed in this study. We show that the proposed new AlphaFold2 adaptation combined with local frustration profiling of conformational states enables accurate prediction of the protein kinase structures and conformational ensembles, also offering a robust approach for interpretable characterization of the AlphaFold2 predictions and detection of hidden allosteric states. We found that the large high frustration residue clusters are uniquely characteristic of the low-populated, fully inactive ABL form and can define energetically frustrated cracking sites of conformational transitions, presenting difficult targets for AlphaFold2. The results of this study uncovered previously unappreciated fundamental connections between local frustration profiles of the functional allosteric states and the ability of AlphaFold2 methods to predict protein structural ensembles of the active and inactive states. This study showed that integration of the randomized sequence scanning adaptation of AlphaFold2 with a robust landscape-based analysis allows for interpretable atomistic predictions and characterization of protein conformational ensembles, providing a physical basis for the successes and limitations of current AlphaFold2 methods in detecting functional allosteric states that play a significant role in protein kinase regulation.

The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins

Artificial intelligence-driven advances in protein structure prediction in recent years have raised the question: has the protein structure-prediction problem been solved? Here, with a focus on nonglobular proteins, we highlight the many strengths and potential weaknesses of DeepMind's AlphaFold2 in the context of its biological and therapeutic applications. We summarize the subtleties associated with evaluation of AlphaFold2 model quality and reliability using the predicted local distance difference test (pLDDT) and predicted aligned error (PAE) values. We highlight various classes of proteins that AlphaFold2 can be applied to and the caveats involved. Concrete examples of how AlphaFold2 models can be integrated with experimental data in the form of small-angle X-ray scattering (SAXS), solution NMR, cryo-electron microscopy (cryo-EM) and X-ray diffraction are discussed. Finally, we highlight the need to move beyond structure prediction of rigid, static structural snapshots toward conformational ensembles and alternate biologically relevant states. The overarching theme is that careful consideration is due when using AlphaFold2-generated models to generate testable hypotheses and structural models, rather than treating predicted models as de facto ground truth structures.

Metamorphic proteins and how to find them

In the last two decades, our existing notion that most foldable proteins have a unique native state has been challenged by the discovery of metamorphic proteins, which reversibly interconvert between multiple, sometimes highly dissimilar, native states. As the number of known metamorphic proteins increases, several computational and experimental strategies have emerged for gaining insights about their refolding processes and identifying unknown metamorphic proteins amongst the known proteome. In this review, we describe the current advances in biophysically and functionally ascertaining the structural interconversions of metamorphic proteins and how coevolution can be harnessed to identify novel metamorphic proteins from sequence information. We also discuss the challenges and ongoing efforts in using artificial intelligence-based protein structure prediction methods to discover metamorphic proteins and predict their corresponding three-dimensional structures.

Application of artificial intelligence and machine learning techniques to the analysis of dynamic protein sequences

We apply methods of Artificial Intelligence and Machine Learning to protein dynamic bioinformatics. We rewrite the sequences of a large protein data set, containing both folded and intrinsically disordered molecules, using a representation developed previously, which encodes the intrinsic dynamic properties of the naturally occurring amino acids. We Fourier analyze the resulting sequences. It is demonstrated that classification models built using several different supervised learning methods are able to successfully distinguish folded from intrinsically disordered proteins from sequence alone. It is further shown that the most important sequence property for this discrimination is the sequence mobility, which is the sequence averaged value of the residue-specific average alpha carbon B factor. This is in agreement with previous work, in which we have demonstrated the central role played by the sequence mobility in protein dynamic bioinformatics and biophysics. This finding opens a path to the application of dynamic bioinformatics, in combination with machine learning algorithms, to a range of significant biomedical problems.

Prediction of Conformational Ensembles and Structural Effects of State-Switching Allosteric Mutants in the Protein Kinases Using Comparative Analysis of AlphaFold2 Adaptations with Sequence Masking and Shallow Subsampling

Despite the success of AlphaFold2 approaches in predicting single protein structures, these methods showed intrinsic limitations in predicting multiple functional conformations of allosteric proteins and have been challenged to accurately capture of the effects of single point mutations that induced significant structural changes. We systematically examined several implementations of AlphaFold2 methods to predict conformational ensembles for state-switching mutants of the ABL kinase. The results revealed that a combination of randomized alanine sequence masking with shallow multiple sequence alignment subsampling can significantly expand the conformational diversity of the predicted structural ensembles and capture shifts in populations of the active and inactive ABL states. Consistent with the NMR experiments, the predicted conformational ensembles for M309L/L320I and M309L/H415P ABL mutants that perturb the regulatory spine networks featured the increased population of the fully closed inactive state. On the other hand, the predicted conformational ensembles for the G269E/M309L/T334I and M309L/L320I/T334I triple ABL mutants that share activating T334I gate-keeper substitution are dominated by the active ABL form. The proposed adaptation of AlphaFold can reproduce the experimentally observed mutation-induced redistributions in the relative populations of the active and inactive ABL states and capture the effects of regulatory mutations on allosteric structural rearrangements of the kinase domain. The ensemble-based network analysis complemented AlphaFold predictions by revealing allosteric mediating centers that often directly correspond to state-switching mutational sites or reside in their immediate local structural proximity, which may explain the global effect of regulatory mutations on structural changes between the ABL states. This study suggested that attention-based learning of long-range dependencies between sequence positions in homologous folds and deciphering patterns of allosteric interactions may further augment the predictive abilities of AlphaFold methods for modeling of alternative protein sates, conformational ensembles and mutation-induced structural transformations.

KIS counteracts PTBP2 and regulates alternative exon usage in neurons

Alternative RNA splicing is an essential and dynamic process in neuronal differentiation and synapse maturation, and dysregulation of this process has been associated with neurodegenerative diseases. Recent studies have revealed the importance of RNA-binding proteins in the regulation of neuronal splicing programs. However, the molecular mechanisms involved in the control of these splicing regulators are still unclear. Here, we show that KIS, a kinase upregulated in the developmental brain, imposes a genome-wide alteration in exon usage during neuronal differentiation in mice. KIS contains a protein-recognition domain common to spliceosomal components and phosphorylates PTBP2, counteracting the role of this splicing factor in exon exclusion. At the molecular level, phosphorylation of unstructured domains within PTBP2 causes its dissociation from two co-regulators, Matrin3 and hnRNPM, and hinders the RNA-binding capability of the complex. Furthermore, KIS and PTBP2 display strong and opposing functional interactions in synaptic spine emergence and maturation. Taken together, our data uncover a post-translational control of splicing regulators that link transcriptional and alternative exon usage programs in neuronal development.

Predicting Functional Conformational Ensembles and Binding Mechanisms of Convergent Evolution for SARS-CoV-2 Spike Omicron Variants Using AlphaFold2 Sequence Scanning Adaptations and Molecular Dynamics Simulations

In this study, we combined AlphaFold-based approaches for atomistic modeling of multiple protein states and microsecond molecular simulations to accurately characterize conformational ensembles and binding mechanisms of convergent evolution for the SARS-CoV-2 Spike Omicron variants BA.1, BA.2, BA.2.75, BA.3, BA.4/BA.5 and BQ.1.1. We employed and validated several different adaptations of the AlphaFold methodology for modeling of conformational ensembles including the introduced randomized full sequence scanning for manipulation of sequence variations to systematically explore conformational dynamics of Omicron Spike protein complexes with the ACE2 receptor. Microsecond atomistic molecular dynamic simulations provide a detailed characterization of the conformational landscapes and thermodynamic stability of the Omicron variant complexes. By integrating the predictions of conformational ensembles from different AlphaFold adaptations and applying statistical confidence metrics we can expand characterization of the conformational ensembles and identify functional protein conformations that determine the equilibrium dynamics for the Omicron Spike complexes with the ACE2. Conformational ensembles of the Omicron RBD-ACE2 complexes obtained using AlphaFold-based approaches for modeling protein states and molecular dynamics simulations are employed for accurate comparative prediction of the binding energetics revealing an excellent agreement with the experimental data. In particular, the results demonstrated that AlphaFold-generated extended conformational ensembles can produce accurate binding energies for the Omicron RBD-ACE2 complexes. The results of this study suggested complementarities and potential synergies between AlphaFold predictions of protein conformational ensembles and molecular dynamics simulations showing that integrating information from both methods can potentially yield a more adequate characterization of the conformational landscapes for the Omicron RBD-ACE2 complexes. This study provides insights in the interplay between conformational dynamics and binding, showing that evolution of Omicron variants through acquisition of convergent mutational sites may leverage conformational adaptability and dynamic couplings between key binding energy hotspots to optimize ACE2 binding affinity and enable immune evasion.

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.

AlphaFold2-Enabled Atomistic Modeling of Structure, Conformational Ensembles, and Binding Energetics of the SARS-CoV-2 Omicron BA.2.86 Spike Protein with ACE2 Host Receptor and Antibodies: Compensatory Functional Effects of Binding Hotspots in Modulating Mechanisms of Receptor Binding and Immune Escape

The latest wave of SARS-CoV-2 Omicron variants displayed a growth advantage and increased viral fitness through convergent evolution of functional hotspots that work synchronously to balance fitness requirements for productive receptor binding and efficient immune evasion. In this study, we combined AlphaFold2-based structural modeling approaches with atomistic simulations and mutational profiling of binding energetics and stability for prediction and comprehensive analysis of the structure, dynamics, and binding of the SARS-CoV-2 Omicron BA.2.86 spike variant with ACE2 host receptor and distinct classes of antibodies. We adapted several AlphaFold2 approaches to predict both the structure and conformational ensembles of the Omicron BA.2.86 spike protein in the complex with the host receptor. The results showed that the AlphaFold2-predicted structural ensemble of the BA.2.86 spike protein complex with ACE2 can accurately capture the main conformational states of the Omicron variant. Complementary to AlphaFold2 structural predictions, microsecond molecular dynamics simulations reveal the details of the conformational landscape and produced equilibrium ensembles of the BA.2.86 structures that are used to perform mutational scanning of spike residues and characterize structural stability and binding energy hotspots. The ensemble-based mutational profiling of the receptor binding domain residues in the BA.2 and BA.2.86 spike complexes with ACE2 revealed a group of conserved hydrophobic hotspots and critical variant-specific contributions of the BA.2.86 convergent mutational hotspots R403K, F486P, and R493Q. To examine the immune evasion properties of BA.2.86 in atomistic detail, we performed structure-based mutational profiling of the spike protein binding interfaces with distinct classes of antibodies that displayed significantly reduced neutralization against the BA.2.86 variant. The results revealed the molecular basis of compensatory functional effects of the binding hotspots, showing that BA.2.86 lineage may have evolved to outcompete other Omicron subvariants by improving immune evasion while preserving binding affinity with ACE2 via through a compensatory effect of R493Q and F486P convergent mutational hotspots. This study demonstrated that an integrative approach combining AlphaFold2 predictions with complementary atomistic molecular dynamics simulations and robust ensemble-based mutational profiling of spike residues can enable accurate and comprehensive characterization of structure, dynamics, and binding mechanisms of newly emerging Omicron variants.

Modeling Flexible Protein Structure With AlphaFold2 and Crosslinking Mass Spectrometry

We propose a pipeline that combines AlphaFold2 (AF2) and crosslinking mass spectrometry (XL-MS) to model the structure of proteins with multiple conformations. The pipeline consists of two main steps: ensemble generation using AF2 and conformer selection using XL-MS data. For conformer selection, we developed two scores-the monolink probability score (MP) and the crosslink probability score (XLP)-both of which are based on residue depth from the protein surface. We benchmarked MP and XLP on a large dataset of decoy protein structures and showed that our scores outperform previously developed scores. We then tested our methodology on three proteins having an open and closed conformation in the Protein Data Bank: Complement component 3 (C3), luciferase, and glutamine-binding periplasmic protein, first generating ensembles using AF2, which were then screened for the open and closed conformations using experimental XL-MS data. In five out of six cases, the most accurate model within the AF2 ensembles-or a conformation within 1 Å of this model-was identified using crosslinks, as assessed through the XLP score. In the remaining case, only the monolinks (assessed through the MP score) successfully identified the open conformation of glutamine-binding periplasmic protein, and these results were further improved by including the "occupancy" of the monolinks. This serves as a compelling proof-of-concept for the effectiveness of monolinks. In contrast, the AF2 assessment score was only able to identify the most accurate conformation in two out of six cases. Our results highlight the complementarity of AF2 with experimental methods like XL-MS, with the MP and XLP scores providing reliable metrics to assess the quality of the predicted models. The MP and XLP scoring functions mentioned above are available at https://gitlab.com/topf-lab/xlms-tools.

Investigating the ability of deep learning-based structure prediction to extrapolate and/or enrich the set of antibody CDR canonical forms

Deep learning models have been shown to accurately predict protein structure from sequence, allowing researchers to explore protein space from the structural viewpoint. In this paper we explore whether "novel" features, such as distinct loop conformations can arise from these predictions despite not being present in the training data. Here we have used ABodyBuilder2, a deep learning antibody structure predictor, to predict the structures of ~1.5M paired antibody sequences. We examined the predicted structures of the canonical CDR loops and found that most of these predictions fall into the already described CDR canonical form structural space. We also found a small number of "new" canonical clusters composed of heterogeneous sequences united by a common sequence motif and loop conformation. Analysis of these novel clusters showed their origins to be either shapes seen in the training data at very low frequency or shapes seen at high frequency but at a shorter sequence length. To evaluate explicitly the ability of ABodyBuilder2 to extrapolate, we retrained several models whilst withholding all antibody structures of a specific CDR loop length or canonical form. These "starved" models showed evidence of generalisation across CDRs of different lengths, but they did not extrapolate to loop conformations which were highly distinct from those present in the training data. However, the models were able to accurately predict a canonical form even if only a very small number of examples of that shape were in the training data. Our results suggest that deep learning protein structure prediction methods are unable to make completely out-of-domain predictions for CDR loops. However, in our analysis we also found that even minimal amounts of data of a structural shape allow the method to recover its original predictive abilities. We have made the ~1.5 M predicted structures used in this study available to download at https://doi.org/10.5281/zenodo.10280181.

Interpretable Atomistic Prediction and Functional Analysis of Conformational Ensembles and Allosteric States in Protein Kinases Using AlphaFold2 Adaptation with Randomized Sequence Scanning and Local Frustration Profiling

The groundbreaking achievements of AlphaFold2 (AF2) approaches in protein structure modeling marked a transformative era in structural biology. Despite the success of AF2 tools in predicting single protein structures, these methods showed intrinsic limitations in predicting multiple functional conformations of allosteric proteins and fold-switching systems. The recent NMR-based structural determination of the unbound ABL kinase in the active state and two inactive low-populated functional conformations that are unique for ABL kinase presents an ideal challenge for AF2 approaches. In the current study we employ several implementations of AF2 methods to predict protein conformational ensembles and allosteric states of the ABL kinase including (a) multiple sequence alignments (MSA) subsampling approach; (b) SPEACH_AF approach in which alanine scanning is performed on generated MSAs; and (c) introduced in this study randomized full sequence mutational scanning for manipulation of sequence variations combined with the MSA subsampling. We show that the proposed AF2 adaptation combined with local frustration mapping of conformational states enable accurate prediction of the ABL active and intermediate structures and conformational ensembles, also offering a robust approach for interpretable characterization of the AF2 predictions and limitations in detecting hidden allosteric states. We found that the large high frustration residue clusters are uniquely characteristic of the low-populated, fully inactive ABL form and can define energetically frustrated cracking sites of conformational transitions, presenting difficult targets for AF2 methods. This study uncovered previously unappreciated, fundamental connections between distinct patterns of local frustration in functional kinase states and AF2 successes/limitations in detecting low-populated frustrated conformations, providing a better understanding of benefits and limitations of current AF2-based adaptations in modeling of conformational ensembles.

Protein structure generation via folding diffusion

The ability to computationally generate novel yet physically foldable protein structures could lead to new biological discoveries and new treatments targeting yet incurable diseases. Despite recent advances in protein structure prediction, directly generating diverse, novel protein structures from neural networks remains difficult. In this work, we present a diffusion-based generative model that generates protein backbone structures via a procedure inspired by the natural folding process. We describe a protein backbone structure as a sequence of angles capturing the relative orientation of the constituent backbone atoms, and generate structures by denoising from a random, unfolded state towards a stable folded structure. Not only does this mirror how proteins natively twist into energetically favorable conformations, the inherent shift and rotational invariance of this representation crucially alleviates the need for more complex equivariant networks. We train a denoising diffusion probabilistic model with a simple transformer backbone and demonstrate that our resulting model unconditionally generates highly realistic protein structures with complexity and structural patterns akin to those of naturally-occurring proteins. As a useful resource, we release an open-source codebase and trained models for protein structure diffusion.

Rosetta Energy Analysis of AlphaFold2 models: Point Mutations and Conformational Ensembles

There has been an explosive growth in the applications of AlphaFold2, and other structure prediction platforms, to accurately predict protein structures from a multiple sequence alignment (MSA) for downstream structural analysis. However, two outstanding questions persist in the field regarding the robustness of AlphaFold2 predictions of the consequences of point mutations and the completeness of its prediction of protein conformational ensembles. We combined our previously developed method SPEACH_AF with model relaxation and energetic analysis with Rosetta to address these questions. SPEACH_AF introduces residue substitutions across the MSA and not just within the input sequence. With respect to conformational ensembles, we combined SPEACH_AF and a new MSA subsampling method, AF_cluster, and for a benchmarked set of proteins, we found that the energetics of the conformational ensembles generated by AlphaFold2 correspond to those of experimental structures and explored by standard molecular dynamic methods. With respect to point mutations, we compared the structural and energetic consequences of having the mutation(s) in the input sequence versus in the whole MSA (SPEACH_AF). Both methods yielded models different from the wild-type sequence, with more robust changes when the mutation(s) were in the whole MSA. While our findings demonstrate the robustness of AlphaFold2 in analyzing point mutations and exploring conformational ensembles, they highlight the need for multi parameter structural and energetic analyses of these models to generate experimentally testable hypotheses.

Accelerated Molecular Dynamics and AlphaFold Uncover a Missing Conformational State of Transporter Protein OxlT

Transporter proteins change their conformations to carry their substrate across the cell membrane. The conformational dynamics is vital to understanding the transport function. We have studied the oxalate transporter (OxlT), an oxalate:formate antiporter from Oxalobacter formigenes, significant in avoiding kidney stone formation. The atomic structure of OxlT has been recently solved in the outward-open and occluded states. However, the inward-open conformation is still missing, hindering a complete understanding of the transporter. Here, we performed a Gaussian accelerated molecular dynamics simulation to sample the extensive conformational space of OxlT and successfully predicted the inward-open conformation where cytoplasmic substrate formate binding was preferred over oxalate binding. We also identified critical interactions for the inward-open conformation. The results were complemented by an AlphaFold2 structure prediction. Although AlphaFold2 solely predicted OxlT in the outward-open conformation, mutation of the identified critical residues made it partly predict the inward-open conformation, identifying possible state-shifting mutations.

Sequence clustering confounds AlphaFold2

Though typically associated with a single folded state, some globular proteins remodel their secondary and/or tertiary structures in response to cellular stimuli. AlphaFold21 (AF2) readily generates one dominant protein structure for these fold-switching (a.k.a. metamorphic) proteins2, but it often fails to predict their alternative experimentally observed structures3,4. Wayment-Steele, et al. steered AF2 to predict alternative structures of a few metamorphic proteins using a method they call AF-cluster5. However, their Paper lacks some essential controls needed to assess AF-cluster's reliability. We find that these controls show AF-cluster to be a poor predictor of metamorphic proteins. First, closer examination of the Paper's results reveals that random sequence sampling outperforms sequence clustering, challenging the claim that AF-cluster works by "deconvolving conflicting sets of couplings." Further, we observe that AF-cluster mistakes some single-folding KaiB homologs for fold switchers, a critical flaw bound to mislead users. Finally, proper error analysis reveals that AF-cluster predicts many correct structures with low confidence and some experimentally unobserved conformations with confidences similar to experimentally observed ones. For these reasons, we suggest using ColabFold6-based random sequence sampling7-augmented by other predictive approaches-as a more accurate and less computationally intense alternative to AF-cluster.

Recent Advances and Challenges in Protein Structure Prediction

Artificial intelligence has made significant advances in the field of protein structure prediction in recent years. In particular, DeepMind's end-to-end model, AlphaFold2, has demonstrated the capability to predict three-dimensional structures of numerous unknown proteins with accuracy levels comparable to those of experimental methods. This breakthrough has opened up new possibilities for understanding protein structure and function as well as accelerating drug discovery and other applications in the field of biology and medicine. Despite the remarkable achievements of artificial intelligence in the field, there are still some challenges and limitations. In this Review, we discuss the recent progress and some of the challenges in protein structure prediction. These challenges include predicting multidomain protein structures, protein complex structures, multiple conformational states of proteins, and protein folding pathways. Furthermore, we highlight directions in which further improvements can be conducted.

Predicting multiple conformations via sequence clustering and AlphaFold2

AlphaFold2 (ref. 1) has revolutionized structural biology by accurately predicting single structures of proteins. However, a protein's biological function often depends on multiple conformational substates2, and disease-causing point mutations often cause population changes within these substates3,4. We demonstrate that clustering a multiple-sequence alignment by sequence similarity enables AlphaFold2 to sample alternative states of known metamorphic proteins with high confidence. Using this method, named AF-Cluster, we investigated the evolutionary distribution of predicted structures for the metamorphic protein KaiB5 and found that predictions of both conformations were distributed in clusters across the KaiB family. We used nuclear magnetic resonance spectroscopy to confirm an AF-Cluster prediction: a cyanobacteria KaiB variant is stabilized in the opposite state compared with the more widely studied variant. To test AF-Cluster's sensitivity to point mutations, we designed and experimentally verified a set of three mutations predicted to flip KaiB from Rhodobacter sphaeroides from the ground to the fold-switched state. Finally, screening for alternative states in protein families without known fold switching identified a putative alternative state for the oxidoreductase Mpt53 in Mycobacterium tuberculosis. Further development of such bioinformatic methods in tandem with experiments will probably have a considerable impact on predicting protein energy landscapes, essential for illuminating biological function.

Adaptive Sampling Methods for Molecular Dynamics in the Era of Machine Learning

Molecular dynamics (MD) simulations are fundamental computational tools for the study of proteins and their free energy landscapes. However, sampling protein conformational changes through MD simulations is challenging due to the relatively long time scales of these processes. Many enhanced sampling approaches have emerged to tackle this problem, including biased sampling and path-sampling methods. In this Perspective, we focus on adaptive sampling algorithms. These techniques differ from other approaches because the thermodynamic ensemble is preserved and the sampling is enhanced solely by restarting MD trajectories at particularly chosen seeds rather than introducing biasing forces. We begin our treatment with an overview of theoretically transparent methods, where we discuss principles and guidelines for adaptive sampling. Then, we present a brief summary of select methods that have been applied to realistic systems in the past. Finally, we discuss recent advances in adaptive sampling methodology powered by deep learning techniques, as well as their shortcomings.

Predicting Relative Populations of Protein Conformations without a Physics Engine Using AlphaFold 2

This paper presents a novel 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 NMR 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, NMR analysis, and evolution.

AlphaFold2 has more to learn about protein energy landscapes

Recent work suggests that AlphaFold2 (AF2)-a deep learning-based model that can accurately infer protein structure from sequence-may discern important features of folded protein energy landscapes, defined by the diversity and frequency of different conformations in the folded state. Here, we test the limits of its predictive power on fold-switching proteins, which assume two structures with regions of distinct secondary and/or tertiary structure. Using several implementations of AF2, including two published enhanced sampling approaches, we generated >280,000 models of 93 fold-switching proteins whose experimentally determined conformations were likely in AF2's training set. Combining all models, AF2 predicted fold switching with a modest success rate of ~25%, indicating that it does not readily sample both experimentally characterized conformations of most fold switchers. Further, AF2's confidence metrics selected against models consistent with experimentally determined fold-switching conformations in favor of inconsistent models. Accordingly, these confidence metrics-though suggested to evaluate protein energetics reliably-did not discriminate between low and high energy states of fold-switching proteins. We then evaluated AF2's performance on seven fold-switching proteins outside of its training set, generating >159,000 models in total. Fold switching was accurately predicted in one of seven targets with moderate confidence. Further, AF2 demonstrated no ability to predict alternative conformations of two newly discovered targets without homologs in the set of 93 fold switchers. These results indicate that AF2 has more to learn about the underlying energetics of protein ensembles and highlight the need for further developments of methods that readily predict multiple protein conformations.

Deep generative models of LDLR protein structure to predict variant pathogenicity

The complex structure and function of low density lipoprotein receptor (LDLR) makes classification of protein-coding missense variants challenging. Deep generative models, including Evolutionary model of Variant Effect (EVE), Evolutionary Scale Modeling (ESM), and AlphaFold 2 (AF2), have enabled significant progress in the prediction of protein structure and function. ESM and EVE directly estimate the likelihood of a variant sequence but are purely data-driven and challenging to interpret. AF2 predicts LDLR structures, but variant effects are explicitly modeled by estimating changes in stability. We tested the effectiveness of these models for predicting variant pathogenicity compared to established methods. AF2 produced two distinct conformations based on a novel hinge mechanism. Within ESM's hidden space, benign and pathogenic variants had different distributions. In EVE, these distributions were similar. EVE and ESM were comparable to Polyphen-2, SIFT, REVEL, and Primate AI for predicting binary classifications in ClinVar. However, they were more strongly correlated with experimental measures of LDL uptake. AF2 poorly performed in these tasks. Using the UK Biobank to compare association with clinical phenotypes, ESM and EVE were more strongly associated with serum LDL-C than Polyphen-2. ESM was able to identify variants with more extreme LDL-C levels than EVE and had a significantly stronger association with atherosclerotic cardiovascular disease. In conclusion, AF2 predicted LDLR structures do not accurately model variant pathogenicity. ESM and EVE are competitive with prior scoring methods for prediction based on binary classifications in ClinVar but are superior based on correlations with experimental assays and clinical phenotypes.

Accurate Characterization of Conformational Ensembles and Binding Mechanisms of the SARS-CoV-2 Omicron BA.2 and BA.2.86 Spike Protein with the Host Receptor and Distinct Classes of Antibodies Using AlphaFold2-Augmented Integrative Computational Modeling

The latest wave SARS-CoV-2 Omicron variants displayed a growth advantage and the increased viral fitness through convergent evolution of functional hotspots that work synchronously to balance fitness requirements for productive receptor binding and efficient immune evasion. In this study, we combined AlphaFold2-based structural modeling approaches with all-atom MD simulations and mutational profiling of binding energetics and stability for prediction and comprehensive analysis of the structure, dynamics, and binding of the SARS-CoV-2 Omicron BA.2.86 spike variant with ACE2 host receptor and distinct classes of antibodies. We adapted several AlphaFold2 approaches to predict both structure and conformational ensembles of the Omicron BA.2.86 spike protein in the complex with the host receptor. The results showed that AlphaFold2-predicted conformational ensemble of the BA.2.86 spike protein complex can accurately capture the main dynamics signatures obtained from microscond molecular dynamics simulations. The ensemble-based dynamic mutational scanning of the receptor binding domain residues in the BA.2 and BA.2.86 spike complexes with ACE2 dissected the role of the BA.2 and BA.2.86 backgrounds in modulating binding free energy changes revealing a group of conserved hydrophobic hotspots and critical variant-specific contributions of the BA.2.86 mutational sites R403K, F486P and R493Q. To examine immune evasion properties of BA.2.86 in atomistic detail, we performed large scale structure-based mutational profiling of the S protein binding interfaces with distinct classes of antibodies that displayed significantly reduced neutralization against BA.2.86 variant. The results quantified specific function of the BA.2.86 mutations to ensure broad resistance against different classes of RBD antibodies. This study revealed the molecular basis of compensatory functional effects of the binding hotspots, showing that BA.2.86 lineage may have primarily evolved to improve immune escape while modulating binding affinity with ACE2 through cooperative effect of R403K, F486P and R493Q mutations. The study supports a hypothesis that the impact of the increased ACE2 binding affinity on viral fitness is more universal and is mediated through cross-talk between convergent mutational hotspots, while the effect of immune evasion could be more variant-dependent.

Tutorial: a guide for the selection of fast and accurate computational tools for the prediction of intrinsic disorder in proteins

Intrinsic disorder is instrumental for a wide range of protein functions, and its analysis, using computational predictions from primary structures, complements secondary and tertiary structure-based approaches. In this Tutorial, we provide an overview and comparison of 23 publicly available computational tools with complementary parameters useful for intrinsic disorder prediction, partly relying on results from the Critical Assessment of protein Intrinsic Disorder prediction experiment. We consider factors such as accuracy, runtime, availability and the need for functional insights. The selected tools are available as web servers and downloadable programs, offer state-of-the-art predictions and can be used in a high-throughput manner. We provide examples and instructions for the selected tools to illustrate practical aspects related to the submission, collection and interpretation of predictions, as well as the timing and their limitations. We highlight two predictors for intrinsically disordered proteins, flDPnn as accurate and fast and IUPred as very fast and moderately accurate, while suggesting ANCHOR2 and MoRFchibi as two of the best-performing predictors for intrinsically disordered region binding. We link these tools to additional resources, including databases of predictions and web servers that integrate multiple predictive methods. Altogether, this Tutorial provides a hands-on guide to comparatively evaluating multiple predictors, submitting and collecting their own predictions, and reading and interpreting results. It is suitable for experimentalists and computational biologists interested in accurately and conveniently identifying intrinsic disorder, facilitating the functional characterization of the rapidly growing collections of protein sequences.

Developing similarity matrices for antibody-protein binding interactions

The inventions of AlphaFold and RoseTTAFold are revolutionizing computational protein science due to their abilities to reliably predict protein structures. Their unprecedented successes are due to the parallel consideration of several types of information, one of which is protein sequence similarity information. Sequence homology has been studied for many decades and depends on similarity matrices to define how similar or different protein sequences are to one another. A natural extension of predicting protein structures is predicting the interactions between proteins, but similarity matrices for protein-protein interactions do not exist. This study conducted a mutational analysis of 384 non-redundant antibody-protein antigen complexes to calculate antibody-protein interaction similarity matrices. Every important residue in each antibody and each antigen was mutated to each of the other 19 commonly occurring amino acids and the percentage changes in interaction energies were calculated using three force fields: CHARMM, Amber, and Rosetta. The data were used to construct six interaction similarity matrices, one for antibodies and another for antigens using each force field. The matrices exhibited both commonalities, such as mutations of aromatic and charged residues being the most detrimental, and differences, such as Rosetta predicting mutations of serines to be better tolerated than either Amber or CHARMM. A comparison to nine previously published similarity matrices for protein sequences revealed that the new interaction matrices are more similar to one another than they are to any of the previous matrices. The created similarity matrices can be used in force field specific applications to help guide decisions regarding mutations in protein-protein binding interfaces.

Computing Free Energies of Fold-Switching Proteins Using MELD x MD

Some proteins are conformational switches, able to transition between relatively different conformations. To understand what drives them requires computing the free-energy difference ΔGAB between their stable states, A and B. Molecular dynamics (MD) simulations alone are often slow because they require a reaction coordinate and must sample many transitions in between. Here, we show that modeling employing limited data (MELD) x MD on known endstates A and B is accurate and efficient because it does not require passing over barriers or knowing reaction coordinates. We validate this method on two problems: (1) it gives correct relative populations of α and β conformers for small designed chameleon sequences of protein G; and (2) it correctly predicts the conformations of the C-terminal domain (CTD) of RfaH. Free-energy methods like MELD x MD can often resolve structures that confuse machine-learning (ML) methods.

The Origin of Discrepancies between Predictions and Annotations in Intrinsically Disordered Proteins

Disorder prediction methods that can discriminate between ordered and disordered regions have contributed fundamentally to our understanding of the properties and prevalence of intrinsically disordered proteins (IDPs) in proteomes as well as their functional roles. However, a recent large-scale assessment of the performance of these methods indicated that there is still room for further improvements, necessitating novel approaches to understand the strengths and weaknesses of individual methods. In this study, we compared two methods, IUPred and disorder prediction, based on the pLDDT scores derived from AlphaFold2 (AF2) models. We evaluated these methods using a dataset from the DisProt database, consisting of experimentally characterized disordered regions and subsets associated with diverse experimental methods and functions. IUPred and AF2 provided consistent predictions in 79% of cases for long disordered regions; however, for 15% of these cases, they both suggested order in disagreement with annotations. These discrepancies arose primarily due to weak experimental support, the presence of intermediate states, or context-dependent behavior, such as binding-induced transitions. Furthermore, AF2 tended to predict helical regions with high pLDDT scores within disordered segments, while IUPred had limitations in identifying linker regions. These results provide valuable insights into the inherent limitations and potential biases of disorder prediction methods.

Evolutionary selection of proteins with two folds

Although most globular proteins fold into a single stable structure, an increasing number have been shown to remodel their secondary and tertiary structures in response to cellular stimuli. State-of-the-art algorithms predict that these fold-switching proteins adopt only one stable structure, missing their functionally critical alternative folds. Why these algorithms predict a single fold is unclear, but all of them infer protein structure from coevolved amino acid pairs. Here, we hypothesize that coevolutionary signatures are being missed. Suspecting that single-fold variants could be masking these signatures, we developed an approach, called Alternative Contact Enhancement (ACE), to search both highly diverse protein superfamilies-composed of single-fold and fold-switching variants-and protein subfamilies with more fold-switching variants. ACE successfully revealed coevolution of amino acid pairs uniquely corresponding to both conformations of 56/56 fold-switching proteins from distinct families. Then, we used ACE-derived contacts to (1) predict two experimentally consistent conformations of a candidate protein with unsolved structure and (2) develop a blind prediction pipeline for fold-switching proteins. The discovery of widespread dual-fold coevolution indicates that fold-switching sequences have been preserved by natural selection, implying that their functionalities provide evolutionary advantage and paving the way for predictions of diverse protein structures from single sequences.

Predicted models and CCP4

In late 2020, the results of CASP14, the 14th event in a series of competitions to assess the latest developments in computational protein structure-prediction methodology, revealed the giant leap forward that had been made by Google's Deepmind in tackling the prediction problem. The level of accuracy in their predictions was the first instance of a competitor achieving a global distance test score of better than 90 across all categories of difficulty. This achievement represents both a challenge and an opportunity for the field of experimental structural biology. For structure determination by macromolecular X-ray crystallography, access to highly accurate structure predictions is of great benefit, particularly when it comes to solving the phase problem. Here, details of new utilities and enhanced applications in the CCP4 suite, designed to allow users to exploit predicted models in determining macromolecular structures from X-ray diffraction data, are presented. The focus is mainly on applications that can be used to solve the phase problem through molecular replacement.

Fluid protein fold space and its implications

Fold-switching proteins, which remodel their secondary and tertiary structures in response to cellular stimuli, suggest a new view of protein fold space. For decades, experimental evidence has indicated that protein fold space is discrete: dissimilar folds are encoded by dissimilar amino acid sequences. Challenging this assumption, fold-switching proteins interconnect discrete groups of dissimilar protein folds, making protein fold space fluid. Three recent observations support the concept of fluid fold space: (1) some amino acid sequences interconvert between folds with distinct secondary structures, (2) some naturally occurring sequences have switched folds by stepwise mutation, and (3) fold switching is evolutionarily selected and likely confers advantage. These observations indicate that minor amino acid sequence modifications can transform protein structure and function. Consequently, proteomic structural and functional diversity may be expanded by alternative splicing, small nucleotide polymorphisms, post-translational modifications, and modified translation rates.

Exploring the structural acrobatics of fold-switching proteins using simplified structure-based models

Metamorphic proteins are a paradigm of the protein folding process, by encoding two or more native states, highly dissimilar in terms of their secondary, tertiary, and even quaternary structure, on a single amino acid sequence. Moreover, these proteins structurally interconvert between these native states in a reversible manner at biologically relevant timescales as a result of different environmental cues. The large-scale rearrangements experienced by these proteins, and their sometimes high mass interacting partners that trigger their metamorphosis, makes the computational and experimental study of their structural interconversion challenging. Here, we present our efforts in studying the refolding landscapes of two quintessential metamorphic proteins, RfaH and KaiB, using simplified dual-basin structure-based models (SBMs), rigorously footed on the energy landscape theory of protein folding and the principle of minimal frustration. By using coarse-grained models in which the native contacts and bonded interactions extracted from the available experimental structures of the two native states of RfaH and KaiB are merged into a single Hamiltonian, dual-basin SBM models can be generated and savvily calibrated to explore their fold-switch in a reversible manner in molecular dynamics simulations. We also describe how some of the insights offered by these simulations have driven the design of experiments and the validation of the conformational ensembles and refolding routes observed using this simple and computationally efficient models.

Metamorphic protein folding as evolutionary adaptation

Metamorphic proteins switch reversibly between multiple distinct, stable structures, often with different functions. It was previously hypothesized that metamorphic proteins arose as intermediates in the evolution of a new fold - rare and transient exceptions to the 'one sequence, one fold' paradigm. However, as described herein, mounting evidence suggests that metamorphic folding is an adaptive feature, preserved and optimized over evolutionary time as exemplified by the NusG family and the chemokine XCL1. Analysis of extant protein families and resurrected protein ancestors demonstrates that large regions of sequence space are compatible with metamorphic folding. As a category that enhances biological fitness, metamorphic proteins are likely to employ fold switching to perform important biological functions and may be more common than previously thought.

AlphaCutter: Efficient removal of non-globular regions from predicted protein structures

A huge number of high-quality predicted protein structures are now publicly available. However, many of these structures contain non-globular regions, which diminish the performance of downstream structural bioinformatic applications. In this study, we develop AlphaCutter for the removal of non-globular regions from predicted protein structures. A large-scale cleaning of 542,380 predicted SwissProt structures highlights that AlphaCutter is able to (1) remove non-globular regions that are undetectable using pLDDT scores and (2) preserve high integrity of the cleaned domain regions. As useful applications, AlphaCutter improved the folding energy scores and sequence recovery rates in the re-design of domain regions. On average, AlphaCutter takes less than 3 s to clean a protein structure, enabling efficient cleaning of the exploding number of predicted protein structures. AlphaCutter is available at https://github.com/johnnytam100/AlphaCutter. AlphaCutter-cleaned SwissProt structures are available for download at https://doi.org/10.5281/zenodo.7944483.

Global Survey of Protein Dynamic Properties

Using tools developed to study the dynamic bioinformatics of proteins, we are able to study the dynamic characteristics of very large numbers of protein sequences simultaneously. We study herein the distribution of protein sequences in a space determined by sequence mobility. It is shown that there are statistically significant differences in mobility distribution between folded sequences of different structural classes and between those and sequences of intrinsically disordered proteins. It is also shown that the several regions of mobility space differ significantly with respect to structural makeup. Helical proteins are shown to have distinctive dynamic characteristics at both extremes of the mobility spectrum.

Comparative evaluation of AlphaFold2 and disorder predictors for prediction of intrinsic disorder, disorder content and fully disordered proteins

We expand studies of AlphaFold2 (AF2) in the context of intrinsic disorder prediction by comparing it against a broad selection of 20 accurate, popular and recently released disorder predictors. We use 25% larger benchmark dataset with 646 proteins and cover protein-level predictions of disorder content and fully disordered proteins. AF2-based disorder predictions secure a relatively high Area Under receiver operating characteristic Curve (AUC) of 0.77 and are statistically outperformed by several modern disorder predictors that secure AUCs around 0.8 with median runtime of about 20 s compared to 1200 s for AF2. Moreover, AF2 provides modestly accurate predictions of fully disordered proteins (F1 = 0.59 vs. 0.91 for the best disorder predictor) and disorder content (mean absolute error of 0.21 vs. 0.15). AF2 also generates statistically more accurate disorder predictions for about 20% of proteins that have relatively short sequences and a few disordered regions that tend to be located at the sequence termini, and which are absent of disordered protein-binding regions. Interestingly, AF2 and the most accurate disorder predictors rely on deep neural networks, suggesting that these models are useful for protein structure and disorder predictions.

Identification of a covert evolutionary pathway between two protein folds

Although homologous protein sequences are expected to adopt similar structures, some amino acid substitutions can interconvert α-helices and β-sheets. Such fold switching may have occurred over evolutionary history, but supporting evidence has been limited by the: (1) abundance and diversity of sequenced genes, (2) quantity of experimentally determined protein structures, and (3) assumptions underlying the statistical methods used to infer homology. Here, we overcome these barriers by applying multiple statistical methods to a family of ~600,000 bacterial response regulator proteins. We find that their homologous DNA-binding subunits assume divergent structures: helix-turn-helix versus α-helix + β-sheet (winged helix). Phylogenetic analyses, ancestral sequence reconstruction, and AlphaFold2 models indicate that amino acid substitutions facilitated a switch from helix-turn-helix into winged helix. This structural transformation likely expanded DNA-binding specificity. Our approach uncovers an evolutionary pathway between two protein folds and provides a methodology to identify secondary structure switching in other protein families.

Thermodynamic Evolution of a Metamorphic Protein: A Theoretical-Computational Study of Human Lymphotactin

Metamorphic, or fold-switching, proteins feature different folds that are physiologically relevant. The human chemokine XCL1 (or Lymphotactin) is a metamorphic protein that features two native states, an [Formula: see text] and an all[Formula: see text] fold, which have similar stability at physiological condition. Here, extended molecular dynamics (MD) simulations, principal component analysis of atomic fluctuations and thermodynamic modeling based on both the configurational volume and free energy landscape, are used to obtain a detailed characterization of the conformational thermodynamics of human Lymphotactin and of one of its ancestors (as was previously obtained by genetic reconstruction). Comparison of our computational results with the available experimental data show that the MD-based thermodynamics can explain the experimentally observed variation of the conformational equilibrium between the two proteins. In particular, our computational data provide an interpretation of the thermodynamic evolution in this protein, revealing the relevance of the configurational entropy and of the shape of the free energy landscape within the essential space (i.e., the space defined by the generalized internal coordinates providing the largest, typically non-Gaussian, structural fluctuations).

Integrated mass spectrometry strategy for functional protein complex discovery and structural characterization

The discovery of functional protein complex and the interrogation of the complex structure-function relationship (SFR) play crucial roles in the understanding and intervention of biological processes. Affinity purification-mass spectrometry (AP-MS) has been proved as a powerful tool in the discovery of protein complexes. However, validation of these novel protein complexes as well as elucidation of their molecular interaction mechanisms are still challenging. Recently, native top-down MS (nTDMS) is rapidly developed for the structural analysis of protein complexes. In this review, we discuss the integration of AP-MS and nTDMS in the discovery and structural characterization of functional protein complexes. Further, we think the emerging artificial intelligence (AI)-based protein structure prediction is highly complementary to nTDMS and can promote each other. We expect the hybridization of integrated structural MS with AI prediction to be a powerful workflow in the discovery and SFR investigation of functional protein complexes.

An agnostic analysis of the human AlphaFold2 proteome using local protein conformations

Knowledge of the 3D structure of proteins is a valuable asset for understanding their precise biological mechanisms. However, the cost of production of 3D structures and experimental difficulties limit their obtaining. The proposal of 3D structural models is consequently an appealing alternative. The release of the AlphaFold Deep Learning approach has revolutionized the field. The recent near-complete human proteome proposal makes it possible to analyse large amounts of data and evaluate the results of the approach in greater depth. The 3D human proteome was thus analysed in light of the classic secondary structures, and many less-used protein local conformations (PolyProline II helices, type of γ-turns, of β-turns and of β-bulges, curvature of the helices, and a structural alphabet). Without questioning the global quality of the approach, this analysis highlights certain local conformations, which maybe poorly predicted and they could therefore be better addressed.

AlphaFold2 and its applications in the fields of biology and medicine

AlphaFold2 (AF2) is an artificial intelligence (AI) system developed by DeepMind that can predict three-dimensional (3D) structures of proteins from amino acid sequences with atomic-level accuracy. Protein structure prediction is one of the most challenging problems in computational biology and chemistry, and has puzzled scientists for 50 years. The advent of AF2 presents an unprecedented progress in protein structure prediction and has attracted much attention. Subsequent release of structures of more than 200 million proteins predicted by AF2 further aroused great enthusiasm in the science community, especially in the fields of biology and medicine. AF2 is thought to have a significant impact on structural biology and research areas that need protein structure information, such as drug discovery, protein design, prediction of protein function, et al. Though the time is not long since AF2 was developed, there are already quite a few application studies of AF2 in the fields of biology and medicine, with many of them having preliminarily proved the potential of AF2. To better understand AF2 and promote its applications, we will in this article summarize the principle and system architecture of AF2 as well as the recipe of its success, and particularly focus on reviewing its applications in the fields of biology and medicine. Limitations of current AF2 prediction will also be discussed.

Exploring and Learning the Universe of Protein Allostery Using Artificial Intelligence Augmented Biophysical and Computational Approaches

Allosteric mechanisms are commonly employed regulatory tools used by proteins to orchestrate complex biochemical processes and control communications in cells. The quantitative understanding and characterization of allosteric molecular events are among major challenges in modern biology and require integration of innovative computational experimental approaches to obtain atomistic-level knowledge of the allosteric states, interactions, and dynamic conformational landscapes. The growing body of computational and experimental studies empowered by emerging artificial intelligence (AI) technologies has opened up new paradigms for exploring and learning the universe of protein allostery from first principles. In this review we analyze recent developments in high-throughput deep mutational scanning of allosteric protein functions; applications and latest adaptations of Alpha-fold structural prediction methods for studies of protein dynamics and allostery; new frontiers in integrating machine learning and enhanced sampling techniques for characterization of allostery; and recent advances in structural biology approaches for studies of allosteric systems. We also highlight recent computational and experimental studies of the SARS-CoV-2 spike (S) proteins revealing an important and often hidden role of allosteric regulation driving functional conformational changes, binding interactions with the host receptor, and mutational escape mechanisms of S proteins which are critical for viral infection. We conclude with a summary and outlook of future directions suggesting that AI-augmented biophysical and computer simulation approaches are beginning to transform studies of protein allostery toward systematic characterization of allosteric landscapes, hidden allosteric states, and mechanisms which may bring about a new revolution in molecular biology and drug discovery.

Distinguishing features of fold-switching proteins

Though many folded proteins assume one stable structure that performs one function, a small-but-increasing number remodel their secondary and tertiary structures and change their functions in response to cellular stimuli. These fold-switching proteins regulate biological processes and are associated with autoimmune dysfunction, severe acute respiratory syndrome coronavirus-2 infection, and more. Despite their biological importance, it is difficult to computationally predict fold switching. With the aim of advancing computational prediction and experimental characterization of fold switchers, this review discusses several features that distinguish fold-switching proteins from their single-fold and intrinsically disordered counterparts. First, the isolated structures of fold switchers are less stable and more heterogeneous than single folders but more stable and less heterogeneous than intrinsically disordered proteins (IDPs). Second, the sequences of single fold, fold switching, and intrinsically disordered proteins can evolve at distinct rates. Third, proteins from these three classes are best predicted using different computational techniques. Finally, late-breaking results suggest that single folders, fold switchers, and IDPs have distinct patterns of residue-residue coevolution. The review closes by discussing high-throughput and medium-throughput experimental approaches that might be used to identify new fold-switching proteins.

Mutational scan inferred binding energetics and structure in intrinsically disordered protein CcdA

Unlike globular proteins, mutational effects on the function of Intrinsically Disordered Proteins (IDPs) are not well-studied. Deep Mutational Scanning of a yeast surface displayed mutant library yields insights into sequence-function relationships in the CcdA IDP. The approach enables facile prediction of interface residues and local structural signatures of the bound conformation. In contrast to previous titration-based approaches which use a number of ligand concentrations, we show that use of a single rationally chosen ligand concentration can provide quantitative estimates of relative binding constants for large numbers of protein variants. This is because the extended interface of IDP ensures that energetic effects of point mutations are spread over a much smaller range than for globular proteins. Our data also provides insights into the much-debated role of helicity and disorder in partner binding of IDPs. Based on this exhaustive mutational sensitivity dataset, a rudimentary model was developed in an attempt to predict mutational effects on binding affinity of IDPs that form alpha-helical structures upon binding.