VoroCNN: Deep convolutional neural network built on 3D Voronoi tessellation of protein structures

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.

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.

VoroIF-GNN: Voronoi tessellation-derived protein-protein interface assessment using a graph neural network

We present VoroIF-GNN (Voronoi InterFace Graph Neural Network), a novel method for assessing inter-subunit interfaces in a structural model of a protein-protein complex, relying solely on the input structure without any additional information. Given a multimeric protein structural model, we derive interface contacts from the Voronoi tessellation of atomic balls, construct a graph of those contacts, and predict the accuracy of every contact using an attention-based GNN. The contact-level predictions are then summarized to produce whole interface-level scores. VoroIF-GNN was blindly tested for its ability to estimate the accuracy of protein complexes during CASP15 and showed strong performance in selecting the best multimeric model out of many. The method implementation is freely available at https://kliment-olechnovic.github.io/voronota/expansion_js/.

Intelligent Protein Design and Molecular Characterization Techniques: A Comprehensive Review

In recent years, the widespread application of artificial intelligence algorithms in protein structure, function prediction, and de novo protein design has significantly accelerated the process of intelligent protein design and led to many noteworthy achievements. This advancement in protein intelligent design holds great potential to accelerate the development of new drugs, enhance the efficiency of biocatalysts, and even create entirely new biomaterials. Protein characterization is the key to the performance of intelligent protein design. However, there is no consensus on the most suitable characterization method for intelligent protein design tasks. This review describes the methods, characteristics, and representative applications of traditional descriptors, sequence-based and structure-based protein characterization. It discusses their advantages, disadvantages, and scope of application. It is hoped that this could help researchers to better understand the limitations and application scenarios of these methods, and provide valuable references for choosing appropriate protein characterization techniques for related research in the field, so as to better carry out protein research.

Tree-Invent: A Novel Multipurpose Molecular Generative Model Constrained with a Topological Tree

De novo molecular design plays an important role in drug discovery. Here, a novel generative model, Tree-Invent, was proposed to integrate topological constraints in the generation of a molecular graph. In this model, a molecular graph is represented as a topological tree in which a ring system, a nonring atom, and a chemical bond are regarded as the ring node, single node, and edge, respectively. The molecule generation is driven by three independent submodels for carrying out operations of node addition, ring generation, and node connection. One unique feature of the generative model is that the topological tree structure can be specified as a constraint for structure generation, which provides more precise control of structure generation. Combined with reinforcement learning, the Tree-Invent model could efficiently explore targeted chemical space. Moreover, the Tree-Invent model is flexible enough to be used in versatile molecule design settings such as scaffold decoration, scaffold hopping, and linker generation.

Telomere-to-Telomere genome assemblies of human-infecting Encephalitozoon species

BACKGROUND

Microsporidia are diverse spore forming, fungal-related obligate intracellular pathogens infecting a wide range of hosts. This diversity is reflected at the genome level with sizes varying by an order of magnitude, ranging from less than 3 Mb in Encephalitozoon species (the smallest known in eukaryotes) to more than 50 Mb in Edhazardia spp. As a paradigm of genome reduction in eukaryotes, the small Encephalitozoon genomes have attracted much attention with investigations revealing gene dense, repeat- and intron-poor genomes characterized by a thorough pruning of molecular functions no longer relevant to their obligate intracellular lifestyle. However, because no Encephalitozoon genome has been sequenced from telomere-to-telomere and since no methylation data is available for these species, our understanding of their overall genetic and epigenetic architectures is incomplete.

METHODS

In this study, we sequenced the complete genomes from telomere-to-telomere of three human-infecting Encephalitozoon spp. -E. intestinalis ATCC 50506, E. hellem ATCC 50604 and E. cuniculi ATCC 50602- using short and long read platforms and leveraged the data generated as part of the sequencing process to investigate the presence of epigenetic markers in these genomes. We also used a mixture of sequence- and structure-based computational approaches, including protein structure prediction, to help identify which Encephalitozoon proteins are involved in telomere maintenance, epigenetic regulation, and heterochromatin formation.

RESULTS

The Encephalitozoon chromosomes were found capped by TTAGG 5-mer telomeric repeats followed by telomere associated repeat elements (TAREs) flanking hypermethylated ribosomal RNA (rRNA) gene loci featuring 5-methylcytosines (5mC) and 5-hemimethylcytosines (5hmC), themselves followed by lesser methylated subtelomeres and hypomethylated chromosome cores. Strong nucleotide biases were identified between the telomeres/subtelomeres and chromosome cores with significant changes in GC/AT, GT/AC and GA/CT contents. The presence of several genes coding for proteins essential to telomere maintenance, epigenetic regulation, and heterochromatin formation was further confirmed in the Encephalitozoon genomes.

CONCLUSION

Altogether, our results strongly support the subtelomeres as sites of heterochromatin formation in Encephalitozoon genomes and further suggest that these species might shutdown their energy-consuming ribosomal machinery while dormant as spores by silencing of the rRNA genes using both 5mC/5hmC methylation and facultative heterochromatin formation at these loci.

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 .

Beyond sequence: Structure-based machine learning

Recent breakthroughs in protein structure prediction demarcate the start of a new era in structural bioinformatics. Combined with various advances in experimental structure determination and the uninterrupted pace at which new structures are published, this promises an age in which protein structure information is as prevalent and ubiquitous as sequence. Machine learning in protein bioinformatics has been dominated by sequence-based methods, but this is now changing to make use of the deluge of rich structural information as input. Machine learning methods making use of structures are scattered across literature and cover a number of different applications and scopes; while some try to address questions and tasks within a single protein family, others aim to capture characteristics across all available proteins. In this review, we look at the variety of structure-based machine learning approaches, how structures can be used as input, and typical applications of these approaches in protein biology. We also discuss current challenges and opportunities in this all-important and increasingly popular field.

Predicting residue-specific qualities of individual protein models using residual neural networks and graph neural networks

The estimation of protein model accuracy (EMA) or model quality assessment (QA) is important for protein structure prediction. An accurate EMA algorithm can guide the refinement of models or pick the best model or best parts of models from a pool of predicted tertiary structures. We developed two novel methods: MASS2 and LAW, for predicting residue-specific or local qualities of individual models, which incorporate residual neural networks and graph neural networks, respectively. These two methods use similar features extracted from protein models but different architectures of neural networks to predict the local accuracies of single models. MASS2 and LAW participated in the QA category of CASP14, and according to our evaluations based on CASP14 official criteria, MASS2 and LAW are the best and second-best methods based on the Z-scores of ASE/100, AUC, and ULR-1.F1. We also evaluated MASS2, LAW, and the residue-specific predicted deviations (between model and native structure) generated by AlphaFold2 on CASP14 AlphaFold2 tertiary structure (TS) models. LAW achieved comparable or better performances compared to the predicted deviations generated by AlphaFold2 on AlphaFold2 TS models, even though LAW was not trained on any AlphaFold2 TS models. Specifically, LAW performed better on AUC and ULR scores, and AlphaFold2 performed better on ASE scores. This means that AlphaFold2 is better at predicting deviations, but LAW is better at classifying accurate and inaccurate residues and detecting unreliable local regions. MASS2 and LAW can be freely accessed from http://dna.cs.miami.edu/MASS2-CASP14/ and http://dna.cs.miami.edu/LAW-CASP14/, respectively.

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.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

A Benchmark Dataset for Evaluating Practical Performance of Model Quality Assessment of Homology Models

Protein structure prediction is an important issue in structural bioinformatics. In this process, model quality assessment (MQA), which estimates the accuracy of the predicted structure, is also practically important. Currently, the most commonly used dataset to evaluate the performance of MQA is the critical assessment of the protein structure prediction (CASP) dataset. However, the CASP dataset does not contain enough targets with high-quality models, and thus cannot sufficiently evaluate the MQA performance in practical use. Additionally, most application studies employ homology modeling because of its reliability. However, the CASP dataset includes models generated by de novo methods, which may lead to the mis-estimation of MQA performance. In this study, we created new benchmark datasets, named a homology models dataset for model quality assessment (HMDM), that contain targets with high-quality models derived using homology modeling. We then benchmarked the performance of the MQA methods using the new datasets and compared their performance to that of the classical selection based on the sequence identity of the template proteins. The results showed that model selection by the latest MQA methods using deep learning is better than selection by template sequence identity and classical statistical potentials. Using HMDM, it is possible to verify the MQA performance for high-accuracy homology models.

ProFitFun: a protein tertiary structure fitness function for quantifying the accuracies of model structures

MOTIVATION

An accurate estimation of the quality of protein model structures typifies as a cornerstone in protein structure prediction regimes. Despite the recent groundbreaking success in the field of protein structure prediction, there are certain prospects for the improvement in model quality estimation at multiple stages of protein structure prediction and thus, to further push the prediction accuracy. Here, a novel approach, named ProFitFun, for assessing the quality of protein models is proposed by harnessing the sequence and structural features of experimental protein structures in terms of the preferences of backbone dihedral angles and relative surface accessibility of their amino acid residues at the tripeptide level. The proposed approach leverages upon the backbone dihedral angle and surface accessibility preferences of the residues by accounting for its N-terminal and C-terminal neighbors in the protein structure. These preferences are used to evaluate protein structures through a machine learning approach and tested on an extensive dataset of diverse proteins.

RESULTS

The approach was extensively validated on a large test dataset (n = 25 005) of protein structures, comprising 23 661 models of 82 non-homologous proteins and 1344 non-homologous experimental structures. In addition, an external dataset of 40 000 models of 200 non-homologous proteins was also used for the validation of the proposed method. Both datasets were further used for benchmarking the proposed method with four different state-of-the-art methods for protein structure quality assessment. In the benchmarking, the proposed method outperformed some state-of-the-art methods in terms of Spearman's and Pearson's correlation coefficients, average GDT-TS loss, sum of z-scores and average absolute difference of predictions over corresponding observed values. The high accuracy of the proposed approach promises a potential use of the sequence and structural features in computational protein design.

AVAILABILITY AND IMPLEMENTATION

http://github.com/KYZ-LSB/ProTerS-FitFun.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

OUP accepted manuscript

DNA repair is an important component of genome integrity and organisms with reduced repair capabilities tend to accumulate mutations at elevated rates. Microsporidia are intracellular parasites exhibiting high levels of genetic divergence postulated to originate from the lack of several proteins, including the heterotrimeric Rad9–Rad1–Hus1 DNA repair clamp. Microsporidian species from the Encephalitozoonidae have undergone severe streamlining with small genomes coding for about 2,000 proteins. The highly divergent sequences found in Microsporidia render functional inferences difficult such that roughly half of these 2,000 proteins have no known function. Using a structural homology-based annotation approach combining protein structure prediction and tridimensional similarity searches, we found that the Rad9–Rad1–Hus1 DNA clamp is present in Microsporidia, together with many other components of the DNA repair machinery previously thought to be missing from these organisms. Altogether, our results indicate that the DNA repair machinery is present and likely functional in Microsporidia.

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

The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching near-experimental accuracy. This success comes from advances transferred from other machine learning areas, as well as methods specifically designed to deal with protein sequences and structures, and their abstractions. Novel emerging approaches include (i) geometric learning, that is, learning on representations such as graphs, three-dimensional (3D) Voronoi tessellations, and point clouds; (ii) pretrained protein language models leveraging attention; (iii) equivariant architectures preserving the symmetry of 3D space; (iv) use of large meta-genome databases; (v) combinations of protein representations; and (vi) finally truly end-to-end architectures, that is, differentiable models starting from a sequence and returning a 3D structure. Here, we provide an overview and our opinion of the novel deep learning approaches developed in the last 2 years and widely used in CASP14.

Spherical convolutions on molecular graphs for protein model quality assessment

Processing information on three-dimensional (3D) objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution operation on these structures. In this work, we propose spherical graph convolutional network that processes 3D models of proteins represented as molecular graphs. In a protein molecule, individual amino acids have common topological elements. This allows us to unambiguously associate each amino acid with a local coordinate system and construct rotation-equivariant spherical filters that operate on angular information between graph nodes. Within the framework of the protein model quality assessment problem, we demonstrate that the proposed spherical convolution method significantly improves the quality of model assessment compared to the standard message-passing approach. It is also comparable to state-of-the-art methods, as we demonstrate on critical assessment of structure prediction benchmarks. The proposed technique operates only on geometric features of protein 3D models. This makes it universal and applicable to any other geometric-learning task where the graph structure allows constructing local coordinate systems. The method is available at https://team.inria.fr/nano-d/software/s-gcn/.

High-accuracy protein structure prediction in CASP14

The application of state-of-the-art deep-learning approaches to the protein modeling problem has expanded the "high-accuracy" category in CASP14 to encompass all targets. Building on the metrics used for high-accuracy assessment in previous CASPs, we evaluated the performance of all groups that submitted models for at least 10 targets across all difficulty classes, and judged the usefulness of those produced by AlphaFold2 (AF2) as molecular replacement search models with AMPLE. Driven by the qualitative diversity of the targets submitted to CASP, we also introduce DipDiff as a new measure for the improvement in backbone geometry provided by a model versus available templates. Although a large leap in high-accuracy is seen due to AF2, the second-best method in CASP14 out-performed the best in CASP13, illustrating the role of community-based benchmarking in the development and evolution of the protein structure prediction field.

Fast and effective protein model refinement using deep graph neural networks

Protein model refinement is the last step applied to improve the quality of a predicted protein model. Currently the most successful refinement methods rely on extensive conformational sampling and thus, take hours or days to refine even a single protein model. Here we propose a fast and effective model refinement method that applies GNN (graph neural networks) to predict refined inter-atom distance probability distribution from an initial model and then rebuilds 3D models from the predicted distance distribution. Tested on the CASP (Critical Assessment of Structure Prediction) refinement targets, our method has comparable accuracy as two leading human groups Feig and Baker, but runs substantially faster. Our method may refine one protein model within ~11 minutes on 1 CPU while Baker needs ~30 hours on 60 CPUs and Feig needs ~16 hours on 1 GPU. Finally, our study shows that GNN outperforms ResNet (convolutional residual neural networks) for model refinement when very limited conformational sampling is allowed.

The impact of structural bioinformatics tools and resources on SARS-CoV-2 research and therapeutic strategies

SARS-CoV-2 is the causative agent of COVID-19, the ongoing global pandemic. It has posed a worldwide challenge to human health as no effective treatment is currently available to combat the disease. Its severity has led to unprecedented collaborative initiatives for therapeutic solutions against COVID-19. Studies resorting to structure-based drug design for COVID-19 are plethoric and show good promise. Structural biology provides key insights into 3D structures, critical residues/mutations in SARS-CoV-2 proteins, implicated in infectivity, molecular recognition and susceptibility to a broad range of host species. The detailed understanding of viral proteins and their complexes with host receptors and candidate epitope/lead compounds is the key to developing a structure-guided therapeutic design. Since the discovery of SARS-CoV-2, several structures of its proteins have been determined experimentally at an unprecedented speed and deposited in the Protein Data Bank. Further, specialized structural bioinformatics tools and resources have been developed for theoretical models, data on protein dynamics from computer simulations, impact of variants/mutations and molecular therapeutics. Here, we provide an overview of ongoing efforts on developing structural bioinformatics tools and resources for COVID-19 research. We also discuss the impact of these resources and structure-based studies, to understand various aspects of SARS-CoV-2 infection and therapeutic development. These include (i) understanding differences between SARS-CoV-2 and SARS-CoV, leading to increased infectivity of SARS-CoV-2, (ii) deciphering key residues in the SARS-CoV-2 involved in receptor-antibody recognition, (iii) analysis of variants in host proteins that affect host susceptibility to infection and (iv) analyses facilitating structure-based drug and vaccine design against SARS-CoV-2.

Improved Protein Model Quality Assessment By Integrating Sequential And Pairwise Features Using Deep Learning

MOTIVATION

Accurately estimating protein model quality in the absence of experimental structure is not only important for model evaluation and selection, but also useful for model refinement. Progress has been steadily made by introducing new features and algorithms (especially deep neural networks), but the accuracy of quality assessment (QA) is still not very satisfactory, especially local QA on hard protein targets.

RESULTS

We propose a new single-model-based QA method ResNetQA for both local and global quality assessment. Our method predicts model quality by integrating sequential and pairwise features using a deep neural network composed of both 1 D and 2 D convolutional residual neural networks (ResNet). The 2 D ResNet module extracts useful information from pairwise features such as model-derived distance maps, co-evolution information, and predicted distance potential from sequences. The 1 D ResNet is used to predict local (global) model quality from sequential features and pooled pairwise information generated by 2 D ResNet. Tested on the CASP12 and CASP13 datasets, our experimental results show that our method greatly outperforms existing state-of-the-art methods. Our ablation studies indicate that the 2 D ResNet module and pairwise features play an important role in improving model quality assessment.

AVAILABILITY

https://github.com/AndersJing/ResNetQA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.