Aug 2026· IEEE transactions on computational biology and bioinformatics· Vol PP, pp. 1-11· 0 citations
Medicine
TL;DR
A hybrid quantum-classical machine learning approach that combines variational quantum circuits with the ESM2 protein language model for multi-class IDR binding partner prediction using a prototypical network is presented, establishing that quantum advantage in computational biology emerges from architectural design principles rather than computational scale.
Abstract
Intrinsically Disordered Regions (IDRs) play essential roles in cellular processes through interactions with proteins, nucleic acids, lipids, and metal ions, yet predicting their binding partners remains challenging for understanding protein function and drug discovery. However, current computational methods including protein language models face performance plateaus where traditional approaches to improve accuracy have become ineffective. Here, we present a hybrid quantum-classical machine learning approach that combines variational quantum circuits with the ESM2 protein language model for multi-class IDR binding partner prediction using a prototypical network. Through systematic evaluation of quantum circuit architectures across factorial experiments, we demonstrate that the hybrid model achieves statistically significant performance improvements over classical baselines, with entanglement topology governing model stability and encoding methods determining performance gains. These findings establish that quantum advantage in computational biology emerges from architectural design principles rather than computational scale, providing a framework for overcoming performance limitations in bioinformatics applications where dataset expansion is constrained.
Intrinsically disordered proteins and regions (IDPs/IDRs) mediate diverse cellular functions through binding segments whose functional properties are encoded in dynamic conformational ensembles rather than a single static state. Existing predictors of linear interacting peptides (LIPs) and molecular recognition features (MoRFs) rely primarily on sequence-derived features, leaving ensemble-level biophysical properties largely unexplored. Here, we introduce BindCORE, an ensemble-aware deep learning framework that integrates global, local, and pairwise biophysical descriptors to predict interaction sites within IDRs. These features are processed through a multi-scale architecture that enables information exchange between sequence- and ensemble-based global, local, and pairwise information. Across established LIP and MoRF benchmarks, BindCORE consistently improves performance over sequence-based baselines, demonstrating the predictive signals of ensemble-derived properties beyond sequence-based representations alone. Feature-attribution analyses reveal that pairwise descriptors are the dominant contributors to prediction, while solvent accessibility, backbone dihedral entropy, and global geometric properties provide complementary information. Feature-importance rankings vary substantially across ensemble flavours, indicating that different conformational generators encode distinct biophysical signatures of interaction-site propensity. Together, our results show that conformational ensembles contain interpretable determinants of LIP and MoRF binding residues and establish BindCORE as a general framework for incorporating biophysical information into the prediction of functional regions in intrinsically disordered proteins. BindCORE is freely available as a ready-to-use Google Colab notebook (BindCORE Colab notebook). Key Messages BindCORE integrates ensemble-derived biophysical descriptors to predict residue-level interaction sites in intrinsically disordered proteins. Ensemble-derived features improve prediction performance over state-of-the-art sequence-based methods on both LIP and MoRF benchmarks. Pairwise ensemble descriptors, especially contact and dynamic cross-correlation maps, provide the strongest signals for predicting interaction-site residues, while global chain geometry, solvent accessibility, and backbone dihedral preferences add complementary information.
Nicolas Buton, Luiz Felipe Piochi, Hammed Khakzad· bioRxiv· 0 citations
By combining protein language model embeddings with topology-adaptive geometric reasoning, DiConSite offers a reusable framework for residue-level protein interaction analysis and achieves consistently strong and often best-performing results, while improving robustness to structural uncertainty and cross-modal variation.
Shou-Zhi Chen, Zhenchao Tang, Linlin You et al.· IEEE Transactions on Pattern...· 1 citation
Protein-RNA interactions (RPIs) stand for the central process in post-transcriptional regulation and have catalyzed a fast proliferation of computational approaches in recent years. Adopting a task-oriented classification method, RPIs calculation prediction schemes proposed over the period 2010-2025 fall into five primary categories: RNA-binding protein (RBP) classification, RPIs prediction, binding site and binding profile modeling on RNA, residue-level RNA-binding interface prediction on proteins, and quantitative estimation of binding affinity and mutation effects. This study reviews the methodological evolution from conventional machine learning to deep learning, graph neural networks and large-scale pre-trained language models, and compares their differences in data preparation, evaluation protocols and generalization behavior. Particular emphasis is placed on recent advances in structure-aware and condition-aware models, as well as learning in low-data regimes. Finally, the study outlines practical recommendations for field-wide benchmarking and looks ahead to the integration with spatial omics and the development of dynamic, generative landscapes of RPIs to better empower biomedical research.
These approaches improve generalisability, reduce reliance on deep evolutionary information, and enable proteome-scale prediction of RNA-binding residues, providing a route to map and interpret the molecular logic of protein-RNA interactions.
Rozeena Arif, Alfredo Castello· Current Opinion in Structura...· 0 citations
Membrane molecular recognition features (MemMoRFs) are lipid-binding intrinsically disordered regions (IDRs) that undergo disorder-to-order transitions to mediate critical membrane dynamics. Consequently, their dysregulation is closely linked to severe human pathologies, including neurodegenerative diseases and viral infections. Despite their biological significance, annotations for MemMoRFs are scarce, limiting the accuracy of computational predictors. We introduce PreMemMoRF, a deep learning framework that leverages transfer learning to alleviate data scarcity. The model is pre-trained on linear interacting peptides (LIPs) with similar conformational transitions and fine-tuned on MemMoRF datasets, capturing generalizable binding-related sequence features. PreMemMoRF outperforms existing predictors across multiple metrics and demonstrates robust performance on transmembrane and membrane-associated proteins. It also performs consistently in short linear motif prediction, highlighting cross-task generalizability. Proteome-wide analysis in yeast shows that predicted scores exhibit systematic differences across distinct transmembrane topological regions and are consistent with established physicochemical constraints of membrane proteins. Collectively, these results validate PreMemMoRF as a robust and reliable computational framework for the large-scale identification of MemMoRFs.
Chenxi Xia, Jiayi Hao, Hao Liu et al.· IEEE journal of biomedical a...· 0 citations
The results demonstrate the effectiveness of integrating multi-scale and multi-modal representations with cross-scale alignment for protein–RNA affinity prediction, and suggest that M2-PRNet can highlight relevant RNA-binding regions and support preliminary discrimination between strong and weak binders when plausible complex structures are available.
Junkai Wang, G. Luo, Yun-Song Yang et al.· Bioinformatics· 0 citations