Biology subjects

Wei, D.-Q.

Publications and source records attributed to Wei, D.-Q..

8 recordsLinked to original sources

bioRxiv2026

EnzOracle: Mechanism-aware prediction of enzyme environmental adaptation via a classification-guided mixture-of-experts framework

Industrial biocatalysis increasingly requires enzymes capable of operating under extreme physicochemical conditions, yet most natural sequence data reflect adaptation to mild environments, leading conventional predictive models to suffer from regression-to-the-mean effects in extremophilic regimes. Here we present EnzOracle, a classification-guided mixture-of-experts framework that enables distribution-aware prediction of enzyme melting temperature (Tm), optimal catalytic temperature (Topt), and optimal pH (pHopt) directly from sequence. EnzOracle demonstrated robust predictive accuracy across diverse benchmarks, achieving RMSE of 5.245{degrees}C for Tm, 11.458{degrees}C for Topt, and 0.781 for pHopt. Beyond predictive accuracy, we introduce a trait-resolved molecular simulation strategy to evaluate whether EnzOracle-derived attribution patterns correspond to independent physical mechanisms. Across representative systems, attention hotspots mapped onto rigidity-conferring interaction networks for Tm, dynamically preorganized active-site ensembles for Topt, and pH-dependent electrostatic and hydration networks for pHopt. These orthogonal validations indicate that EnzOracle captures transferable biophysical principles of enzyme environmental adaptation rather than merely exploiting dataset-specific correlations, positioning sequence-based learning as a mechanism-aware framework for discovering stability and activity determinants across diverse catalytic landscapes.

bioinformatics↗

bioRxiv2026

RNASTOP: A Deep Learning Framework for mRNA Chemical Stability Prediction and Optimization

Messenger RNA (mRNA) vaccines offer promising therapeutics for combating various diseases, yet their inherent chemical instability hampers their long-term efficacy. Although several methods have been developed to predict mRNA degradation, they exhibit limited accuracy and lack the capability for rational sequence optimization. Here, we propose RNASTOP, a novel framework integrating deep learning with heuristic search to simultaneously predict and optimize mRNA chemical stability. RNASTOP achieves a 13% accuracy improvement over the top-performing model on the Stanford OpenVaccine competition dataset and demonstrates robust generalization in predicting full-length mRNA degradation. Applied to mRNA codon optimization, RNASTOP reduces the minimum free energy of the Varicella-Zoster Virus vaccine sequence by 75.73% while maintaining high translation efficiency. Overall, RNASTOP serves as a powerful tool for predicting and optimizing mRNA chemical stability, poised to expedite the development of mRNA therapeutics. The source code of RNASTOP can be accessed at https://github.com/xlab-BioAI/RNASTOP.

bioinformatics↗

bioRxiv2024

Target-specific design of drug-like PPI inhibitors via hot-spot-guided generative deep learning

Protein-protein interactions (PPIs) are vital therapeutic targets. However, the large and flat PPI interfaces pose challenges for the development of small-molecule inhibitors. Traditional computer-aided drug design approaches typically rely on pre-existing libraries or expert knowledge, limiting the exploration of novel chemical spaces needed for effective PPI inhibition. To overcome these limitations, we introduce Hot2Mol, a deep learning framework for the de novo design of drug-like, target-specific PPI inhibitors. Hot2Mol generates small molecules by mimicking the pharmacophoric features of hot-spot residues, enabling precise targeting of PPI interfaces without the need for bioactive ligands. The framework integrates three key components: a conditional transformer for pharmacophore-guided, drug-likeness-constrained molecular generation; an E(n)-equivariant graph neural network for accurate alignment with PPI hot-spot pharmacophores; and a variational autoencoder for generating novel and diverse molecular structures. Experimental evaluations demonstrate that Hot2Mol outperforms baseline models across multiple metrics, including docking affinities, drug-likenesses, synthetic accessibility, validity, uniqueness, and novelty. Furthermore, molecular dynamics simulations confirm the good binding stability of the generated molecules. Case studies underscore Hot2Mols ability to design high-affinity and selective PPI inhibitors, demonstrating its potential to accelerate rational PPI drug discovery.

bioinformatics↗

bioRxiv2024

GRATCR: epitope-specific T cell receptor sequence generation with data-efficient pre-trained models

T cell receptors (TCRs) play a crucial role in numerous immunotherapies targeting tumor cells. However, their acquisition and optimization present significant challenges, involving laborious and time-consuming wet lab experimental resource. Deep generative model has demonstrated remarkable capabilities in functional protein sequence generation, offering a promising solution for enhancing the acquisition of specific TCR sequences. Here, we propose GRATCR, a framework incorporates two pre-trained modules through a novel "grafting" strategy, to de-novo generate TCR sequences targeting specific epitopes. Experimental results demonstrate that TCRs generated by GRATCR exhibit higher specificity toward desired epitopes and are more biologically functional compared with state-of-the-art model, by using significantly fewer training data. Additionally, the generated sequences display novelty compared to natural sequences, and the interpretability evaluation further confirmed that the model is capable of capturing important binding patterns. GRATCR is freely available at https://github.com/zhzhou23/GRATCR.

bioinformatics↗

bioRxiv2023

MultiPPIMI: a multimodal deep learning framework for predicting interactions between protein-protein interaction targets and modulators

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 inter-molecular interactions. Experimental results on our curated benchmark dataset 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 show that MultiPPIMI can assist molecular simulations in screening inhibitors of Keap1/Nrf2 PPI interactions. We believe that the proposed method provides a promising way to screen PPI-targeted modulators.

bioinformatics↗

bioRxiv2020

Predicting drug-target interactions using multi-label learning with community detection method (DTI-MLCD)

Identifying drug-target interactions (DTIs) is an important step for drug discovery and drug repositioning. To reduce heavily experiment cost, booming machine learning has been applied to this field and developed many computational methods, especially binary classification methods. However, there is still much room for improvement in the performance of current methods. Multi-label learning can reduce difficulties faced by binary classification learning with high predictive performance, and has not been explored extensively. The key challenge it faces is the exponential-sized output space, and considering label correlations can help it. Thus, we facilitate the multi-label classification by introducing community detection methods for DTIs prediction, named DTI-MLCD. On the other hand, we updated the gold standard data set proposed in 2008 and still in use today. The proposed DTI-MLCD is performed on the gold standard data set before and after the update, and shows the superiority than other classical machine learning methods and other benchmark proposed methods, which confirms the efficiency of it. The data and code for this study can be found at https://github.com/a96123155/DTI-MLCD.

bioinformatics↗

bioRxiv2020

Computational vaccinology based development of multi-epitope subunit vaccine for protection against the Norovirus infections

Human Norovirus belong to family Calciviridae, it was identified in the outbreak of gastroenteritis in Norwalk, due to its seasonal prevalence known as "winter vomiting disease". Treatment of Norovirus infection is still mysterious because there is no effective antiviral drugs or vaccine developed to protect against the infection, to eradicate the infection an effective vaccine should be developed. In this study capsid protein (A7YK10), small protein (A7YK11) and polyprotein (A7YK09) were utilized. These proteins were subjected to B and T cell epitopes prediction by using reliable immunoinformatics tools. The antigenic and non-allergenic epitopes were selected for subunit vaccine, which can activate cellular and humoral immune responses. Linkers joined these epitopes together. The vaccine structure was modelled and validated by using Errat, ProSA and rampage servers. The modelled vaccine was docked with TLR-7. Stability of the docked complex was evaluated by MD simulation. In order to apply the concept in a wet lab, the reverse translated vaccine sequence was cloned in pET28a (+). The vaccine developed in this study requires experimental validation to ensure its effectiveness against the disease.

immunology↗

bioRxiv2019

An Accurate Bioinformatics Tool For Anti-Cancer Peptide Generation Through Deep Learning Omics

The Anti-cancer targets play crucial role in signalling processes of cells. We have developed an Anti-Cancer Scanner (ACS) tool for identification of Anti-cancer targets in form of peptides. ACS tool also allows fast fingerprinting of the Anti-cancer targets of significance in the current bioinformatics research. There are tools currently available which predicts the above-mentioned features in single platform. In the present work, we have compared the features predicted by ACS with other on-line available methods and evaluated the performance of the ACS tool. ACS scanned the Anti-cancer target protein sequences provided by the user against the Anti-cancer target data-sets. It has been developed in PERL language and it is scalable having an extensible application in bioinformatics with robust coding architecture. It achieves a prediction accuracy of 95%, which is much higher than the existing tools.

bioinformatics↗