A neural network-based pipeline that integrates amino acid sequences with structural features is developed and provides a modular prototype for follow-up, more extensive protein modeling, including larger proteins and sequence of variable sizes.
Abstract
In view of understanding protein–protein interactions, we present a proof-of-principles workflow able to learn and make predictions. To this end, a neural network-based pipeline that integrates amino acid sequences with structural features is developed. At a first step, an undercomplete autoencoder compresses the high-dimensional protein sequence and structural into embeddings. These, and thereby the learned encoder together with protein–protein interaction scores from known databases, are passed to a supervised interaction-prediction network, which is constructed as a fully connected architecture. The latter can process embeddings of protein pairs and perform two tasks: (a) classify whether an interaction occurs (binary classification) or (b) predict this interaction through a score metric (regression). The use of structural data in addition to sequence data is assessed in view of an enhancement in the prediction. By this, a proof-of-principles investigation of protein interactions is demonstrated based on different embedding information. Our learning results underline the importance of sequence data rather than raw protein residue coordinates in the predictive workflow. The latter provides a modular prototype for follow-up, more extensive protein modeling, including larger proteins and sequence of variable sizes. This prototype workflow should be combined with physics-based modeling for enhanced information gain and a detailed insight into interaction and conformational aspects of protein complexes.
In computational structural biology, it is still very hard to accurately find protein-protein interaction (PPI) sites and estimate how strong the interaction would be. In this research, we provide an innovative two-stage deep learning framework that combines residue-level graph representation learning with protein-level regression to achieve a thorough modeling of protein interactions. Protein structures first encoded as residue graphs, with nodes that stand for amino acids and edges that show how close they are to each other in space. To find binding residues, a deep residual Graph Attention Network v2 (GATv2) uses multi-head attention, residual connections, and Jumping Knowledge aggregation to collect long-range relationships and structural information at different scales. Using residue-level predictions, protein embeddings are created and put together to provide paired representations that show how similar and different two interacting proteins are. After that, these representations utilized to train a regression model that can predict continuous interaction strength ratings. The proposed model tested using a huge human PPI dataset that has 2,242 complexes. The proposed model performs very well at the residue level, with an AUROC of 0.9625, an AUPRC of 0.9149, an F1-score of 0.8192, and an MCC of 0.7674. The protein-level regression model also does a great job of predicting, with an RMSE of 0.2806, an MAE of 0.1635, and a R2 of 0.6500 on the test set. It also has high correlation coefficients (Pearson = 0.8069, Spearman = 0.7500), which means that the predicted and true interaction strengths are very similar. In general, the proposed model is a single, scalable approach that connects predicting binding sites at the residue level with estimating interaction strength at the protein level. This gives us a better understanding of the structural processes that control PPI.
Oras A. Hussein, E. Al-Shamery· Journal of Intelligent Infor...· 0 citations
HyBind-NN is developed, a multimodal graph neural network that integrates protein language models (PLMs) with 3D structural and dynamic datasets to predict protein–protein and protein–peptide affinity, and it is demonstrated that combining ESM-2 sequence embeddings with precise 3D Voronoi spatial geometry enables accurate affinity predictions across diverse structural datasets.
E. A. Bogdanova, A. Chernukhin, Alexey K. Shaytan· International Journal of Mol...· 0 citations
A protein’s function depends not just on its own structure and localization, but also on the interactions with its partners. Many proteins are therefore better described by a set of partner-dependent roles than by a single annotation. Yet most approaches to the functional interpretation of protein-protein interactions (PPIs) remain protein or set-centric. They rely on pre-existing annotations, and perform worst where knowledge is sparse. Here, we present MAPPIE (Map of Protein-Protein Interaction Embeddings), a method that treats each PPI, rather than each protein, as a unit of representation. From 199,137 human interactions spanning 15,503 proteins, we build a two-dimensional map of the human PPI landscape for functional discovery. Protein language model embeddings for two protein interaction partners are combined and compressed into a latent space, with model selection guided by domain-domain interactions used as a structural proxy for interaction similarity. The resulting geometry separates domain defined interaction classes, organizes disorder associated interactions spatially, and splits interactions involving the same protein by partner. A query PPI’s latent neighbourhood recovers its own annotated functions across molecular, complex, pathway, and biological processes. MAPPIE contributes most where existing functional evidence is weakest, outperforming interactome and sequence identity baselines for sparsely connected interactions. MAPPIE neighbours of query PPIs are enriched for partners in independent protein networks, recovering curated complex-level function even when subunits are spread across the map. Applied to a human dark interactome, MAPPIE assigns specific, experimentally supported functions to dark hub proteins.
Mert Cihan, Ute Distler, M. Andrade-Navarro· bioRxiv· 0 citations
Mapping the protein interactome is fundamental to understanding disease mechanisms and facilitating therapeutic development. Although protein language models (PLMs) such as ESM-2 have advanced protein-protein interaction (PPI) prediction, their high-dimensional representations remain difficult to connect to verifiable biological signals. To address this limitation, we propose HybridStack-PPI, a gray-box framework that combines ESM-2 sequence representations with explicit physicochemical and motif-derived biological descriptors. The architecture uses motif-anchored local pooling global mean pooling, symmetric pair encoding, fold-internal feature selection, LightGBM branch learners, and an elastic-net logistic-regression stacking layer. We evaluated the method using a C3 cluster-based cross-validation protocol with a 40% sequence-identity clustering threshold and a Same-GO hard-negative setting in which negative candidates shared functional annotations with positive pairs. Under this setting, HybridStack-PPI reached a Human ROC-AUC of 73.65%, PR-AUC of 91.35%, MCC of 28.06%, and specificity of 75.61%. The results indicate a conservative operating point: compared to more recall-oriented baselines, the proposed stack trades lower recall and F1 for higher specificity, MCC, and ranking behavior under functionally similar negative samples. We further reported cross-species transfer, ablation, latency, SHAP-based descriptor attribution, and meta-learner coefficient analyses to clarify both the promise and limitations of biologically informed PPI prediction.
T. T. Nguyen, X. Mai, N. Nguyen· IEEE Access· 0 citations
Multiple sequence alignment (MSA) Pairformer is presented, a protein language model that builds on AlphaFold2/3's bidirectional refinement between sequence and pairwise residue representations to accurately model the evolution of protein-protein interactions, despite training exclusively on individual chains.
Yo Akiyama, Zhidian Zhang, Olivia Tang et al.· Cell· 2 citations
Computational modeling provides geometric insight into protein-protein interactions without requiring the resources of experimentation. However, reliability can be hindered when modeling proteins with distinctive features, such as antibodies, that use flexible, polar-rich loops to bind antigens. We developed ProteinDock, a physics-based tool that can be used in combination with leading modeling programs to improve the reliability of protein-protein docking; this work provides a case study of antibody-antigen interfaces. ProteinDock was layered onto Rosetta for docking unbound experimentally determined structures, and when evaluated on Docking Benchmark Set 5.5, generated CAPRI acceptable-quality or better for 80.2% of targets, an improvement of 32.8 percentage points over vanilla Rosetta’s 47.4% on the same dataset. To improve protein-protein prediction reliability from sequence inputs, we demonstrate that a truncated version of ProteinDock can be used to choose the optimal prediction among outputs from multiple deep learning-based tools. We show that this strategy is a computationally efficient alternative to increasing the seed quantity for deep-learning predictions. A graphical user interface for layering ProteinDock has been created and is available at https://github.com/Kimmel-Lab/proteindock and https://proteindock.com/. TOC Figure
G. Rajagopal, Søren C. Spina, Joe Bailey et al.· bioRxiv· 0 citations