GastroDL-Fusion：一种融合蛋白质-配体复合物与基因序列的双模态深度学习框架，用于胃肠道疾病药物发现
GastroDL-Fusion: A Dual-Modal Deep Learning Framework Integrating Protein-Ligand Complexes and Gene Sequences for Gastrointestinal Disease Drug Discovery
AI总结：
本文提出GastroDL-Fusion双模态深度学习框架，融合蛋白质-配体复合物图结构与基因序列嵌入，在胃肠道疾病靶点上以MAE 1.12、RMSE 1.75显著提升结合亲和力预测性能。
摘要：
准确预测蛋白质-配体结合亲和力在加速新药和疫苗发现中发挥着关键作用，尤其是对于胃溃疡、克罗恩病和溃疡性结肠炎等胃肠道（GI）疾病。传统计算模型通常仅依赖结构信息，因而无法捕捉影响疾病机制和治疗反应的遗传决定因素。为弥补这一不足，我们提出了GastroDL-Fusion，一个双模态深度学习框架，将蛋白质-配体复合物数据与疾病相关基因序列信息相整合，用于药物和疫苗开发。在该方法中，蛋白质-配体复合物被表示为分子图，并使用图同构网络（GIN）进行建模，而基因序列则通过预训练的Transformer（ProtBERT/ESM）编码为具有生物学意义的嵌入表示。这两种互补模态通过多层感知机进行融合，以实现稳健的跨模态交互学习。我们在胃肠道疾病相关靶点的基准数据集上评估了该模型，结果表明GastroDL-Fusion相较于传统方法显著提升了预测性能。具体而言，该模型实现了1.12的平均绝对误差（MAE）和1.75的均方根误差（RMSE），优于仅使用CNN、BiLSTM、GIN和Transformer的基线模型。这些结果证实，同时结合结构特征和遗传特征能够更准确地预测结合亲和力，为加速胃肠道疾病背景下靶向疗法和疫苗的设计提供了可靠的计算工具。
英文摘要：
Accurate prediction of protein-ligand binding affinity plays a pivotal role in accelerating the discovery of novel drugs and vaccines, particularly for gastrointestinal (GI) diseases such as gastric ulcers, Crohn's disease, and ulcerative colitis. Traditional computational models often rely on structural information alone and thus fail to capture the genetic determinants that influence disease mechanisms and therapeutic responses. To address this gap, we propose GastroDL-Fusion, a dual-modal deep learning framework that integrates protein-ligand complex data with disease-associated gene sequence information for drug and vaccine development. In our approach, protein-ligand complexes are represented as molecular graphs and modeled using a Graph Isomorphism Network (GIN), while gene sequences are encoded into biologically meaningful embeddings via a pre-trained Transformer (ProtBERT/ESM). These complementary modalities are fused through a multi-layer perceptron to enable robust cross-modal interaction learning. We evaluate the model on benchmark datasets of GI disease-related targets, demonstrating that GastroDL-Fusion significantly improves predictive performance over conventional methods. Specifically, the model achieves a mean absolute error (MAE) of 1.12 and a root mean square error (RMSE) of 1.75, outperforming CNN, BiLSTM, GIN, and Transformer-only baselines. These results confirm that incorporating both structural and genetic features yields more accurate predictions of binding affinities, providing a reliable computational tool for accelerating the design of targeted therapies and vaccines in the context of gastrointestinal diseases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
