EGRET: edge aggregated graph attention networks and transfer learning improve protein-protein interaction site prediction

Pair-EGRET: enhancing the prediction of protein-protein interaction sites through graph attention networks and protein language models

MOTIVATION

Proteins are responsible for most biological functions, many of which require the interaction of more than one protein molecule. However, accurately predicting protein-protein interaction (PPI) sites (the interfacial residues of a protein that interact with other protein molecules) remains a challenge. The growing demand and cost associated with the reliable identification of PPI sites using conventional experimental methods call for computational tools for automated prediction and understanding of PPIs.

RESULTS

We present Pair-EGRET, an edge-aggregated graph attention network that leverages the features extracted from pretrained transformer-like models to accurately predict PPI sites. Pair-EGRET works on a k-nearest neighbor graph, representing the 3D structure of a protein, and utilizes the cross-attention mechanism for accurate identification of interfacial residues of a pair of proteins. Through an extensive evaluation study using a diverse array of experimental data, evaluation metrics, and case studies on representative protein sequences, we demonstrate that Pair-EGRET can achieve remarkable performance in predicting PPI sites. Moreover, Pair-EGRET can provide interpretable insights from the learned cross-attention matrix.

AVAILABILITY AND IMPLEMENTATION

Pair-EGRET is freely available in open source form at the GitHub Repository https://github.com/1705004/Pair-EGRET.

PMSFF: Improved Protein Binding Residues Prediction through Multi-Scale Sequence-Based Feature Fusion Strategy

Proteins perform different biological functions through binding with various molecules which are mediated by a few key residues and accurate prediction of such protein binding residues (PBRs) is crucial for understanding cellular processes and for designing new drugs. Many computational prediction approaches have been proposed to identify PBRs with sequence-based features. However, these approaches face two main challenges: (1) these methods only concatenate residue feature vectors with a simple sliding window strategy, and (2) it is challenging to find a uniform sliding window size suitable for learning embeddings across different types of PBRs. In this study, we propose one novel framework that could apply multiple types of PBRs Prediciton task through Multi-scale Sequence-based Feature Fusion (PMSFF) strategy. Firstly, PMSFF employs a pre-trained language model named ProtT5, to encode amino acid residues in protein sequences. Then, it generates multi-scale residue embeddings by applying multi-size windows to capture effective neighboring residues and multi-size kernels to learn information across different scales. Additionally, the proposed model treats protein sequences as sentences, employing a bidirectional GRU to learn global context. We also collect benchmark datasets encompassing various PBRs types and evaluate our PMSFF approach to these datasets. Compared with state-of-the-art methods, PMSFF demonstrates superior performance on most PBRs prediction tasks.

DGCPPISP: a PPI site prediction model based on dynamic graph convolutional network and two-stage transfer learning

BACKGROUND

Proteins play a pivotal role in the diverse array of biological processes, making the precise prediction of protein-protein interaction (PPI) sites critical to numerous disciplines including biology, medicine and pharmacy. While deep learning methods have progressively been implemented for the prediction of PPI sites within proteins, the task of enhancing their predictive performance remains an arduous challenge.

RESULTS

In this paper, we propose a novel PPI site prediction model (DGCPPISP) based on a dynamic graph convolutional neural network and a two-stage transfer learning strategy. Initially, we implement the transfer learning from dual perspectives, namely feature input and model training that serve to supply efficacious prior knowledge for our model. Subsequently, we construct a network designed for the second stage of training, which is built on the foundation of dynamic graph convolution.

CONCLUSIONS

To evaluate its effectiveness, the performance of the DGCPPISP model is scrutinized using two benchmark datasets. The ensuing results demonstrate that DGCPPISP outshines competing methods in terms of performance. Specifically, DGCPPISP surpasses the second-best method, EGRET, by margins of 5.9%, 10.1%, and 13.3% for F1-measure, AUPRC, and MCC metrics respectively on Dset_186_72_PDB164. Similarly, on Dset_331, it eclipses the performance of the runner-up method, HN-PPISP, by 14.5%, 19.8%, and 29.9% respectively.

PhosAF: An integrated deep learning architecture for predicting protein phosphorylation sites with AlphaFold2 predicted structures

Phosphorylation is indispensable in comprehending biological processes, while biological experimental methods for identifying phosphorylation sites are tedious and arduous. With the rapid growth of biotechnology, deep learning methods have made significant progress in site prediction tasks. Nevertheless, most existing predictors only consider protein sequence information, that limits the capture of protein spatial information. Building upon the latest advancement in protein structure prediction by AlphaFold2, a novel integrated deep learning architecture PhosAF is developed to predict phosphorylation sites in human proteins by integrating CMA-Net and MFC-Net, which considers sequence and structure information predicted by AlphaFold2. Here, CMA-Net module is composed of multiple convolutional neural network layers and multi-head attention is appended to obtaining the local and long-term dependencies of sequence features. Meanwhile, the MFC-Net module composed of deep neural network layers is used to capture the complex representations of evolutionary and structure features. Furthermore, different features are combined to predict the final phosphorylation sites. In addition, we put forward a new strategy to construct reliable negative samples via protein secondary structures. Experimental results on independent test data and case study indicate that our model PhosAF surpasses the current most advanced methods in phosphorylation site prediction.

Protein-Protein Interfaces: A Graph Neural Network Approach

Protein-protein interactions (PPIs) are fundamental processes governing cellular functions, crucial for understanding biological systems at the molecular level. Compared to experimental methods for PPI prediction and site identification, computational deep learning approaches represent an affordable and efficient solution to tackle these problems. Since protein structure can be summarized as a graph, graph neural networks (GNNs) represent the ideal deep learning architecture for the task. In this work, PPI prediction is modeled as a node-focused binary classification task using a GNN to determine whether a generic residue is part of the interface. Biological data were obtained from the Protein Data Bank in Europe (PDBe), leveraging the Protein Interfaces, Surfaces, and Assemblies (PISA) service. To gain a deeper understanding of how proteins interact, the data obtained from PISA were assembled into three datasets: Whole, Interface, and Chain, consisting of data on the whole protein, couples of interacting chains, and single chains, respectively. These three datasets correspond to three different nuances of the problem: identifying interfaces between protein complexes, between chains of the same protein, and interface regions in general. The results indicate that GNNs are capable of solving each of the three tasks with very good performance levels.

Improving AlphaFold Predicted Contacts for Alpha-Helical Transmembrane Proteins Using Structural Features

Residue contact maps provide a condensed two-dimensional representation of three-dimensional protein structures, serving as a foundational framework in structural modeling but also as an effective tool in their own right in identifying inter-helical binding sites and drawing insights about protein function. Treating contact maps primarily as an intermediate step for 3D structure prediction, contact prediction methods have limited themselves exclusively to sequential features. Now that AlphaFold2 predicts 3D structures with good accuracy in general, we examine (1) how well predicted 3D structures can be directly used for deciding residue contacts, and (2) whether features from 3D structures can be leveraged to further improve residue contact prediction. With a well-known benchmark dataset, we tested predicting inter-helical residue contact based on AlphaFold2's predicted structures, which gave an 83% average precision, already outperforming a sequential features-based state-of-the-art model. We then developed a procedure to extract features from atomic structure in the neighborhood of a residue pair, hypothesizing that these features will be useful in determining if the residue pair is in contact, provided the structure is decently accurate, such as predicted by AlphaFold2. Training on features generated from experimentally determined structures, we leveraged knowledge from known structures to significantly improve residue contact prediction, when testing using the same set of features but derived using AlphaFold2 structures. Our results demonstrate a remarkable improvement over AlphaFold2, achieving over 91.9% average precision for a held-out subset and over 89.5% average precision in cross-validation experiments.

A comprehensive review of protein-centric predictors for biomolecular interactions: from proteins to nucleic acids and beyond

Proteins interact with diverse ligands to perform a large number of biological functions, such as gene expression and signal transduction. Accurate identification of these protein-ligand interactions is crucial to the understanding of molecular mechanisms and the development of new drugs. However, traditional biological experiments are time-consuming and expensive. With the development of high-throughput technologies, an increasing amount of protein data is available. In the past decades, many computational methods have been developed to predict protein-ligand interactions. Here, we review a comprehensive set of over 160 protein-ligand interaction predictors, which cover protein-protein, protein-nucleic acid, protein-peptide and protein-other ligands (nucleotide, heme, ion) interactions. We have carried out a comprehensive analysis of the above four types of predictors from several significant perspectives, including their inputs, feature profiles, models, availability, etc. The current methods primarily rely on protein sequences, especially utilizing evolutionary information. The significant improvement in predictions is attributed to deep learning methods. Additionally, sequence-based pretrained models and structure-based approaches are emerging as new trends.

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

Seq-InSite: sequence supersedes structure for protein interaction site prediction

MOTIVATION

Proteins accomplish cellular functions by interacting with each other, which makes the prediction of interaction sites a fundamental problem. As experimental methods are expensive and time consuming, computational prediction of the interaction sites has been studied extensively. Structure-based programs are the most accurate, while the sequence-based ones are much more widely applicable, as the sequences available outnumber the structures by two orders of magnitude. Ideally, we would like a tool that has the quality of the former and the applicability of the latter.

RESULTS

We provide here the first solution that achieves these two goals. Our new sequence-based program, Seq-InSite, greatly surpasses the performance of sequence-based models, matching the quality of state-of-the-art structure-based predictors, thus effectively superseding the need for models requiring structure. The predictive power of Seq-InSite is illustrated using an analysis of evolutionary conservation for four protein sequences.

AVAILABILITY AND IMPLEMENTATION

Seq-InSite is freely available as a web server at http://seq-insite.csd.uwo.ca/ and as free source code, including trained models and all datasets used for training and testing, at https://github.com/lucian-ilie/Seq-InSite.

GHGPR-PPIS: A graph convolutional network for identifying protein-protein interaction site using heat kernel with Generalized PageRank techniques and edge self-attention feature processing block

Accurately pinpointing protein-protein interaction site (PPIS) on the molecular level is of utmost significance for annotating protein function and comprehending the mechanisms underpinning various diseases. While numerous computational methods for predicting PPIS have emerged, they have indeed mitigated the labor and time constraints associated with traditional experimental methods. However, the predictive accuracy of these methods has yet to reach the desired threshold. In this context, we proposed a groundbreaking graph-based computational model called GHGPR-PPIS. This innovative model leveraged a graph convolutional network using heat kernel (GraphHeat) in conjunction with Generalized PageRank techniques (GHGPR) to predict PPIS. Additionally, building upon the GHGPR framework, we devised an edge self-attention feature processing block, further augmenting the performance of the model. Experimental findings conclusively demonstrated that GHGPR-PPIS surpassed all competing state-of-the-art models when evaluated on the benchmark test set. Impressively, on two distinct independent test sets and a specific protein chain, GHGPR-PPIS consistently demonstrated superior generalization performance and practical applicability compared to the comparative model, AGAT-PPIS. Lastly, leveraging the t-SNE dimensionality reduction algorithm and clustering visualization technique, we delved into an interpretability analysis of the effectiveness of GHGPR-PPIS by meticulously comparing the outputs from different stages of the model.

Leveraging transformers-based language models in proteome bioinformatics

In recent years, the rapid growth of biological data has increased interest in using bioinformatics to analyze and interpret this data. Proteomics, which studies the structure, function, and interactions of proteins, is a crucial area of bioinformatics. Using natural language processing (NLP) techniques in proteomics is an emerging field that combines machine learning and text mining to analyze biological data. Recently, transformer-based NLP models have gained significant attention for their ability to process variable-length input sequences in parallel, using self-attention mechanisms to capture long-range dependencies. In this review paper, we discuss the recent advancements in transformer-based NLP models in proteome bioinformatics and examine their advantages, limitations, and potential applications to improve the accuracy and efficiency of various tasks. Additionally, we highlight the challenges and future directions of using these models in proteome bioinformatics research. Overall, this review provides valuable insights into the potential of transformer-based NLP models to revolutionize proteome bioinformatics.

Protein-DNA interface hotspots prediction based on fusion features of embeddings of protein language model and handcrafted features

The identification of hotspot residues at the protein-DNA binding interfaces plays a crucial role in various aspects such as drug discovery and disease treatment. Although experimental methods such as alanine scanning mutagenesis have been developed to determine the hotspot residues on protein-DNA interfaces, they are both inefficient and costly. Therefore, it is highly necessary to develop efficient and accurate computational methods for predicting hotspot residues. Several computational methods have been developed, however, they are mainly based on hand-crafted features which may not be able to represent all the information of proteins. In this regard, we propose a model called PDH-EH, which utilizes fused features of embeddings extracted from a protein language model (PLM) and handcrafted features. After we extracted the total 1141 dimensional features, we used mRMR to select the optimal feature subset. Based on the optimal feature subset, several different learning algorithms such as Random Forest, Support Vector Machine, and XGBoost were used to build the models. The cross-validation results on the training dataset show that the model built by using Random Forest achieves the highest AUROC. Further evaluation on the independent test set shows that our model outperforms the existing state-of-the-art models. Moreover, the effectiveness and interpretability of embeddings extracted from PLM were demonstrated in our analysis. The codes and datasets used in this study are available at: https://github.com/lixiangli01/PDH-EH.

Co-embedding of edges and nodes with deep graph convolutional neural networks

Graph neural networks (GNNs) have significant advantages in dealing with non-Euclidean data and have been widely used in various fields. However, most of the existing GNN models face two main challenges: (1) Most GNN models built upon the message-passing framework exhibit a shallow structure, which hampers their ability to efficiently transmit information between distant nodes. To address this, we aim to propose a novel message-passing framework, enabling the construction of GNN models with deep architectures akin to convolutional neural networks (CNNs), potentially comprising dozens or even hundreds of layers. (2) Existing models often approach the learning of edge and node features as separate tasks. To overcome this limitation, we aspire to develop a deep graph convolutional neural network learning framework capable of simultaneously acquiring edge embeddings and node embeddings. By utilizing the learned multi-dimensional edge feature matrix, we construct multi-channel filters to more effectively capture accurate node features. To address these challenges, we propose the Co-embedding of Edges and Nodes with Deep Graph Convolutional Neural Networks (CEN-DGCNN). In our approach, we propose a novel message-passing framework that can fully integrate and utilize both node features and multi-dimensional edge features. Based on this framework, we develop a deep graph convolutional neural network model that prevents over-smoothing and obtains node non-local structural features and refined high-order node features by extracting long-distance dependencies between nodes and utilizing multi-dimensional edge features. Moreover, we propose a novel graph convolutional layer that can learn node embeddings and multi-dimensional edge embeddings simultaneously. The layer updates multi-dimensional edge embeddings across layers based on node features and an attention mechanism, which enables efficient utilization and fusion of both node and edge features. Additionally, we propose a multi-dimensional edge feature encoding method based on directed edges, and use the resulting multi-dimensional edge feature matrix to construct a multi-channel filter to filter the node information. Lastly, extensive experiments show that CEN-DGCNN outperforms a large number of graph neural network baseline methods, demonstrating the effectiveness of our proposed method.

A Transformer-Based Ensemble Framework for the Prediction of Protein-Protein Interaction Sites

The identification of protein-protein interaction (PPI) sites is essential in the research of protein function and the discovery of new drugs. So far, a variety of computational tools based on machine learning have been developed to accelerate the identification of PPI sites. However, existing methods suffer from the low predictive accuracy or the limited scope of application. Specifically, some methods learned only global or local sequential features, leading to low predictive accuracy, while others achieved improved performance by extracting residue interactions from structures but were limited in their application scope for the serious dependence on precise structure information. There is an urgent need to develop a method that integrates comprehensive information to realize proteome-wide accurate profiling of PPI sites. Herein, a novel ensemble framework for PPI sites prediction, EnsemPPIS, was therefore proposed based on transformer and gated convolutional networks. EnsemPPIS can effectively capture not only global and local patterns but also residue interactions. Specifically, EnsemPPIS was unique in (a) extracting residue interactions from protein sequences with transformer and (b) further integrating global and local sequential features with the ensemble learning strategy. Compared with various existing methods, EnsemPPIS exhibited either superior performance or broader applicability on multiple PPI sites prediction tasks. Moreover, pattern analysis based on the interpretability of EnsemPPIS demonstrated that EnsemPPIS was fully capable of learning residue interactions within the local structure of PPI sites using only sequence information. The web server of EnsemPPIS is freely available at http://idrblab.org/ensemppis.

Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review

Deep learning, a potent branch of artificial intelligence, is steadily leaving its transformative imprint across multiple disciplines. Within computational biology, it is expediting progress in the understanding of Protein-Protein Interactions (PPIs), key components governing a wide array of biological functionalities. Hence, an in-depth exploration of PPIs is crucial for decoding the intricate biological system dynamics and unveiling potential avenues for therapeutic interventions. As the deployment of deep learning techniques in PPI analysis proliferates at an accelerated pace, there exists an immediate demand for an exhaustive review that encapsulates and critically assesses these novel developments. Addressing this requirement, this review offers a detailed analysis of the literature from 2021 to 2023, highlighting the cutting-edge deep learning methodologies harnessed for PPI analysis. Thus, this review stands as a crucial reference for researchers in the discipline, presenting an overview of the recent studies in the field. This consolidation helps elucidate the dynamic paradigm of PPI analysis, the evolution of deep learning techniques, and their interdependent dynamics. This scrutiny is expected to serve as a vital aid for researchers, both well-established and newcomers, assisting them in maneuvering the rapidly shifting terrain of deep learning applications in PPI analysis.

E-SNPs&GO: embedding of protein sequence and function improves the annotation of human pathogenic variants

MOTIVATION

The advent of massive DNA sequencing technologies is producing a huge number of human single-nucleotide polymorphisms occurring in protein-coding regions and possibly changing their sequences. Discriminating harmful protein variations from neutral ones is one of the crucial challenges in precision medicine. Computational tools based on artificial intelligence provide models for protein sequence encoding, bypassing database searches for evolutionary information. We leverage the new encoding schemes for an efficient annotation of protein variants.

RESULTS

E-SNPs&GO is a novel method that, given an input protein sequence and a single amino acid variation, can predict whether the variation is related to diseases or not. The proposed method adopts an input encoding completely based on protein language models and embedding techniques, specifically devised to encode protein sequences and GO functional annotations. We trained our model on a newly generated dataset of 101 146 human protein single amino acid variants in 13 661 proteins, derived from public resources. When tested on a blind set comprising 10 266 variants, our method well compares to recent approaches released in literature for the same task, reaching a Matthews Correlation Coefficient score of 0.72. We propose E-SNPs&GO as a suitable, efficient and accurate large-scale annotator of protein variant datasets.

AVAILABILITY AND IMPLEMENTATION

The method is available as a webserver at https://esnpsandgo.biocomp.unibo.it. Datasets and predictions are available at https://esnpsandgo.biocomp.unibo.it/datasets.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.