Prediction of protein assemblies, the next frontier: The CASP14-CAPRI experiment

Recent advances and challenges in protein complex model accuracy estimation

Estimation of model accuracy plays a crucial role in protein structure prediction, aiming to evaluate the quality of predicted protein structure models accurately and objectively. This process is not only key to screening candidate models that are close to the real structure, but also provides guidance for further optimization of protein structures. With the significant advancements made by AlphaFold2 in monomer structure, the problem of single-domain protein structure prediction has been widely solved. Correspondingly, the importance of assessing the quality of single-domain protein models decreased, and the research focus has shifted to estimation of model accuracy of protein complexes. In this review, our goal is to provide a comprehensive overview of the reference and statistical metrics, as well as representative methods, and the current challenges within four distinct facets (Topology Global Score, Interface Total Score, Interface Residue-Wise Score, and Tertiary Residue-Wise Score) in the field of complex EMA.

Citrullinating enzyme PADI4 and transcriptional repressor RING1B bind in cancer cells

Polycomb groups (PcGs) are transcriptional repressors, formed by a complex of several proteins, involved in multicellular development and cancer epigenetics. One of these proteins is the E3 ubiquitin-protein ligase RING1 (or RING1B), associated with the regulation of transcriptional repression and responsible for monoubiquitylation of the histone H2A. On the other hand, PADI4 is one of the human isoforms of a family of enzymes implicated in the conversion of arginine to citrulline, and it is also involved in the development of glioblastoma, among other types of cancers. In this work, we showed the association of PADI4 and RING1B in the nucleus and cytosol in several cancer cell lines by using immunofluorescence and proximity ligation assays. Furthermore, we demonstrated that binding was hampered in the presence of GSK484, an enzymatic PADI4 inhibitor, suggesting that RING1B could bind to the active site of PADI4, as confirmed by protein-protein docking simulations. In vitro and in silico findings showed that binding to PADI4 occurred for the isolated fragments corresponding to both the N-terminal (residues 1-221) and C-terminal (residues 228-336) regions of RING1B. Binding to PADI4 was also hampered by GSK484, as shown by isothermal titration calorimetry (ITC) experiments for the sole N-terminal region, and by both NMR and ITC for the C-terminal one. The dissociation constants between PADI4 and any of the two isolated RING1B fragments were in the low micromolar range (~2-10 μM), as measured by fluorescence and ITC. The interaction between RING1B and PADI4 might imply citrullination of the former, leading to several biological consequences, as well as being of potential therapeutic relevance for improving cancer treatment with the generation of new antigens.

SARS-CoV-2 spike does not interact with the T cell receptor or directly activate T cells

Suggested edit: SARS-CoV-2infection can induce multisystem inflammatory syndrome in children, which resembles superantigen-induced toxic shock syndrome. Recent work has suggested that the SARS-CoV-2 spike (S) protein could act as a superantigen by binding T cell receptors (TCRs) and inducing broad antigen-independent T cell responses. Structure-based computational modeling identified potential TCR-binding sites near the S receptor-binding domain, in addition to a site with homology to known neurotoxins. We experimentally examined the mechanism underpinning this theory-the direct interaction between the TCR and S protein. Surface plasmon resonance of recombinantly expressed S protein and TCR revealed no detectable binding. Orthogonally, we pseudotyped lentiviruses with SARS-CoV-2 S in both wild-type and prefusion-stabilized forms, demonstrated their functionality in a cell line assay, and observed no transduction, activation, or stimulation of proliferation of CD8+ T cells. We conclude that it is unlikely that the SARS-CoV-2 spike protein engages nonspecifically with TCRs or has superantigenic character.

Induction of the Mdm2 gene and protein by kinase signaling pathways is repressed by the pVHL tumor suppressor

The tumor suppressor von Hippel-Lindau, pVHL, is a multifaceted protein. One function is to dock to the hypoxia-inducible transcription factor (HIF) and recruit a larger protein complex that destabilizes HIF via ubiquitination, preventing angiogenesis and tumor development. pVHL also binds to the tumor suppressor p53 to activate specific p53 target genes. The oncogene Mdm2 impairs the formation of the p53-pVHL complex and activation of downstream genes by conjugating nedd8 to pVHL. While Mdm2 can impact p53 and pVHL, how pVHL may impact Mdm2 is unclear. Like p53 somatic mutations, point mutations are evident in pVHL that are common in renal clear cell carcinomas (RCC). In patients with RCC, Mdm2 levels are elevated, and we examined whether there was a relationship between Mdm2 and pVHL. TCGA and DepMap analysis revealed that mdm2 gene expression was elevated in RCC with vhl point mutations or copy number loss. In pVHL reconstituted or deleted isogenetically match RCC or MEF cell lines, Mdm2 was decreased in the presence of pVHL. Furthermore, through analysis using genetic and pharmacological approaches, we show that pVHL represses Mdm2 gene expression by blocking the MAPK-Ets signaling pathway and blocks Akt-mediated phosphorylation and stabilization of Mdm2. Mdm2 inhibition results in an increase in the p53-p21 pathway to impede cell growth. This finding shows how pVHL can indirectly impact the function of Mdm2 by regulating signaling pathways to restrict cell growth.

Computational tools to predict context-specific protein complexes

Interactions between thousands of proteins define cells' protein-protein interaction (PPI) network. Some of these interactions lead to the formation of protein complexes. It is challenging to identify a protein complex in a haystack of protein-protein interactions, and it is even more difficult to predict all protein complexes of the complexome. Simulations and machine learning approaches try to crack these problems by looking at the PPI network or predicted protein structures. Clustering of PPI networks led to the first protein complex predictions, while most recently, atomistic models of protein complexes and deep-learning-based structure prediction methods have also emerged. The simulation of PPI level interactions even enables the quantitative prediction of protein complexes. These methods, the required data sources, and their potential future developments are discussed in this review.

PPI3D: a web server for searching, analyzing and modeling protein-protein, protein-peptide and protein-nucleic acid interactions

Structure-resolved protein interactions with other proteins, peptides and nucleic acids are key for understanding molecular mechanisms. The PPI3D web server enables researchers to query preprocessed and clustered structural data, analyze the results and make homology-based inferences for protein interactions. PPI3D offers three interaction exploration modes: (i) all interactions for proteins homologous to the query, (ii) interactions between two proteins or their homologs and (iii) interactions within a specific PDB entry. The server allows interactive analysis of the identified interactions in both summarized and detailed manner. This includes protein annotations, structures, the interface residues and the corresponding contact surface areas. In addition, users can make inferences about residues at the interaction interface for the query protein(s) from the sequence alignments and homology models. The weekly updated PPI3D database includes all the interaction interfaces and binding sites from PDB, clustered based on both protein sequence and structural similarity, yielding non-redundant datasets without loss of alternative interaction modes. Consequently, the PPI3D users avoid being flooded with redundant information, a typical situation for intensely studied proteins. Furthermore, PPI3D provides a possibility to download user-defined sets of interaction interfaces and analyze them locally. The PPI3D web server is available at https://bioinformatics.lt/ppi3d.

Quantum Chemistry-Based Protein-Protein Docking without Empirical Parameters

This study developed a novel protein-protein docking approach based on quantum chemistry. To judge the appropriateness of complex structures, we introduced two criterion values, EV1 and EV2, computed using the fragment molecular orbital method without any empirical parameters. These criterion values enable us to search complex structures in which patterns of the electrostatic potential of the two proteins are optimally aligned at their interface. The performance of our method was validated using 53 complexes in a benchmark set provided for protein-protein docking. When employing bound state structures, docking success rates reached 64% for EV1 and 76% for EV2. On the other hand, when employing unbound state structures, docking success rates reached 13% for EV1 and 17% for EV2.

Unveiling the Ro60-Ro52 complex

The coexistence within a subcellular complex of inter-cellular proteins Ro60, responsible for preserving ncRNA quality, and Ro52, involved in intracellular proteolysis, has been a subject of ongoing debate. Employing molecular docking in tandem with experimental methods like Quartz Crystal Microbalance with Dissipation (QCM-D), Proximity Ligation Assay (PLA), and Indirect Immunofluorescence (IIF), we reveal the presence of Ro60 associating with Ro52 within the cytoplasm. This result unveils the formation of a weak transient complex with a Ka ≈ (3.7 ± 0.3) x 106 M-1, where the toroid-shaped Ro60 structure interacts with the Ro52's Fc receptor, aligning horizontally within the PRY-SPRY domains of the Ro52's homodimer. The stability of this complex relies on the interaction between Ro52 chain A and specific Ro60 residues, such as K133, W177, or L185, vital in the Ro60-YRNA bond. These findings bridge the role of Ro60 in YRNA management with Ro52's function in intracellular proteolysis, emphasizing the potential impact of transient complexes on cellular pathways. See also the graphical abstract(Fig. 1).

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

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

SurfPro-NN: A 3D point cloud neural network for the scoring of protein-protein docking models based on surfaces features and protein language models

Protein-protein interactions (PPI) play a crucial role in numerous key biological processes, and the structure of protein complexes provides valuable clues for in-depth exploration of molecular-level biological processes. Protein-protein docking technology is widely used to simulate the spatial structure of proteins. However, there are still challenges in selecting candidate decoys that closely resemble the native structure from protein-protein docking simulations. In this study, we introduce a docking evaluation method based on three-dimensional point cloud neural networks named SurfPro-NN, which represents protein structures as point clouds and learns interaction information from protein interfaces by applying a point cloud neural network. With the continuous advancement of deep learning in the field of biology, a series of knowledge-rich pre-trained models have emerged. We incorporate protein surface representation models and language models into our approach, greatly enhancing feature representation capabilities and achieving superior performance in protein docking model scoring tasks. Through comprehensive testing on public datasets, we find that our method outperforms state-of-the-art deep learning approaches in protein-protein docking model scoring. Not only does it significantly improve performance, but it also greatly accelerates training speed. This study demonstrates the potential of our approach in addressing protein interaction assessment problems, providing strong support for future research and applications in the field of biology.

ZEPPI: Proteome-scale sequence-based evaluation of protein-protein interaction models

We introduce ZEPPI (Z-score Evaluation of Protein-Protein Interfaces), a framework to evaluate structural models of a complex based on sequence coevolution and conservation involving residues in protein-protein interfaces. The ZEPPI score is calculated by comparing metrics for an interface to those obtained from randomly chosen residues. Since contacting residues are defined by the structural model, this obviates the need to account for indirect interactions. Further, although ZEPPI relies on species-paired multiple sequence alignments, its focus on interfacial residues allows it to leverage quite shallow alignments. ZEPPI can be implemented on a proteome-wide scale and is applied here to millions of structural models of dimeric complexes in the Escherichia coli and human interactomes found in the PrePPI database. PrePPI's scoring function is based primarily on the evaluation of protein-protein interfaces, and ZEPPI adds a new feature to this analysis through the incorporation of evolutionary information. ZEPPI performance is evaluated through applications to experimentally determined complexes and to decoys from the CASP-CAPRI experiment. As we discuss, the standard CAPRI scores used to evaluate docking models are based on model quality and not on the ability to give yes/no answers as to whether two proteins interact. ZEPPI is able to detect weak signals from PPI models that the CAPRI scores define as incorrect and, similarly, to identify potential PPIs defined as low confidence by the current PrePPI scoring function. A number of examples that illustrate how the combination of PrePPI and ZEPPI can yield functional hypotheses are provided.

Multilevel Framework for Analysis of Protein Folding Involving Disulfide Bond Formation

In this study, a three-layered multicenter ONIOM approach is implemented to characterize the naive folding pathway of bovine pancreatic trypsin inhibitor (BPTI). Each layer represents a distinct level of theory, where the initial layer, encompassing the entire protein, is modeled by a general all-atom force-field GFN-FF. An intermediate electronic structure layer consisting of three multicenter fragments is introduced with the state-of-the-art semiempirical tight-binding method GFN2-xTB. Higher accuracy, specifically addressing the breaking and formation of the three disulfide bonds, is achieved at the innermost layer using the composite DFT method r2SCAN-3c. Our analysis sheds light on the structural stability of BPTI, particularly the significance of interlinking disulfide bonds. The accuracy and efficiency of the multicenter QM/SQM/MM approach are benchmarked using the oxidative formation of cystine. For the folding pathway of BPTI, relative stabilities are investigated through the calculation of free energy contributions for selected intermediates, focusing on the impact of the disulfide bond. Our results highlight the intricate trade-off between accuracy and computational cost, demonstrating that the multicenter ONIOM approach provides a well-balanced and comprehensive solution to describe electronic structure effects in biomolecular systems. We conclude that multiscale energy landscape exploration provides a robust methodology for the study of intriguing biological targets.

Deep learning in modeling protein complex structures: From contact prediction to end-to-end approaches

Protein-protein interactions play crucial roles in many biological processes. Traditionally, protein complex structures are normally built by protein-protein docking. With the rapid development of artificial intelligence and its great success in monomer protein structure prediction, deep learning has widely been applied to modeling protein-protein complex structures through inter-protein contact prediction and end-to-end approaches in the past few years. This article reviews the recent advances of deep-learning-based approaches in modeling protein-protein complex structures as well as their advantages and limitations. Challenges and possible future directions are also briefly discussed in applying deep learning for the prediction of protein complex structures.

Assembly of Protein Complexes in and on the Membrane with Predicted Spatial Arrangement Constraints

Membrane proteins play crucial roles in various cellular processes, and their interactions with other proteins in and on the membrane are essential for their proper functioning. While an increasing number of structures of more membrane proteins are being determined, the available structure data is still sparse. To gain insights into the mechanisms of membrane protein complexes, computational docking methods are necessary due to the challenge of experimental determination. Here, we introduce Mem-LZerD, a rigid-body membrane docking algorithm designed to take advantage of modern membrane modeling and protein docking techniques to facilitate the docking of membrane protein complexes. Mem-LZerD is based on the LZerD protein docking algorithm, which has been constantly among the top servers in many rounds of CAPRI protein docking assessment. By employing a combination of geometric hashing, newly constrained by the predicted membrane height and tilt angle, and model scoring accounting for the energy of membrane insertion, we demonstrate the capability of Mem-LZerD to model diverse membrane protein-protein complexes. Mem-LZerD successfully performed unbound docking on 13 of 21 (61.9%) transmembrane complexes in an established benchmark, more than shown by previous approaches. It was additionally tested on new datasets of 44 transmembrane complexes and 92 peripheral membrane protein complexes, of which it successfully modeled 35 (79.5%) and 15 (16.3%) complexes respectively. When non-blind orientations of peripheral targets were included, the number of successes increased to 54 (58.7%). We further demonstrate that Mem-LZerD produces complex models which are suitable for molecular dynamics simulation. Mem-LZerD is made available at https://lzerd.kiharalab.org.

Deep learning for advancing peptide drug development: Tools and methods in structure prediction and design

Peptides can bind challenging disease targets with high affinity and specificity, offering enormous opportunities for addressing unmet medical needs. However, peptides' unique features, including smaller size, increased structural flexibility, and limited data availability, pose additional challenges to the design process compared to proteins. This review explores the dynamic field of peptide therapeutics, leveraging deep learning to enhance structure prediction and design. Our exploration encompasses various facets of peptide research, ranging from dataset curation handling to model development. As deep learning technologies become more refined, we channel our efforts into peptide structure prediction and design, aligning with the fundamental principles of structure-activity relationships in drug development. To guide researchers in harnessing the potential of deep learning to advance peptide drug development, our insights comprehensively explore current challenges and future directions of peptide therapeutics.

Protein structure accuracy estimation using geometry-complete perceptron networks

Estimating the accuracy of protein structural models is a critical task in protein bioinformatics. The need for robust methods in the estimation of protein model accuracy (EMA) is prevalent in the field of protein structure prediction, where computationally-predicted structures need to be screened rapidly for the reliability of the positions predicted for each of their amino acid residues and their overall quality. Current methods proposed for EMA are either coupled tightly to existing protein structure prediction methods or evaluate protein structures without sufficiently leveraging the rich, geometric information available in such structures to guide accuracy estimation. In this work, we propose a geometric message passing neural network referred to as the geometry-complete perceptron network for protein structure EMA (GCPNet-EMA), where we demonstrate through rigorous computational benchmarks that GCPNet-EMA's accuracy estimations are 47% faster and more than 10% (6%) more correlated with ground-truth measures of per-residue (per-target) structural accuracy compared to baseline state-of-the-art methods for tertiary (multimer) structure EMA including AlphaFold 2. The source code and data for GCPNet-EMA are available on GitHub, and a public web server implementation is freely available.

Machine Learning Methods in Protein-Protein Docking

An exponential increase in the number of publications that address artificial intelligence (AI) usage in life sciences has been noticed in recent years, while new modeling techniques are constantly being reported. The potential of these methods is vast-from understanding fundamental cellular processes to discovering new drugs and breakthrough therapies. Computational studies of protein-protein interactions, crucial for understanding the operation of biological systems, are no exception in this field. However, despite the rapid development of technology and the progress in developing new approaches, many aspects remain challenging to solve, such as predicting conformational changes in proteins, or more "trivial" issues as high-quality data in huge quantities.Therefore, this chapter focuses on a short introduction to various AI approaches to study protein-protein interactions, followed by a description of the most up-to-date algorithms and programs used for this purpose. Yet, given the considerable pace of development in this hot area of computational science, at the time you read this chapter, the development of the algorithms described, or the emergence of new (and better) ones should come as no surprise.

Sampling and Scoring in Protein-Protein Docking

Protein-protein docking is considered one of the most important techniques supporting experimental proteomics. Recent developments in the field of computer science helped to improve this computational technique so that it better handles the complexity of protein nature. Sampling algorithms are responsible for the generation of numerous protein-protein ensembles. Unfortunately, a primary docking output comprises a set of both near-native poses and decoys. Application of the efficient scoring function helps to differentiate poses with the most favorable properties from those that are very unlikely to represent a natural state of the complex. This chapter explains the importance of sampling and scoring in the process of protein-protein docking. Moreover, it summarizes advances in the field.

Prediction of protein assemblies by structure sampling followed by interface-focused scoring

Proteins often function as part of permanent or transient multimeric complexes, and understanding function of these assemblies requires knowledge of their three-dimensional structures. While the ability of AlphaFold to predict structures of individual proteins with unprecedented accuracy has revolutionized structural biology, modeling structures of protein assemblies remains challenging. To address this challenge, we developed a protocol for predicting structures of protein complexes involving model sampling followed by scoring focused on the subunit-subunit interaction interface. In this protocol, we diversified AlphaFold models by varying construction and pairing of multiple sequence alignments as well as increasing the number of recycles. In cases when AlphaFold failed to assemble a full protein complex or produced unreliable results, additional diverse models were constructed by docking of monomers or subcomplexes. All the models were then scored using a newly developed method, VoroIF-jury, which relies only on structural information. Notably, VoroIF-jury is independent of AlphaFold self-assessment scores and therefore can be used to rank models originating from different structure prediction methods. We tested our protocol in CASP15 and obtained top results, significantly outperforming the standard AlphaFold-Multimer pipeline. Analysis of our results showed that the accuracy of our assembly models was capped mainly by structure sampling rather than model scoring. This observation suggests that better sampling, especially for the antibody-antigen complexes, may lead to further improvement. Our protocol is expected to be useful for modeling and/or scoring protein assemblies.

Assessment of three-dimensional RNA structure prediction in CASP15

The prediction of RNA three-dimensional structures remains an unsolved problem. Here, we report assessments of RNA structure predictions in CASP15, the first CASP exercise that involved RNA structure modeling. Forty-two predictor groups submitted models for at least one of twelve RNA-containing targets. These models were evaluated by the RNA-Puzzles organizers and, separately, by a CASP-recruited team using metrics (GDT, lDDT) and approaches (Z-score rankings) initially developed for assessment of proteins and generalized here for RNA assessment. The two assessments independently ranked the same predictor groups as first (AIchemy_RNA2), second (Chen), and third (RNAPolis and GeneSilico, tied); predictions from deep learning approaches were significantly worse than these top ranked groups, which did not use deep learning. Further analyses based on direct comparison of predicted models to cryogenic electron microscopy (cryo-EM) maps and x-ray diffraction data support these rankings. With the exception of two RNA-protein complexes, models submitted by CASP15 groups correctly predicted the global fold of the RNA targets. Comparisons of CASP15 submissions to designed RNA nanostructures as well as molecular replacement trials highlight the potential utility of current RNA modeling approaches for RNA nanotechnology and structural biology, respectively. Nevertheless, challenges remain in modeling fine details such as noncanonical pairs, in ranking among submitted models, and in prediction of multiple structures resolved by cryo-EM or crystallography.

Impact of AlphaFold on structure prediction of protein complexes: The CASP15-CAPRI experiment

We present the results for CAPRI Round 54, the 5th joint CASP-CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homodimers, 3 homo-trimers, 13 heterodimers including 3 antibody-antigen complexes, and 7 large assemblies. On average ~70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21 941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their five best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High-quality models were produced for about 40% of the targets compared to 8% two years earlier. This remarkable improvement is due to the wide use of the AlphaFold2 and AlphaFold2-Multimer software and the confidence metrics they provide. Notably, expanded sampling of candidate solutions by manipulating these deep learning inference engines, enriching multiple sequence alignments, or integration of advanced modeling tools, enabled top performing groups to exceed the performance of a standard AlphaFold2-Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.

Energy landscapes for proteins described by the UNRES coarse-grained potential

The self-assembly of proteins is encoded in the underlying potential energy surface (PES), from which we can predict structure, dynamics, and thermodynamic properties. However, the corresponding analysis becomes increasingly challenging with larger protein sizes, due to the computational time required, which grows significantly with the number of atoms. Coarse-grained models offer an attractive approach to reduce the computational cost. In this Feature Article, we describe our implementation of the UNited RESidue (UNRES) coarse-grained potential in the Cambridge energy landscapes software. We have applied this framework to explore the energy landscapes of four proteins that exhibit native states involving different secondary structures. Here we have tested the ability of the UNRES potential to represent the global energy landscape of proteins containing up to 100 amino acid residues. The resulting potential energy landscapes exhibit good agreement with experiment, with low-lying minima close to the PDB geometries and to results obtained using the all-atom AMBER force field. The new program interfaces will allow us to investigate larger biomolecules in future work, using the UNRES potential in combination with all the methodology available in the computational energy landscapes framework.

Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15

Estimating the accuracy of quaternary structural models of protein complexes and assemblies (EMA) is important for predicting quaternary structures and applying them to studying protein function and interaction. The pairwise similarity between structural models is proven useful for estimating the quality of protein tertiary structural models, but it has been rarely applied to predicting the quality of quaternary structural models. Moreover, the pairwise similarity approach often fails when many structural models are of low quality and similar to each other. To address the gap, we developed a hybrid method (MULTICOM_qa) combining a pairwise similarity score (PSS) and an interface contact probability score (ICPS) based on the deep learning inter-chain contact prediction for estimating protein complex model accuracy. It blindly participated in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 and performed very well in estimating the global structure accuracy of assembly models. The average per-target correlation coefficient between the model quality scores predicted by MULTICOM_qa and the true quality scores of the models of CASP15 assembly targets is 0.66. The average per-target ranking loss in using the predicted quality scores to rank the models is 0.14. It was able to select good models for most targets. Moreover, several key factors (i.e., target difficulty, model sampling difficulty, skewness of model quality, and similarity between good/bad models) for EMA are identified and analyzed. The results demonstrate that combining the multi-model method (PSS) with the complementary single-model method (ICPS) is a promising approach to EMA.

The impact of AI-based modeling on the accuracy of protein assembly prediction: Insights from CASP15

In CASP15, 87 predictors submitted around 11 000 models on 41 assembly targets. The community demonstrated exceptional performance in overall fold and interface contact predictions, achieving an impressive success rate of 90% (compared to 31% in CASP14). This remarkable accomplishment is largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines. To evaluate the added value of participating methods, we compared the community models to the baseline AF2-Multimer predictor. In over 1/3 of cases, the community models were superior to the baseline predictor. The main reasons for this improved performance were the use of custom-built multiple sequence alignments, optimized AF2-Multimer sampling, and the manual assembly of AF2-Multimer-built subcomplexes. The best three groups, in order, are Zheng, Venclovas, and Wallner. Zheng and Venclovas reached a 73.2% success rate over all (41) cases, while Wallner attained 69.4% success rate over 36 cases. Nonetheless, challenges remain in predicting structures with weak evolutionary signals, such as nanobody-antigen, antibody-antigen, and viral complexes. Expectedly, modeling large complexes also remains challenging due to their high memory compute demands. In addition to the assembly category, we assessed the accuracy of modeling interdomain interfaces in the tertiary structure prediction targets. Models on seven targets featuring 17 unique interfaces were analyzed. Best predictors achieved a 76.5% success rate, with the UM-TBM group being the leader. In the interdomain category, we observed that the predictors faced challenges, as in the case of the assembly category, when the evolutionary signal for a given domain pair was weak or the structure was large. Overall, CASP15 witnessed unprecedented improvement in interface modeling, reflecting the AI revolution seen in CASP14.

CoDock-Ligand: combined template-based docking and CNN-based scoring in ligand binding prediction

For ligand binding prediction, it is crucial for molecular docking programs to integrate template-based modeling with a precise scoring function. Here, we proposed the CoDock-Ligand docking method that combines template-based modeling and the GNINA scoring function, a Convolutional Neural Network-based scoring function, for the ligand binding prediction in CASP15. Among the 21 targets, we obtained successful predictions in top 5 submissions for 14 targets and partially successful predictions for 4 targets. In particular, for the most complicated target, H1114, which contains 56 metal cofactors and small molecules, our docking method successfully predicted the binding of most ligands. Analysis of the failed systems showed that the predicted receptor protein presented conformational changes in the backbone and side chains of the binding site residues, which may cause large structural deviations in the ligand binding prediction. In summary, our hybrid docking scheme was efficiently adapted to the ligand binding prediction challenges in CASP15.

Enhancing alphafold-multimer-based protein complex structure prediction with MULTICOM in CASP15

To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine its outputs. MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural predictions by using both traditional sequence alignments and Foldseek-based structure alignments, ranks structural predictions through multiple complementary metrics, and refines the structural predictions via a Foldseek structure alignment-based refinement method. The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. MULTICOM_qa ranked 3rd among 26 CASP15 server predictors and MULTICOM_human ranked 7th among 87 CASP15 server and human predictors. The average TM-score of the first predictions submitted by MULTICOM_qa for CASP15 assembly targets is ~0.76, 5.3% higher than ~0.72 of the standard AlphaFold-Multimer. The average TM-score of the best of top 5 predictions submitted by MULTICOM_qa is ~0.80, about 8% higher than ~0.74 of the standard AlphaFold-Multimer. Moreover, the Foldseek Structure Alignment-based Multimer structure Generation (FSAMG) method outperforms the widely used sequence alignment-based multimer structure generation.

Assembly of Protein Complexes In and On the Membrane with Predicted Spatial Arrangement Constraints

Membrane proteins play crucial roles in various cellular processes, and their interactions with other proteins in and on the membrane are essential for their proper functioning. While an increasing number of structures of more membrane proteins are being determined, the available structure data is still sparse. To gain insights into the mechanisms of membrane protein complexes, computational docking methods are necessary due to the challenge of experimental determination. Here, we introduce Mem-LZerD, a rigid-body membrane docking algorithm designed to take advantage of modern membrane modeling and protein docking techniques to facilitate the docking of membrane protein complexes. Mem-LZerD is based on the LZerD protein docking algorithm, which has been constantly among the top servers in many rounds of CAPRI protein docking assessment. By employing a combination of geometric hashing, newly constrained by the predicted membrane height and tilt angle, and model scoring accounting for the energy of membrane insertion, we demonstrate the capability of Mem-LZerD to model diverse membrane protein-protein complexes. Mem-LZerD successfully performed unbound docking on 13 of 21 (61.9%) transmembrane complexes in an established benchmark, more than shown by previous approaches. It was additionally tested on new datasets of 44 transmembrane complexes and 92 peripheral membrane protein complexes, of which it successfully modeled 35 (79.5%) and 15 (16.3%) complexes respectively. When non-blind orientations of peripheral targets were included, the number of successes increased to 54 (58.7%). We further demonstrate that Mem-LZerD produces complex models which are suitable for molecular dynamics simulation. Mem-LZerD is made available at https://lzerd.kiharalab.org.

Assessment of three-dimensional RNA structure prediction in CASP15

The prediction of RNA three-dimensional structures remains an unsolved problem. Here, we report assessments of RNA structure predictions in CASP15, the first CASP exercise that involved RNA structure modeling. Forty two predictor groups submitted models for at least one of twelve RNA-containing targets. These models were evaluated by the RNA-Puzzles organizers and, separately, by a CASP-recruited team using metrics (GDT, lDDT) and approaches (Z-score rankings) initially developed for assessment of proteins and generalized here for RNA assessment. The two assessments independently ranked the same predictor groups as first (AIchemy_RNA2), second (Chen), and third (RNAPolis and GeneSilico, tied); predictions from deep learning approaches were significantly worse than these top ranked groups, which did not use deep learning. Further analyses based on direct comparison of predicted models to cryogenic electron microscopy (cryo-EM) maps and X-ray diffraction data support these rankings. With the exception of two RNA-protein complexes, models submitted by CASP15 groups correctly predicted the global fold of the RNA targets. Comparisons of CASP15 submissions to designed RNA nanostructures as well as molecular replacement trials highlight the potential utility of current RNA modeling approaches for RNA nanotechnology and structural biology, respectively. Nevertheless, challenges remain in modeling fine details such as non-canonical pairs, in ranking among submitted models, and in prediction of multiple structures resolved by cryo-EM or crystallography.

Adaptive Ensemble Refinement of Protein Structures in High Resolution Electron Microscopy Density Maps with Radical Augmented Molecular Dynamics Flexible Fitting

Recent advances in cryo-electron microscopy (cryo-EM) have enabled modeling macromolecular complexes that are essential components of the cellular machinery. The density maps derived from cryo-EM experiments are often integrated with manual, knowledge-driven or artificial intelligence-driven and physics-guided computational methods to build, fit, and refine molecular structures. Going beyond a single stationary-structure determination scheme, it is becoming more common to interpret the experimental data with an ensemble of models that contributes to an average observation. Hence, there is a need to decide on the quality of an ensemble of protein structures on-the-fly while refining them against the density maps. We introduce such an adaptive decision-making scheme during the molecular dynamics flexible fitting (MDFF) of biomolecules. Using RADICAL-Cybertools, the new RADICAL augmented MDFF implementation (R-MDFF) is examined in high-performance computing environments for refinement of two prototypical protein systems, adenylate kinase and carbon monoxide dehydrogenase. For these test cases, use of multiple replicas in flexible fitting with adaptive decision making in R-MDFF improves the overall correlation to the density by 40% relative to the refinements of the brute-force MDFF. The improvements are particularly significant at high, 2-3 Å map resolutions. More importantly, the ensemble model captures key features of biologically relevant molecular dynamics that are inaccessible to a single-model interpretation. Finally, the pipeline is applicable to systems of growing sizes, which is demonstrated using ensemble refinement of capsid proteins from the chimpanzee adenovirus. The overhead for decision making remains low and robust to computing environments. The software is publicly available on GitHub and includes a short user guide to install R-MDFF on different computing environments, from local Linux-based workstations to high-performance computing environments.

The Impact of AI-Based Modeling on the Accuracy of Protein Assembly Prediction: Insights from CASP15

In CASP15, 87 predictors submitted around 11,000 models on 41 assembly targets. The community demonstrated exceptional performance in overall fold and interface contact prediction, achieving an impressive success rate of 90% (compared to 31% in CASP14). This remarkable accomplishment is largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines. To evaluate the added value of participating methods, we compared the community models to the baseline AF2-Multimer predictor. In over 1/3 of cases the community models were superior to the baseline predictor. The main reasons for this improved performance were the use of custom-built multiple sequence alignments, optimized AF2-Multimer sampling, and the manual assembly of AF2-Multimer-built subcomplexes. The best three groups, in order, are Zheng, Venclovas and Wallner. Zheng and Venclovas reached a 73.2% success rate over all (41) cases, while Wallner attained 69.4% success rate over 36 cases. Nonetheless, challenges remain in predicting structures with weak evolutionary signals, such as nanobody-antigen, antibody-antigen, and viral complexes. Expectedly, modeling large complexes remains also challenging due to their high memory compute demands. In addition to the assembly category, we assessed the accuracy of modeling interdomain interfaces in the tertiary structure prediction targets. Models on seven targets featuring 17 unique interfaces were analyzed. Best predictors achieved the 76.5% success rate, with the UM-TBM group being the leader. In the interdomain category, we observed that the predictors faced challenges, as in the case of the assembly category, when the evolutionary signal for a given domain pair was weak or the structure was large. Overall, CASP15 witnessed unprecedented improvement in interface modeling, reflecting the AI revolution seen in CASP14.

Discriminating physiological from non-physiological interfaces in structures of protein complexes: A community-wide study

Reliably scoring and ranking candidate models of protein complexes and assigning their oligomeric state from the structure of the crystal lattice represent outstanding challenges. A community-wide effort was launched to tackle these challenges. The latest resources on protein complexes and interfaces were exploited to derive a benchmark dataset consisting of 1677 homodimer protein crystal structures, including a balanced mix of physiological and non-physiological complexes. The non-physiological complexes in the benchmark were selected to bury a similar or larger interface area than their physiological counterparts, making it more difficult for scoring functions to differentiate between them. Next, 252 functions for scoring protein-protein interfaces previously developed by 13 groups were collected and evaluated for their ability to discriminate between physiological and non-physiological complexes. A simple consensus score generated using the best performing score of each of the 13 groups, and a cross-validated Random Forest (RF) classifier were created. Both approaches showed excellent performance, with an area under the Receiver Operating Characteristic (ROC) curve of 0.93 and 0.94, respectively, outperforming individual scores developed by different groups. Additionally, AlphaFold2 engines recalled the physiological dimers with significantly higher accuracy than the non-physiological set, lending support to the reliability of our benchmark dataset annotations. Optimizing the combined power of interface scoring functions and evaluating it on challenging benchmark datasets appears to be a promising strategy.

PointDE: Protein Docking Evaluation Using 3D Point Cloud Neural Network

Protein-protein interactions (PPIs) play essential roles in many vital movements and the determination of protein complex structure is helpful to discover the mechanism of PPI. Protein-protein docking is being developed to model the structure of the protein. However, there is still a challenge to selecting the near-native decoys generated by protein-protein docking. Here, we propose a docking evaluation method using 3D point cloud neural network named PointDE. PointDE transforms protein structure to the point cloud. Using the state-of-the-art point cloud network architecture and a novel grouping mechanism, PointDE can capture the geometries of the point cloud and learn the interaction information from the protein interface. On public datasets, PointDE surpasses the state-of-the-art method using deep learning. To further explore the ability of our method in different types of protein structures, we developed a new dataset generated by high-quality antibody-antigen complexes. The result in this antibody-antigen dataset shows the strong performance of PointDE, which will be helpful for the understanding of PPI mechanisms.

Modeling protein-nucleic acid complexes with extremely large conformational changes using Flex-LZerD

Proteins and nucleic acids are key components in many processes in living cells, and interactions between proteins and nucleic acids are often crucial pathway components. In many cases, large flexibility of proteins as they interact with nucleic acids is key to their function. To understand the mechanisms of these processes, it is necessary to consider the 3D atomic structures of such protein-nucleic acid complexes. When such structures are not yet experimentally determined, protein docking can be used to computationally generate useful structure models. However, such docking has long had the limitation that the consideration of flexibility is usually limited to small movements or to small structures. We previously developed a method of flexible protein docking which could model ordered proteins which undergo large-scale conformational changes, which we also showed was compatible with nucleic acids. Here, we elaborate on the ability of that pipeline, Flex-LZerD, to model specifically interactions between proteins and nucleic acids, and demonstrate that Flex-LZerD can model more interactions and types of conformational change than previously shown.

Improved prediction of MHC-peptide binding using protein language models

Major histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system. Predicting whether a given peptide binds to an MHC molecule is an important step in the above process and has motivated the introduction of many computational approaches to address this problem. NetMHCPan, a pan-specific model for predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using shallow neural networks. The recent successful results of Deep Learning (DL) methods, especially Natural Language Processing (NLP-based) pretrained models in various applications, including protein structure determination, motivated us to explore their use in this problem. Specifically, we consider the application of deep learning models pretrained on large datasets of protein sequences to predict MHC Class I-peptide binding. Using the standard performance metrics in this area, and the same training and test sets, we show that our models outperform NetMHCpan4.1, currently considered as the-state-of-the-art.

PrePPI: A Structure Informed Proteome-wide Database of Protein-Protein Interactions

We present an updated version of the Predicting Protein-Protein Interactions (PrePPI) webserver which predicts PPIs on a proteome-wide scale. PrePPI combines structural and non-structural evidence within a Bayesian framework to compute a likelihood ratio (LR) for essentially every possible pair of proteins in a proteome; the current database is for the human interactome. The structural modeling (SM) component is derived from template-based modeling and its application on a proteome-wide scale is enabled by a unique scoring function used to evaluate a putative complex. The updated version of PrePPI leverages AlphaFold structures that are parsed into individual domains. As has been demonstrated in earlier applications, PrePPI performs extremely well as measured by receiver operating characteristic curves derived from testing on E. coli and human protein-protein interaction (PPI) databases. A PrePPI database of ∼1.3 million human PPIs can be queried with a webserver application that comprises multiple functionalities for examining query proteins, template complexes, 3D models for predicted complexes, and related features (https://honiglab.c2b2.columbia.edu/PrePPI). PrePPI is a state-of-the-art resource that offers an unprecedented structure-informed view of the human interactome.

Integrative modeling of diverse protein-peptide systems using CABS-dock

The CABS model can be applied to a wide range of protein-protein and protein-peptide molecular modeling tasks, such as simulating folding pathways, predicting structures, docking, and analyzing the structural dynamics of molecular complexes. In this work, we use the CABS-dock tool in two diverse modeling tasks: 1) predicting the structures of amyloid protofilaments and 2) identifying cleavage sites in the peptide substrates of proteolytic enzymes. In the first case, simulations of the simultaneous docking of amyloidogenic peptides indicated that the CABS model can accurately predict the structures of amyloid protofilaments which have an in-register parallel architecture. Scoring based on a combination of symmetry criteria and estimated interaction energy values for bound monomers enables the identification of protofilament models that closely match their experimental structures for 5 out of 6 analyzed systems. For the second task, it has been shown that CABS-dock coarse-grained docking simulations can be used to identify the positions of cleavage sites in the peptide substrates of proteolytic enzymes. The cleavage site position was correctly identified for 12 out of 15 analyzed peptides. When combined with sequence-based methods, these docking simulations may lead to an efficient way of predicting cleavage sites in degraded proteins. The method also provides the atomic structures of enzyme-substrate complexes, which can give insights into enzyme-substrate interactions that are crucial for the design of new potent inhibitors.

Narrow funnel-like interaction energy distribution is an indicator of specific protein interaction partner

Protein interaction networks underlie countless biological mechanisms. However, most protein interaction predictions are based on biological evidence that are biased to well-known protein interaction or physical evidence that exhibits low accuracy for weak interactions and requires high computational power. In this study, a novel method has been suggested to predict protein interaction partners by investigating narrow funnel-like interaction energy distribution. In this study, it was demonstrated that various protein interactions including kinases and E3 ubiquitin ligases have narrow funnel-like interaction energy distribution. To analyze protein interaction distribution, modified scores of iRMS and TM-score are introduced. Then, using these scores, algorithm and deep learning model for prediction of protein interaction partner and substrate of kinase and E3 ubiquitin ligase were developed. The prediction accuracy was similar to or even better than that of yeast two-hybrid screening. Ultimately, this knowledge-free protein interaction prediction method will broaden our understanding of protein interaction networks.

Enhancing AlphaFold-Multimer-based Protein Complex Structure Prediction with MULTICOM in CASP15

AlphaFold-Multimer has emerged as the state-of-the-art tool for predicting the quaternary structure of protein complexes (assemblies or multimers) since its release in 2021. To further enhance the AlphaFold-Multimer-based complex structure prediction, we developed a new quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine the outputs generated by AlphaFold2-Multimer. Specifically, MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural models by using both traditional sequence alignments and new Foldseek-based structure alignments, ranks structural models through multiple complementary metrics, and refines the structural models via a Foldseek structure alignment-based refinement method. The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. Our server (MULTICOM_qa) ranked 3rd among 26 CASP15 server predictors and our human predictor (MULTICOM_human) ranked 7th among 87 CASP15 server and human predictors. The average TM-score of the first models predicted by MULTICOM_qa for CASP15 assembly targets is ~0.76, 5.3% higher than ~0.72 of the standard AlphaFold-Multimer. The average TM-score of the best of top 5 models predicted by MULTICOM_qa is ~0.80, about 8% higher than ~0.74 of the standard AlphaFold-Multimer. Moreover, the novel Foldseek Structure Alignment-based Model Generation (FSAMG) method based on AlphaFold-Multimer outperforms the widely used sequence alignment-based model generation. The source code of MULTICOM is available at: https://github.com/BioinfoMachineLearning/MULTICOM3.

Critical Assessment of Methods for Predicting the 3D Structure of Proteins and Protein Complexes

Advances in a scientific discipline are often measured by small, incremental steps. In this review, we report on two intertwined disciplines in the protein structure prediction field, modeling of single chains and modeling of complexes, that have over decades emulated this pattern, as monitored by the community-wide blind prediction experiments CASP and CAPRI. However, over the past few years, dramatic advances were observed for the accurate prediction of single protein chains, driven by a surge of deep learning methodologies entering the prediction field. We review the mainscientific developments that enabled these recent breakthroughs and feature the important role of blind prediction experiments in building up and nurturing the structure prediction field. We discuss how the new wave of artificial intelligence-based methods is impacting the fields of computational and experimental structural biology and highlight areas in which deep learning methods are likely to lead to future developments, provided that major challenges are overcome.

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.

Recent advances in predicting and modeling protein-protein interactions

Protein-protein interactions (PPIs) drive biological processes, and disruption of PPIs can cause disease. With recent breakthroughs in structure prediction and a deluge of genomic sequence data, computational methods to predict PPIs and model spatial structures of protein complexes are now approaching the accuracy of experimental approaches for permanent interactions and show promise for elucidating transient interactions. As we describe here, the key to this success is rich evolutionary information deciphered from thousands of homologous sequences that coevolve in interacting partners. This covariation signal, revealed by sophisticated statistical and machine learning (ML) algorithms, predicts physiological interactions. Accurate artificial intelligence (AI)-based modeling of protein structures promises to provide accurate 3D models of PPIs at a proteome-wide scale.

The opportunities and challenges posed by the new generation of deep learning-based protein structure predictors

The function of proteins can often be inferred from their three-dimensional structures. Experimental structural biologists spent decades studying these structures, but the accelerated pace of protein sequencing continuously increases the gaps between sequences and structures. The early 2020s saw the advent of a new generation of deep learning-based protein structure prediction tools that offer the potential to predict structures based on any number of protein sequences. In this review, we give an overview of the impact of this new generation of structure prediction tools, with examples of the impacted field in the life sciences. We discuss the novel opportunities and new scientific and technical challenges these tools present to the broader scientific community. Finally, we highlight some potential directions for the future of computational protein structure prediction.

Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15

Estimating the accuracy of quaternary structural models of protein complexes and assemblies (EMA) is important for predicting quaternary structures and applying them to studying protein function and interaction. The pairwise similarity between structural models is proven useful for estimating the quality of protein tertiary structural models, but it has been rarely applied to predicting the quality of quaternary structural models. Moreover, the pairwise similarity approach often fails when many structural models are of low quality and similar to each other. To address the gap, we developed a hybrid method (MULTICOM_qa) combining a pairwise similarity score (PSS) and an interface contact probability score (ICPS) based on the deep learning inter-chain contact prediction for estimating protein complex model accuracy. It blindly participated in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 and ranked first out of 24 predictors in estimating the global accuracy of assembly models. The average per-target correlation coefficient between the model quality scores predicted by MULTICOM_qa and the true quality scores of the models of CASP15 assembly targets is 0.66. The average per-target ranking loss in using the predicted quality scores to rank the models is 0.14. It was able to select good models for most targets. Moreover, several key factors (i.e., target difficulty, model sampling difficulty, skewness of model quality, and similarity between good/bad models) for EMA are identified and analayzed. The results demonstrate that combining the multi-model method (PSS) with the complementary single-model method (ICPS) is a promising approach to EMA. The source code of MULTICOM_qa is available at https://github.com/BioinfoMachineLearning/MULTICOM_qa .

Computational prediction of disordered binding regions

One of the key features of intrinsically disordered regions (IDRs) is their ability to interact with a broad range of partner molecules. Multiple types of interacting IDRs were identified including molecular recognition fragments (MoRFs), short linear sequence motifs (SLiMs), and protein-, nucleic acids- and lipid-binding regions. Prediction of binding IDRs in protein sequences is gaining momentum in recent years. We survey 38 predictors of binding IDRs that target interactions with a diverse set of partners, such as peptides, proteins, RNA, DNA and lipids. We offer a historical perspective and highlight key events that fueled efforts to develop these methods. These tools rely on a diverse range of predictive architectures that include scoring functions, regular expressions, traditional and deep machine learning and meta-models. Recent efforts focus on the development of deep neural network-based architectures and extending coverage to RNA, DNA and lipid-binding IDRs. We analyze availability of these methods and show that providing implementations and webservers results in much higher rates of citations/use. We also make several recommendations to take advantage of modern deep network architectures, develop tools that bundle predictions of multiple and different types of binding IDRs, and work on algorithms that model structures of the resulting complexes.

PrePPI: A structure informed proteome-wide database of protein-protein interactions

We present an updated version of the Predicting Protein-Protein Interactions (PrePPI) webserver which predicts PPIs on a proteome-wide scale. PrePPI combines structural and non-structural clues within a Bayesian framework to compute a likelihood ratio (LR) for essentially every possible pair of proteins in a proteome; the current database is for the human interactome. The structural modeling (SM) clue is derived from templatebased modeling and its application on a proteome-wide scale is enabled by a unique scoring function used to evaluate a putative complex. The updated version of PrePPI leverages AlphaFold structures that are parsed into individual domains. As has been demonstrated in earlier applications, PrePPI performs extremely well as measured by receiver operating characteristic curves derived from testing on E. coli and human protein-protein interaction (PPI) databases. A PrePPI database of ~1.3 million human PPIs can be queried with a webserver application that comprises multiple functionalities for examining query proteins, template complexes, 3D models for predicted complexes, and related features ( https://honiglab.c2b2.columbia.edu/PrePPI ). PrePPI is a state-of- the-art resource that offers an unprecedented structure-informed view of the human interactome.

Graphic Abstract

Growing ecosystem of deep learning methods for modeling protein-protein interactions

Numerous cellular functions rely on protein-protein interactions. Efforts to comprehensively characterize them remain challenged however by the diversity of molecular recognition mechanisms employed within the proteome. Deep learning has emerged as a promising approach for tackling this problem by exploiting both experimental data and basic biophysical knowledge about protein interactions. Here, we review the growing ecosystem of deep learning methods for modeling protein interactions, highlighting the diversity of these biophysically informed models and their respective trade-offs. We discuss recent successes in using representation learning to capture complex features pertinent to predicting protein interactions and interaction sites, geometric deep learning to reason over protein structures and predict complex structures, and generative modeling to design de novo protein assemblies. We also outline some of the outstanding challenges and promising new directions. Opportunities abound to discover novel interactions, elucidate their physical mechanisms, and engineer binders to modulate their functions using deep learning and, ultimately, unravel how protein interactions orchestrate complex cellular behaviors.

Simulation toolkits at the molecular scale for trans-scale thermal signaling

Thermogenesis is a physiological activity of releasing heat that originates from intracellular biochemical reactions. Recent experimental studies discovered that externally applied heat changes intracellular signaling locally, resulting in global changes in cell morphology and signaling. Therefore, we hypothesize an inevitable contribution of thermogenesis in modulating biological system functions throughout the spatial scales from molecules to individual organisms. One key issue examining the hypothesis, namely, the "trans-scale thermal signaling," resides at the molecular scale on the amount of heat released via individual reactions and by which mechanism the heat is employed for cellular function operations. This review introduces atomistic simulation tool kits for studying the mechanisms of thermal signaling processes at the molecular scale that even state-of-the-art experimental methodologies of today are hardly accessible. We consider biological processes and biomolecules as potential heat sources in cells, such as ATP/GTP hydrolysis and multiple biopolymer complex formation and disassembly. Microscopic heat release could be related to mesoscopic processes via thermal conductivity and thermal conductance. Additionally, theoretical simulations to estimate these thermal properties in biological membranes and proteins are introduced. Finally, we envisage the future direction of this research field.

Pairwise and Multi-chain Protein Docking Enhanced Using LZerD Web Server

Interactions of proteins with other macromolecules have important structural and functional roles in the basic processes of living cells. To understand and elucidate the mechanisms of interactions, it is important to know the 3D structures of the complexes. Proteomes contain numerous protein-protein complexes, for which experimentally determined structures often do not exist. Computational techniques can be a practical alternative to obtain useful complex structure models. Here, we present a web server that provides access to the LZerD and Multi-LZerD protein docking tools, which can perform both pairwise and multi-chain docking. The web server is user-friendly, with options to visualize the distribution and structures of binding poses of top-scoring models. The LZerD web server is available at https://lzerd.kiharalab.org . This chapter dictates the algorithm and step-by-step procedure to model the monomeric structures with AttentiveDist, and also provides the detail of pairwise LZerD docking, and multi-LZerD. This also provided case studies for each of the three modules.

DeepRank-GNN: a graph neural network framework to learn patterns in protein-protein interfaces

MOTIVATION

Gaining structural insights into the protein-protein interactome is essential to understand biological phenomena and extract knowledge for rational drug design or protein engineering. We have previously developed DeepRank, a deep-learning framework to facilitate pattern learning from protein-protein interfaces using convolutional neural network (CNN) approaches. However, CNN is not rotation invariant and data augmentation is required to desensitize the network to the input data orientation which dramatically impairs the computation performance. Representing protein-protein complexes as atomic- or residue-scale rotation invariant graphs instead enables using graph neural networks (GNN) approaches, bypassing those limitations.

RESULTS

We have developed DeepRank-GNN, a framework that converts protein-protein interfaces from PDB 3D coordinates files into graphs that are further provided to a pre-defined or user-defined GNN architecture to learn problem-specific interaction patterns. DeepRank-GNN is designed to be highly modularizable, easily customized and is wrapped into a user-friendly python3 package. Here, we showcase DeepRank-GNN's performance on two applications using a dedicated graph interaction neural network: (i) the scoring of docking poses and (ii) the discriminating of biological and crystal interfaces. In addition to the highly competitive performance obtained in those tasks as compared to state-of-the-art methods, we show a significant improvement in speed and storage requirement using DeepRank-GNN as compared to DeepRank.

AVAILABILITY AND IMPLEMENTATION

DeepRank-GNN is freely available from https://github.com/DeepRank/DeepRank-GNN.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Domain-Based Protein Docking with Extremely Large Conformational Changes

Proteins are key components in many processes in living cells, and physical interactions with other proteins and nucleic acids often form key parts of their functions. In many cases, large flexibility of proteins as they interact is key to their function. To understand the mechanisms of these processes, it is necessary to consider the 3D structures of such protein complexes. When such structures are not yet experimentally determined, protein docking has long been present to computationally generate useful structure models. However, protein docking has long had the limitation that the consideration of flexibility is usually limited to very small movements or very small structures. Methods have been developed which handle minor flexibility via normal mode or other structure sampling, but new methods are required to model ordered proteins which undergo large-scale conformational changes to elucidate their function at the molecular level. Here, we present Flex-LZerD, a framework for docking such complexes. Via partial assembly multidomain docking and an iterative normal mode analysis admitting curvilinear motions, we demonstrate the ability to model the assembly of a variety of protein-protein and protein-nucleic acid complexes.