No abstract

Fbxo45, a conserved F-box protein, comprises of an atypical SKP1, CUL1, F-box protein (SCF) ubiquitin ligase complex that promotes tumorigenesis and development. However, the biological function and molecular mechanisms of Fbxo45 involved in pancreatic carcinogenesis are ambiguous. We conducted several approaches, including transfection, coIP, real-time polymerase chain reaction (RT-PCR), Western blotting, ubiquitin assays, and animal studies, to explore the role of Fbxo45 in pancreatic cancer. Here, we report that USP49 stability is governed by Fbxo45-mediated ubiquitination and is enhanced by the absence of Fbxo45. Moreover, Fbxo45 binds to a short consensus sequence of USP49 through its SPRY domain. Furthermore, Fbxo45-mediated USP49 ubiquitination and degradation are enhanced by NEK6 kinase. Functionally, Fbxo45 increases cell viability and motility capacity by targeting USP49 in pancreatic cancer cells. Xenograft mouse experiments demonstrated that ectopic expression of Fbxo45 enhanced tumor growth in mice and that USP49 overexpression inhibited tumor growth in vivo. Notably, Fbxo45 expression was negatively associated with USP49 expression in pancreatic cancer tissues. Fbxo45 serves as an oncoprotein to facilitate pancreatic oncogenesis by regulating the stability of the tumor suppressor USP49 in pancreatic cancer.

Learning effective representations is crucial for understanding proteins and their biological functions. Recent advancements in language models and graph neural networks have enabled protein models to leverage primary or tertiary structure information to learn representations. However, the lack of practical methods to deeply co-model the relationships between protein sequences and structures has led to suboptimal embeddings. In this work, we propose CoupleNet, a network that couples protein sequence and structure to obtain informative protein representations. CoupleNet incorporates multiple levels of features in proteins, including the residue identities and positions for sequences, as well as geometric representations for tertiary structures. We construct two types of graphs to model the extracted sequential features and structural geometries, achieving completeness on these graphs, respectively, and perform convolution on nodes and edges simultaneously to obtain superior embeddings. Experimental results on a range of tasks, such as protein fold classification and function prediction, demonstrate that our proposed model outperforms the state-of-the-art methods by large margins.

No abstract

Graph Neural Networks (GNNs) and Transformer have emerged as dominant tools for AI-driven drug discovery. Many state-of-the-art methods first pre-train GNNs or the hybrid of GNNs and Transformer on a large molecular database and then fine-tune on downstream tasks. However, different from other domains such as computer vision (CV) or natural language processing (NLP), getting labels for molecular data of downstream tasks often requires resource-intensive wet-lab experiments. Besides, the pre-trained models are often of extremely high complexity with huge parameters. These often cause the fine-tuned model to over-fit the training data of downstream tasks and significantly deteriorate the performance. To alleviate these critical yet underexplored issues, we propose two straightforward yet effective strategies to attain better generalization performance: 1. MolAug, which enriches the molecular datasets of downstream tasks with chemical homologies and enantiomers; 2. WordReg, which controls the complexity of the pre-trained models with a smoothness-inducing regularization built on dropout. Extensive experiments demonstrate that our proposed strategies achieve notable and consistent improvements over vanilla fine-tuning and yield multiple state-of-the-art results. Also, these strategies are model-agnostic and readily pluggable into fine-tuning of various pre-trained molecular graph models. We will release the code and the fine-tuned models.