Zihan Liu

• PhD
• PhD Student at Zhejiang University

The elucidation of aggregation rules for short peptides (e.g., tetrapeptides and pentapeptides) is crucial for the precise manipulation of aggregation. In this study, we derive comprehensive aggregation rules for tetrapeptides and pentapeptides across the entire sequence space based on the aggregation propensity values predicted by a transformer-ba...

Protein structure-based property prediction has emerged as a promising approach for various biological tasks, such as protein function prediction and sub-cellular location estimation. The existing methods highly rely on experimental protein structure data and fail in scenarios where these data are unavailable. Predicted protein structures from AI t...

Self‐assembling of peptides is essential for a variety of biological and medical applications. However, it is challenging to investigate the self‐assembling properties of peptides within the complete sequence space due to the enormous sequence quantities. Here, it is demonstrated that a transformer‐based deep learning model is effective in predicti...

In recent years, there has been an explosion of research on the application of deep learning to the prediction of various peptide properties, due to the significant development and market potential of peptides. Molecular dynamics has enabled the efficient collection of large peptide datasets, providing reliable training data for deep learning. Howe...

Recent years have witnessed great successes in performing graph structure learning for Graph Neural Networks (GNNs). However, comparatively little work studies structure augmentation for graphs, where the augmented structures are only used for training and are not available during inference. This is mainly due to that structure augmentation is a di...

In recent years, there has been an explosion of research on the application of deep learning to the prediction of various peptide properties, due to the significant development and market potential of peptides. Molecular dynamics has enabled the efficient collection of large peptide datasets, providing reliable training data for deep learning. Howe...

Graph neural networks (GNNs) have recently achieved remarkable success on a variety of graph-related tasks, while such success relies heavily on a given graph structure that may not always be available in real-world applications. To address this problem, graph structure learning (GSL) is emerging as a promising research topic where task-specific gr...

It has become cognitive inertia to employ cross-entropy loss function in classification related tasks. In the untargeted attacks on graph structure, the gradients derived from the attack objective are the attacker's basis for evaluating a perturbation scheme. Previous methods use negative cross-entropy loss as the attack objective in attacking node...

(Dis)agreement detection aims to identify the authors' attitudes or positions (\textit{{agree, disagree, neutral}}) towards a specific text. It is limited for existing methods merely using textual information for identifying (dis)agreements, especially for cross-domain settings. Social relation information can play an assistant role in the (dis)agr...

Self-assembling of peptides is essential for a variety of biological and medical applications. However, it is challenging to investigate the self-assembling properties of peptides within the complete sequence space due to the enormous sequence quantities. Here, we demonstrate that a Transformer-based deep learning model is effective in predicting t...

Data mixing augmentation have proved to be effective for improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency information to match the mixed samples and labels via complex offline optimization. However, there arises a trad...

Recent studies have proven that graph neural networks are vulnerable to adversarial attacks. Attackers can rely solely on the training labels to disrupt the performance of the agnostic victim model by edge perturbations. Researchers observe that the saliency-based attackers tend to add edges rather than delete them, which is previously explained by...

The stance detection task aims to classify the stance toward given documents and topics. Since the topics can be implicit in documents and unseen in training data for zero-shot settings, we propose to boost the transferability of the stance detection model by using sentiment and commonsense knowledge, which are seldom considered in previous studies...

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for the task, which suffer from instability and poor generalization. In this paper, we explore contrastive learnin...

Graph edge perturbations are dedicated to damaging the prediction of graph neural networks by modifying the graph structure. Previous gray-box attackers employ gradients from the surrogate model to locate the vulnerable edges to perturb the graph structure. However, unreliability exists in gradients on graph structures, which is rarely studied by p...

Gray-box graph attacks aim to disrupt the victim model's performance by using inconspicuous attacks with limited knowledge of the victim model. The details of the victim model and the labels of the test nodes are invisible to the attacker. The attacker constructs an imaginary surrogate model trained under supervision to obtain the gradient on the n...

Mixup is a popular data-dependent augmentation technique for deep neural networks, which contains two sub-tasks, mixup generation and classification. The community typically confines mixup to supervised learning (SL) and the objective of generation sub-task is fixed to the sampled pairs instead of considering the whole data manifold. To overcome su...

Path planning is the key technology for autonomous mobile robots. In view of the shortage of paths found by traditional best first search (BFS) and rapidly-exploring random trees (RRT) algorithm which are not short and smooth enough for robot navigation, a new global planning algorithm combined with reinforcement learning is presented for robots. I...