ReLo is a simple and rapid colocalization assay to identify and characterize direct protein-protein interactions.

The characterization of protein-protein interactions (PPIs) is fundamental to the understanding of biochemical processes. Many methods have been established to identify and study direct PPIs; however, screening and investigating PPIs involving large or poorly soluble proteins remains challenging. Here, we introduce ReLo, a simple, rapid, and versatile cell culture-based method for detecting and investigating interactions in a cellular context. Our experiments demonstrate that ReLo specifically detects direct binary PPIs. Furthermore, we show that ReLo bridging experiments can also be used to determine the binding topology of subunits within multiprotein complexes. In addition, ReLo facilitates the identification of protein domains that mediate complex formation, allows screening for interfering point mutations, and it is sensitive to drugs that mediate or disrupt an interaction. In summary, ReLo is a simple and rapid alternative for the study of PPIs, especially when studying structurally complex proteins or when established methods fail.

A protein network refinement method based on module discovery and biological information.

BACKGROUND: The identification of essential proteins can help in understanding the minimum requirements for cell survival and development to discover drug targets and prevent disease. Nowadays, node ranking methods are a common way to identify essential proteins, but the poor data quality of the underlying PIN has somewhat hindered the identification accuracy of essential proteins for these methods in the PIN. Therefore, researchers constructed refinement networks by considering certain biological properties of interacting protein pairs to improve the performance of node ranking methods in the PIN. Studies show that proteins in a complex are more likely to be essential than proteins not present in the complex. However, the modularity is usually ignored for the refinement methods of the PINs. METHODS: Based on this, we proposed a network refinement method based on module discovery and biological information. The idea is, first, to extract the maximal connected subgraph in the PIN, and to divide it into different modules by using Fast-unfolding algorithm; then, to detect critical modules according to the orthologous information, subcellular localization information and topology information within each module; finally, to construct a more refined network (CM-PIN) by using the identified critical modules. RESULTS: To evaluate the effectiveness of the proposed method, we used 12 typical node ranking methods (LAC, DC, DMNC, NC, TP, LID, CC, BC, PR, LR, PeC, WDC) to compare the overall performance of the CM-PIN with those on the S-PIN, D-PIN and RD-PIN. The experimental results showed that the CM-PIN was optimal in terms of the identification number of essential proteins, precision-recall curve, Jackknifing method and other criteria, and can help to identify essential proteins more accurately.

Graph-theoretical prediction of biological modules in quaternary structures of large protein complexes.

MOTIVATION: The functional complexity of biochemical processes is strongly related to the interplay of proteins and their assembly into protein complexes. In recent years, the discovery and characterization of protein complexes have substantially progressed through advances in cryo-electron microscopy, proteomics, and computational structure prediction. This development results in a strong need for computational approaches to analyse the data of large protein complexes for structural and functional characterization. Here, we aim to provide a suitable approach, which processes the growing number of large protein complexes, to obtain biologically meaningful information on the hierarchical organization of the structures of protein complexes. RESULTS: We modelled the quaternary structure of protein complexes as undirected, labelled graphs called complex graphs. In complex graphs, the vertices represent protein chains and the edges spatial chain-chain contacts. We hypothesized that clusters based on the complex graph correspond to functional biological modules. To compute the clusters, we applied the Leiden clustering algorithm. To evaluate our approach, we chose the human respiratory complex I, which has been extensively investigated and exhibits a known biological module structure experimentally validated. Additionally, we characterized a eukaryotic group II chaperonin TRiC/CCT and the head of the bacteriophage Φ29. The analysis of the protein complexes correlated with experimental findings and indicated known functional, biological modules. Using our approach enables not only to predict functional biological modules in large protein complexes with characteristic features but also to investigate the flexibility of specific regions and coformational changes. The predicted modules can aid in the planning and analysis of experiments. AVAILABILITY AND IMPLEMENTATION: Jupyter notebooks to reproduce the examples are available on our public GitHub repository: https://github.com/MolBIFFM/PTGLtools/tree/main/PTGLmodulePrediction.

PPII-AEAT: Prediction of protein-protein interaction inhibitors based on autoencoders with adversarial training.

Protein-protein interactions (PPIs) have shown increasing potential as novel drug targets. The design and development of small molecule inhibitors targeting specific PPIs are crucial for the prevention and treatment of related diseases. Accordingly, effective computational methods are highly desired to meet the emerging need for the large-scale accurate prediction of PPI inhibitors. However, existing machine learning models rely heavily on the manual screening of features and lack generalizability. Here, we propose a new PPI inhibitor prediction method based on autoencoders with adversarial training (named PPII-AEAT) that can adaptively learn molecule representation to cope with different PPI targets. First, Extended-connectivity fingerprints and Mordred descriptors are employed to extract the primary features of small molecular compounds. Then, an autoencoder architecture is trained in three phases to learn high-level representations and predict inhibitory scores. We evaluate PPII-AEAT on nine PPI targets and two different tasks, including the PPI inhibitor identification task and inhibitory potency prediction task. The experimental results show that our proposed PPII-AEAT outperforms state-of-the-art methods.

Revolutionizing protein-protein interaction prediction with deep learning.

Protein-protein interactions (PPIs) are pivotal for driving diverse biological processes, and any disturbance in these interactions can lead to disease. Thus, the study of PPIs has been a central focus in biology. Recent developments in deep learning methods, coupled with the vast genomic sequence data, have significantly boosted the accuracy of predicting protein structures and modeling protein complexes, approaching levels comparable to experimental techniques. Herein, we review the latest advances in the computational methods for modeling 3D protein complexes and the prediction of protein interaction partners, emphasizing the application of deep learning methods deriving from coevolution analysis. The review also highlights biomedical applications of PPI prediction and outlines challenges in the field.

Structural assembly of the bacterial essential interactome.

The study of protein interactions in living organisms is fundamental for understanding biological processes and central metabolic pathways. Yet, our knowledge of the bacterial interactome remains limited. Here, we combined gene deletion mutant analysis with deep-learning protein folding using AlphaFold2 to predict the core bacterial essential interactome. We predicted and modeled 1402 interactions between essential proteins in bacteria and generated 146 high-accuracy models. Our analysis reveals previously unknown details about the assembly mechanisms of these complexes, highlighting the importance of specific structural features in their stability and function. Our work provides a framework for predicting the essential interactomes of bacteria and highlight the potential of deep-learning algorithms in advancing our understanding of the complex biology of living organisms. Also, the results presented here offer a promising approach to identify novel antibiotic targets.

Pitfalls of machine learning models for protein-protein interaction networks.

MOTIVATION: Protein-protein interactions (PPIs) are essential to understanding biological pathways as well as their roles in development and disease. Computational tools, based on classic machine learning, have been successful at predicting PPIs in silico, but the lack of consistent and reliable frameworks for this task has led to network models that are difficult to compare and discrepancies between algorithms that remain unexplained. RESULTS: To better understand the underlying inference mechanisms that underpin these models, we designed an open-source framework for benchmarking that accounts for a range of biological and statistical pitfalls while facilitating reproducibility. We use it to shed light on the impact of network topology and how different algorithms deal with highly connected proteins. By studying functional genomics-based and sequence-based models on human PPIs, we show their complementarity as the former performs best on lone proteins while the latter specializes in interactions involving hubs. We also show that algorithm design has little impact on performance with functional genomic data. We replicate our results between both human and S. cerevisiae data and demonstrate that models using functional genomics are better suited to PPI prediction across species. With rapidly increasing amounts of sequence and functional genomics data, our study provides a principled foundation for future construction, comparison, and application of PPI networks. AVAILABILITY AND IMPLEMENTATION: The code and data are available on GitHub: https://github.com/Llannelongue/B4PPI.

Human-virus protein-protein interactions maps assist in revealing the pathogenesis of viral infection.

Many significant viral infections have been recorded in human history, which have caused enormous negative impacts worldwide. Human-virus protein-protein interactions (PPIs) mediate viral infection and immune processes in the host. The identification, quantification, localization, and construction of human-virus PPIs maps are critical prerequisites for understanding the biophysical basis of the viral invasion process and characterising the framework for all protein functions. With the technological revolution and the introduction of artificial intelligence, the human-virus PPIs maps have been expanded rapidly in the past decade and shed light on solving complicated biomedical problems. However, there is still a lack of prospective insight into the field. In this work, we comprehensively review and compare the effectiveness, potential, and limitations of diverse approaches for constructing large-scale PPIs maps in human-virus, including experimental methods based on biophysics and biochemistry, databases of human-virus PPIs, computational methods based on artificial intelligence, and tools for visualising PPIs maps. The work aims to provide a toolbox for researchers, hoping to better assist in deciphering the relationship between humans and viruses.

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.

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.

AraPathogen2.0: An Improved Prediction of Plant-Pathogen Protein-Protein Interactions Empowered by the Natural Language Processing Technique.

Plant-pathogen protein-protein interactions (PPIs) play crucial roles in the arm race between plants and pathogens. Therefore, the identification of these interspecies PPIs is very important for the mechanistic understanding of pathogen infection and plant immunity. Computational prediction methods can complement experimental efforts, but their predictive performance still needs to be improved. Motivated by the rapid development of natural language processing and its successful applications in the field of protein bioinformatics, here we present an improved XGBoost-based plant-pathogen PPI predictor (i.e., AraPathogen2.0), in which sequence encodings from the pretrained protein language model ESM2 and Arabidopsis PPI network-related node representations from the graph embedding technique struc2vec are used as input. Stringent benchmark experiments showed that AraPathogen2.0 could achieve a better performance than its precedent version, especially for processing the test data set with novel proteins unseen in the training data.

A Multimodal Deep Learning Framework for Predicting PPI-Modulator Interactions.

Protein-protein interactions (PPIs) are essential for various biological processes and diseases. However, most existing computational methods for identifying PPI modulators require either target structure or reference modulators, which restricts their applicability to novel PPI targets. To address this challenge, we propose MultiPPIMI, a sequence-based deep learning framework that predicts the interaction between any given PPI target and modulator. MultiPPIMI integrates multimodal representations of PPI targets and modulators and uses a bilinear attention network to capture intermolecular interactions. Experimental results on our curated benchmark data set show that MultiPPIMI achieves an average AUROC of 0.837 in three cold-start scenarios and an AUROC of 0.994 in the random-split scenario. Furthermore, the case study shows that MultiPPIMI can assist molecular docking simulations in screening inhibitors of Keap1/Nrf2 PPI interactions. We believe that the proposed method provides a promising way to screen PPI-targeted modulators.

DL-PPI: a method on prediction of sequenced protein-protein interaction based on deep learning.

PURPOSE: Sequenced Protein-Protein Interaction (PPI) prediction represents a pivotal area of study in biology, playing a crucial role in elucidating the mechanistic underpinnings of diseases and facilitating the design of novel therapeutic interventions. Conventional methods for extracting features through experimental processes have proven to be both costly and exceedingly complex. In light of these challenges, the scientific community has turned to computational approaches, particularly those grounded in deep learning methodologies. Despite the progress achieved by current deep learning technologies, their effectiveness diminishes when applied to larger, unfamiliar datasets. RESULTS: In this study, the paper introduces a novel deep learning framework, termed DL-PPI, for predicting PPIs based on sequence data. The proposed framework comprises two key components aimed at improving the accuracy of feature extraction from individual protein sequences and capturing relationships between proteins in unfamiliar datasets. 1. Protein Node Feature Extraction Module: To enhance the accuracy of feature extraction from individual protein sequences and facilitate the understanding of relationships between proteins in unknown datasets, the paper devised a novel protein node feature extraction module utilizing the Inception method. This module efficiently captures relevant patterns and representations within protein sequences, enabling more informative feature extraction. 2. Feature-Relational Reasoning Network (FRN): In the Global Feature Extraction module of our model, the paper developed a novel FRN that leveraged Graph Neural Networks to determine interactions between pairs of input proteins. The FRN effectively captures the underlying relational information between proteins, contributing to improved PPI predictions. DL-PPI framework demonstrates state-of-the-art performance in the realm of sequence-based PPI prediction.

Growing ecosystem of deep learning methods for modeling protein-protein interactions.

Numerous cellular functions rely on protein-protein interactions. Efforts to comprehensively characterize them remain challenged however by the diversity of molecular recognition mechanisms employed within the proteome. Deep learning has emerged as a promising approach for tackling this problem by exploiting both experimental data and basic biophysical knowledge about protein interactions. Here, we review the growing ecosystem of deep learning methods for modeling protein interactions, highlighting the diversity of these biophysically informed models and their respective trade-offs. We discuss recent successes in using representation learning to capture complex features pertinent to predicting protein interactions and interaction sites, geometric deep learning to reason over protein structures and predict complex structures, and generative modeling to design de novo protein assemblies. We also outline some of the outstanding challenges and promising new directions. Opportunities abound to discover novel interactions, elucidate their physical mechanisms, and engineer binders to modulate their functions using deep learning and, ultimately, unravel how protein interactions orchestrate complex cellular behaviors.

Mapping protein states and interactions across the tree of life with co-fractionation mass spectrometry.

We present CFdb, a harmonized resource of interaction proteomics data from 411 co-fractionation mass spectrometry (CF-MS) datasets spanning 21,703 fractions. Meta-analysis of this resource charts protein abundance, phosphorylation, and interactions throughout the tree of life, including a reference map of the human interactome. We show how large-scale CF-MS data can enhance analyses of individual CF-MS datasets, and exemplify this strategy by mapping the honey bee interactome.

SAMNA: accurate alignment of multiple biological networks based on simulated annealing.

Proteins are important parts of the biological structures and encode a lot of biological information. Protein-protein interaction network alignment is a model for analyzing proteins that helps discover conserved functions between organisms and predict unknown functions. In particular, multi-network alignment aims at finding the mapping relationship among multiple network nodes, so as to transfer the knowledge across species. However, with the increasing complexity of PPI networks, how to perform network alignment more accurately and efficiently is a new challenge. This paper proposes a new global network alignment algorithm called Simulated Annealing Multiple Network Alignment (SAMNA), using both network topology and sequence homology information. To generate the alignment, SAMNA first generates cross-network candidate clusters by a clustering algorithm on a k-partite similarity graph constructed with sequence similarity information, and then selects candidate cluster nodes as alignment results and optimizes them using an improved simulated annealing algorithm. Finally, the SAMNA algorithm was experimented on synthetic and real-world network datasets, and the results showed that SAMNA outperformed the state-of-the-art algorithm in biological performance.

The social and structural architecture of the yeast protein interactome.

Cellular functions are mediated by protein-protein interactions, and mapping the interactome provides fundamental insights into biological systems. Affinity purification coupled to mass spectrometry is an ideal tool for such mapping, but it has been difficult to identify low copy number complexes, membrane complexes and complexes that are disrupted by protein tagging. As a result, our current knowledge of the interactome is far from complete, and assessing the reliability of reported interactions is challenging. Here we develop a sensitive high-throughput method using highly reproducible affinity enrichment coupled to mass spectrometry combined with a quantitative two-dimensional analysis strategy to comprehensively map the interactome of Saccharomyces cerevisiae. Thousand-fold reduced volumes in 96-well format enabled replicate analysis of the endogenous GFP-tagged library covering the entire expressed yeast proteome1. The 4,159 pull-downs generated a highly structured network of 3,927 proteins connected by 31,004 interactions, doubling the number of proteins and tripling the number of reliable interactions compared with existing interactome maps2. This includes very-low-abundance epigenetic complexes, organellar membrane complexes and non-taggable complexes inferred by abundance correlation. This nearly saturated interactome reveals that the vast majority of yeast proteins are highly connected, with an average of 16 interactors. Similar to social networks between humans, the average shortest distance between proteins is 4.2 interactions. AlphaFold-Multimer provided novel insights into the functional roles of previously uncharacterized proteins in complexes. Our web portal ( www.yeast-interactome.org ) enables extensive exploration of the interactome dataset.

Elucidating the dynamic remodelling of Escherichia coli interactome in different growth conditions using multiplex co-fractionation MS (mCF-MS).

Most proteins function by forming complexes within a dynamic interconnected network that underlies various biological mechanisms. To systematically investigate such interactomes, high-throughput techniques, including CF-MS, have been developed to capture, identify, and quantify protein-protein interactions (PPIs) on a large scale. Compared to other techniques, CF-MS allows the global identification and quantification of native protein complexes in one setting, without genetic manipulation. Furthermore, quantitative CF-MS can potentially elucidate the distribution of a protein in multiple co-elution features, informing the stoichiometries and dynamics of a target protein complex. In this issue, Youssef et al. (Proteomics 2023, 00, e2200404) combined multiplex CF-MS and a new algorithm to study the dynamics of the PPI network for Escherichia coli grown under ten different conditions. Although the results demonstrated that most proteins remained stable, the authors were able to detect disrupted interactions that were growth condition specific. Further bioinformatics analyses also revealed the biophysical properties and structural patterns that govern such a response.

A seed expansion-based method to identify essential proteins by integrating protein-protein interaction sub-networks and multiple biological characteristics.

BACKGROUND: The identification of essential proteins is of great significance in biology and pathology. However, protein-protein interaction (PPI) data obtained through high-throughput technology include a high number of false positives. To overcome this limitation, numerous computational algorithms based on biological characteristics and topological features have been proposed to identify essential proteins. RESULTS: In this paper, we propose a novel method named SESN for identifying essential proteins. It is a seed expansion method based on PPI sub-networks and multiple biological characteristics. Firstly, SESN utilizes gene expression data to construct PPI sub-networks. Secondly, seed expansion is performed simultaneously in each sub-network, and the expansion process is based on the topological features of predicted essential proteins. Thirdly, the error correction mechanism is based on multiple biological characteristics and the entire PPI network. Finally, SESN analyzes the impact of each biological characteristic, including protein complex, gene expression data, GO annotations, and subcellular localization, and adopts the biological data with the best experimental results. The output of SESN is a set of predicted essential proteins. CONCLUSIONS: The analysis of each component of SESN indicates the effectiveness of all components. We conduct comparison experiments using three datasets from two species, and the experimental results demonstrate that SESN achieves superior performance compared to other methods.

BBLN: A bilateral-branch learning network for unknown protein-protein interaction prediction.

Unknown Protein-Protein Interactions (PPIs) prediction has a huge demand in the biological analysis field. Since the effect of the limited availability of protein data is severe, transferable representations are highly demanded to be learned from various data. The latest works enhance the model performance on unknown PPIs prediction and have achieved certain improvements by combining protein information and relation information on PPI graph. However, such methods inevitably suffer from a so-called information monotonicity problem that limits the improvements when encountering large amounts of unknown PPIs. The prediction performance cannot be actually increased without considering the complementary information and relationship information among various modalities of protein data. To this end, we propose a bilateral-branch learning network to deeply enhance the both complementary and relationship information based on the amino acid sequence and gene ontology from multi- and cross-modal views. Experimental results on massive real-world datasets show that our method significantly outperforms the previous state-of-the-art on both traditional and novel unknown PPIs prediction.