Predicting Transmembrane Protein Topology from 3D Structure
Predicting Transmembrane Protein Topology from 3D Structure
基于三维结构的跨膜蛋白拓扑结构预测
Abstract: This paper presents a novel approach to infer protein topology using the state-of-the-art graph neural network (GNN), SchNet. The model is trained on the same dataset used to develop the recent DeepTMHMM model with 5-fold cross-validation.
摘要: 本文提出了一种利用最先进的图神经网络(GNN)——SchNet 来推断蛋白质拓扑结构的新方法。该模型在与近期 DeepTMHMM 模型开发所使用的相同数据集上进行了训练,并采用了 5 折交叉验证。
Unlike the conventional approaches based on using only the protein sequences or the $\alpha$-carbons as features, we have decoded our classifier in this way, so all atom-level embeddings are used. Without applying any pre-trained weight, the final results have shown great potential that GNNs can be used for topological predictions.
与仅使用蛋白质序列或 $\alpha$-碳作为特征的传统方法不同,我们以这种方式解码了分类器,从而利用了所有原子级的嵌入(embeddings)。在不使用任何预训练权重的情况下,最终结果显示出图神经网络(GNN)在拓扑预测方面具有巨大的潜力。
Paper Details:
- Authors: Sitong Chen, Xiaopeng Mao
- Subject: Artificial Intelligence (cs.AI)
- arXiv ID: 2609.30446
- Submission Date: 24 Sep 2026
论文详情:
- 作者: Sitong Chen, Xiaopeng Mao
- 学科: 人工智能 (cs.AI)
- arXiv ID: 2609.30446
- 提交日期: 2026年9月24日