InterPepRank: Assessment of Docked Peptide Conformations by a Deep Graph Network

Leveraging machine learning models for peptide-protein interaction prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as docking and molecular dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

Leveraging Machine Learning Models for Peptide-Protein Interaction Prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as Docking and Molecular Dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

Systematic discovery of protein interaction interfaces using AlphaFold and experimental validation

Structural resolution of protein interactions enables mechanistic and functional studies as well as interpretation of disease variants. However, structural data is still missing for most protein interactions because we lack computational and experimental tools at scale. This is particularly true for interactions mediated by short linear motifs occurring in disordered regions of proteins. We find that AlphaFold-Multimer predicts with high sensitivity but limited specificity structures of domain-motif interactions when using small protein fragments as input. Sensitivity decreased substantially when using long protein fragments or full length proteins. We delineated a protein fragmentation strategy particularly suited for the prediction of domain-motif interfaces and applied it to interactions between human proteins associated with neurodevelopmental disorders. This enabled the prediction of highly confident and likely disease-related novel interfaces, which we further experimentally corroborated for FBXO23-STX1B, STX1B-VAMP2, ESRRG-PSMC5, PEX3-PEX19, PEX3-PEX16, and SNRPB-GIGYF1 providing novel molecular insights for diverse biological processes. Our work highlights exciting perspectives, but also reveals clear limitations and the need for future developments to maximize the power of Alphafold-Multimer for interface predictions.

Super High-Throughput Screening of Enzyme Variants by Spectral Graph Convolutional Neural Networks

Finding new enzyme variants with the desired substrate scope requires screening through a large number of potential variants. In a typical in silico enzyme engineering workflow, it is possible to scan a few thousands of variants, and gather several candidates for further screening or experimental verification. In this work, we show that a Graph Convolutional Neural Network (GCN) can be trained to predict the binding energy of combinatorial libraries of enzyme complexes using only sequence information. The GCN model uses a stack of message-passing and graph pooling layers to extract information from the protein input graph and yield a prediction. The GCN model is agnostic to the identity of the ligand, which is kept constant within the mutant libraries. Using a miniscule subset of the total combinatorial space (20⁴-20⁸ mutants) as training data, the proposed GCN model achieves a high accuracy in predicting the binding energy of unseen variants. The network's accuracy was further improved by injecting feature embeddings obtained from a language module pretrained on 10 million protein sequences. Since no structural information is needed to evaluate new variants, the deep learning algorithm is capable of scoring an enzyme variant in under 1 ms, allowing the search of billions of candidates on a single GPU.

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.

Improving peptide-protein docking with AlphaFold-Multimer using forced sampling

Protein interactions are key in vital biological processes. In many cases, particularly in regulation, this interaction is between a protein and a shorter peptide fragment. Such peptides are often part of larger disordered regions in other proteins. The flexible nature of peptides enables the rapid yet specific regulation of important functions in cells, such as their life cycle. Consequently, knowledge of the molecular details of peptide-protein interactions is crucial for understanding and altering their function, and many specialized computational methods have been developed to study them. The recent release of AlphaFold and AlphaFold-Multimer has led to a leap in accuracy for the computational modeling of proteins. In this study, the ability of AlphaFold to predict which peptides and proteins interact, as well as its accuracy in modeling the resulting interaction complexes, are benchmarked against established methods. We find that AlphaFold-Multimer predicts the structure of peptide-protein complexes with acceptable or better quality (DockQ ≥0.23) for 66 of the 112 complexes investigated—25 of which were high quality (DockQ ≥0.8). This is a massive improvement on previous methods with 23 or 47 acceptable models and only four or eight high quality models, when using energy-based docking or interaction templates, respectively. In addition, AlphaFold-Multimer can be used to predict whether a peptide and a protein will interact. At 1% false positives, AlphaFold-Multimer found 26% of the possible interactions with a precision of 85%, the best among the methods benchmarked. However, the most interesting result is the possibility of improving AlphaFold by randomly perturbing the neural network weights to force the network to sample more of the conformational space. This increases the number of acceptable models from 66 to 75 and improves the median DockQ from 0.47 to 0.55 (17%) for first ranked models. The best possible DockQ improves from 0.58 to 0.72 (24%), indicating that selecting the best possible model is still a challenge. This scheme of generating more structures with AlphaFold should be generally useful for many applications involving multiple states, flexible regions, and disorder.

InterPepScore: A Deep Learning Score for Improving the FlexPepDock Refinement Protocol

Motivation

Interactions between peptide fragments and protein receptors are vital to cell function yet difficult to experimentally determine in structural details of. As such, many computational methods have been developed to aid in peptide–protein docking or structure prediction. One such method is Rosetta FlexPepDock which consistently refines coarse peptide–protein models into sub-Ångström precision using Monte-Carlo simulations and statistical potentials. Deep learning has recently seen increased use in protein structure prediction, with graph neural networks used for protein model quality assessment.

Results

Here, we introduce a graph neural network, InterPepScore, as an additional scoring term to complement and improve the Rosetta FlexPepDock refinement protocol. InterPepScore is trained on simulation trajectories from FlexPepDock refinement starting from thousands of peptide–protein complexes generated by a wide variety of docking schemes. The addition of InterPepScore into the refinement protocol consistently improves the quality of models created, and on an independent benchmark on 109 peptide–protein complexes its inclusion results in an increase in the number of complexes for which the top-scoring model had a DockQ-score of 0.49 (Medium quality) or better from 14.8% to 26.1%.

Availability and implementation

InterPepScore is available online at http://wallnerlab.org/InterPepScore.

Supplementary information

Supplementary data are available at Bioinformatics online.