There are various interaction/association bipartite networks in biomolecular systems. Identifying unobserved links in biomedical bipartite networks helps to understand the underlying molecular mechanisms of human complex diseases and thus benefits the diagnosis and treatment of diseases. Although a great number of computational methods have been proposed to predict links in biomedical bipartite networks, most of them heavily depend on features and structures involving the bioentities in one specific bipartite network, which limits the generalization capacity of applying the models to other bipartite networks. Meanwhile, bioentities usually have multiple features, and how to leverage them has also been challenging. In this study, we propose a novel multi-view graph convolution network (MVGCN) framework for link prediction in biomedical bipartite networks. We first construct a multi-view heterogeneous network (MVHN) by combining the similarity networks with the biomedical bipartite network, and then perform a self-supervised learning strategy on the bipartite network to obtain node attributes as initial embeddings. Further, a neighborhood information aggregation (NIA) layer is designed for iteratively updating the embeddings of nodes by aggregating information from inter- and intra-domain neighbors in every view of the MVHN. Next, we combine embeddings of multiple NIA layers in each view, and integrate multiple views to obtain the final node embeddings, which are then fed into a discriminator to predict the existence of links. Extensive experiments show MVGCN performs better than or on par with baseline methods and has the generalization capacity on six benchmark datasets involving three typical tasks. Source code and data can be downloaded from https://github.com/fuhaitao95/MVGCN. Supplementary data are available at Bioinformatics online.

Accurate prediction of molecular properties is an important topic in drug discovery. Recent works have developed various representation schemes for molecular structures to capture different chemical information in molecules. The atom and motif can be viewed as hierarchical molecular structures that are widely used for learning molecular representations to predict chemical properties. Previous works have attempted to exploit both atom and motif to address the problem of information loss in single representation learning for various tasks. To further fuse such hierarchical information, the correspondence between learned chemical features from different molecular structures should be considered. Herein, we propose a novel framework for molecular property prediction, called hierarchical molecular graph neural networks (HimGNN). HimGNN learns hierarchical topology representations by applying graph neural networks on atom- and motif-based graphs. In order to boost the representational power of the motif feature, we design a Transformer-based local augmentation module to enrich motif features by introducing heterogeneous atom information in motif representation learning. Besides, we focus on the molecular hierarchical relationship and propose a simple yet effective rescaling module, called contextual self-rescaling, that adaptively recalibrates molecular representations by explicitly modelling interdependencies between atom and motif features. Extensive computational experiments demonstrate that HimGNN can achieve promising performances over state-of-the-art baselines on both classification and regression tasks in molecular property prediction.

Nuclear transfer embryonic stem cells (ntESCs) hold enormous promise for individual-specific regenerative medicine. However, the chromatin states of ntESCs remain poorly characterized. In this study, we employed ATAC-seq and Hi-C techniques to explore the chromatin accessibility and three-dimensional (3D) genome organization of ntESCs. The results show that the chromatin accessibility and genome structures of somatic cells are re-arranged to ESC-like states overall in ntESCs, including compartments, topologically associating domains (TADs) and chromatin loops. However, compared to fertilized ESCs (fESCs), ntESCs show some abnormal openness and structures that have not been reprogrammed completely, which impair the differentiation potential of ntESCs. The histone modification H3K9me3 may be involved in abnormal structures in ntESCs, including incorrect compartment switches and incomplete TAD rebuilding. Moreover, ntESCs and iPSCs show high similarity in 3D genome structures, while a few differences are detected due to different somatic cell origins and reprogramming mechanisms. Through systematic analyses, our study provides a global view of chromatin accessibility and 3D genome organization in ntESCs, which can further facilitate the understanding of the similarities and differences between ntESCs and fESCs.

Tumorigenesis arises from the dysfunction of cancer genes, leading to uncontrolled cell proliferation through various mechanisms. Establishing a complete cancer gene catalogue will make precision oncology possible. Although existing methods based on graph neural networks (GNN) are effective in identifying cancer genes, they fall short in effectively integrating data from multiple views and interpreting predictive outcomes. To address these shortcomings, an interpretable representation learning framework IMVRL-GCN is proposed to capture both shared and specific representations from multiview data, offering significant insights into the identification of cancer genes. Experimental results demonstrate that IMVRL-GCN outperforms state-of-the-art cancer gene identification methods and several baselines. Furthermore, IMVRL-GCN is employed to identify a total of 74 high-confidence novel cancer genes, and multiview data analysis highlights the pivotal roles of shared, mutation-specific, and structure-specific representations in discriminating distinctive cancer genes. Exploration of the mechanisms behind their discriminative capabilities suggests that shared representations are strongly associated with gene functions, while mutation-specific and structure-specific representations are linked to mutagenic propensity and functional synergy, respectively. Finally, our in-depth analyses of these candidates suggest potential insights for individualized treatments: afatinib could counteract many mutation-driven risks, and targeting interactions with cancer gene SRC is a reasonable strategy to mitigate interaction-induced risks for NR3C1, RXRA, HNF4A, and SP1.

Nowadays, as human activities are shifting to social media, fake news detection has been a crucial problem. Existing methods ignore the classification difference in online news and cannot take full advantage of multi-classification knowledges. For example, when coping with a post “A mouse is frightened by a cat,” a model that learns “computer” knowledge tends to misunderstand “mouse” and give a fake label, but a model that learns “animal” knowledge tends to give a true label. Therefore, this research proposes a multi-classification division-aggregation framework to detect fake news, named $CKA$, which innovatively learns classification knowledges during training stages and aggregates them during prediction stages. It consists of three main components: a news characterizer, an ensemble coordinator, and a truth predictor. The news characterizer is responsible for extracting news features and obtaining news classifications. Cooperating with the news characterizer, the ensemble coordinator generates classification-specifical models for the maximum reservation of classification knowledges during the training stage, where each classification-specifical model maximizes the detection performance of fake news on corresponding news classifications. Further, to aggregate the classification knowledges during the prediction stage, the truth predictor uses the truth discovery technology to aggregate the predictions from different classification-specifical models based on reliability evaluation of classification-specifical models. Extensive experiments prove that our proposed $CKA$ outperforms state-of-the-art baselines in fake news detection.

Antibody lead discovery, crucial for immunotherapy development, requires identifying candidates with potent binding affinities to target antigens. Recent advances in protein language models have opened promising avenues to tackle this challenge by predicting antibody–antigen interactions (AAIs). Despite their appeals, precisely detecting binding sites (i.e., paratopes and epitopes) within the complex landscape of long-sequence biomolecules remains challenging. Herein, we propose MambaAAI, a bio-inspired model built upon the Mamba architecture, designed to predict AAIs and identify binding sites through selective attention mechanisms. Technically, we employ ESM-2, a pre-trained protein language model to extract evolutionarily enriched representations from input antigen and antibody sequences, which are modeled as residue-level interaction matrixes. Subsequently, a dual-view Mamba encoder is devised to capture important binding patterns, by dynamically learning embeddings of interaction matrixes from both antibody and antigen perspectives. Finally, the learned embeddings are decoded using a multilayer perceptron to output interaction probabilities. MambaAAI provides a unique advantage, relative to prior techniques, in dynamically selecting bio-enhancing residue sites that contribute to AAI prediction. We evaluate MambaAAI on two large-scale antibody–antigen neutralization datasets, and in silico results demonstrate that our method marginally outperforms the state-of-the-art baselines in terms of prediction accuracy, while maintaining robust generalization to unseen antibodies and antigens. In further analysis of the selective attention mechanism, we found that MambaAAI successfully uncovers critical epitope and paratope regions in the SARS-CoV-2 antibody examples. It is believed that MambaAAI holds great potential to discover lead candidates targeting specific antigens at a lower burden.