DeepMainmast: integrated protocol of protein structure modeling for cryo-EM with deep learning and structure prediction.

Three-dimensional structure modeling from maps is an indispensable step for studying proteins and their complexes with cryogenic electron microscopy. Although the resolution of determined cryogenic electron microscopy maps has generally improved, there are still many cases where tracing protein main chains is difficult, even in maps determined at a near-atomic resolution. Here we developed a protein structure modeling method, DeepMainmast, which employs deep learning to capture the local map features of amino acids and atoms to assist main-chain tracing. Moreover, we integrated AlphaFold2 with the de novo density tracing protocol to combine their complementary strengths and achieved even higher accuracy than each method alone. Additionally, the protocol is able to accurately assign the chain identity to the structure models of homo-multimers, which is not a trivial task for existing methods.

CryoREAD: de novo structure modeling for nucleic acids in cryo-EM maps using deep learning.

DNA and RNA play fundamental roles in various cellular processes, where their three-dimensional structures provide information critical to understanding the molecular mechanisms of their functions. Although an increasing number of nucleic acid structures and their complexes with proteins are determined by cryogenic electron microscopy (cryo-EM), structure modeling for DNA and RNA remains challenging particularly when the map is determined at a resolution coarser than atomic level. Moreover, computational methods for nucleic acid structure modeling are relatively scarce. Here, we present CryoREAD, a fully automated de novo DNA/RNA atomic structure modeling method using deep learning. CryoREAD identifies phosphate, sugar and base positions in a cryo-EM map using deep learning, which are traced and modeled into a three-dimensional structure. When tested on cryo-EM maps determined at 2.0 to 5.0 Å resolution, CryoREAD built substantially more accurate models than existing methods. We also applied the method to cryo-EM maps of biomolecular complexes in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Residue-wise local quality estimation for protein models from cryo-EM maps.

An increasing number of protein structures are being determined by cryogenic electron microscopy (cryo-EM). Although the resolution of determined cryo-EM density maps is improving in general, there are still many cases where amino acids of a protein are assigned with different levels of confidence. Here we developed a method that identifies potential misassignment of residues in the map, including residue shifts along an otherwise correct main-chain trace. The score, named DAQ, computes the likelihood that the local density corresponds to different amino acids, atoms, and secondary structures, estimated via deep learning, and assesses the consistency of the amino acid assignment in the protein structure model with that likelihood. When DAQ was applied to different versions of model structures in the Protein Data Bank that were derived from the same density maps, a clear improvement in the DAQ score was observed in the newer versions of the models. DAQ also found potential misassignment errors in a substantial number of deposited protein structure models built into cryo-EM maps.

Cryo-EM model validation recommendations based on outcomes of the 2019 EMDataResource challenge.

This paper describes outcomes of the 2019 Cryo-EM Model Challenge. The goals were to (1) assess the quality of models that can be produced from cryogenic electron microscopy (cryo-EM) maps using current modeling software, (2) evaluate reproducibility of modeling results from different software developers and users and (3) compare performance of current metrics used for model evaluation, particularly Fit-to-Map metrics, with focus on near-atomic resolution. Our findings demonstrate the relatively high accuracy and reproducibility of cryo-EM models derived by 13 participating teams from four benchmark maps, including three forming a resolution series (1.8 to 3.1 Å). The results permit specific recommendations to be made about validating near-atomic cryo-EM structures both in the context of individual experiments and structure data archives such as the Protein Data Bank. We recommend the adoption of multiple scoring parameters to provide full and objective annotation and assessment of the model, reflective of the observed cryo-EM map density.

Enhancing cryo-EM maps with 3D deep generative networks for assisting protein structure modeling.

MOTIVATION: The tertiary structures of an increasing number of biological macromolecules have been determined using cryo-electron microscopy (cryo-EM). However, there are still many cases where the resolution is not high enough to model the molecular structures with standard computational tools. If the resolution obtained is near the empirical borderline (3-4.5 Å), improvement in the map quality facilitates structure modeling. RESULTS: We report EM-GAN, a novel approach that modifies an input cryo-EM map to assist protein structure modeling. The method uses a 3D generative adversarial network (GAN) that has been trained on high- and low-resolution density maps to learn the density patterns, and modifies the input map to enhance its suitability for modeling. The method was tested extensively on a dataset of 65 EM maps in the resolution range of 3-6 Å and showed substantial improvements in structure modeling using popular protein structure modeling tools. AVAILABILITY AND IMPLEMENTATION: https://github.com/kiharalab/EM-GAN, Google Colab: https://tinyurl.com/3ccxpttx.

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.

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.

Genotype & phenotype in Lowe Syndrome: specific OCRL1 patient mutations differentially impact cellular phenotypes.

Lowe Syndrome (LS) is a lethal genetic disorder caused by mutations in the OCRL1 gene which encodes the lipid 5' phosphatase Ocrl1. Patients exhibit a characteristic triad of symptoms including eye, brain and kidney abnormalities with renal failure as the most common cause of premature death. Over 200 OCRL1 mutations have been identified in LS, but their specific impact on cellular processes is unknown. Despite observations of heterogeneity in patient symptom severity, there is little understanding of the correlation between genotype and its impact on phenotype. Here, we show that different mutations had diverse effects on protein localization and on triggering LS cellular phenotypes. In addition, some mutations affecting specific domains imparted unique characteristics to the resulting mutated protein. We also propose that certain mutations conformationally affect the 5'-phosphatase domain of the protein, resulting in loss of enzymatic activity and causing common and specific phenotypes (a conformational disease scenario). This study is the first to show the differential effect of patient 5'-phosphatase mutations on cellular phenotypes and introduces a conformational disease component in LS. This work provides a framework that explains symptom heterogeneity and can help stratify patients as well as to produce a more accurate prognosis depending on the nature and location of the mutation within the OCRL1 gene.

Protein secondary structure detection in intermediate-resolution cryo-EM maps using deep learning.

Although structures determined at near-atomic resolution are now routinely reported by cryo-electron microscopy (cryo-EM), many density maps are determined at an intermediate resolution, and extracting structure information from these maps is still a challenge. We report a computational method, Emap2sec, that identifies the secondary structures of proteins (α-helices, ß-sheets and other structures) in EM maps at resolutions of between 5 and 10 Å. Emap2sec uses a three-dimensional deep convolutional neural network to assign secondary structure to each grid point in an EM map. We tested Emap2sec on EM maps simulated from 34 structures at resolutions of 6.0 and 10.0 Å, as well as on 43 maps determined experimentally at resolutions of between 5.0 and 9.5 Å. Emap2sec was able to clearly identify the secondary structures in many maps tested, and showed substantially better performance than existing methods.

Protein contact map refinement for improving structure prediction using generative adversarial networks.

MOTIVATION: Protein structure prediction remains as one of the most important problems in computational biology and biophysics. In the past few years, protein residue-residue contact prediction has undergone substantial improvement, which has made it a critical driving force for successful protein structure prediction. Boosting the accuracy of contact predictions has, therefore, become the forefront of protein structure prediction. RESULTS: We show a novel contact map refinement method, ContactGAN, which uses Generative Adversarial Networks (GAN). ContactGAN was able to make a significant improvement over predictions made by recent contact prediction methods when tested on three datasets including protein structure modeling targets in CASP13 and CASP14. We show improvement of precision in contact prediction, which translated into improvement in the accuracy of protein tertiary structure models. On the other hand, observed improvement over trRosetta was relatively small, reasons for which are discussed. ContactGAN will be a valuable addition in the structure prediction pipeline to achieve an extra gain in contact prediction accuracy. AVAILABILITY AND IMPLEMENTATION: https://github.com/kiharalab/ContactGAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Protein docking model evaluation by 3D deep convolutional neural networks.

MOTIVATION: Many important cellular processes involve physical interactions of proteins. Therefore, determining protein quaternary structures provide critical insights for understanding molecular mechanisms of functions of the complexes. To complement experimental methods, many computational methods have been developed to predict structures of protein complexes. One of the challenges in computational protein complex structure prediction is to identify near-native models from a large pool of generated models. RESULTS: We developed a convolutional deep neural network-based approach named DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE) for evaluating protein docking models. To evaluate a protein docking model, DOVE scans the protein-protein interface of the model with a 3D voxel and considers atomic interaction types and their energetic contributions as input features applied to the neural network. The deep learning models were trained and validated on docking models available in the ZDock and DockGround databases. Among the different combinations of features tested, almost all outperformed existing scoring functions. AVAILABILITY AND IMPLEMENTATION: Codes available at http://github.com/kiharalab/DOVE, http://kiharalab.org/dove/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Efficient Flexible Fitting Refinement with Automatic Error Fixing for De Novo Structure Modeling from Cryo-EM Density Maps.

Structural modeling of proteins from cryo-electron microscopy (cryo-EM) density maps is one of the challenging issues in structural biology. De novo modeling combined with flexible fitting refinement (FFR) has been widely used to build a structure of new proteins. In de novo prediction, artificial conformations containing local structural errors such as chirality errors, cis peptide bonds, and ring penetrations are frequently generated and cannot be easily removed in the subsequent FFR. Moreover, refinement can be significantly suppressed due to the low mobility of atoms inside the protein. To overcome these problems, we propose an efficient scheme for FFR, in which the local structural errors are fixed first, followed by FFR using an iterative simulated annealing (SA) molecular dynamics protocol with the united atom (UA) model in an implicit solvent model; we call this scheme "SAUA-FFR". The best model is selected from multiple flexible fitting runs with various biasing force constants to reduce overfitting. We apply our scheme to the decoys obtained from MAINMAST and demonstrate an improvement of the best model of eight selected proteins in terms of the root-mean-square deviation, MolProbity score, and RWplus score compared to the original scheme of MAINMAST. Fixing the local structural errors can enhance the formation of secondary structures, and the UA model enables progressive refinement compared to the all-atom model owing to its high mobility in the implicit solvent. The SAUA-FFR scheme realizes efficient and accurate protein structure modeling from medium-resolution maps with less overfitting.

Performance and enhancement of the LZerD protein assembly pipeline in CAPRI 38-46.

We report the performance of the protein docking prediction pipeline of our group and the results for Critical Assessment of Prediction of Interactions (CAPRI) rounds 38-46. The pipeline integrates programs developed in our group as well as other existing scoring functions. The core of the pipeline is the LZerD protein-protein docking algorithm. If templates of the target complex are not found in PDB, the first step of our docking prediction pipeline is to run LZerD for a query protein pair. Meanwhile, in the case of human group prediction, we survey the literature to find information that can guide the modeling, such as protein-protein interface information. In addition to any literature information and binding residue prediction, generated docking decoys were selected by a rank aggregation of statistical scoring functions. The top 10 decoys were relaxed by a short molecular dynamics simulation before submission to remove atom clashes and improve side-chain conformations. In these CAPRI rounds, our group, particularly the LZerD server, showed robust performance. On the other hand, there are failed cases where some other groups were successful. To understand weaknesses of our pipeline, we analyzed sources of errors for failed targets. Since we noted that structure refinement is a step that needs improvement, we newly performed a comparative study of several refinement approaches. Finally, we show several examples that illustrate successful and unsuccessful cases by our group.

MAINMASTseg: Automated Map Segmentation Method for Cryo-EM Density Maps with Symmetry.

For structural interpretation of cryo-electron microscopy (cryo-EM) density maps that contain multiple chains, map segmentation is an important step. If a map is segmented accurately into regions of individual protein components, the structure of each protein can be separately modeled using an existing modeling tool. Here, we developed new software, MAINMASTseg, for segmenting maps with symmetry. MAINMASTseg is an extension of the MAINMAST de novo cryo-EM protein structure modeling tool, which builds protein structures from a graph structure that captures the distribution of salient density points in the map. MAINMASTseg uses this graph and segments the map by considering symmetry corresponding density points in the graph. We tested MAINMASTseg on a data set of 38 experimentally determined EM density maps. MAINMASTseg successfully identified an individual protein unit for the majority of the maps, which was significantly better than two other popular existing methods, Segger and Phenix. The software is made freely available for academic users at http://kiharalab.org/mainmast_seg.

Blind prediction of homo- and hetero-protein complexes: The CASP13-CAPRI experiment.

We present the results for CAPRI Round 46, the third joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of 20 targets including 14 homo-oligomers and 6 heterocomplexes. Eight of the homo-oligomer targets and one heterodimer comprised proteins that could be readily modeled using templates from the Protein Data Bank, often available for the full assembly. The remaining 11 targets comprised 5 homodimers, 3 heterodimers, and two higher-order assemblies. These were more difficult to model, as their prediction mainly involved "ab-initio" docking of subunit models derived from distantly related templates. A total of ~30 CAPRI groups, including 9 automatic servers, submitted on average ~2000 models per target. About 17 groups participated in the CAPRI scoring rounds, offered for most targets, submitting ~170 models per target. The prediction performance, measured by the fraction of models of acceptable quality or higher submitted across all predictors groups, was very good to excellent for the nine easy targets. Poorer performance was achieved by predictors for the 11 difficult targets, with medium and high quality models submitted for only 3 of these targets. A similar performance "gap" was displayed by scorer groups, highlighting yet again the unmet challenge of modeling the conformational changes of the protein components that occur upon binding or that must be accounted for in template-based modeling. Our analysis also indicates that residues in binding interfaces were less well predicted in this set of targets than in previous Rounds, providing useful insights for directions of future improvements.

Modeling the assembly order of multimeric heteroprotein complexes.

Protein-protein interactions are the cornerstone of numerous biological processes. Although an increasing number of protein complex structures have been determined using experimental methods, relatively fewer studies have been performed to determine the assembly order of complexes. In addition to the insights into the molecular mechanisms of biological function provided by the structure of a complex, knowing the assembly order is important for understanding the process of complex formation. Assembly order is also practically useful for constructing subcomplexes as a step toward solving the entire complex experimentally, designing artificial protein complexes, and developing drugs that interrupt a critical step in the complex assembly. There are several experimental methods for determining the assembly order of complexes; however, these techniques are resource-intensive. Here, we present a computational method that predicts the assembly order of protein complexes by building the complex structure. The method, named Path-LzerD, uses a multimeric protein docking algorithm that assembles a protein complex structure from individual subunit structures and predicts assembly order by observing the simulated assembly process of the complex. Benchmarked on a dataset of complexes with experimental evidence of assembly order, Path-LZerD was successful in predicting the assembly pathway for the majority of the cases. Moreover, when compared with a simple approach that infers the assembly path from the buried surface area of subunits in the native complex, Path-LZerD has the strong advantage that it can be used for cases where the complex structure is not known. The path prediction accuracy decreased when starting from unbound monomers, particularly for larger complexes of five or more subunits, for which only a part of the assembly path was correctly identified. As the first method of its kind, Path-LZerD opens a new area of computational protein structure modeling and will be an indispensable approach for studying protein complexes.

Geometrical Conversion of the EGFR Extracellular Domain by Adiabatic Mapping Combining Normal Mode Analysis of the Elastic Network Model and Energy Optimization.

The activation of epidermal growth factor receptor (EGFR) involves the geometrical conversion of the extracellular domain (ECD) from the tethered to the extended forms with the dynamic rearrangement of the relative positions of four subdomains (SDs); however, this conversion process has not yet been thoroughly understood. We compare the two different forms of the X-ray crystal structures of ECD and simulate the ECD conversion process using adiabatic mapping that combines normal mode analysis of the elastic network model (ENM-NMA) and energy optimization. A comparison of the crystal structures reveals the rigidity of the intradomain geometry of the SD-I and -III backbone regardless of the form. The forward mapping from the tethered to the extended forms retains the intradomain geometry of the SD-I and -III backbone and reveals the trends to rearrange the relative positions of SD-I and -III and to dissociate the C-terminal tail of SD-IV from the hairpin loop in SD-II. The reverse mapping from the extended to the tethered forms complements the promotion of ECD conversion in the presence of epidermal growth factor (EGF).

De novo main-chain modeling with MAINMAST in 2015/2016 EM Model Challenge.

Protein tertiary structure modeling is a critical step for the interpretation of three dimensional (3D) election microscopy density. Our group participated the 2015/2016 EM Model Challenge using the MAINMAST software for a de novo main chain modeling. The software generates local dense points using the mean shifting algorithm, and connects them into Cα models by calculating the minimum spanning tree and the longest path. Subsequently, full atom structure models are generated, which are subject to structural refinement. Here, we summarize the qualities of our submitted models and examine successful and unsuccessful models, including 3D models we did not submit to the Challenge. Our protocol using the MAINMAST software was sometimes able to build correct conformations with 3.4-5.1 ŠRMSD. Unsuccessful models had failure of chain traces, however, their Cα positions and some local structures were quite correctly built. For evaluate the quality of the models, the MAINMAST software provides a confidence score for each Cα position from the consensus of top 100 scoring models.

Protein structure model refinement in CASP12 using short and long molecular dynamics simulations in implicit solvent.

Protein structure prediction has matured over years, particularly those which use structure templates for building a model. It can build a model with correct overall conformation in cases where appropriate templates are available. Models with the correct topology can be practically useful for limited purposes that need residue-level accuracy, but further improvement of the models can allow the models to be used in tasks that need detailed structures, such as molecular replacement in X-ray crystallography or structure-based drug screening. Thus, model refinement is an important final step in protein structure prediction to bridge predictions to real-life applications. Model refinement is one of the categories in recent rounds of critical assessment of techniques in protein structure prediction (CASP) and has recently been drawing more attention due to its realized importance. Here we report our group's performance in the refinement category in CASP12. Our method is based on inexpensive short molecular dynamics (MD) simulations in implicit solvent. Our performance in CASP12 was among the top, which was consistent with the previous round, CASP11. Our method with short MD runs achieved comparable performance with other methods that used longer simulations. Detailed analyses found that improvements typically occurred in entire regions of a structure rather than only in flexible loop regions. The remaining challenge in the structure refinement includes large conformational refinement which involves substantial motions of secondary structure elements or domains.