Biology subjects

Xue, L. C.

Publications and source records attributed to Xue, L. C..

13 recordsLinked to original sources

bioRxiv2026

IMMREP25: Unseen Peptides

T cell receptors (TCRs) can bind to peptides presented by MHC molecules (pMHC) as a first step to trigger a T cell response. Reliable approaches to predict TCR:pMHC binding would have broad applications in clinical diagnostics, therapeutics, and the fundamental understanding of molecular interactions. IMMREP is a community organized series of prediction contests that asks participants to predict TCR:pMHC binding on unpublished datasets. Previous iterations in 2022 and 2023 showed multiple approaches can predict TCR-pMHC binding with significant accuracy (median AUC_0.1[≥]0.7) for peptides where experimental data is available ("seen" peptides). In contrast, models did not outperform random guessing for peptides that have no such data available ("unseen" peptides). Here we report on the results of IMMREP25, which focused solely on unseen peptides in order to evaluate the cutting edge of the field. We received 126 named submissions predicting the specificity of 1,000 TCRs against twenty unseen peptides restricted by one of two MHC molecules (HLA-A*02:01 and HLA-B*40:01). The best performing methods showed a macro-AUC_0.1 of 0.60, significantly better than random, demonstrating significant advances in the field. The top performing methods incorporated structural modeling into their approach, indicating that especially for unseen peptides, a structural understanding aids in the prediction of TCR:pMHC interactions. The results from this benchmark highlight the significant challenges remaining for TCR:pMHC predictions and will inform future method development.

bioinformatics↗

bioRxiv2025

Fast and Accurate Peptide - MHC Structure Prediction via an Equivariant Diffusion Model

Accurate modeling of peptide-MHC (Major Histocompatibility Complex) structures is critical for the development of personalized cancer vaccines and T-cell therapies, as MHC proteins present peptides on the cell surface for immune recognition. Here, we introduce MHC-Diff, a specialized SE(3)-equivariant diffusion model leveraging Geometric Deep Learning to predict the 3D C-alpha atom structures of peptide-MHC complexes with high accuracy. Unlike previous deep learning models that generate a single static structure, our probabilistic approach samples multiple diverse candidates, capturing the inherent flexibility of peptide-MHC binding. Validated on the Pandora benchmark and experimental X-ray crystallography data, MHC-Diff achieves sub-angstrom accuracy, outperforming existing methods by a large margin while matching the inference speed of the fastest available techniques. By enabling rapid and highly accurate structure prediction across diverse peptide lengths and MHC alleles, MHC-Diff provides a powerful new tool for accelerating the design of next-generation cancer vaccines and T-cell therapies.

bioinformatics↗

bioRxiv2025

SwiftMHC: A High-Speed Attention Network for MHC-Bound Peptide Identification and 3D Modeling

Identifying tumor peptides that bind patient MHC proteins and elicit immune responses is central to immunotherapy, yet progress remains limited to a handful of well-studied alleles. Structure-based methods generalize better than sequence-only models but are constrained by the high computational cost of 3D modeling. We present SwiftMHC, the fastest structure-based framework for peptide-MHC (pMHC) modeling and binding affinity prediction. SwiftMHC predicts peptide-MHC binding in 0.009 sec/case in batch mode on a single A100 GPU--nearly an order of magnitude faster than leading sequence-based methods such as NetMHCpan 4.1 (0.081 sec/case)--while performing competitively in predictive accuracy. In addition to affinity estimation, SwiftMHC generates all-atom 3D pMHC structures and achieves a median C-RMSD of 1.32 [A] against X-ray benchmarks, matching or better than the accuracy of state-of-the-art approaches (e.g., AlphaFold with fine-tuning) but running thousands of times faster (excluding disk-writing time). These results demonstrate the power of task-specific AI trained on physics-derived synthetic data to overcome the scarcity of experimental structures. Optimized for HLA-A*02:01 9-mers but readily extensible to other alleles, SwiftMHC enables rapid and accurate identification of peptides distinct from self at T-cell-exposed surfaces. This capability may expand immunotherapy targets, improve the safety of TCR-based therapies, and accelerate the development of next-generation cancer immunotherapies.

immunology↗

bioRxiv2024

SwiftTCR: Efficient Computational Docking protocol of TCRpMHC-I Complexes Using Restricted Rotation Matrices

The T cells ability to discern self and non-self depends on its T cell receptor (TCR), which recognizes peptides presented by MHC molecules. Understanding this TCR-peptide-MHC (TCRpMHC) interaction is important for cancer immunotherapy design, tissue transplantation, pathogen identification, and autoimmune disease treatments. Understanding the intricacies of TCR recognition, encapsulated in TCRpMHC structures, remains challenging due to the immense diversity of TCRs (>108/individual), rendering experimental determination and general-purpose computational docking impractical. Addressing this gap, we have developed a rapid integrative modeling protocol leveraging unique docking patterns in TCRpMHC complexes. Built upon PIPER, our pipeline significantly cuts down FFT rotation sets, exploiting the consistent polarized docking angle of TCRs at pMHC. Additionally, our ultra-fast structure superimposition tool, GradPose, accelerates clustering. It models a case in 3-4 minutes on 12 CPUs, showcasing a speedup of up to 25-40 times compared to the ClusPro webserver. On a benchmark set of 38 TCRpMHC class I (TCRpMHC-I) complexes, our protocol outperforms the state-of-the-art docking tools in model quality. This protocol can potentially provide structural information to TCR repertoires targeting specific peptides. Its computational efficiency can also enrich existing pMHC-specific single-cell sequencing TCR data, facilitating the development of structure-based deep learning (DL) algorithms. These insights are essential for understanding T cell recognition and specificity, advancing the development of therapeutic interventions.

bioinformatics↗

bioRxiv2023

Improving generalizability for MHC-binding peptide predictions through structure-based geometric deep learning

The interaction between peptides and major histocompatibility complex (MHC) molecules is pivotal in autoimmunity, pathogen recognition and tumor immunity. Recent advances in cancer immunotherapies demand for more accurate computational prediction of MHC-bound peptides. We address the generalizability challenge of MHC-bound peptide predictions, revealing limitations in current sequence-based approaches. Our structure-based methods leveraging geometric deep learning (GDL) demonstrated promising improvement in generalizability across unseen MHC alleles. Further, we tackle data efficiency by introducing a self-supervised learning approach on structures (3D-SSL). Without being exposed to any binding affinity data, our 3D-SSL outperforms sequence-based methods trained on [~]90 times more datapoints. Finally, we demonstrate the resilience of structure-based GDL methods to biases in binding data on an Hepatitis B virus vaccine immunopeptidomics case study. This proof-of-concept study highlights structure-based methods potential to enhance generalizability and data efficiency, with important implications for data-intensive fields like T-cell receptor specificity predictions, paving the way for enhanced comprehension and manipulation of immune responses.

bioinformatics↗

bioRxiv2023

PANDORA v2.0: Benchmarking peptide-MHC II models and software improvements

T-cell specificity to differentiate between self and non-self relies on T-cell receptor (TCR) recognition of peptides presented by the Major Histocompatibility Complex (MHC). Investigations into the three-dimensional (3D) structures of peptide:MHC (pMHC) complexes have provided valuable insights of MHC functions. Given the limited availability of experimental pMHC structures and considerable diversity of peptides and MHC alleles, it calls for the development of efficient and reliable computational approaches for modeling pMHC structures. Here we present an update of PANDORA and the systematic evaluation of its performance in modelling 3D structures of pMHC class II complexes (pMHC-II), which play a key role in the cancer immune response. PANDORA is a modelling software that can build low-energy models in a few minutes by restraining peptide residues inside the MHC-II binding groove. We benchmarked PANDORA on 136 experimentally determined pMHC-II structures covering 44 unique {beta} chain pairs. Our pipeline achieves a median backbone Ligand-Root Mean Squared Deviation (L-RMSD) of 0.42 [A] on the binding core and 0.88 [A] on the whole peptide for the benchmark dataset. We incorporated software improvements to make PANDORA a pan-allele framework and improved the user interface and software quality. Its computational efficiency allows enriching the wealth of pMHC binding affinity and mass spectrometry data with 3D models. These models can be used as a starting point for molecular dynamics simulations or structure-boosted deep learning algorithms to identify MHC-binding peptides. PANDORA is available as a Python package through Conda or as a source installation at https://github.com/X-lab-3D/PANDORA.

bioinformatics↗

bioRxiv2023

Synergizing Geometric Deep Learning and Data-Centric Methods for Improved Protein Structural Alignment

MotivationStructures are replacing the role of sequences. Traditional bioinformatics research focused on sequences because they were easily obtained. Advances in techniques like cryo-electron microscopy, molecular modeling, docking algorithms, and structure prediction software have shifted the focus to structures. Given the importance of deep learning in many of these breakthroughs, it makes sense to also explore how it can modernize classic bioinformatics tools. However, empirical findings have shown that machine learning based methods have many pitfalls resulting in overoptimistic conclusions, including data leakage between test and training data. Thus, there is a need for new innovations to make neural networks more intelligible. ResultsWe have developed vanGOGH, a geometric deep learning-based structural alignment approach that performs on par with the state-of-the-art without ever having been trained on a pair of naturally found homologs. We adopted a data-centric approach to address deep learning and data limitations by augmenting protein templates into synthetic homologs for training. Our method allowed us to supplement homolog data by knowledge-driven augmentation, self-learning of relevant structural features by supervised examples and protein alignment that is competitive with state-of-the art methods. AvailabilityGNN framework: https://github.com/DeepRank/deeprank-core/tree/main/deeprankcore ContactLi.Xue@radboudumc.nl

bioinformatics↗

bioRxiv2022

PANDORA: a fast, anchor-restrained modelling protocol for peptide:MHC complexes

Deeper understanding T-cell mediated adaptive immune responses bears important implications in designing cancer immunotherapies and antiviral vaccines against pandemic outbreaks. T cells fire when they recognize foreign peptides that are presented on the cell surface by Major Histocompatibility Complexes (MHC), forming peptide:MHC (pMHC) complexes. 3D structure of pMHC complexes provides fundamental insight of T-cell recognition mechanism and aids immunotherapy design. High MHC and peptide diversities necessitate efficient computational modelling to enable whole proteome structural analysis. Here we present PANDORA, a robust pMHC structure modelling pipeline. Given a query, PANDORA searches for structural templates in its extensive database and then applies anchor restraints to the modelling process. This restrained energy minimization ensures one of the fastest pMHC modelling pipelines so far. On a set of 835 pMHC-I complexes over 78 MHC types, PANDORA generated models with a median RMSD of 0.68 [A] and achieved a 93% success rate in top 10 models. PANDORA performs competitively with three pMHC-I modelling state-of-the-art approaches and outperforms AlphaFold in terms of accuracy while being superior to it in speed. PANDORA is a modularized and user-configurable python package with easy installation. We envision PANDORA to fuel deep learning with large-scale high-quality 3D models to tackle long-standing immunology challenges.

bioinformatics↗

bioRxiv2021

DeepRank-GNN: A Graph Neural Network Framework to Learn Patterns in Protein-Protein Interfaces

Gaining structural insights into the protein-protein interactome is essential to understand biological phenomena and extract knowledge for rational drug design or protein engineering. We have previously developed DeepRank, a deep-learning framework to facilitate pattern learning from protein-protein interfaces using Convolutional Neural Network (CNN) approaches. However, CNN is not rotation invariant and data augmentation is required to desensitize the network to the input data orientation which dramatically impairs the computation performance. Representing protein-protein complexes as atomic- or residue-scale rotation invariant graphs instead enables using graph neural networks (GNN) approaches, bypassing those limitations. We have developed DeepRank-GNN, a framework that converts protein-protein interfaces from PDB 3D coordinates files into graphs that are further provided to a pre-defined or user-defined GNN architecture to learn problem-specific interaction patterns. DeepRank-GNN is designed to be highly modularizable, easily customized, and is wrapped into a user-friendly python3 package. Here, we showcase DeepRank-GNNs performance for scoring docking models using a dedicated graph interaction neural network (GINet). We show that this graph-based model performs better than DeepRank, DOVE and HADDOCK scores and competes with iScore on the CAPRI score set. We show a significant gain in speed and storage requirement using DeepRank-GNN as compared to DeepRank. DeepRank-GNN is freely available from https://github.com/DeepRank/DeepRank-GNN. Contacta.m.j.j.bonvin@uu.nl

bioinformatics↗

bioRxiv2021

MetaScore: A novel machine-learning based approach to improve traditional scoring functions for scoring protein-protein docking conformations

Protein-protein interactions play a ubiquitous role in biological function. Knowledge of the three-dimensional (3D) structures of the complexes they form is essential for understanding the structural basis of those interactions and how they orchestrate key cellular processes. Computational docking has become an indispensable alternative to the expensive and timeconsuming experimental approaches for determining 3D structures of protein complexes. Despite recent progress, identifying near-native models from a large set of conformations sampled by docking - the so-called scoring problem - still has considerable room for improvement. We present here MetaScore, a new machine-learning based approach to improve the scoring of docked conformations. MetaScore utilizes a random forest (RF) classifier trained to distinguish near-native from non-native conformations using a rich set of features extracted from the respective protein-protein interfaces. These include physico-chemical properties, energy terms, interaction propensity-based features, geometric properties, interface topology features, evolutionary conservation and also scores produced by traditional scoring functions (SFs). MetaScore scores docked conformations by simply averaging of the score produced by the RF classifier with that produced by any traditional SF. We demonstrate that (i) MetaScore consistently outperforms each of nine traditional SFs included in this work in terms of success rate and hit rate evaluated over the top 10 predicted conformations; (ii) An ensemble method, MetaScore-Ensemble, that combines 10 variants of MetaScore obtained by combining the RF score with each of the traditional SFs outperforms each of the MetaScore variants. We conclude that the performance of traditional SFs can be improved upon by judiciously leveraging machine-learning.

bioinformatics↗

bioRxiv2021

DeepRank: A deep learning framework for data mining 3D protein-protein interfaces

Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. The vast amount of experimentally and computationally resolved protein-protein interfaces (PPIs) offers the possibility of training deep learning models to aid the predictions of their biological relevance. We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). DeepRank maps features of PPIs onto 3D grids and trains a user-specified CNN on these 3D grids. DeepRank allows for efficient training of 3D CNNs with data sets containing millions of PPIs and supports both classification and regression. We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models. For both problems DeepRank is competitive or outperforms state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology.

bioinformatics↗

bioRxiv2018

iScore: A novel graph kernel-based function for scoring protein-protein docking models

Protein complexes play a central role in many aspects of biological function. Knowledge of the three-dimensional (3D) structures of protein complexes is critical for gaining insights into the structural basis of interactions and their roles in the biomolecular pathways that orchestrate key cellular processes. Because of the expense and effort associated with experimental determination of 3D structures of protein complexes, computational docking has evolved as a valuable tool to predict the 3D structures of biomolecular complexes. Despite recent progress, reliably distinguishing near-native docking conformations from a large number of candidate conformations, the so-called scoring problem, remains a major challenge. Here we present iScore, a novel approach to scoring docked conformations that combines HADDOCK energy terms with a score obtained using a graph representation of the protein-protein interfaces and a measure of evolutionary conservation. It achieves a scoring performance competitive with, or superior to that of the state-of-the-art scoring functions on independent data sets consisting docking software-specific data sets and the CAPRI score set built from a wide variety of docking approaches. iScore ranks among the top scoring approaches on the CAPRI score set (13 targets) when compared with the 37 scoring groups in CAPRI. The results demonstrate the utility of combining evolutionary and topological, and physicochemical information for scoring docked conformations. This work represents the first successful demonstration of graph kernel to protein interfaces for effective discrimination of near-native and non-native conformations of protein complexes. It paves the way for the further development of computational methods for predicting the structure of protein complexes.

bioinformatics↗

bioRxiv2018

iSEE: Interface Structure, Evolution and Energy-based machine learning predictor of binding affinity changes upon mutations

Quantitative evaluation of binding affinity changes upon mutations is crucial for protein engineering and drug design. Machine learning-based methods are gaining increasing momentum in this field. Due to the limited number of experimental data, using a small number of sensitive predictive features is vital to the generalization and robustness of such machine learning methods. Here we introduce a fast and reliable predictor of binding affinity changes upon single point mutation, based on a random forest approach. Our method, iSEE, uses a limited number of interface Structure, Evolution and Energy-based features for the prediction. iSEE achieves, using only 31 features, a high prediction performance with a Pearson correlation coefficient (PCC) of 0.80 and a root mean square error of 1.41 kcal mol-1 on a diverse training dataset consisting of 1102 mutations in 57 protein-protein complexes. It competes with existing state-of-the-art methods on two blind test datasets. Predictions for a new dataset of 540 mutations in 58 protein complexes from the recently published SKEMPI 2.0 database reveals that none of the current methods perform well (PCC<0.4), although their combination does improve the predictions. Feature analysis for iSEE underlines the significance of evolutionary conservations for quantitative prediction of mutation effects.

bioinformatics↗