CasANGCL: pre-training and fine-tuning model based on cascaded attention network and graph contrastive learning for molecular property prediction.

MOTIVATION: Molecular property prediction is a significant requirement in AI-driven drug design and discovery, aiming to predict the molecular property information (e.g. toxicity) based on the mined biomolecular knowledge. Although graph neural networks have been proven powerful in predicting molecular property, unbalanced labeled data and poor generalization capability for new-synthesized molecules are always key issues that hinder further improvement of molecular encoding performance. RESULTS: We propose a novel self-supervised representation learning scheme based on a Cascaded Attention Network and Graph Contrastive Learning (CasANGCL). We design a new graph network variant, designated as cascaded attention network, to encode local-global molecular representations. We construct a two-stage contrast predictor framework to tackle the label imbalance problem of training molecular samples, which is an integrated end-to-end learning scheme. Moreover, we utilize the information-flow scheme for training our network, which explicitly captures the edge information in the node/graph representations and obtains more fine-grained knowledge. Our model achieves an 81.9% ROC-AUC average performance on 661 tasks from seven challenging benchmarks, showing better portability and generalizations. Further visualization studies indicate our model's better representation capacity and provide interpretability.

Hydrazone-Linked Covalent Organic Frameworks.

Hydrazone-linked covalent organic frameworks (COFs) with structural flexibility, heteroatomic sites, post-modification ability and high hydrolytic stability have attracted great attention from scientific community. Hydrazone-linked COFs, as a subclass of Schiff-base COFs, was firstly reported in 2011 by Yaghi's group and later witnessed prosperous development in various aspects. Their adjustable structures, precise pore channels and plentiful heteroatomic sites of hydrazone-linked structures possess much potential in diverse applications, for example, adsorption/separation, chemical sensing, catalysis and energy storage, etc. Up to date, the systematic reviews about the reported hydrazone-linked COFs are still rare. Therefore, in this review, we will summarize their preparation methods, characteristics and related applications, and discuss the opportunity or challenge of hydrazone-linked COFs. We hope this review could provide new insights about hydrazone-linked COFs for exploring more appealing functions or applications.

Engineered reversible adhesive biofoams for accelerated dermal wound healing: Intriguing multi-covalent phenylboronic acid/cis-diol interaction.

Development of wound dressings that not only have multiple advantages including good biocompatibility, barrier properties, adhesive properties, but also exhibit anti-bacterial, anti-infection, and promote cell adhesion, accelerated wound healing process, remains challenging in the skin tissue engineering. In this work, a noninvasive adhesive biofoam with interconnectivity structure and antibacterial property was first-time designed through solid surfactant stabilized high internal phase emulsion (HIPE) template, where bacteriostatic Zn-CuO@GO nanosheets dynamic assemble with 4-vinylphenylboronic acid at the oil/water interface as cooperative emulsifier. Taking advantage of the cooperative assembly of the PBA/Zn-CuO@GO, the biofoams display microfibrousity and interconnectivity to facilitate material-cellular interaction as well nutrient exchange, and can effectively inhibit the growth of E. coli and S. aureus. Meanwhile, phenylboronic acid functional groups not only endow biofoam reversible adhesive property though dynamic phenylboronic acid/cis-diol interaction, but also facilitate the rearrangement of Zn-CuO@GO nanosheets in more uniform way at emulsion interface. Taken together, the biofoams can strongly adhere to the wound bed reducing the risk of infection and accelerate earlier tissue regeneration, which exhibit great potential in bioengineering application.

Multi-View Graph Contrastive Learning via Adaptive Channel Optimization for Depression Detection in EEG Signals.

Automated detection of depression using Electroencephalogram (EEG) signals has become a promising application in advanced bioinformatics technology. Although current methods have achieved high detection performance, several challenges still need to be addressed: (1) Previous studies do not consider data redundancy when modeling multi-channel EEG signals, resulting in some unrecognized noise channels remaining. (2) Most works focus on the functional connection of EEG signals, ignoring their spatial proximity. The spatial topological structure of EEG signals has not been fully utilized to capture more fine-grained features. (3) Prior depression detection models fail to provide interpretability. To address these challenges, this paper proposes a new model, Multi-view Graph Contrastive Learning via Adaptive Channel Optimization (MGCL-ACO) for depression detection in EEG signals. Specifically, the proposed model first selects the critical channels by maximizing the mutual information between tracks and labels of EEG signals to eliminate data redundancy. Then, the MGCL-ACO model builds two similarity metric views based on functional connectivity and spatial proximity. MGCL-ACO constructs the feature extraction module by graph convolutions and contrastive learning to capture more fine-grained features of different perspectives. Finally, our model provides interpretability by visualizing a brain map related to the significance scores of the selected channels. Extensive experiments have been performed on public datasets, and the results show that our proposed model outperforms the most advanced baselines. Our proposed model not only provides a promising approach for automated depression detection using optimal EEG signals but also has the potential to improve the accuracy and interpretability of depression diagnosis in clinical practice.