Score_set: A CAPRI benchmark for scoring protein complexes

Strengths and limitations of web servers for the modeling of TCRpMHC complexes

Cellular immunity relies on the ability of a T-cell receptor (TCR) to recognize a peptide (p) presented by a class I major histocompatibility complex (MHC) receptor on the surface of a cell. The TCR-peptide-MHC (TCRpMHC) interaction is a crucial step in activating T-cells, and the structural characteristics of these molecules play a significant role in determining the specificity and affinity of this interaction. Hence, obtaining 3D structures of TCRpMHC complexes offers valuable insights into various aspects of cellular immunity and can facilitate the development of T-cell-based immunotherapies. Here, we aimed to compare three popular web servers for modeling the structures of TCRpMHC complexes, namely ImmuneScape (IS), TCRpMHCmodels, and TCRmodel2, to examine their strengths and limitations. Each method employs a different modeling strategy, including docking, homology modeling, and deep learning. The accuracy of each method was evaluated by reproducing the 3D structures of a dataset of 87 TCRpMHC complexes with experimentally determined crystal structures available on the Protein Data Bank (PDB). All selected structures were limited to human MHC alleles, presenting a diverse set of peptide ligands. A detailed analysis of produced models was conducted using multiple metrics, including Root Mean Square Deviation (RMSD) and standardized assessments from CAPRI and DockQ. Special attention was given to the complementarity-determining region (CDR) loops of the TCRs and to the peptide ligands, which define most of the unique features and specificity of a given TCRpMHC interaction. Our study provides an optimistic view of the current state-of-the-art for TCRpMHC modeling but highlights some remaining challenges that must be addressed in order to support the future application of these tools for TCR engineering and computer-aided design of TCR-based immunotherapies.

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.

Human cytokine and coronavirus nucleocapsid protein interactivity using large-scale virtual screens

Understanding the interactions between SARS-CoV-2 and the human immune system is paramount to the characterization of novel variants as the virus co-evolves with the human host. In this study, we employed state-of-the-art molecular docking tools to conduct large-scale virtual screens, predicting the binding affinities between 64 human cytokines against 17 nucleocapsid proteins from six betacoronaviruses. Our comprehensive in silico analyses reveal specific changes in cytokine-nucleocapsid protein interactions, shedding light on potential modulators of the host immune response during infection. These findings offer valuable insights into the molecular mechanisms underlying viral pathogenesis and may guide the future development of targeted interventions. This manuscript serves as insight into the comparison of deep learning based AlphaFold2-Multimer and the semi-physicochemical based HADDOCK for protein-protein docking. We show the two methods are complementary in their predictive capabilities. We also introduce a novel algorithm for rapidly assessing the binding interface of protein-protein docks using graph edit distance: graph-based interface residue assessment function (GIRAF). The high-performance computational framework presented here will not only aid in accelerating the discovery of effective interventions against emerging viral threats, but extend to other applications of high throughput protein-protein screens.

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.

A Survey of Deep Learning Methods for Estimating the Accuracy of Protein Quaternary Structure Models

The quality prediction of quaternary structure models of a protein complex, in the absence of its true structure, is known as the Estimation of Model Accuracy (EMA). EMA is useful for ranking predicted protein complex structures and using them appropriately in biomedical research, such as protein-protein interaction studies, protein design, and drug discovery. With the advent of more accurate protein complex (multimer) prediction tools, such as AlphaFold2-Multimer and ESMFold, the estimation of the accuracy of protein complex structures has attracted increasing attention. Many deep learning methods have been developed to tackle this problem; however, there is a noticeable absence of a comprehensive overview of these methods to facilitate future development. Addressing this gap, we present a review of deep learning EMA methods for protein complex structures developed in the past several years, analyzing their methodologies, data and feature construction. We also provide a prospective summary of some potential new developments for further improving the accuracy of the EMA methods.

ProInterVal: Validation of Protein-Protein Interfaces through Learned Interface Representations

Proteins are vital components of the biological world and serve a multitude of functions. They interact with other molecules through their interfaces and participate in crucial cellular processes. Disruption of these interactions can have negative effects on organisms, highlighting the importance of studying protein-protein interfaces for developing targeted therapies for diseases. Therefore, the development of a reliable method for investigating protein-protein interactions is of paramount importance. In this work, we present an approach for validating protein-protein interfaces using learned interface representations. The approach involves using a graph-based contrastive autoencoder architecture and a transformer to learn representations of protein-protein interaction interfaces from unlabeled data and then validating them through learned representations with a graph neural network. Our method achieves an accuracy of 0.91 for the test set, outperforming existing GNN-based methods. We demonstrate the effectiveness of our approach on a benchmark data set and show that it provides a promising solution for validating protein-protein interfaces.

A significance score for protein-protein interaction models through random docking

Comparing accuracies of structural protein-protein interaction (PPI) models for different complexes on an absolute scale is a challenge, requiring normalization of scores across structures of different sizes and shapes. To help address this challenge, we have developed a statistical significance metric for docking models, called random-docking (RD) p-value. This score evaluates a PPI model based on how likely a random docking process is to produce a model of better or equal accuracy. The binding partners are randomly docked against each other a large number of times, and the probability of sampling a model of equal or greater accuracy from this reference distribution is the RD p-value. Using a subset of top predicted models from CAPRI (Critical Assessment of PRediction of Interactions) rounds over 2017-2020, we find that the ease of achieving a given root mean squared deviation or DOCKQ score varies considerably by target; achieving the same relative metric can be thousands of times easier for one complex compared to another. In contrast, RD p-values inherently normalize scores for models of different complexes, making them globally comparable. Furthermore, one can calculate RD p-values after generating a reference distribution that accounts for prior information about the interface geometry, such as residues involved in binding, by giving the random-docking process access the same information. Thus, one can decouple improvements in prediction accuracy that arise solely from basic modeling constraints from those due to the rest of the method. We provide efficient code for computing RD p-values at https://github.com/Grigoryanlab/RDP.

DeepRank-GNN-esm: a graph neural network for scoring protein-protein models using protein language model

Motivation

Protein-Protein interactions (PPIs) play critical roles in numerous cellular processes. By modelling the 3D structures of the correspond protein complexes valuable insights can be obtained, providing, e.g. starting points for drug and protein design. One challenge in the modelling process is however the identification of near-native models from the large pool of generated models. To this end we have previously developed DeepRank-GNN, a graph neural network that integrates structural and sequence information to enable effective pattern learning at PPI interfaces. Its main features are related to the Position Specific Scoring Matrices (PSSMs), which are computationally expensive to generate, significantly limits the algorithm's usability.

Results

We introduce here DeepRank-GNN-esm that includes as additional features protein language model embeddings from the ESM-2 model. We show that the ESM-2 embeddings can actually replace the PSSM features at no cost in-, or even better performance on two PPI-related tasks: scoring docking poses and detecting crystal artifacts. This new DeepRank version bypasses thus the need of generating PSSM, greatly improving the usability of the software and opening new application opportunities for systems for which PSSM profiles cannot be obtained or are irrelevant (e.g. antibody-antigen complexes).

Availability and implementation

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

ComplexQA: a deep graph learning approach for protein complex structure assessment

MOTIVATION

In recent years, the end-to-end deep learning method for single-chain protein structure prediction has achieved high accuracy. For example, the state-of-the-art method AlphaFold, developed by Google, has largely increased the accuracy of protein structure predictions to near experimental accuracy in some of the cases. At the same time, there are few methods that can evaluate the quality of protein complexes at the residue level. In particular, evaluating the quality of residues at the interface of protein complexes can lead to a wide range of applications, such as protein function analysis and drug design. In this paper, we introduce a new deep graph neural network-based method ComplexQA, to evaluate the local quality of interfaces for protein complexes by utilizing the residue-level structural information in 3D space and the sequence-level constraints.

RESULTS

We benchmark our method to other state-of-the-art quality assessment approaches on the HAF2 and DBM55-AF2 datasets (high-quality structural models predicted by AlphaFold-Multimer), and the BM5 docking dataset. The experimental results show that our proposed method achieves better or similar performance compared with other state-of-the-art methods, especially on difficult targets which only contain a few acceptable models. Our method is able to suggest a score for each interfac e residue, which demonstrates a powerful assessment tool for the ever-increasing number of protein complexes.

AVAILABILITY

https://github.com/Cao-Labs/ComplexQA.git. Contact: caora@plu.edu.

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.

A gated graph transformer for protein complex structure quality assessment and its performance in CASP15

MOTIVATION

Proteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery.

RESULTS

In this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures.

AVAILABILITY AND IMPLEMENTATION

The source code, data, and pre-trained models are available at https://github.com/jianlin-cheng/DProQA.

GDockScore: a graph-based protein-protein docking scoring function

Summary

Protein complexes play vital roles in a variety of biological processes, such as mediating biochemical reactions, the immune response and cell signalling, with 3D structure specifying function. Computational docking methods provide a means to determine the interface between two complexed polypeptide chains without using time-consuming experimental techniques. The docking process requires the optimal solution to be selected with a scoring function. Here, we propose a novel graph-based deep learning model that utilizes mathematical graph representations of proteins to learn a scoring function (GDockScore). GDockScore was pre-trained on docking outputs generated with the Protein Data Bank biounits and the RosettaDock protocol, and then fine-tuned on HADDOCK decoys generated on the ZDOCK Protein Docking Benchmark. GDockScore performs similarly to the Rosetta scoring function on docking decoys generated using the RosettaDock protocol. Furthermore, state-of-the-art is achieved on the CAPRI score set, a challenging dataset for developing docking scoring functions.

Availability and implementation

The model implementation is available at https://gitlab.com/mcfeemat/gdockscore.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

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.

G-RANK: an equivariant graph neural network for the scoring of protein-protein docking models

Motivation

Protein complex structure prediction is important for many applications in bioengineering. A widely used method for predicting the structure of protein complexes is computational docking. Although many tools for scoring protein-protein docking models have been developed, it is still a challenge to accurately identify near-native models for unknown protein complexes. A recently proposed model called the geometric vector perceptron-graph neural network (GVP-GNN), a subtype of equivariant graph neural networks, has demonstrated success in various 3D molecular structure modeling tasks.

Results

Herein, we present G-RANK, a GVP-GNN-based method for the scoring of protein-protein docking models. When evaluated on two different test datasets, G-RANK achieved a performance competitive with or better than the state-of-the-art scoring functions. We expect G-RANK to be a useful tool for various applications in biological engineering.

Availability and implementation

Source code is available at https://github.com/ha01994/grank.

Contact

kds@kaist.ac.kr.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

MetaScore: A Novel Machine-Learning-Based Approach to Improve Traditional Scoring Functions for Scoring Protein-Protein Docking Conformations

Protein-protein interactions play a ubiquitous role in biological function. Knowledge of the three-dimensional (3D) structures of the complexes they form is essential for understanding the structural basis of those interactions and how they orchestrate key cellular processes. Computational docking has become an indispensable alternative to the expensive and time-consuming experimental approaches for determining the 3D structures of protein complexes. Despite recent progress, identifying near-native models from a large set of conformations sampled by docking-the so-called scoring problem-still has considerable room for improvement. We present MetaScore, a new machine-learning-based approach to improve the scoring of docked conformations. MetaScore utilizes a random forest (RF) classifier trained to distinguish near-native from non-native conformations using their protein-protein interfacial features. The features include physicochemical properties, energy terms, interaction-propensity-based features, geometric properties, interface topology features, evolutionary conservation, and also scores produced by traditional scoring functions (SFs). MetaScore scores docked conformations by simply averaging the score produced by the RF classifier with that produced by any traditional SF. We demonstrate that (i) MetaScore consistently outperforms each of the nine traditional SFs included in this work in terms of success rate and hit rate evaluated over conformations ranked among the top 10; (ii) an ensemble method, MetaScore-Ensemble, that combines 10 variants of MetaScore obtained by combining the RF score with each of the traditional SFs outperforms each of the MetaScore variants. We conclude that the performance of traditional SFs can be improved upon by using machine learning to judiciously leverage protein-protein interfacial features and by using ensemble methods to combine multiple scoring functions.

A scoring function for the prediction of protein complex interfaces based on the neighborhood preferences of amino acids

Proteins often assemble into functional complexes, the structures of which are more difficult to obtain than those of the individual protein molecules. Given the structures of the subunits, it is possible to predict plausible complex models via computational methods such as molecular docking. Assessing the quality of the predicted models is crucial to obtain correct complex structures. Here, an energy-scoring function was developed based on the interfacial residues of structures in the Protein Data Bank. The statistically derived energy function (Nepre) imitates the neighborhood preferences of amino acids, including the types and relative positions of neighboring residues. Based on the preference statistics, a program iNepre was implemented and its performance was evaluated with several benchmarking decoy data sets. The results show that iNepre scores are powerful in model ranking to select the best protein complex structures.

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.

Induced-Fit Docking Enables Accurate Free Energy Perturbation Calculations in Homology Models

Homology models have been used for virtual screening and to understand the binding mode of a known active compound; however, rarely have the models been shown to be of sufficient accuracy, comparable to crystal structures, to support free-energy perturbation (FEP) calculations. We demonstrate here that the use of an advanced induced-fit docking methodology reliably enables predictive FEP calculations on congeneric series across homology models ≥30% sequence identity. Furthermore, we show that retrospective FEP calculations on a congeneric series of drug-like ligands are sufficient to discriminate between predicted binding modes. Results are presented for a total of 29 homology models for 14 protein targets, showing FEP results comparable to those obtained using experimentally determined crystal structures for 86% of homology models with template structure sequence identities ranging from 30 to 50%. Implications for the use and validation of homology models in drug discovery projects are discussed.

Scoring of protein–protein docking models utilizing predicted interface residues

Scoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today's best scoring functions can significantly increase the number of top‐ranked models but still fail for most targets. Here, we examine the possibility of utilizing predicted interface residues to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the regions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. This study systematically tests different interface prediction methods for scoring >300.000 low‐resolution rigid‐body template free docking decoys. Overall we find that contact‐based interface prediction by BIPSPI is the best method to score docking solutions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high‐importance metric when estimating interface prediction quality, focusing on docking constraints production. Finally, we discussed several limitations for adopting interface predictions as constraints in a docking protocol.

Computational epitope binning reveals functional equivalence of sequence-divergent paratopes

•

Epitope binning groups target-specific protein binders recognizing the same binding region.

•

The “Epibin” method utilizes docking models to computationally predict competition and identify bins.

•

Epibin recapitulated binding competition of repebody variants as determined by immunoassays.

•

In addition, Epibin enabled identification of ‘paratope-equivalent’ residues in sequence-dissimilar variants.

•

Computational epitope binning can scale to allow characterization of entire antigen-specific antibody repertoires.

The therapeutic efficacy of a protein binder largely depends on two factors: its binding site and its binding affinity. Advances in in vitro library display screening and next-generation sequencing have enabled accelerated development of strong binders, yet identifying their binding sites still remains a major challenge. The differentiation, or “binning”, of binders into different groups that recognize distinct binding sites on their target is a promising approach that facilitates high-throughput screening of binders that may show different biological activity. Here we study the extent to which the information contained in the amino acid sequences comprising a set of target-specific binders can be leveraged to bin them, inferring functional equivalence of their binding regions, or paratopes, based directly on comparison of the sequences, their modeled structures, or their modeled interactions. Using a leucine-rich repeat binding scaffold known as a “repebody” as the source of diversity in recognition against interleukin-6 (IL-6), we show that the “Epibin” approach introduced here effectively utilized structural modelling and docking to extract specificity information encoded in the repebody amino acid sequences and thereby successfully recapitulate IL-6 binding competition observed in immunoassays. Furthermore, our computational binning provided a basis for designing in vitro mutagenesis experiments to pinpoint specificity-determining residues. Finally, we demonstrate that the Epibin approach can extend to antibodies, retrospectively comparing its predictions to results from antigen-specific antibody competition studies. The study thus demonstrates the utility of modeling structure and binding from the amino acid sequences of different binders against the same target, and paves the way for larger-scale binning and analysis of entire repertoires.

Modeling the Dynamics of Protein–Protein Interfaces, How and Why?

Protein–protein assemblies act as a key component in numerous cellular processes. Their accurate modeling at the atomic level remains a challenge for structural biology. To address this challenge, several docking and a handful of deep learning methodologies focus on modeling protein–protein interfaces. Although the outcome of these methods has been assessed using static reference structures, more and more data point to the fact that the interaction stability and specificity is encoded in the dynamics of these interfaces. Therefore, this dynamics information must be taken into account when modeling and assessing protein interactions at the atomistic scale. Expanding on this, our review initially focuses on the recent computational strategies aiming at investigating protein–protein interfaces in a dynamic fashion using enhanced sampling, multi-scale modeling, and experimental data integration. Then, we discuss how interface dynamics report on the function of protein assemblies in globular complexes, in fuzzy complexes containing intrinsically disordered proteins, as well as in active complexes, where chemical reactions take place across the protein–protein interface.

ZoomQA: residue-level protein model accuracy estimation with machine learning on sequential and 3D structural features

MOTIVATION

The Estimation of Model Accuracy problem is a cornerstone problem in the field of Bioinformatics. As of CASP14, there are 79 global QA methods, and a minority of 39 residue-level QA methods with very few of them working on protein complexes. Here, we introduce ZoomQA, a novel, single-model method for assessing the accuracy of a tertiary protein structure/complex prediction at residue level, which have many applications such as drug discovery. ZoomQA differs from others by considering the change in chemical and physical features of a fragment structure (a portion of a protein within a radius $r$ of the target amino acid) as the radius of contact increases. Fourteen physical and chemical properties of amino acids are used to build a comprehensive representation of every residue within a protein and grade their placement within the protein as a whole. Moreover, we have shown the potential of ZoomQA to identify problematic regions of the SARS-CoV-2 protein complex.

RESULTS

We benchmark ZoomQA on CASP14, and it outperforms other state-of-the-art local QA methods and rivals state of the art QA methods in global prediction metrics. Our experiment shows the efficacy of these new features and shows that our method is able to match the performance of other state-of-the-art methods without the use of homology searching against databases or PSSM matrices.

AVAILABILITY

http://zoomQA.renzhitech.com.

DeepRank: a deep learning framework for data mining 3D protein-protein interfaces

Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. The vast amount of experimentally and computationally resolved protein-protein interfaces (PPIs) offers the possibility of training deep learning models to aid the predictions of their biological relevance. We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). DeepRank maps features of PPIs onto 3D grids and trains a user-specified CNN on these 3D grids. DeepRank allows for efficient training of 3D CNNs with data sets containing millions of PPIs and supports both classification and regression. We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models. For both problems DeepRank is competitive with, or outperforms, state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology.

Native or Non-Native Protein-Protein Docking Models? Molecular Dynamics to the Rescue

Molecular docking excels at creating a plethora of potential models of protein-protein complexes. To correctly distinguish the favorable, native-like models from the remaining ones remains, however, a challenge. We assessed here if a protocol based on molecular dynamics (MD) simulations would allow distinguishing native from non-native models to complement scoring functions used in docking. To this end, the first models for 25 protein-protein complexes were generated using HADDOCK. Next, MD simulations complemented with machine learning were used to discriminate between native and non-native complexes based on a combination of metrics reporting on the stability of the initial models. Native models showed higher stability in almost all measured properties, including the key ones used for scoring in the Critical Assessment of PRedicted Interaction (CAPRI) competition, namely the positional root mean square deviations and fraction of native contacts from the initial docked model. A random forest classifier was trained, reaching a 0.85 accuracy in correctly distinguishing native from non-native complexes. Reasonably modest simulation lengths of the order of 50-100 ns are sufficient to reach this accuracy, which makes this approach applicable in practice.

Moving pictures: Reassessing docking experiments with a dynamic view of protein interfaces

The modeling of protein assemblies at the atomic level remains a central issue in structural biology, as protein interactions play a key role in numerous cellular processes. This problem is traditionally addressed using docking tools, where the quality of the models is based on their similarity to a single reference experimental structure. However, using a static reference does not take into account the dynamic quality of the protein interface. Here, we used all-atom classical Molecular Dynamics simulations to investigate the stability of the reference interface for three complexes that previously served as targets in the CAPRI competition. For each one of these targets, we also ran MD simulations for ten models that are distributed over the High, Medium and Acceptable accuracy categories. To assess the quality of these models from a dynamic perspective, we set up new criteria which take into account the stability of the reference experimental protein interface. We show that, when the protein interfaces are allowed to evolve along time, the original ranking based on the static CAPRI criteria no longer holds as over 50% of the docking models undergo a category change (which can be either toward a better or a lower accuracy group) when reassessing their quality using dynamic information.

Protein Docking Model Evaluation by Graph Neural Networks

Physical interactions of proteins play key functional roles in many important cellular processes. To understand molecular mechanisms of such functions, it is crucial to determine the structure of protein complexes. To complement experimental approaches, which usually take a considerable amount of time and resources, various computational methods have been developed for predicting the structures of protein complexes. In computational modeling, one of the challenges is to identify near-native structures from a large pool of generated models. Here, we developed a deep learning-based approach named Graph Neural Network-based DOcking decoy eValuation scorE (GNN-DOVE). To evaluate a protein docking model, GNN-DOVE extracts the interface area and represents it as a graph. The chemical properties of atoms and the inter-atom distances are used as features of nodes and edges in the graph, respectively. GNN-DOVE was trained, validated, and tested on docking models in the Dockground database and further tested on a combined dataset of Dockground and ZDOCK benchmark as well as a CAPRI scoring dataset. GNN-DOVE performed better than existing methods, including DOVE, which is our previous development that uses a convolutional neural network on voxelized structure models.

Mapping specificity, cleavage entropy, allosteric changes and substrates of blood proteases in a high-throughput screen

Proteases are among the largest protein families and critical regulators of biochemical processes like apoptosis and blood coagulation. Knowledge of proteases has been expanded by the development of proteomic approaches, however, technology for multiplexed screening of proteases within native environments is currently lacking behind. Here we introduce a simple method to profile protease activity based on isolation of protease products from native lysates using a 96FASP filter, their analysis in a mass spectrometer and a custom data analysis pipeline. The method is significantly faster, cheaper, technically less demanding, easy to multiplex and produces accurate protease fingerprints. Using the blood cascade proteases as a case study, we obtain protease substrate profiles that can be used to map specificity, cleavage entropy and allosteric effects and to design protease probes. The data further show that protease substrate predictions enable the selection of potential physiological substrates for targeted validation in biochemical assays.

Characterizing proteases in their native environment is still challenging. Here, the authors develop a proteomics workflow for analyzing protease-specific peptides from cell lysates in 96-well format, providing mechanistic insights into blood proteases and enabling the prediction of protease substrates.

Simplified geometric representations of protein structures identify complementary interaction interfaces

Protein-protein interactions are critical to protein function, but three-dimensional (3D) arrangements of interacting proteins have proven hard to predict, even given the identities and 3D structures of the interacting partners. Specifically, identifying the relevant pairwise interaction surfaces remains difficult, often relying on shape complementarity with molecular docking while accounting for molecular motions to optimize rigid 3D translations and rotations. However, such approaches can be computationally expensive, and faster, less accurate approximations may prove useful for large-scale prediction and assembly of 3D structures of multi-protein complexes. We asked if a reduced representation of protein geometry retains enough information about molecular properties to predict pairwise protein interaction interfaces that are tolerant of limited structural rearrangements. Here, we describe a reduced representation of 3D protein accessible surfaces on which molecular properties such as charge, hydrophobicity, and evolutionary rate can be easily mapped, implemented in the MorphProt package. Pairs of surfaces are compared to rapidly assess partner-specific potential surface complementarity. On two available benchmarks of 185 overall known protein complexes, we observe predictions comparable to other structure-based tools at correctly identifying protein interaction surfaces. Furthermore, we examined the effect of molecular motion through normal mode simulation on a benchmark receptor-ligand pair and observed no marked loss of predictive accuracy for distortions of up to 6 Å Cα-RMSD. Thus, a shape reduction of protein surfaces retains considerable information about surface complementarity, offers enhanced speed of comparison relative to more complex geometric representations, and exhibits tolerance to conformational changes.

Guardians of the Cell: State-of-the-Art of Membrane Proteins from a Computational Point-of-View

Membrane proteins (MPs) encompass a large family of proteins with distinct cellular functions, and although representing over 50% of existing pharmaceutical drug targets, their structural and functional information is still very scarce. Over the last years, in silico analysis and algorithm development were essential to characterize MPs and overcome some limitations of experimental approaches. The optimization and improvement of these methods remain an ongoing process, with key advances in MPs' structure, folding, and interface prediction being continuously tackled. Herein, we discuss the latest trends in computational methods toward a deeper understanding of the atomistic and mechanistic details of MPs.

A knowledge-based scoring function to assess quaternary associations of proteins

MOTIVATION

The elucidation of all inter-protein interactions would significantly enhance our knowledge of cellular processes at a molecular level. Given the enormity of the problem, the expenses and limitations of experimental methods, it is imperative that this problem is tackled computationally. In silico predictions of protein interactions entail sampling different conformations of the purported complex and then scoring these to assess for interaction viability. In this study, we have devised a new scheme for scoring protein-protein interactions.

RESULTS

Our method, PIZSA (Protein Interaction Z-Score Assessment), is a binary classification scheme for identification of native protein quaternary assemblies (binders/nonbinders) based on statistical potentials. The scoring scheme incorporates residue-residue contact preference on the interface with per residue-pair atomic contributions and accounts for clashes. PIZSA can accurately discriminate between native and non-native structural conformations from protein docking experiments and outperform other contact-based potential scoring functions. The method has been extensively benchmarked and is among the top 6 methods, outperforming 31 other statistical, physics based and machine learning scoring schemes. The PIZSA potentials can also distinguish crystallization artifacts from biological interactions.

AVAILABILITY AND IMPLEMENTATION

PIZSA is implemented as a web server at http://cospi.iiserpune.ac.in/pizsa and can be downloaded as a standalone package from http://cospi.iiserpune.ac.in/pizsa/Download/Download.html.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Integrative modeling of membrane-associated protein assemblies

Membrane proteins are among the most challenging systems to study with experimental structural biology techniques. The increased number of deposited structures of membrane proteins has opened the route to modeling their complexes by methods such as docking. Here, we present an integrative computational protocol for the modeling of membrane-associated protein assemblies. The information encoded by the membrane is represented by artificial beads, which allow targeting of the docking toward the binding-competent regions. It combines efficient, artificial intelligence-based rigid-body docking by LightDock with a flexible final refinement with HADDOCK to remove potential clashes at the interface. We demonstrate the performance of this protocol on eighteen membrane-associated complexes, whose interface lies between the membrane and either the cytosolic or periplasmic regions. In addition, we provide a comparison to another state-of-the-art docking software, ZDOCK. This protocol should shed light on the still dark fraction of the interactome consisting of membrane proteins.

Protein Interaction Z Score Assessment (PIZSA): an empirical scoring scheme for evaluation of protein-protein interactions

Our web server, PIZSA (http://cospi.iiserpune.ac.in/pizsa), assesses the likelihood of protein–protein interactions by assigning a Z Score computed from interface residue contacts. Our score takes into account the optimal number of atoms that mediate the interaction between pairs of residues and whether these contacts emanate from the main chain or side chain. We tested the score on 174 native interactions for which 100 decoys each were constructed using ZDOCK. The native structure scored better than any of the decoys in 146 cases and was able to rank within the 95th percentile in 162 cases. This easily outperforms a competing method, CIPS. We also benchmarked our scoring scheme on 15 targets from the CAPRI dataset and found that our method had results comparable to that of CIPS. Further, our method is able to analyse higher order protein complexes without the need to explicitly identify chains as receptors or ligands. The PIZSA server is easy to use and could be used to score any input three-dimensional structure and provide a residue pair-wise break up of the results. Attractively, our server offers a platform for users to upload their own potentials and could serve as an ideal testing ground for this class of scoring schemes.

A community proposal to integrate structural bioinformatics activities in ELIXIR (3D-Bioinfo Community)

Structural bioinformatics provides the scientific methods and tools to analyse, archive, validate, and present the biomolecular structure data generated by the structural biology community. It also provides an important link with the genomics community, as structural bioinformaticians also use the extensive sequence data to predict protein structures and their functional sites. A very broad and active community of structural bioinformaticians exists across Europe, and 3D-Bioinfo will establish formal platforms to address their needs and better integrate their activities and initiatives. Our mission will be to strengthen the ties with the structural biology research communities in Europe covering life sciences, as well as chemistry and physics and to bridge the gap between these researchers in order to fully realize the potential of structural bioinformatics. Our Community will also undertake dedicated educational, training and outreach efforts to facilitate this, bringing new insights and thus facilitating the development of much needed innovative applications e.g. for human health, drug and protein design. Our combined efforts will be of critical importance to keep the European research efforts competitive in this respect.

Here we highlight the major European contributions to the field of structural bioinformatics, the most pressing challenges remaining and how Europe-wide interactions, enabled by ELIXIR and its platforms, will help in addressing these challenges and in coordinating structural bioinformatics resources across Europe. In particular, we present recent activities and future plans to consolidate an ELIXIR 3D-Bioinfo Community in structural bioinformatics and propose means to develop better links across the community. These include building new consortia, organising workshops to establish data standards and seeking community agreement on benchmark data sets and strategies. We also highlight existing and planned collaborations with other ELIXIR Communities and other European infrastructures, such as the structural biology community supported by Instruct-ERIC, with whom we have synergies and overlapping common interests.

Energy-based graph convolutional networks for scoring protein docking models

Structural information about protein-protein interactions, often missing at the interactome scale, is important for mechanistic understanding of cells and rational discovery of therapeutics. Protein docking provides a computational alternative for such information. However, ranking near-native docked models high among a large number of candidates, often known as the scoring problem, remains a critical challenge. Moreover, estimating model quality, also known as the quality assessment problem, is rarely addressed in protein docking. In this study, the two challenging problems in protein docking are regarded as relative and absolute scoring, respectively, and addressed in one physics-inspired deep learning framework. We represent protein and complex structures as intra- and inter-molecular residue contact graphs with atom-resolution node and edge features. And we propose a novel graph convolutional kernel that aggregates interacting nodes' features through edges so that generalized interaction energies can be learned directly from 3D data. The resulting energy-based graph convolutional networks (EGCN) with multihead attention are trained to predict intra- and inter-molecular energies, binding affinities, and quality measures (interface RMSD) for encounter complexes. Compared to a state-of-the-art scoring function for model ranking, EGCN significantly improves ranking for a critical assessment of predicted interactions (CAPRI) test set involving homology docking; and is comparable or slightly better for Score_set, a CAPRI benchmark set generated by diverse community-wide docking protocols not known to training data. For Score_set quality assessment, EGCN shows about 27% improvement to our previous efforts. Directly learning from 3D structure data in graph representation, EGCN represents the first successful development of graph convolutional networks for protein docking.

Dockground Tool for Development and Benchmarking of Protein Docking Procedures

Databases of protein-protein complexes are essential for the development of protein modeling/docking techniques. Such databases provide a knowledge base for docking algorithms, intermolecular potentials, search procedures, scoring functions, and refinement protocols. Development of docking techniques requires systematic validation of the modeling protocols on carefully curated benchmark sets of complexes. We present a description and a guide to the DOCKGROUND resource ( http://dockground.compbio.ku.edu ) for structural modeling of protein interactions. The resource integrates various datasets of protein complexes and other data for the development and testing of protein docking techniques. The sets include bound complexes, experimentally determined unbound, simulated unbound, model-model complexes, and docking decoys. The datasets are available to the user community through a Web interface.

iScore: a novel graph kernel-based function for scoring protein-protein docking models

MOTIVATION

Protein complexes play critical roles in many aspects of biological functions. Three-dimensional (3D) structures of protein complexes are critical for gaining insights into structural bases of interactions and their roles in the biomolecular pathways that orchestrate key cellular processes. Because of the expense and effort associated with experimental determinations of 3D protein complex structures, computational docking has evolved as a valuable tool to predict 3D structures of biomolecular complexes. Despite recent progress, reliably distinguishing near-native docking conformations from a large number of candidate conformations, the so-called scoring problem, remains a major challenge.

RESULTS

Here we present iScore, a novel approach to scoring docked conformations that combines HADDOCK energy terms with a score obtained using a graph representation of the protein-protein interfaces and a measure of evolutionary conservation. It achieves a scoring performance competitive with, or superior to, that of state-of-the-art scoring functions on two independent datasets: (i) Docking software-specific models and (ii) the CAPRI score set generated by a wide variety of docking approaches (i.e. docking software-non-specific). iScore ranks among the top scoring approaches on the CAPRI score set (13 targets) when compared with the 37 scoring groups in CAPRI. The results demonstrate the utility of combining evolutionary, topological and energetic information for scoring docked conformations. This work represents the first successful demonstration of graph kernels to protein interfaces for effective discrimination of near-native and non-native conformations of protein complexes.

AVAILABILITY AND IMPLEMENTATION

The iScore code is freely available from Github: https://github.com/DeepRank/iScore (DOI: 10.5281/zenodo.2630567). And the docking models used are available from SBGrid: https://data.sbgrid.org/dataset/684).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

iScore: An MPI supported software for ranking protein-protein docking models based on a random walk graph kernel and support vector machines

Computational docking is a promising tool to model three-dimensional (3D) structures of protein-protein complexes, which provides fundamental insights of protein functions in the cellular life. Singling out near-native models from the huge pool of generated docking models (referred to as the scoring problem) remains as a major challenge in computational docking. We recently published iScore, a novel graph kernel based scoring function. iScore ranks docking models based on their interface graph similarities to the training interface graph set. iScore uses a support vector machine approach with random-walk graph kernels to classify and rank protein-protein interfaces. Here, we present the software for iScore. The software provides executable scripts that fully automate the computational workflow. In addition, the creation and analysis of the interface graph can be distributed across different processes using Message Passing interface (MPI) and can be offloaded to GPUs thanks to dedicated CUDA kernels.

Refinement of protein-protein complexes in contact map space with metadynamics simulations

Accurate protein-protein complex prediction, to atomic detail, is a challenging problem. For flexible docking cases, current state-of-the-art docking methods are limited in their ability to exhaustively search the high dimensionality of the problem space. In this study, to obtain more accurate models, an investigation into the local optimization of initial docked solutions is presented with respect to a reference crystal structure. We show how physics-based refinement of protein-protein complexes in contact map space (CMS), within a metadynamics protocol, can be performed. The method uses 5 times replicated 10 ns simulations for sampling and ranks the generated conformational snapshots with ZRANK to identify an ensemble of n snapshots for final model building. Furthermore, we investigated whether the reconstructed free energy surface (FES), or a combination of both FES and ZRANK, referred to as CSα , can help to reduce snapshot ranking error.

Development of a new benchmark for assessing the scoring functions applicable to protein–protein interactions

Aim: Scoring functions are important component of protein–protein docking methods. They need to be evaluated on high-quality benchmarks to reveal their strengths and weaknesses. Evaluation results obtained on such benchmarks can provide valuable guidance for developing more advanced scoring functions. Methodology & results: In our comparative assessment of scoring functions for protein–protein interactions benchmark, the performance of a scoring function was characterized by ‘docking power’ and ‘scoring power’. A high-quality dataset of 273 protein–protein complexes was compiled and employed in both tests. Four scoring functions, including FASTCONTACT, ZRANK, dDFIRE and ATTRACT were tested as demonstration. ZRANK and ATTRACT exhibited encouraging performance in the docking power test. However, all four scoring functions failed badly in the scoring power test. Conclusion: Our comparative assessment of scoring functions for protein–protein interaction benchmark is created especially for assessing the scoring functions applicable to protein–protein interactions. It is different from other benchmarks for assessing protein–protein docking methods. Our benchmark is available to the public at www.pdbbind-cn.org/download/CASF-PPI/ .

Comparing side chain packing in soluble proteins, protein-protein interfaces, and transmembrane proteins

We compare side chain prediction and packing of core and non-core regions of soluble proteins, protein-protein interfaces, and transmembrane proteins. We first identified or created comparable databases of high-resolution crystal structures of these 3 protein classes. We show that the solvent-inaccessible cores of the 3 classes of proteins are equally densely packed. As a result, the side chains of core residues at protein-protein interfaces and in the membrane-exposed regions of transmembrane proteins can be predicted by the hard-sphere plus stereochemical constraint model with the same high prediction accuracies (>90%) as core residues in soluble proteins. We also find that for all 3 classes of proteins, as one moves away from the solvent-inaccessible core, the packing fraction decreases as the solvent accessibility increases. However, the side chain predictability remains high (80% within 30°) up to a relative solvent accessibility, rSASA≲0.3, for all 3 protein classes. Our results show that ≈40% of the interface regions in protein complexes are "core", that is, densely packed with side chain conformations that can be accurately predicted using the hard-sphere model. We propose packing fraction as a metric that can be used to distinguish real protein-protein interactions from designed, non-binding, decoys. Our results also show that cores of membrane proteins are the same as cores of soluble proteins. Thus, the computational methods we are developing for the analysis of the effect of hydrophobic core mutations in soluble proteins will be equally applicable to analyses of mutations in membrane proteins.

Properties that rank protein:protein docking poses with high accuracy

The development of docking algorithms to predict near-native structures of protein:protein complexes from the structure of the isolated monomers is of paramount importance for molecular biology and drug discovery.

Dockground: A comprehensive data resource for modeling of protein complexes

Characterization of life processes at the molecular level requires structural details of protein interactions. The number of experimentally determined structures of protein-protein complexes accounts only for a fraction of known protein interactions. This gap in structural description of the interactome has to be bridged by modeling. An essential part of the development of structural modeling/docking techniques for protein interactions is databases of protein-protein complexes. They are necessary for studying protein interfaces, providing a knowledge base for docking algorithms, and developing intermolecular potentials, search procedures, and scoring functions. Development of protein-protein docking techniques requires thorough benchmarking of different parts of the docking protocols on carefully curated sets of protein-protein complexes. We present a comprehensive description of the Dockground resource (http://dockground.compbio.ku.edu) for structural modeling of protein interactions, including previously unpublished unbound docking benchmark set 4, and the X-ray docking decoy set 2. The resource offers a variety of interconnected datasets of protein-protein complexes and other data for the development and testing of different aspects of protein docking methodologies. Based on protein-protein complexes extracted from the PDB biounit files, Dockground offers sets of X-ray unbound, simulated unbound, model, and docking decoy structures. All datasets are freely available for download, as a whole or selecting specific structures, through a user-friendly interface on one integrated website.

Finding correct protein-protein docking models using ProQDock

Motivation: Protein–protein interactions are a key in virtually all biological processes. For a detailed understanding of the biological processes, the structure of the protein complex is essential. Given the current experimental techniques for structure determination, the vast majority of all protein complexes will never be solved by experimental techniques. In lack of experimental data, computational docking methods can be used to predict the structure of the protein complex. A common strategy is to generate many alternative docking solutions (atomic models) and then use a scoring function to select the best. The success of the computational docking technique is, to a large degree, dependent on the ability of the scoring function to accurately rank and score the many alternative docking models.

Results: Here, we present ProQDock, a scoring function that predicts the absolute quality of docking model measured by a novel protein docking quality score (DockQ). ProQDock uses support vector machines trained to predict the quality of protein docking models using features that can be calculated from the docking model itself. By combining different types of features describing both the protein–protein interface and the overall physical chemistry, it was possible to improve the correlation with DockQ from 0.25 for the best individual feature (electrostatic complementarity) to 0.49 for the final version of ProQDock. ProQDock performed better than the state-of-the-art methods ZRANK and ZRANK2 in terms of correlations, ranking and finding correct models on an independent test set. Finally, we also demonstrate that it is possible to combine ProQDock with ZRANK and ZRANK2 to improve performance even further.

Availability and implementation:http://bioinfo.ifm.liu.se/ProQDock

Contact:bjornw@ifm.liu.se

Supplementary information:Supplementary data are available at Bioinformatics online.

A machine learning approach for ranking clusters of docked protein-protein complexes by pairwise cluster comparison

Reliable identification of near-native poses of docked protein-protein complexes is still an unsolved problem. The intrinsic heterogeneity of protein-protein interactions is challenging for traditional biophysical or knowledge based potentials and the identification of many false positive binding sites is not unusual. Often, ranking protocols are based on initial clustering of docked poses followed by the application of an energy function to rank each cluster according to its lowest energy member. Here, we present an approach of cluster ranking based not only on one molecular descriptor (e.g., an energy function) but also employing a large number of descriptors that are integrated in a machine learning model, whereby, an extremely randomized tree classifier based on 109 molecular descriptors is trained. The protocol is based on first locally enriching clusters with additional poses, the clusters are then characterized using features describing the distribution of molecular descriptors within the cluster, which are combined into a pairwise cluster comparison model to discriminate near-native from incorrect clusters. The results show that our approach is able to identify clusters containing near-native protein-protein complexes. In addition, we present an analysis of the descriptors with respect to their power to discriminate near native from incorrect clusters and how data transformations and recursive feature elimination can improve the ranking performance. Proteins 2017; 85:528-543. © 2016 Wiley Periodicals, Inc.

Protein-protein interactions: scoring schemes and binding affinity

Protein-protein interactions mediate several cellular functions, which can be understood from the information obtained using the three-dimensional structures of protein-protein complexes and binding affinity data. This review focuses on computational aspects of predicting the best native-like complex structure and binding affinities. The first part covers the prediction of protein-protein complex structures and the advantages of conformational searching and scoring functions in protein-protein docking. The second part is devoted to various aspects of protein-protein interaction thermodynamics, such as databases for binding affinities and other thermodynamic parameters, computational methods to predict the binding affinity using either the three-dimensional structures of complexes or amino acid sequences, and change in binding affinities of the complexes upon mutations. We provide the latest developments on protein-protein docking and binding affinity studies along with a list of available computational resources for understanding protein-protein interactions.