Understand protein functions by comparing the similarity of local structural environments

Predicting the location of coordinated metal ion-ligand binding sites using geometry-aware graph neural networks

More than 50 % of proteins bind to metal ions. Interactions between metal ions and proteins, especially coordinated interactions, are essential for biological functions, such as maintaining protein structure and signal transport. Physiological metal-ion binding prediction is pivotal for both elucidating the biological functions of proteins and for the design of new drugs. However, accurately predicting these interactions remains challenging. In this study, we proposed GPred, a novel structure-based method that transforms the 3-dimensional structure of a protein into a point cloud representation and then designs a geometry-aware graph neural network to learn the local structural properties of each amino acid residue under specific ligand-binding supervision. We trained our model to predict the location of coordinated binding sites for five essential metal ions: Zn2+, Ca2+, Mg2+, Mn2+, and Fe2+. We further demonstrated the versatility of GPred by applying transfer learning to predict the binding sites of 2 heavy metal ions, that is, cadmium (Cd2+) and mercury (Hg2+). We achieved greater than 19.62 %, 14.32 %, 36.62 %, and 40.69 % improvement in the area under the precision-recall curve (AUPR) of Zn2+, Ca2+, Mg2+, Mn2+, and Fe2+, respectively, when compared with 6 current accessible state-of-the-art sequence-based or structure-based tools. We also validated the proposed approach on protein structures predicted by AlphaFold2, and its performance was similar to experimental protein structures. In both cases, achieving a low false discovery rate for proteins without annotated ion-binding sites was demonstrated. © 2017 Elsevier Inc. All rights reserved.

PepCA: Unveiling protein-peptide interaction sites with a multi-input neural network model

The protein-peptide interaction plays a pivotal role in fields such as drug development, yet remains underexplored experimentally and challenging to model computationally. Herein, we introduce PepCA, a sequence-based approach for predicting peptide-binding sites on proteins. A primary obstacle in predicting peptide-protein interactions is the difficulty in acquiring precise protein structures, coupled with the uncertainty of polypeptide configurations. To address this, we first encode protein sequences using the Evolutionary Scale Modeling 2 (ESM-2) pre-trained model to extract latent structural information. Additionally, we have developed a multi-input coattention mechanism to concurrently update the encoding of both peptide and protein residues. PepCA integrates this module within an encoder-decoder structure. This model's high precision in identifying binding sites significantly advances the field of computational biology, offering vital insights for peptide drug development and protein science.

Advances in the Application of Protein Language Modeling for Nucleic Acid Protein Binding Site Prediction

Protein and nucleic acid binding site prediction is a critical computational task that benefits a wide range of biological processes. Previous studies have shown that feature selection holds particular significance for this prediction task, making the generation of more discriminative features a key area of interest for many researchers. Recent progress has shown the power of protein language models in handling protein sequences, in leveraging the strengths of attention networks, and in successful applications to tasks such as protein structure prediction. This naturally raises the question of the applicability of protein language models in predicting protein and nucleic acid binding sites. Various approaches have explored this potential. This paper first describes the development of protein language models. Then, a systematic review of the latest methods for predicting protein and nucleic acid binding sites is conducted by covering benchmark sets, feature generation methods, performance comparisons, and feature ablation studies. These comparisons demonstrate the importance of protein language models for the prediction task. Finally, the paper discusses the challenges of protein and nucleic acid binding site prediction and proposes possible research directions and future trends. The purpose of this survey is to furnish researchers with actionable suggestions for comprehending the methodologies used in predicting protein-nucleic acid binding sites, fostering the creation of protein-centric language models, and tackling real-world obstacles encountered in this field.

Protein-protein and protein-nucleic acid binding site prediction via interpretable hierarchical geometric deep learning

Identification of protein-protein and protein-nucleic acid binding sites provides insights into biological processes related to protein functions and technical guidance for disease diagnosis and drug design. However, accurate predictions by computational approaches remain highly challenging due to the limited knowledge of residue binding patterns. The binding pattern of a residue should be characterized by the spatial distribution of its neighboring residues combined with their physicochemical information interaction, which yet cannot be achieved by previous methods. Here, we design GraphRBF, a hierarchical geometric deep learning model to learn residue binding patterns from big data. To achieve it, GraphRBF describes physicochemical information interactions by designing an enhanced graph neural network and characterizes residue spatial distributions by introducing a prioritized radial basis function neural network. After training and testing, GraphRBF shows great improvements over existing state-of-the-art methods and strong interpretability of its learned representations. Applying GraphRBF to the SARS-CoV-2 omicron spike protein, it successfully identifies known epitopes of the protein. Moreover, it predicts multiple potential binding regions for new nanobodies or even new drugs with strong evidence. A user-friendly online server for GraphRBF is freely available at http://liulab.top/GraphRBF/server.

DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model

MOTIVATION

Identifying the functional sites of a protein, such as the binding sites of proteins, peptides, or other biological components, is crucial for understanding related biological processes and drug design. However, existing sequence-based methods have limited predictive accuracy, as they only consider sequence-adjacent contextual features and lack structural information.

RESULTS

In this study, DeepProSite is presented as a new framework for identifying protein binding site that utilizes protein structure and sequence information. DeepProSite first generates protein structures from ESMFold and sequence representations from pretrained language models. It then uses Graph Transformer and formulates binding site predictions as graph node classifications. In predicting protein-protein/peptide binding sites, DeepProSite outperforms state-of-the-art sequence- and structure-based methods on most metrics. Moreover, DeepProSite maintains its performance when predicting unbound structures, in contrast to competing structure-based prediction methods. DeepProSite is also extended to the prediction of binding sites for nucleic acids and other ligands, verifying its generalization capability. Finally, an online server for predicting multiple types of residue is established as the implementation of the proposed DeepProSite.

AVAILABILITY AND IMPLEMENTATION

The datasets and source codes can be accessed at https://github.com/WeiLab-Biology/DeepProSite. The proposed DeepProSite can be accessed at https://inner.wei-group.net/DeepProSite/.

Unraveling a Conserved Conformation of the FG Loop upon the Binding of Natural Ligands to the Human and Murine PD1

The activation of T cells is normally accompanied by inhibitory mechanisms within which the PD1 receptor stands out. PD1 drives T cells to an unresponsive state called exhaustion, characterized by a markedly decreased capacity to exert effector functions upon binding the ligands PDL1 and PDL2. For this reason, PD1 has become one of the most important targets in cancer immunotherapy. Despite the numerous studies about PD1 signaling modulation, how the PD1 signaling pathway is activated upon the ligands' binding remains an open question. In this work, we used molecular dynamics simulations to assess the differences of the PD1 motion in the free state and in complex with the ligands. We found that, in both human and murine systems, the binding of PDL1 and PDL2 stabilizes the conformation of the FG loop similarly. This result, combined with the conservation of the FG loop residues across species, suggests that the conformation of the FG loop is somehow related to the signaling process. We also found a high similarity between the PD1-PDL1 structures with the variable region of an antibody structure, where the FG loop occupies a similar position to the CDR3 light chain.

A structural-based machine learning method to classify binding affinities between TCR and peptide-MHC complexes

The activation of T cells is triggered by the interactions of T cell receptors (TCRs) with their epitopes, which are peptides presented by major histocompatibility complex (MHC) on the surfaces of antigen presenting cells (APC). While each TCR can only recognize a specific subset from a large repertoire of peptide-MHC (pMHC) complexes, it is very often that peptides in this subset share little sequence similarity. This is known as the specificity and cross-reactivity of T cells, respectively. The binding affinities between different types of TCRs and pMHC are the major driving force to shape this specificity and cross-reactivity in T cell recognition. The binding affinities, furthermore, are determined by the sequence and structural properties at the interfaces between TCRs and pMHC. Fortunately, a wealth of data on binding and structures of TCR-pMHC interactions becomes publicly accessible in online resources, which offers us the opportunity to develop a random forest classifier for predicting the binding affinities between TCR and pMHC based on the structure of their complexes. Specifically, the structure and sequence of a given complex were projected onto a high-dimensional feature space as the input of the classifier, which was then trained by a large-scale benchmark dataset. Based on the cross-validation results, we found that our machine learning model can predict if the binding affinity of a given TCR-pMHC complex is stronger or weaker than a predefined threshold with an overall accuracy approximately around 75 %. The significance of our prediction was estimated by statistical analysis. Moreover, more than 60 % of binding affinities in the ATLAS database can be successfully classified into groups within the range of 2 kcal/mol. Additionally, we show that TCR-pMHC complexes with strong binding affinity prefer hydrophobic interactions between amino acids with large aromatic rings instead of electrostatic interactions. Our results therefore provide insights to design engineered TCRs which enhance the specificity for their targeted epitopes. Taken together, this method can serve as a useful addition to a suite of existing approaches which study binding between TCR and pMHC.

Classification of protein-protein association rates based on biophysical informatics

BACKGROUND

Proteins form various complexes to carry out their versatile functions in cells. The dynamic properties of protein complex formation are mainly characterized by the association rates which measures how fast these complexes can be formed. It was experimentally observed that the association rates span an extremely wide range with over ten orders of magnitudes. Identification of association rates within this spectrum for specific protein complexes is therefore essential for us to understand their functional roles.

RESULTS

To tackle this problem, we integrate physics-based coarse-grained simulations into a neural-network-based classification model to estimate the range of association rates for protein complexes in a large-scale benchmark set. The cross-validation results show that, when an optimal threshold was selected, we can reach the best performance with specificity, precision, sensitivity and overall accuracy all higher than 70%. The quality of our cross-validation data has also been testified by further statistical analysis. Additionally, given an independent testing set, we can successfully predict the group of association rates for eight protein complexes out of ten. Finally, the analysis of failed cases suggests the future implementation of conformational dynamics into simulation can further improve model.

CONCLUSIONS

In summary, this study demonstrated that a new modeling framework that combines biophysical simulations with bioinformatics approaches is able to identify protein-protein interactions with low association rates from those with higher association rates. This method thereby can serve as a useful addition to a collection of existing experimental approaches that measure biomolecular recognition.

GraphBind: protein structural context embedded rules learned by hierarchical graph neural networks for recognizing nucleic-acid-binding residues

Knowledge of the interactions between proteins and nucleic acids is the basis of understanding various biological activities and designing new drugs. How to accurately identify the nucleic-acid-binding residues remains a challenging task. In this paper, we propose an accurate predictor, GraphBind, for identifying nucleic-acid-binding residues on proteins based on an end-to-end graph neural network. Considering that binding sites often behave in highly conservative patterns on local tertiary structures, we first construct graphs based on the structural contexts of target residues and their spatial neighborhood. Then, hierarchical graph neural networks (HGNNs) are used to embed the latent local patterns of structural and bio-physicochemical characteristics for binding residue recognition. We comprehensively evaluate GraphBind on DNA/RNA benchmark datasets. The results demonstrate the superior performance of GraphBind than state-of-the-art methods. Moreover, GraphBind is extended to other ligand-binding residue prediction to verify its generalization capability. Web server of GraphBind is freely available at http://www.csbio.sjtu.edu.cn/bioinf/GraphBind/.

Computational Assessment of Protein-Protein Binding Affinity by Reverse Engineering the Energetics in Protein Complexes

The cellular functions of proteins are maintained by forming diverse complexes. The stability of these complexes is quantified by the measurement of binding affinity, and mutations that alter the binding affinity can cause various diseases such as cancer and diabetes. As a result, accurate estimation of the binding stability and the effects of mutations on changes of binding affinity is a crucial step to understanding the biological functions of proteins and their dysfunctional consequences. It has been hypothesized that the stability of a protein complex is dependent not only on the residues at its binding interface by pairwise interactions but also on all other remaining residues that do not appear at the binding interface. Here, we computationally reconstruct the binding affinity by decomposing it into the contributions of interfacial residues and other non-interfacial residues in a protein complex. We further assume that the contributions of both interfacial and non-interfacial residues to the binding affinity depend on their local structural environments such as solvent-accessible surfaces and secondary structural types. The weights of all corresponding parameters are optimized by Monte-Carlo simulations. After cross-validation against a large-scale dataset, we show that the model not only shows a strong correlation between the absolute values of the experimental and calculated binding affinities, but can also be an effective approach to predict the relative changes of binding affinity from mutations. Moreover, we have found that the optimized weights of many parameters can capture the first-principle chemical and physical features of molecular recognition, therefore reversely engineering the energetics of protein complexes. These results suggest that our method can serve as a useful addition to current computational approaches for predicting binding affinity and understanding the molecular mechanism of protein–protein interactions.

PredictSuperFam-PSS-3D1D: A server for predicting superfamily for the annotation of twilight zone protein sequences

Annotation of twilight zone protein sequences has been hitherto attempted by predicting the fold of the given sequence. We report here the PredictSuperFam-PSS-3D1D method, which predicts the superfamily for a given twilight zone (TZ) protein sequence. Earlier, we have reported that adding predicted secondary structure information into the threading methods could improve fold prediction especially for the TZ protein sequences. In this study, we have analysed the application of the same method to predict superfamilies. Here, in this method, the twilight zone protein sequence is threaded with the 3D1D profiles of the known protein superfamilies library. In addition, weightage for the predicted secondary structure (PSS) is also employed. The performance of the method is benchmarked with twilight zone sequences. In the benchmarks, 62 and 65 percentages of superfamily predictions are obtained with GOR IV and NPS@ predicted secondary structures, respectively. Receiver Operating Characteristic (ROC) curves indicate that the method is sensitive in predicting the superfamilies. A case study has been conducted with the hypothetical protein sequences of Schistosoma haematobium (Blood Fluke) using this method and the results are analyzed. Our method predicts the superfamily for TZ sequences for which, methods based on sequence similarity alone are inadequate. A web server has been developed for our method and it is available online at http://bioinfo.bdu.ac.in/psfpss.